arXiv subjects

Weisong Shi

Publications and source records attributed to Weisong Shi.

At least 55 records · Page 3Linked to original sources

arXiv2021

Resource Scheduling in Edge Computing: A Survey

With the proliferation of the Internet of Things (IoT) and the wide penetration of wireless networks, the surging demand for data communications and computing calls for the emerging edge computing paradigm. By moving the services and functions located in the cloud to the proximity of users, edge computing can provide powerful communication, storage, networking, and communication capacity. The resource scheduling in edge computing, which is the key to the success of edge computing systems, has attracted increasing research interests. In this paper, we survey the state-of-the-art research findings to know the research progress in this field. Specifically, we present the architecture of edge computing, under which different collaborative manners for resource scheduling are discussed. Particularly, we introduce a unified model before summarizing the current works on resource scheduling from three research issues, including computation offloading, resource allocation, and resource provisioning. Based on two modes of operation, i.e., centralized and distributed modes, different techniques for resource scheduling are discussed and compared. Also, we summarize the main performance indicators based on the surveyed literature. To shed light on the significance of resource scheduling in real-world scenarios, we discuss several typical application scenarios involved in the research of resource scheduling in edge computing. Finally, we highlight some open research challenges yet to be addressed and outline several open issues as the future research direction.

cs.NI↗

arXiv2021

Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning

Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new domains/environments without any expensive label cost. However, without ground truth labels, most prior works on UDA for object detection tasks can only perform coarse image-level and/or feature-level adaptation by using adversarial learning methods. In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors. To overcome this limitation, we propose the Cross-Domain Semi-Supervised Learning (CDSSL) framework by leveraging high-quality pseudo labels to learn better representations from the target domain directly. To enable SSL for cross-domain object detection, we propose fine-grained domain transfer, progressive-confidence-based label sharpening and imbalanced sampling strategy to address two challenges: (i) non-identical distribution between source and target domain data, (ii) error amplification/accumulation due to noisy pseudo labeling on the target domain. Experiment results show that our proposed approach consistently achieves new state-of-the-art performance (2.2% - 9.5% better than prior best work on mAP) under various domain gap scenarios. The code will be released.

cs.CV↗

arXiv2021

4C: A Computation, Communication, and Control Co-Design Framework for CAVs

Connected and autonomous vehicles (CAVs) are promising due to their potential safety and efficiency benefits and have attracted massive investment and interest from government agencies, industry, and academia. With more computing and communication resources are available, both vehicles and edge servers are equipped with a set of camera-based vision sensors, also known as Visual IoT (V-IoT) techniques, for sensing and perception. Tremendous efforts have been made for achieving programmable communication, computation, and control. However, they are conducted mainly in the silo mode, limiting the responsiveness and efficiency of handling challenging scenarios in the real world. To improve the end-to-end performance, we envision that future CAVs require the co-design of communication, computation, and control. This paper presents our vision of the end-to-end design principle for CAVs, called 4C, which extends the V-IoT system by providing a unified communication, computation, and control co-design framework. With programmable communications, fine-grained heterogeneous computation, and efficient vehicle controls in 4C, CAVs can handle critical scenarios and achieve energy-efficient autonomous driving. Finally, we present several challenges to achieving the vision of the 4C framework.

cs.DC↗

arXiv2021

Revisiting the Arguments for Edge Computing Research

This article argues that low latency, high bandwidth, device proliferation, sustainable digital infrastructure, and data privacy and sovereignty continue to motivate the need for edge computing research even though its initial concepts were formulated more than a decade ago.

cs.DC↗

arXiv2021

Reinforcement Learning for Adaptive Video Compressive Sensing

We apply reinforcement learning to video compressive sensing to adapt the compression ratio. Specifically, video snapshot compressive imaging (SCI), which captures high-speed video using a low-speed camera is considered in this work, in which multiple (B) video frames can be reconstructed from a snapshot measurement. One research gap in previous studies is how to adapt B in the video SCI system for different scenes. In this paper, we fill this gap utilizing reinforcement learning (RL). An RL model, as well as various convolutional neural networks for reconstruction, are learned to achieve adaptive sensing of video SCI systems. Furthermore, the performance of an object detection network using directly the video SCI measurements without reconstruction is also used to perform RL-based adaptive video compressive sensing. Our proposed adaptive SCI method can thus be implemented in low cost and real time. Our work takes the technology one step further towards real applications of video SCI.

