Technology

Cuckoo Trie: Exploiting Memory-Level Parallelism for Efficient DRAM Indexing

We present the Cuckoo Trie, a fast, memory-efficient ordered index structure. The Cuckoo Trie is designed to have memory-level parallelism -- which a modern out-of-order processor can exploit to execute DRAM accesses in parallel -- without sacrificing memory efficiency. The Cuckoo Trie thus breaks a fundamental performance barrier faced by current indexes, whose bottleneck is a series of dependent pointer-chasing DRAM accesses -- e.g., traversing a search tree path -- which the processor cannot parallelize. Our evaluation shows that the Cuckoo Trie outperforms state-of-the-art-indexes by up to 20%--360% on a variety of datasets and workloads, typically with a smaller or comparable memory footprint.

DeepScalper: A Risk-Aware Deep Reinforcement Learning Framework for Intraday Trading with Micro-level Market Embedding

Reinforcement learning (RL) techniques have shown great success in quantitative investment tasks, such as portfolio management and algorithmic trading. Especially, intraday trading is one of the most profitable and risky tasks because of the intraday behaviors of the financial market that reflect billions of rapidly fluctuating values. However, it is hard to apply existing RL methods to intraday trading due to the following three limitations: 1) overlooking micro-level market information (e.g., limit order book); 2) only focusing on local price fluctuation and failing to capture the overall trend of the whole trading day; 3) neglecting the impact of market risk. To tackle these limitations, we propose DeepScalper, a deep reinforcement learning framework for intraday trading. Specifically, we adopt an encoder-decoder architecture to learn robust market embedding incorporating both macro-level and micro-level market information. Moreover, a novel hindsight reward function is designed to provide the agent a long-term horizon for capturing the overall price trend. In addition, we propose a risk-aware auxiliary task by predicting future volatility, which helps the agent take market risk into consideration while maximizing profit. Finally, extensive experiments on two stock index futures and four treasury bond futures demonstrate that DeepScalper achieves significant improvement against many state-of-the-art approaches.

Effective Anomaly Detection in Smart Home by Integrating Event Time Intervals

Smart home IoT systems and devices are susceptible to attacks and malfunctions. As a result, users' concerns about their security and safety issues arise along with the prevalence of smart home deployments. In a smart home, various anomalies (such as fire or flooding) could happen, due to cyber attacks, device malfunctions, or human mistakes. These concerns motivate researchers to propose various anomaly detection approaches. Existing works on smart home anomaly detection focus on checking the sequence of IoT devices' events but leave out the temporal information of events. This limitation prevents them to detect anomalies that cause delay rather than missing/injecting events. To fill this gap, in this paper, we propose a novel anomaly detection method that takes the inter-event intervals into consideration. We propose an innovative metric to quantify the temporal similarity between two event sequences. We design a mechanism to learn the temporal patterns of event sequences of common daily activities. Delay-caused anomalies are detected by comparing the sequence with the learned patterns. We collect device events from a real-world testbed for training and testing. The experiment results show that our proposed method achieves accuracies of 93%, 88%, 89% for three daily activities.

ThorFI: A Novel Approach for Network Fault Injection as a Service

In this work, we present a novel fault injection solution (ThorFI) for virtual networks in cloud computing infrastructures. ThorFI is designed to provide non-intrusive fault injection capabilities for a cloud tenant, and to isolate injections from interfering with other tenants on the infrastructure. We present the solution in the context of the OpenStack cloud management platform, and release this implementation as open-source software. Finally, we present two relevant case studies of ThorFI, respectively in an NFV IMS and of a high-availability cloud application. The case studies show that ThorFI can enhance functional tests with fault injection, as in 4%-34% of the test cases the IMS is unable to handle faults; and that despite redundancy in virtual networks, faults in one virtual network segment can propagate to other segments, and can affect the throughput and response time of the cloud application as a whole, by about 3 times in the worst case.

Analyzing Enterprise DNS Traffic to Classify Assets and Track Cyber-Health

The Domain Name System (DNS) is a critical service that enables domain names to be converted to IP addresses (or vice versa); consequently, it is generally permitted through enterprise security systems (e.g., firewalls) with little restriction. This has exposed organizational networks to DDoS, exfiltration, and reflection attacks, inflicting significant financial and reputational damage. Large organizations with loosely federated IT departments (e.g., Universities and Research Institutes) often do not even fully aware of all their DNS assets and vulnerabilities, let alone the attack surface they expose to the outside world. In this paper, we address the "DNS blind spot" by developing methods to passively analyze live DNS traffic, identify organizational DNS assets, and monitor their health on a continuous basis. Our contributions are threefold. First, we perform a comprehensive analysis of all DNS traffic in two large organizations (a University Campus and a Government Research Institute) for over a month, and identify key behavioral profiles for various asset types such as recursive resolvers, authoritative name servers, and mixed DNS servers. Second, we develop an unsupervised clustering method that classifies enterprise DNS assets using the behavioral attributes identified, and demonstrate that our method successfully classifies over 100 DNS assets across the two organizations. Third, our method continuously tracks various health metrics across the organizational DNS assets and identifies several instances of improper configuration, data exfiltration, DDoS, and reflection attacks. We believe the passive analysis methods in this paper can help enterprises monitor organizational DNS health in an automated and risk-free manner.

ICT systems provide detailed information on computer network traffic. However, due to storage limitations, some of the information on past traffic is often only retained in an aggregated form. In this paper we show that Linear Gaussian State Space Models yield simple yet effective methods to make predictions based on time series at different aggregation levels. The models link coarse-grained and fine-grained time series to a single model that is able to provide fine-grained predictions. Our numerical experiments show up to 3.7 times improvement in expected mean absolute forecast error when forecasts are made using, instead of ignoring, additional coarse-grained observations. The forecasts are obtained in a Bayesian formulation of the model, which allows for provisioning of a traffic prediction service with highly informative priors obtained from coarse-grained historical data.

