Towards cloud-edge collaborative online video analytics with fine-grained serverless pipelines

Zhang, Miao; Wang, Fangxin; Zhu, Yifei; Liu, Jiangchuan; Wang, Zhi

doi:10.1145/3458305.3463377

Cited by 19 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The critic networks are trained according to the loss objective defined in Eq. (17). Then, we optimize the policy objective and loss objective by Adam [33] optimizer.…”

Section: Training Methodologymentioning

confidence: 99%

“…Mainstream [16] designed a video processing system to efficiently utilize resources by dynamically adjusting the degree of resource sharing among applications. CEVAS [17] adopted a collaborative edge-cloud framework that dynamically partitioned the video analytics pipelines to optimize the system. Deepar [18] proposed a hybrid execution framework to fully utilize resources by hierarchically partitioning DNN networks among the device, edge, and cloud.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Collaborative Video Analytics on Distributed Edges with Multiagent Deep Reinforcement Learning

Dong¹,

Gao²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep Neural Network (DNN) based video analytics empowers many computer vision-based applications to achieve high recognition accuracy. To reduce inference delay and bandwidth cost for video analytics, the DNN models can be deployed on the edge nodes, which are proximal to end users. However, the processing capacity of an edge node is limited, potentially incurring substantial delay if the inference requests on an edge node is overloaded. While efforts have been made to enhance the video analytics by optimizing the configurations on a single edge node, we observe that multiple edge nodes can work collaboratively by utilizing the idle resources on each other to improve the overall processing capacity and resource utilization. To this end, we propose a Multiagent Reinforcement Learning (MARL) based approach, named as EdgeVision, for collaborative video analytics on distributed edges. The edge nodes can jointly learn the optimal policies for video preprocessing, model selection, and request dispatching by collaborating with each other to minimize the overall cost. We design an actorcritic based MARL algorithm with an attention mechanism to learn the optimal policies. We build a multi-edge-node testbed and conduct the experiments with real-world datasets to evaluate the performance of our method. The experimental results show our method can improve the overall rewards by 33.6%-86.4% compared with the most competitive baseline methods.

show abstract

“…The critic networks are trained according to the loss objective defined in Eq. (17). Then, we optimize the policy objective and loss objective by Adam [33] optimizer.…”

Section: Training Methodologymentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Collaborative Video Analytics on Distributed Edges with Multiagent Deep Reinforcement Learning

Dong¹,

Gao²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Edge-Edge ✓ ✓ ✓ accomplish real-time data analytics for computation-intensive and bandwidth-hungry video surveillance applications. Among them, solutions based on edge to cloud collaboration [6], [18], [7], [8] and edge to edge collaboration [15], [21], [22] have attracted most attention.…”

Section: Stream Schedulingmentioning

confidence: 99%

“…The three parts collaboratively perform the inference tasks submitted by users. Zhang et al [7] adopted a serverless-based infrastructure to facilitate finegrained and adaptive partitioning of cloud-edge workloads.…”

Section: Stream Schedulingmentioning

confidence: 99%

See 1 more Smart Citation

Blockchain-based Collaborative Edge Intelligence for Trustworthy and Real-Time Video Surveillance

Zhang

Cao

Sahni

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Trustworthy and real-time video surveillance aims to analyze the live camera streams in a privacy-preserving manner for the decision-making of various advanced services, such as pedestrian re-identification and traffic monitoring. In recent years, edge computing has been identified as a promising technology for trustworthy and real-time video surveillance because it keeps confidential video data locally and reduces the latency caused by massive data transmission. Generally, a single edge device can hardly afford the computation-intensive video analytics tasks. Most existing solutions incorporate cloud servers to handle the overloaded tasks. However, such an edge-cloud collaboration approach still suffers from unpredictable latency and privacy concerns because the remote cloud is centralized and distant from the cameras. In this work, we designed a blockchain-based collaborative edge intelligence (BCEI) approach for trustworthy and real-time video surveillance. In BCEI, geo-distributed edge devices form a peer-to-peer network to maintain a permissioned blockchain and share data and computation resources to perform computation-intensive video analytics tasks. The video analytics results are written on the blockchain in an immutable manner to guarantee trustworthiness. To reduce task execution time, we formulate and solve a joint stream mapping and task scheduling problem to schedule video streams and machine learning models among edge devices. A pedestrian re-identification prototype is implemented and deployed based on BCEI with extensive performance evaluation, indicating the superiority of BCEI in latency reduction and system throughput improvement by leveraging collaboration among edge devices.

show abstract

Evaluating NiFi and MQTT based serverless data pipelines in fog computing environments

Mirampalli,

Wankar,

Srirama

2024

Future Generation Computer Systems

View full text Add to dashboard Cite

Towards cloud-edge collaborative online video analytics with fine-grained serverless pipelines

Cited by 19 publications

References 31 publications

Collaborative Video Analytics on Distributed Edges with Multiagent Deep Reinforcement Learning

Collaborative Video Analytics on Distributed Edges with Multiagent Deep Reinforcement Learning

Blockchain-based Collaborative Edge Intelligence for Trustworthy and Real-Time Video Surveillance

Evaluating NiFi and MQTT based serverless data pipelines in fog computing environments

Contact Info

Product

Resources

About