cs.CV↗

arXiv2021

Speedster: A TEE-assisted State Channel System

State channel network is the most popular layer-2 solution to theissues of scalability, high transaction fees, and low transaction throughput of public Blockchain networks. However, the existing works have limitations that curb the wide adoption of the technology, such as the expensive creation and closure of channels, strict synchronization between the main chain and off-chain channels, frozen deposits, and inability to execute multi-party smart contracts. In this work, we present Speedster, an account-based state-channel system that aims to address the above issues. To this end, Speedster leverages the latest development of secure hardware to create dispute-free certified channels that can be operated efficiently off the Blockchain. Speedster is fully decentralized and provides better privacy protection. It supports fast native multi-party contract execution, which is missing in prior TEE-enabled channel networks. Compared to the Lightning Network, Speedster improves the throughput by about 10,000X and generates 97% less on-chain data with a comparable network scale.

cs.CR↗

arXiv2021

A Survey on Simulators for Testing Self-Driving Cars

A rigorous and comprehensive testing plays a key role in training self-driving cars to handle variety of situations that they are expected to see on public roads. The physical testing on public roads is unsafe, costly, and not always reproducible. This is where testing in simulation helps fill the gap, however, the problem with simulation testing is that it is only as good as the simulator used for testing and how representative the simulated scenarios are of the real environment. In this paper, we identify key requirements that a good simulator must have. Further, we provide a comparison of commonly used simulators. Our analysis shows that CARLA and LGSVL simulators are the current state-of-the-art simulators for end to end testing of self-driving cars for the reasons mentioned in this paper. Finally, we also present current challenges that simulation testing continues to face as we march towards building fully autonomous cars.

cs.RO↗

arXiv2020

A Survey on Edge Performance Benchmarking

Edge computing is the next Internet frontier that will leverage computing resources located near users, sensors, and data stores to provide more responsive services. Therefore, it is envisioned that a large-scale, geographically dispersed, and resource-rich distributed system will emerge and play a key role in the future Internet. However, given the loosely coupled nature of such complex systems, their operational conditions are expected to change significantly over time. In this context, the performance characteristics of such systems will need to be captured rapidly, which is referred to as performance benchmarking, for application deployment, resource orchestration, and adaptive decision-making. Edge performance benchmarking is a nascent research avenue that has started gaining momentum over the past five years. This article first reviews articles published over the past three decades to trace the history of performance benchmarking from tightly coupled to loosely coupled systems. It then systematically classifies previous research to identify the system under test, techniques analyzed, and benchmark runtime in edge performance benchmarking.

cs.DC↗

arXiv2020

A Case For Adaptive Deep Neural Networks in Edge Computing

Edge computing offers an additional layer of compute infrastructure closer to the data source before raw data from privacy-sensitive and performance-critical applications is transferred to a cloud data center. Deep Neural Networks (DNNs) are one class of applications that are reported to benefit from collaboratively computing between the edge and the cloud. A DNN is partitioned such that specific layers of the DNN are deployed onto the edge and the cloud to meet performance and privacy objectives. However, there is limited understanding of: (a) whether and how evolving operational conditions (increased CPU and memory utilization at the edge or reduced data transfer rates between the edge and the cloud) affect the performance of already deployed DNNs, and (b) whether a new partition configuration is required to maximize performance. A DNN that adapts to changing operational conditions is referred to as an 'adaptive DNN'. This paper investigates whether there is a case for adaptive DNNs in edge computing by considering three questions: (i) Are DNNs sensitive to operational conditions? (ii) How sensitive are DNNs to operational conditions? (iii) Do individual or a combination of operational conditions equally affect DNNs? (iv) Is DNN partitioning sensitive to hardware architectures on the cloud/edge? The exploration is carried out in the context of 8 pre-trained DNN models and the results presented are from analyzing nearly 8 million data points. The results highlight that network conditions affects DNN performance more than CPU or memory related operational conditions. Repartitioning is noted to provide a performance gain in a number of cases, but a specific trend was not noted in relation to its correlation to the underlying hardware architecture. Nonetheless, the need for adaptive DNNs is confirmed.

cs.DC↗

arXiv2020

Computing Systems for Autonomous Driving: State-of-the-Art and Challenges

The recent proliferation of computing technologies (e.g., sensors, computer vision, machine learning, and hardware acceleration), and the broad deployment of communication mechanisms (e.g., DSRC, C-V2X, 5G) have pushed the horizon of autonomous driving, which automates the decision and control of vehicles by leveraging the perception results based on multiple sensors. The key to the success of these autonomous systems is making a reliable decision in real-time fashion. However, accidents and fatalities caused by early deployed autonomous vehicles arise from time to time. The real traffic environment is too complicated for current autonomous driving computing systems to understand and handle. In this paper, we present state-of-the-art computing systems for autonomous driving, including seven performance metrics and nine key technologies, followed by twelve challenges to realize autonomous driving. We hope this paper will gain attention from both the computing and automotive communities and inspire more research in this direction.

cs.DC↗

arXiv2020

Impact of COVID-19 on City-Scale Transportation and Safety: An Early Experience from Detroit