Without a specific functional context, non-functional requirements can only be approached as cross-cutting concerns and treated uniformly across all features of an application. This neglects, however, the heterogeneity of non-functional requirements that arises from stakeholder interests and the distinct functional scopes of software systems, which mutually influence how these non-functional requirements have to be satisfied. Earlier studies showed that the different types and objectives of non-functional requirements result in either vague or unbalanced specification of non-functional requirements. We propose a task analytic approach for eliciting and modeling user tasks to approach the stakeholders' pursued interests towards the software product. Stakeholder interests are structurally related to user tasks and each interest can be specified individually as a constraint of a specific user task. These constraints support DevOps teams with important guidance on how the interest of the stakeholder can be satisfied in the software lifecycle sufficiently. We propose a structured approach, intertwining task-oriented functional requirements with non-functional stakeholder interests to specify constraints on the level of user tasks. We also present results of a case study with domain experts, which reveals that our task modeling and interest-tailoring method increases the comprehensibility of non-functional requirements as well as their impact on the functional requirements, i.e., the users' tasks.

Software non-functional requirements address a multitude of objectives, expectations, and even liabilities that must be considered during development and operation. Typically, these non-functional requirements originate from different domains and their concrete scope, notion, and demarcation to functional requirements is often ambiguous. In this study we seek to categorize and analyze relevant work related to software engineering in a DevOps context in order to clarify the different focus areas, themes, and objectives underlying non-functional requirements and also to identify future research directions in this field. We conducted a systematic mapping study, including 142 selected primary studies, extracted the focus areas, and synthesized the themes and objectives of the described NFRs. In order to examine non-engineering-focused studies related to non-functional requirements in DevOps, we conducted a backward snowballing step and additionally included 17 primary studies. Our analysis revealed 7 recurrent focus areas and 41 themes that characterize NFRs in DevOps, along with typical objectives for these themes. Overall, the focus areas and themes of NFRs in DevOps are very diverse and reflect the different perspectives required to align software engineering with technical quality, business, compliance, and organizational considerations. The lack of methodological support for specifying, measuring, and evaluating fulfillment of these NFRs in DevOps-driven projects offers ample opportunities for future research in this field. Particularly, there is a need for empirically validated approaches for operationalizing non-engineering-focused objectives of software.

Congestion Control Mechanisms for Inter-Datacenter Networks

Applications running in geographically distributed setting are becoming prevalent. Large-scale online services often share or replicate their data into multiple data centers (DCs) in different geographic regions. Driven by the data communication need of these applications, inter-datacenter network (IDN) is getting increasingly important.

However, we find congestion control for inter-datacenter networks quite challenging. Firstly, the inter-datacenter communication involves both data center networks (DCNs) and wide-area networks (WANs) connecting multiple data centers. Such a network environment presents quite heterogeneous characteristics (e.g., buffer depths, RTTs). Existing congestion control mechanisms consider either DCN or WAN congestion, while not simultaneously capturing the degree of congestion for both.

Secondly, to reduce evolution cost and improve flexibility, large enterprises have been building and deploying their wide-area routers based on shallow-buffered switching chips. However, with legacy congestion control mechanisms (e.g., TCP Cubic), shallow buffer can easily get overwhelmed by large BDP (bandwidth-delay product) wide-area traffic, leading to high packet losses and degraded throughput.

This thesis describes my research efforts on optimizing congestion control mechanisms for the inter-datacenter networks. First, we design GEMINI - a practical congestion control mechanism that simultaneously handles congestions both in DCN andWAN. Second, we present FlashPass - a proactive congestion control mechanism that achieves near zero loss without degrading throughput under the shallow-buffered WAN. Extensive evaluation shows their superior performance over existing congestion control mechanisms.

Dynamic Resource Provisioning of a Scalable E2E Network Slicing Orchestration System

Network slicing allows different applications and network services to be deployed on virtualized resources running on a common underlying physical infrastructure. Developing a scalable system for the orchestration of end-to-end (E2E) mobile network slices requires careful planning and very reliable algorithms. In this paper, we propose a novel E2E Network Slicing Orchestration System (NSOS) and a Dynamic Auto- Scaling Algorithm (DASA) for it. Our NSOS relies strongly on the foundation of a hierarchical architecture that incorporates dedicated entities per domain to manage every segment of the mobile network from the access, to the transport and core network part for a scalable orchestration of federated network slices. The DASA enables the NSOS to autonomously adapt its resources to changes in the demand for slice orchestration requests (SORs) while enforcing a given mean overall time taken by the NSOS to process any SOR. The proposed DASA includes both proactive and reactive resource provisioning techniques). The proposed resource dimensioning heuristic algorithm of the DASA is based on a queuing model for the NSOS, which consists of an open network of G/G/m queues. Finally, we validate the proper operation and evaluate the performance of our DASA solution for the NSOS by means of system-level simulations.

CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAs

We present CFU Playground, a full-stack open-source framework that enables rapid and iterative design of machine learning (ML) accelerators for embedded ML systems. Our toolchain tightly integrates open-source software, RTL generators, and FPGA tools for synthesis, place, and route. This full-stack development framework gives engineers access to explore bespoke architectures that are customized and co-optimized for embedded ML. The rapid, deploy-profile-optimization feedback loop lets ML hardware and software developers achieve significant returns out of a relatively small investment in customization. Using CFU Playground's design loop, we show substantial speedups (55x-75x) and design space exploration between the CPU and accelerator.

Machine Learning: Algorithms, Models, and Applications

Recent times are witnessing rapid development in machine learning algorithm systems, especially in reinforcement learning, natural language processing, computer and robot vision, image processing, speech, and emotional processing and understanding. In tune with the increasing importance and relevance of machine learning models, algorithms, and their applications, and with the emergence of more innovative uses cases of deep learning and artificial intelligence, the current volume presents a few innovative research works and their applications in real world, such as stock trading, medical and healthcare systems, and software automation. The chapters in the book illustrate how machine learning and deep learning algorithms and models are designed, optimized, and deployed. The volume will be useful for advanced graduate and doctoral students, researchers, faculty members of universities, practicing data scientists and data engineers, professionals, and consultants working on the broad areas of machine learning, deep learning, and artificial intelligence.

Traffic Flow Modeling for UAV-Enabled Wireless Networks

This paper investigates traffic flow modeling issue in multi-services oriented unmanned aerial vehicle (UAV)-enabled wireless networks, which is critical for supporting future various applications of such networks. We propose a general traffic flow model for multi-services oriented UAV-enable wireless networks. Under this model, we first classify the network services into three subsets: telemetry, Internet of Things (IoT), and streaming data. Based on the Pareto distribution, we then partition all UAVs into three subgroups with different network usage. We further determine the number of packets for different network services and total data size according to the packet arrival rate for the nine segments, each of which represents one map relationship between a subset of services and a subgroup of UAVs. Simulation results are provided to illustrate that the number of packets and the data size predicted by our traffic model can well match with these under a real scenario.

Symmetry-aware SFC Framework for 5G Networks

Network Function Virtualization (NFV), network slicing, and Software-Defined Networking (SDN) are the key enablers of the fifth generation of mobile networks (5G). Service Function Chaining (SFC) plays a critical role in delivering sophisticated service per slice and enables traffic traversal through a set of ordered Service Functions (SFs). In fully symmetric SFCs, the uplink and downlink traffic traverse the same SFs, while in asymmetric SFC, the reverse-path may not necessarily cross the same SFs in the reverse order. Proposed approaches in the literature support either full symmetry or no symmetry. In this paper, we discuss the partial symmetry concept, that enforces the reverse path to traverse the SFs only when needed. Our contribution is threefold. First, we propose a novel SFC framework with an abstraction layer that can dynamically create partial or full symmetric SFCs across multiple administrative and technological cloud/edge domains. According to the Key Performance Indicators (KPIs) and desired objectives specified at the network slice intent request, the abstraction layer would automatise different SFC operations, but specifically generating partial or full symmetric SFCs. Second, we propose an algorithm to dynamically calculate the reverse path for an SFC by including only SFs requiring symmetry. Third, we implement a prototype application to test the performance of the partial symmetry algorithm. The obtained results show the advantages of partial symmetry in reducing both the SFC delivery time and the load on VNFs.

Designing Internet of Behaviors Systems

The Internet of Behaviors (IoB) puts human behavior at the core of engineering intelligent connected systems. IoB links the digital world to human behavior to establish human-driven design, development, and adaptation processes. This paper defines the novel concept by an IoB model based on a collective effort interacting with software engineers, human-computer interaction scientists, social scientists, and cognitive science communities. The model for IoB is created based on an exploratory study that synthesizes state-of-the-art analysis and experts interviews. The architecture of a real industry 4.0 manufacturing infrastructure helps to explain the IoB model and it's application. The conceptual model was used to successfully implement a socio-technical infrastructure for a crowd monitoring and queue management system for the Uffizi Galleries, Florence, Italy. The experiment, which started in the fall of 2016 and was operational in the fall of 2018, used a data-driven approach to feed the system with real-time sensory data. It also incorporated prediction models on visitors' mobility behavior. The system's main objective was to capture human behavior, model it, and build a mechanism that considers changes, adapts in real-time, and continuously learns from repetitive behaviors. In addition to the conceptual model and the real-life evaluation, this paper provides recommendations from experts and gives future directions for IoB to become a significant technological advancement in the coming few years.

Using Machine Learning for Anomaly Detection on a System-on-Chip under Gamma Radiation

The emergence of new nanoscale technologies has imposed significant challenges to designing reliable electronic systems in radiation environments. A few types of radiation like Total Ionizing Dose (TID) effects often cause permanent damages on such nanoscale electronic devices, and current state-of-the-art technologies to tackle TID make use of expensive radiation-hardened devices. This paper focuses on a novel and different approach: using machine learning algorithms on consumer electronic level Field Programmable Gate Arrays (FPGAs) to tackle TID effects and monitor them to replace before they stop working. This condition has a research challenge to anticipate when the board results in a total failure due to TID effects. We observed internal measurements of the FPGA boards under gamma radiation and used three different anomaly detection machine learning (ML) algorithms to detect anomalies in the sensor measurements in a gamma-radiated environment. The statistical results show a highly significant relationship between the gamma radiation exposure levels and the board measurements. Moreover, our anomaly detection results have shown that a One-Class Support Vector Machine with Radial Basis Function Kernel has an average Recall score of 0.95. Also, all anomalies can be detected before the boards stop working.

Scheduling of Multiple Network Packet Processing Applications using Pythia

Modern commodity computing systems are composed by a number of different heterogeneous processing units, each of which has its own unique performance and energy characteristics. However, the majority of current network packet processing frameworks targets only a specific processing unit (either the CPU or accelerator), leaving the remaining computational resources under-utilized or even idle. In this paper, we propose an adaptive scheduling approach for network packet processing applications, that supports any heterogeneous and asymmetric architectures that can be found in a commodity high-end hardware setup. Our scheduler not only distributes the workloads to the appropriate devices in the system to achieve the desired performance results, but also enables the multiplexing of diverse network packet processing applications that execute concurrently, eliminating the interference effects introduced at runtime. The evaluation results show that our scheduler is able to tackle interferences in the shared hardware resources as well to respond quickly to dynamic fluctuations (e.g., application overloads, traffic bursts, infrastructural changes, etc.) that may occur at real time.