The COVID-19 pandemic brought unprecedented levels of disruption to the local and regional transportation networks throughout the United States, especially the Motor City: Detroit. That was mainly a result of swift restrictive measures such as statewide quarantine and lock-down orders to confine the spread of the virus. This work is driven by analyzing five types of real-world data sets from Detroit related to traffic volume, daily cases, weather, social distancing index, and crashes from January 2019 to June 2020. The primary goal is figuring out the impacts of COVID-19 on the transportation network usage (traffic volume) and safety (crashes) for the Detroit, exploring the potential correlation between these diverse data features, and determining whether each type of data (e.g., traffic volume data) could be a useful factor in the confirmed-cases prediction. In addition, a deep learning model was developed using long short-term memory networks to predict the number of confirmed cases within the next one week. The model demonstrated a promising prediction result with a coefficient of determination (R^2) of up to approximately 0.91. Moreover, in order to provide statistical evaluation measures of confirmed-case prediction and to quantify the prediction effectiveness of each type of data, the prediction results of six feature groups are presented and analyzed. Furthermore, six essential observations with supporting evidence and analyses are presented. The goal of this paper is to present a proposed approach which can be applied, customised, adjusted, and replicated for analysis of the impact of COVID-19 on a transportation network and prediction of the anticipated COVID-19 cases using a similar data set obtained for other large cities in the USA or from around the world.

physics.soc-ph↗

arXiv2020

WatchDog: Real-time Vehicle Tracking on Geo-distributed Edge Nodes

Vehicle tracking, a core application to smart city video analytics, is becoming more widely deployed than ever before thanks to the increasing number of traffic cameras and recent advances of computer vision and machine learning. Due to the constraints of bandwidth, latency, and privacy concerns, tracking tasks are more preferable to run on edge devices sitting close to the cameras. However, edge devices are provisioned with a fixed amount of compute budget, making them incompetent to adapt to time-varying tracking workloads caused by traffic dynamics. In coping with this challenge, we propose WatchDog, a real-time vehicle tracking system fully utilizes edge nodes across the road network. WatchDog leverages computer vision tasks with different resource-accuracy trade-offs, and decompose and schedule tracking tasks judiciously across edge devices based on the current workload to maximize the number of tasks while ensuring a provable response time bound at each edge device. Extensive evaluations have been conducted using real-world city-wide vehicle trajectory datasets, showing a 100% tracking coverage with real-time guarantee.

cs.DC↗

arXiv2019

pCAMP: Performance Comparison of Machine Learning Packages on the Edges

Machine learning has changed the computing paradigm. Products today are built with machine intelligence as a central attribute, and consumers are beginning to expect near-human interaction with the appliances they use. However, much of the deep learning revolution has been limited to the cloud. Recently, several machine learning packages based on edge devices have been announced which aim to offload the computing to the edges. However, little research has been done to evaluate these packages on the edges, making it difficult for end users to select an appropriate pair of software and hardware. In this paper, we make a performance comparison of several state-of-the-art machine learning packages on the edges, including TensorFlow, Caffe2, MXNet, PyTorch, and TensorFlow Lite. We focus on evaluating the latency, memory footprint, and energy of these tools with two popular types of neural networks on different edge devices. This evaluation not only provides a reference to select appropriate combinations of hardware and software packages for end users but also points out possible future directions to optimize packages for developers.

cs.DC↗

arXiv2019

OpenEI: An Open Framework for Edge Intelligence

In the last five years, edge computing has attracted tremendous attention from industry and academia due to its promise to reduce latency, save bandwidth, improve availability, and protect data privacy to keep data secure. At the same time, we have witnessed the proliferation of AI algorithms and models which accelerate the successful deployment of intelligence mainly in cloud services. These two trends, combined together, have created a new horizon: Edge Intelligence (EI). The development of EI requires much attention from both the computer systems research community and the AI community to meet these demands. However, existing computing techniques used in the cloud are not applicable to edge computing directly due to the diversity of computing sources and the distribution of data sources. We envision that there missing a framework that can be rapidly deployed on edge and enable edge AI capabilities. To address this challenge, in this paper we first present the definition and a systematic review of EI. Then, we introduce an Open Framework for Edge Intelligence (OpenEI), which is a lightweight software platform to equip edges with intelligent processing and data sharing capability. We analyze four fundamental EI techniques which are used to build OpenEI and identify several open problems based on potential research directions. Finally, four typical application scenarios enabled by OpenEI are presented.

cs.AI↗

arXiv2019

A Mobility-Aware Vehicular Caching Scheme in Content Centric Networks: Model and Optimization