Have I done enough planning or should I plan more?

People's decisions about how to allocate their limited computational resources are essential to human intelligence. An important component of this metacognitive ability is deciding whether to continue thinking about what to do and move on to the next decision. Here, we show that people acquire this ability through learning and reverse-engineer the underlying learning mechanisms. Using a process-tracing paradigm that externalises human planning, we find that people quickly adapt how much planning they perform to the cost and benefit of planning. To discover the underlying metacognitive learning mechanisms we augmented a set of reinforcement learning models with metacognitive features and performed Bayesian model selection. Our results suggest that the metacognitive ability to adjust the amount of planning might be learned through a policy-gradient mechanism that is guided by metacognitive pseudo-rewards that communicate the value of planning.

Industrial Edge-based Cyber-Physical Systems -- Application Needs and Concerns for Realization

Industry is moving towards advanced Cyber-Physical Systems (CPS), with trends in smartness, automation, connectivity and collaboration. We examine the drivers and requirements for the use of edge computing in critical industrial applications. Our purpose is to provide a better understanding of industrial needs and to initiate a discussion on what role edge computing could take, complementing current industrial and embedded systems, and the cloud. Four domains are chosen for analysis with representative use-cases; manufacturing, transportation, the energy sector and networked applications in the defense domain. We further discuss challenges, open issues and suggested directions that are needed to pave the way for the use of edge computing in industrial CPS.

This paper presents a new and practical approach to lock-free locks based on helping, which allows the user to write code using fine-grained locks, but run it in a lock-free manner.

Although lock-free locks have been suggested in the past, they are widely viewed as impractical, have some key limitations, and, as far as we know, have never been implemented. The paper presents some key techniques that make lock-free locks practical and more general. The most important technique is an approach to idempotence -- i.e. making code that runs multiple times appear as if it ran once. The idea is based on using a shared log among processes running the same protected code. Importantly, the approach can be library based, requiring very little if any change to standard code -- code just needs to use the idempotent versions of memory operations (load, store, LL/SC, allocation, free).

We have implemented a C++ library called Flock based on the ideas. Flock allows lock-based data structures to run in either lock-free or blocking (traditional locks) mode. We implemented a variety of tree and list-based data structures with Flock and compare the performance of the lock-free and blocking modes under a variety of workloads. The lock-free mode is almost as fast as blocking mode under almost all workloads, and significantly faster when threads are oversubscribed (more threads than processors). We also compare with several existing lock-based and lock-free alternatives.

Secure Time-Sensitive Software-Defined Networking in Vehicles

Current designs of future In-Vehicle Networks (IVN) prepare for switched Ethernet backbones, which can host advanced LAN technologies such as IEEE Time-Sensitive Networking (TSN) and Software-Defined Networking (SDN). In this work, we present an integrated Time-Sensitive Software-Defined Networking (TSSDN) architecture that simultaneously enables control of synchronous and asynchronous real-time and best-effort traffic for all IVN traffic classes using a central SDN controller. We validate that the control overhead of SDN can be added without a delay penalty for TSN traffic, provided protocols are properly mapped. Based on our TSSDN concept, we demonstrate adaptable and reliable network security mechanisms for in-vehicle communication. We systematically investigate different strategies for integrating in-vehicle control flows with switched Ether-networks and analyze their security implications for a software-defined IVN. We discuss embeddings of control flow identifiers on different layers, covering a range from a fully exposed mapping to deep encapsulations. We experimentally evaluate these strategies in a production vehicle which we map to a modern Ethernet topology. Our findings indicate that visibility of automotive control flows on lower network layers is essential for providing isolation and access control throughout the network infrastructure. Such a TSSDN backbone can establish and survey trust zones within the IVN and reduce the attack surface of connected cars in various attack scenarios.

A Priority-Aware Multiqueue NIC Design

Low-level embedded systems are used to control cyber-phyiscal systems in industrial and autonomous applications. They need to meet hard real-time requirements as unanticipated controller delays on moving machines can have devastating effects. Modern developments such as the industrial Internet of Things and autonomous machines require these devices to connect to large IP networks. Since Network Interface Controllers (NICs) trigger interrupts for incoming packets, real-time embedded systems are subject to unpredictable preemptions when connected to such networks.

In this work, we propose a priority-aware NIC design to moderate network-generated interrupts by mapping IP flows to processes and based on that, consolidates their packets into different queues. These queues apply priority-dependent interrupt moderation. First experimental evaluations show that 93% of interrupts can be saved leading to an 80% decrease of processing delay of critical tasks in the configurations investigated.

Tiansuan Constellation: An Open Research Platform

Satellite network is the first step of interstellar voyages. It can provide global Internet connectivity everywhere on earth, where most areas cannot access the Internet by the terrestrial infrastructure due to the geographic accessibility and high cost. The space industry experiences a rise in large low-earth-orbit satellite constellations to achieve universal connectivity. The research community is also urgent to do some leading research to bridge the connectivity divide. Researchers now conduct their work by simulation, which is far from enough. However, experiments on real satellites are blocked by the high threshold of space technology, such as deployment cost and unknown risks. To solve the above dilemma, we are eager to contribute to the universal connectivity and build an open research platform, Tiansuan constellation to support experiments on real satellite networks. We discuss the potential research topics that would benefit from Tiansuan constellation. We provide two case studies that have already deployed in two experimental satellites of Tiansuan constellation.

INTCP: Information-centric TCP for Satellite Network

Satellite networks are booming to provide high-speed and low latency Internet access, but the transport layer becomes one of the main obstacles. Legacy end-to-end TCP is designed for terrestrial networks, not suitable for error-prone, propagation delay varying, and intermittent satellite links. It is necessary to make a clean-slate design for the satellite transport layer. This paper introduces a novel Information-centric Hop-by-Hop transport layer design, INTCP. It carries out hop-by-hop packets retransmission and hop-by-hop congestion control with the help of cache and request-response model. Hop-by-hop retransmission recovers lost packets on hop, reduces retransmission delay. INTCP controls traffic and congestion also by hop. Each hop tries its best to maximize its bandwidth utilization and improves end-to-end throughput. The capability of caching enables asynchronous multicast in transport layer. This would save precious spectrum resources in the satellite network. The performance of INTCP is evaluated with the simulated Starlink constellation. Long-distance communication with more than 1000km is carried out. The results demonstrate that, for the unicast scenario INTCP could reduce 42% one-way delay, 53% delay jitters, and improve 60% throughput compared with the legacy TCP. In multicast scenario, INTCP could achieve more than 6X throughput.

Virtualization over Multiprocessor System-on-Chip: an Enabling Paradigm for Industrial IoT

The next-generation Industrial Internet of Things (IIoT) inherently requires smart devices featuring rich connectivity, local intelligence, and autonomous behavior. Emerging Multiprocessor System-on-Chip (MPSoC) platforms along with comprehensive support for virtualization will represent two key building blocks for smart devices in future IIoT edge infrastructures. We review representative existing solutions, highlighting the aspects that are most relevant for integration in IIoT solutions. From the analysis, we derive a reference architecture for a general virtualization-ready edge IIoT node. We then analyze the implications and benefits for a concrete use case scenario and identify the crucial research challenges to be faced to bridge the gap towards full support for virtualization-ready IIoT nodes

With the emergence of new technologies, computer networks are becoming more structurally complex, diverse and heterogenous. The increasing discrepancy (among the interconnected networks) in data rates, delays, packet loss, and transmission scenarios, influence significantly the dynamics of congestion control (CC) parametrization. In contrast to the traditional endto-end CC algorithms that rely on strict rules, new approaches aim to involve machine learning in order to continuously adapt the CC to real-time network requirements. However, due to the high computational complexity and memory consumption, the feasibility of these schemes may still be questioned. This paper surveys selected machine-learning based approaches to CC and proposes a roadmap to their implementation in computer systems, by using dataflow computing and Gallium Arsenide (GaAs) chips.

An Empirical Study of Security Practices for Microservices Systems

Despite the numerous benefits of microservices systems, security has been a critical issue in such systems. Several factors explain this difficulty, including a knowledge gap among microservices practitioners on properly securing a microservices system. To (partially) bridge this gap, we conducted an empirical study to manually analyze 861 security points collected from 10 GitHub open-source microservices systems and Stack Overflow posts concerning security of microservices systems, leading to a catalog of 28 microservices security practices. We then ran a survey with 63 microservices practitioners to evaluate the usefulness of these 28 practices. Our findings demonstrate that the survey respondents affirmed the usefulness of the 28 practices. These 28 security practices are further classified into six categories based on their topics: Authorization and Authentication, Token and Credentials, Internal and External Microservices, Microservices Communications, Private Microservices, and Database and Environments. We believe that the catalog of microservices security practices can serve as a valuable resource for microservices practitioners to more effectively address security issues in microservices systems. It can also inform the research community of the required or less explored areas to develop microservices-specific security practices and tools.

PowerTCP: Pushing the Performance Limits of Datacenter Networks

Increasingly stringent throughput and latency requirements in datacenter networks demand fast and accurate congestion control. We observe that the reaction time and accuracy of existing datacenter congestion control schemes are inherently limited. They either rely only on explicit feedback about the network state (e.g., queue lengths in DCTCP) or only on variations of state (e.g., RTT gradient in TIMELY). To overcome these limitations, we propose a novel congestion control algorithm, PowerTCP, which achieves much more fine-grained congestion control by adapting to the bandwidth-window product (henceforth called power). PowerTCP leverages in-band network telemetry to react to changes in the network instantaneously without loss of throughput and while keeping queues short. Due to its fast reaction time, our algorithm is particularly well-suited for dynamic network environments and bursty traffic patterns. We show analytically and empirically that PowerTCP can significantly outperform the state-of-the-art in both traditional datacenter topologies and emerging reconfigurable datacenters where frequent bandwidth changes make congestion control challenging. In traditional datacenter networks, PowerTCP reduces tail flow completion times of short flows by 80% compared to DCQCN and TIMELY, and by 33% compared to HPCC even at 60% network load. In reconfigurable datacenters, PowerTCP achieves 85% circuit utilization without incurring additional latency and cuts tail latency by at least 2x compared to existing approaches.

Optimal Weighted Load Balancing in TCAMs

Traffic splitting is a required functionality in networks, for example for load balancing over multiple paths or among different servers. The capacities of the servers determine the partition by which traffic should be split. A recent approach implements traffic splitting within the ternary content addressable memory (TCAM), which is often available in switches. It is important to reduce the amount of memory allocated for this task since TCAMs are power consuming and are often also required for other tasks such as classification and routing. Previous work showed how to compute the smallest prefix-matching TCAM necessary to implement a given partition exactly. In this paper we solve the more practical case, where at most $n$ prefix-matching TCAM rules are available, restricting the ability to implement exactly the desired partition. We give simple and efficient algorithms to find $n$ rules that generate a partition closest in $L_\infty$ to the desired one. We do the same for a one-sided version of $L_\infty$ which equals to the maximum overload on a server and for a relative version of it. We use our algorithms to evaluate how the expected error changes as a function of the number of rules, the number of servers, and the width of the TCAM.