Edge caching is being explored as a promising technology to alleviate the network burden of cellular networks by separating the computing functionalities away from cellular base stations. However, the service capability of existing caching scheme is limited by fixed edge infrastructure when facing the uncertainties of users' requests and locations. The vehicular caching, which uses the moving vehicles as cache carriers, is regard as an efficient method to solve the problem above. This paper studies the effectiveness of vehicular caching scheme in content centric networks by developing optimization model towards the minimization of network energy consumption. Particularly, we model the interactions between caching vehicles and mobile users as a 2-D Markov process, in order to characterize the network availability of mobile users. Based on the developed model, we propose an online vehicular caching design by optimizing network energy efficiency. Specifically, the problem of caching decision making is firstly formulated as a fractional optimization model, towards the optimal energy efficiency. Using nonlinear fractional programming technology and Lyapunov optimization theory, we derive the theoretical solution for the optimization model. An online caching algorithm to enable the optimal vehicular caching is developed based on the solution. Finally, extensive simulations are conducted to examine the performance of our proposal. By comparison, our online caching scheme outperforms the existing scheme in terms of energy efficiency, hit ratio, cache utilization, and system gain.

cs.NI↗

arXiv2018

PI-Edge: A Low-Power Edge Computing System for Real-Time Autonomous Driving Services

To simultaneously enable multiple autonomous driving services on affordable embedded systems, we designed and implemented π-Edge, a complete edge computing framework for autonomous robots and vehicles. The contributions of this paper are three-folds: first, we developed a runtime layer to fully utilize the heterogeneous computing resources of low-power edge computing systems; second, we developed an extremely lightweight operating system to manage multiple autonomous driving services and their communications; third, we developed an edge-cloud coordinator to dynamically offload tasks to the cloud to optimize client system energy consumption. To the best of our knowledge, this is the first complete edge computing system of a production autonomous vehicle. In addition, we successfully implemented π-Edge on a Nvidia Jetson and demonstrated that we could successfully support multiple autonomous driving services with only 11 W of power consumption, and hence proving the effectiveness of the proposed π-Edge system.

cs.DC↗

arXiv2018

CAVBench: A Benchmark Suite for Connected and Autonomous Vehicles

Connected and autonomous vehicles (CAVs) have recently attracted a significant amount of attention both from researchers and industry. Numerous studies targeting algorithms, software frameworks, and applications on the CAVs scenario have emerged. Meanwhile, several pioneer efforts have focused on the edge computing system and architecture design for the CAVs scenario and provided various heterogeneous platform prototypes for CAVs. However, a standard and comprehensive application benchmark for CAVs is missing, hindering the study of these emerging computing systems. To address this challenging problem, we present CAVBench, the first benchmark suite for the edge computing system in the CAVs scenario. CAVBench is comprised of six typical applications covering four dominate CAVs scenarios and takes four datasets as standard input. CAVBench provides quantitative evaluation results via application and system perspective output metrics. We perform a series of experiments and acquire three systemic characteristics of the applications in CAVBench. First, the operation intensity of the applications is polarized, which explains why heterogeneous hardware is important for a CAVs computing system. Second, all applications in CAVBench consume high memory bandwidth, so the system should be equipped with high bandwidth memory or leverage good memory bandwidth management to avoid the performance degradation caused by memory bandwidth competition. Third, some applications have worse data/instruction locality based on the cache miss observation, so the computing system targeting these applications should optimize the cache architecture. Last, we use the CAVBench to evaluate a typical edge computing platform and present the quantitative and qualitative analysis of the benchmarking results.

cs.DC↗

arXiv2018

Co-KV: A Collaborative Key-Value Store Using Near-Data Processing to Improve Compaction for the LSM-tree

Log-structured merge tree (LSM-tree) based key-value stores are widely employed in large-scale storage systems. In the compaction of the key-value store, SSTables are merged with overlapping key ranges and sorted for data queries. This, however, incurs write amplification and thus degrades system performance, especially under update-intensive workloads. Current optimization focuses mostly on the reduction of the overload of compaction in the host, but rarely makes full use of computation in the device. To address these issues, we propose Co-KV, a Collaborative Key-Value store between the host and a near-data processing ( i.e., NDP) model based SSD to improve compaction. Co-KV offers three benefits: (1) reducing write amplification by a compaction offloading scheme between host and device; (2) relieving the overload of compaction in the host and leveraging computation in the SSD based on the NDP model; and (3) improving the performance of LSM-tree based key-value stores under update-intensive workloads. Extensive db_bench experiment show that Co-KV largely achieves a 2.0x overall throughput improvement, and a write amplification reduction by up to 36.0% over the state-of-the-art LevelDB. Under YCSB workloads, Co-KV increases the throughput by 1.7x - 2.4x while decreases the write amplification and average latency by up to 30.0% and 43.0%, respectively.

cs.DC↗