Forecasting sales with Bayesian networks: a case study of a supermarket product in the presence of promotions

Sales forecasting is the prerequisite for a lot of managerial decisions such as production planning, material resource planning and budgeting in the supply chain. Promotions are one of the most important business strategies that are often used to boost sales. While promotions are attractive for generating demand, it is often difficult to forecast demand in their presence. In the past few decades, several quantitative models have been developed to forecast sales including statistical and machine learning models. However, these methods may not be adequate to account for all the internal and external factors that may impact sales. As a result, qualitative models have been adopted along with quantitative methods as consulting experts has been proven to improve forecast accuracy by providing contextual information. Such models are being used extensively to account for factors that can lead to a rapid change in sales, such as during promotions. In this paper, we aim to use Bayesian Networks to forecast promotional sales where a combination of factors such as price, type of promotions, and product location impacts sales. We choose to develop a BN model because BN models essentially have the capability to combine various qualitative and quantitative factors with causal forms, making it an attractive tool for sales forecasting during promotions. This can be used to adjust a company's promotional strategy in the context of this case study. We gather sales data for a particular product from a retailer that sells products in Australia. We develop a Bayesian Network for this product and validate our results by empirical analysis. This paper confirms that BNs can be effectively used to forecast sales, especially during promotions. In the end, we provide some research avenues for using BNs in forecasting sales.

Challenges and Solutions to Build a Data Pipeline to Identify Anomalies in Enterprise System Performance

We discuss how VMware is solving the following challenges to harness data to operate our ML-based anomaly detection system to detect performance issues in our Software Defined Data Center (SDDC) enterprise deployments: (i) label scarcity and label bias due to heavy dependency on unscalable human annotators, and (ii) data drifts due to ever-changing workload patterns, software stack and underlying hardware. Our anomaly detection system has been deployed in production for many years and has successfully detected numerous major performance issues. We demonstrate that by addressing these data challenges, we not only improve the accuracy of our performance anomaly detection model by 30%, but also ensure that the model performance to never degrade over time.

Ruta: Dis-aggregated routing system over multi-cloud

Over the years, the SDN evolution create multiple overlay technologies which is inefficient and hard to deploy end-to-end traffic engineering services, Ruta is designed as an unified encapsulation with Segment Routing, Crypto and NAT-Traversal capabilities over UDP.

Ruta could be deployed as a cloud native SDN platform globally over multi-cloud and integrated with each applications on transport layer, which provide nearly zero loss and almost less than 200ms latency to access anywhere in the world over internet.

Controlled Cue Generation for Play Scripts

In this paper, we use a large-scale play scripts dataset to propose the novel task of theatrical cue generation from dialogues. Using over one million lines of dialogue and cues, we approach the problem of cue generation as a controlled text generation task, and show how cues can be used to enhance the impact of dialogue using a language model conditioned on a dialogue/cue discriminator. In addition, we explore the use of topic keywords and emotions for controlled text generation. Extensive quantitative and qualitative experiments show that language models can be successfully used to generate plausible and attribute-controlled texts in highly specialised domains such as play scripts.

Combining Design Thinking and Software Requirements Engineering to create Human-centered Software-intensive Systems

Effective Requirements Engineering is a crucial activity in softwareintensive development projects. The human-centric working mode of Design Thinking is considered a powerful way to complement such activities when designing innovative systems. Research has already made great strides to illustrate the benefits of using Design Thinking for Requirements Engineering. However, it has remained mostly unclear how to actually realize a combination of both. In this chapter, we contribute an artifact-based model that integrates Design Thinking and Requirements Engineering for innovative software-intensive systems. Drawing from our research and project experiences, we suggest three strategies for tailoring and integrating Design Thinking and Requirements Engineering with complementary synergies.

Deep Q-Learning Market Makers in a Multi-Agent Simulated Stock Market

Market makers play a key role in financial markets by providing liquidity. They usually fill order books with buy and sell limit orders in order to provide traders alternative price levels to operate. This paper focuses precisely on the study of these markets makers strategies from an agent-based perspective. In particular, we propose the application of Reinforcement Learning (RL) for the creation of intelligent market markers in simulated stock markets. This research analyzes how RL market maker agents behaves in non-competitive (only one RL market maker learning at the same time) and competitive scenarios (multiple RL market markers learning at the same time), and how they adapt their strategies in a Sim2Real scope with interesting results. Furthermore, it covers the application of policy transfer between different experiments, describing the impact of competing environments on RL agents performance. RL and deep RL techniques are proven as profitable market maker approaches, leading to a better understanding of their behavior in stock markets.

Multi-Task Learning on Networks

The multi-task learning (MTL) paradigm can be traced back to an early paper of Caruana (1997) in which it was argued that data from multiple tasks can be used with the aim to obtain a better performance over learning each task independently. A solution of MTL with conflicting objectives requires modelling the trade-off among them which is generally beyond what a straight linear combination can achieve. A theoretically principled and computationally effective strategy is finding solutions which are not dominated by others as it is addressed in the Pareto analysis. Multi-objective optimization problems arising in the multi-task learning context have specific features and require adhoc methods. The analysis of these features and the proposal of a new computational approach represent the focus of this work. Multi-objective evolutionary algorithms (MOEAs) can easily include the concept of dominance and therefore the Pareto analysis. The major drawback of MOEAs is a low sample efficiency with respect to function evaluations. The key reason for this drawback is that most of the evolutionary approaches do not use models for approximating the objective function. Bayesian Optimization takes a radically different approach based on a surrogate model, such as a Gaussian Process. In this thesis the solutions in the Input Space are represented as probability distributions encapsulating the knowledge contained in the function evaluations. In this space of probability distributions, endowed with the metric given by the Wasserstein distance, a new algorithm MOEA/WST can be designed in which the model is not directly on the objective function but in an intermediate Information Space where the objects from the input space are mapped into histograms. Computational results show that the sample efficiency and the quality of the Pareto set provided by MOEA/WST are significantly better than in the standard MOEA.

The rapid changes in the finance industry due to the increasing amount of data have revolutionized the techniques on data processing and data analysis and brought new theoretical and computational challenges. In contrast to classical stochastic control theory and other analytical approaches for solving financial decision-making problems that heavily reply on model assumptions, new developments from reinforcement learning (RL) are able to make full use of the large amount of financial data with fewer model assumptions and to improve decisions in complex financial environments. This survey paper aims to review the recent developments and use of RL approaches in finance. We give an introduction to Markov decision processes, which is the setting for many of the commonly used RL approaches. Various algorithms are then introduced with a focus on value and policy based methods that do not require any model assumptions. Connections are made with neural networks to extend the framework to encompass deep RL algorithms. Our survey concludes by discussing the application of these RL algorithms in a variety of decision-making problems in finance, including optimal execution, portfolio optimization, option pricing and hedging, market making, smart order routing, and robo-advising.

High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning

This paper proposes a Deep Reinforcement Learning algorithm for financial portfolio trading based on Deep Q-learning. The algorithm is capable of trading high-dimensional portfolios from cross-sectional datasets of any size which may include data gaps and non-unique history lengths in the assets. We sequentially set up environments by sampling one asset for each environment while rewarding investments with the resulting asset's return and cash reservation with the average return of the set of assets. This enforces the agent to strategically assign capital to assets that it predicts to perform above-average. We apply our methodology in an out-of-sample analysis to 48 US stock portfolio setups, varying in the number of stocks from ten up to 500 stocks, in the selection criteria and in the level of transaction costs. The algorithm on average outperforms all considered passive and active benchmark investment strategies by a large margin using only one hyperparameter setup for all portfolios.

Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion

Quadruped locomotion is rapidly maturing to a degree where robots now routinely traverse a variety of unstructured terrains. However, while gaits can be varied typically by selecting from a range of pre-computed styles, current planners are unable to vary key gait parameters continuously while the robot is in motion. The synthesis, on-the-fly, of gaits with unexpected operational characteristics or even the blending of dynamic manoeuvres lies beyond the capabilities of the current state-of-the-art. In this work we address this limitation by learning a latent space capturing the key stance phases constituting a particular gait. This is achieved via a generative model trained on a single trot style, which encourages disentanglement such that application of a drive signal to a single dimension of the latent state induces holistic plans synthesising a continuous variety of trot styles. We demonstrate that specific properties of the drive signal map directly to gait parameters such as cadence, foot step height and full stance duration. Due to the nature of our approach these synthesised gaits are continuously variable online during robot operation and robustly capture a richness of movement significantly exceeding the relatively narrow behaviour seen during training. In addition, the use of a generative model facilitates the detection and mitigation of disturbances to provide a versatile and robust planning framework. We evaluate our approach on a real ANYmal quadruped robot and demonstrate that our method achieves a continuous blend of dynamic trot styles whilst being robust and reactive to external perturbations.

Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Review

Due to their massive success in various domains, deep learning techniques are increasingly used to design network intrusion detection solutions that detect and mitigate unknown and known attacks with high accuracy detection rates and minimal feature engineering. However, it has been found that deep learning models are vulnerable to data instances that can mislead the model to make incorrect classification decisions so-called (adversarial examples). Such vulnerability allows attackers to target NIDSs by adding small crafty perturbations to the malicious traffic to evade detection and disrupt the system's critical functionalities. The problem of deep adversarial learning has been extensively studied in the computer vision domain; however, it is still an area of open research in network security applications. Therefore, this survey explores the researches that employ different aspects of adversarial machine learning in the area of network intrusion detection in order to provide directions for potential solutions. First, the surveyed studies are categorized based on their contribution to generating adversarial examples, evaluating the robustness of ML-based NIDs towards adversarial examples, and defending these models against such attacks. Second, we highlight the characteristics identified in the surveyed research. Furthermore, we discuss the applicability of the existing generic adversarial attacks for the NIDS domain, the feasibility of launching the proposed attacks in real-world scenarios, and the limitations of the existing mitigation solutions.

Container Orchestration Techniques in Cloud and Edge/Fog Computing Environments

Currently, due to the advantages of light weight, simple deployment, multi-environment support, short startup time, scalability, and easy migration, container technology has been widely used in both cloud and edge/fog computing, and addresses the problem of device heterogeneity in different computing environments. On this basis, as one of the most popular container orchestration and management systems, Kubernetes almost dominates the cloud environment. However, since it is primarily designed for centralized resource management scenarios where computing resources are sufficient, the system is unstable in edge environments due to hardware limitations. Therefore, in order to realize container orchestration in the cloud and edge/fog hybrid computing environment, we propose a feasible approach to build a hybrid clustering based on K3s, which solves the problem that virtual instances in different environments cannot be connected due to IP addresses. We also propose three design patterns for deploying the FogBus2 framework into hybrid environments, including 1) Host Network Mode, 2) Proxy Server, and 3) Environment Variable.

PreGAN: Preemptive Migration Prediction Network for Proactive Fault-Tolerant Edge Computing

Building a fault-tolerant edge system that can quickly react to node overloads or failures is challenging due to the unreliability of edge devices and the strict service deadlines of modern applications. Moreover, unnecessary task migrations can stress the system network, giving rise to the need for a smart and parsimonious failure recovery scheme. Prior approaches often fail to adapt to highly volatile workloads or accurately detect and diagnose faults for optimal remediation. There is thus a need for a robust and proactive fault-tolerance mechanism to meet service level objectives. In this work, we propose PreGAN, a composite AI model using a Generative Adversarial Network (GAN) to predict preemptive migration decisions for proactive fault-tolerance in containerized edge deployments. PreGAN uses co-simulations in tandem with a GAN to learn a few-shot anomaly classifier and proactively predict migration decisions for reliable computing. Extensive experiments on a Raspberry-Pi based edge environment show that PreGAN can outperform state-of-the-art baseline methods in fault-detection, diagnosis and classification, thus achieving high quality of service. PreGAN accomplishes this by 5.1% more accurate fault detection, higher diagnosis scores and 23.8% lower overheads compared to the best method among the considered baselines.

Combining Embeddings and Fuzzy Time Series for High-Dimensional Time Series Forecasting in Internet of Energy Applications

The prediction of residential power usage is essential in assisting a smart grid to manage and preserve energy to ensure efficient use. An accurate energy forecasting at the customer level will reflect directly into efficiency improvements across the power grid system, however forecasting building energy use is a complex task due to many influencing factors, such as meteorological and occupancy patterns. In addiction, high-dimensional time series increasingly arise in the Internet of Energy (IoE), given the emergence of multi-sensor environments and the two way communication between energy consumers and the smart grid. Therefore, methods that are capable of computing high-dimensional time series are of great value in smart building and IoE applications. Fuzzy Time Series (FTS) models stand out as data-driven non-parametric models of easy implementation and high accuracy. Unfortunately, the existing FTS models can be unfeasible if all features were used to train the model. We present a new methodology for handling high-dimensional time series, by projecting the original high-dimensional data into a low dimensional embedding space and using multivariate FTS approach in this low dimensional representation. Combining these techniques enables a better representation of the complex content of multivariate time series and more accurate forecasts.

Intelligent Trading Systems: A Sentiment-Aware Reinforcement Learning Approach

The feasibility of making profitable trades on a single asset on stock exchanges based on patterns identification has long attracted researchers. Reinforcement Learning (RL) and Natural Language Processing have gained notoriety in these single-asset trading tasks, but only a few works have explored their combination. Moreover, some issues are still not addressed, such as extracting market sentiment momentum through the explicit capture of sentiment features that reflect the market condition over time and assessing the consistency and stability of RL results in different situations. Filling this gap, we propose the Sentiment-Aware RL (SentARL) intelligent trading system that improves profit stability by leveraging market mood through an adaptive amount of past sentiment features drawn from textual news. We evaluated SentARL across twenty assets, two transaction costs, and five different periods and initializations to show its consistent effectiveness against baselines. Subsequently, this thorough assessment allowed us to identify the boundary between news coverage and market sentiment regarding the correlation of price-time series above which SentARL's effectiveness is outstanding.

PhishMatch: A Layered Approach for Effective Detection of Phishing URLs

Phishing attacks continue to be a significant threat on the Internet. Prior studies show that it is possible to determine whether a website is phishing or not just by analyzing its URL more carefully. A major advantage of the URL based approach is that it can identify a phishing website even before the web page is rendered in the browser, thus avoiding other potential problems such as cryptojacking and drive-by downloads. However, traditional URL based approaches have their limitations. Blacklist based approaches are prone to zero-hour phishing attacks, advanced machine learning based approaches consume high resources, and other approaches send the URL to a remote server which compromises user's privacy. In this paper, we present a layered anti-phishing defense, PhishMatch, which is robust, accurate, inexpensive, and client-side. We design a space-time efficient Aho-Corasick algorithm for exact string matching and n-gram based indexing technique for approximate string matching to detect various cybersquatting techniques in the phishing URL. To reduce false positives, we use a global whitelist and personalized user whitelists. We also determine the context in which the URL is visited and use that information to classify the input URL more accurately. The last component of PhishMatch involves a machine learning model and controlled search engine queries to classify the URL. A prototype plugin of PhishMatch, developed for the Chrome browser, was found to be fast and lightweight. Our evaluation shows that PhishMatch is both efficient and effective.

3D Reconstruction Using a Linear Laser Scanner and a Camera

With the rapid development of computer graphics and vision, several three-dimensional (3D) reconstruction techniques have been proposed and used to obtain the 3D representation of objects in the form of point cloud models, mesh models, and geometric models. The cost of 3D reconstruction is declining due to the maturing of this technology, however, the inexpensive 3D reconstruction scanners on the market may not be able to generate a clear point cloud model as expected. This study systematically reviews some basic types of 3D reconstruction technology and introduces an easy implementation using a linear laser scanner, a camera, and a turntable. The implementation is based on the monovision with laser and has tested several objects like wiki and mug. The accuracy and resolution of the point cloud result are quite satisfying. It turns out everyone can build such a 3D reconstruction system with appropriate procedures.

Forex Trading Volatility Prediction using NeuralNetwork Models

In this paper, we investigate the problem of predicting the future volatility of Forex currency pairs using the deep learning techniques. We show step-by-step how to construct the deep-learning network by the guidance of the empirical patterns of the intra-day volatility. The numerical results show that the multiscale Long Short-Term Memory (LSTM) model with the input of multi-currency pairs consistently achieves the state-of-the-art accuracy compared with both the conventional baselines, i.e. autoregressive and GARCH model, and the other deep learning models.