Zheyi Chen

Prof. Dr. Zheyi Chen

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 July 2021 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
XCXing Chen
Xing Chen
JZJianshan Zhang
Jianshan Zhang
BLBing Lin
Bing Lin
Zheyi ChenZheyi Chen
Zheyi Chen
KWKatinka Wolter
Katinka Wolter
Geyong  MinGeyong Min
Geyong Min
Deep Neural Networks (DNNs) have become an essential and important supporting technology for smart Internet-of-Things (IoT) systems. Due to the high computational costs of large-scale DNNs, it might be infeasible to directly deploy them in energy-constrained IoT devices. Through offloading computation-intensive tasks to the cloud or edges, the computation offloading technology offers a feasible solution to execute DNNs. However, energy-efficient offloading for DNN based smart IoT systems with deadline constraints in the cloud-edge environments is still an open challenge. To address this challenge, we first design a new system energy consumption model, which takes into account the runtime, switching, and computing energy consumption of all participating servers (from both the cloud and edge) and IoT devices. Next, a novel energy-efficient offloading strategy based on a Self-adaptive Particle Swarm Optimization algorithm using the Genetic Algorithm operators (SPSO-GA) is proposed. This new strategy can efficiently make offloading decisions for DNN layers with layer partition operations, which can lessen the encoding dimension and improve the execution time of SPSO-GA. Simulation results demonstrate that the proposed strategy can significantly reduce energy consumption compared to other classic methods.

15 November 2019 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
Zheyi ChenZheyi Chen
Zheyi Chen
Jia HuJia Hu
Jia Hu
Geyong  MinGeyong Min
Geyong Min
Albert ZomayaAlbert Zomaya
Albert Zomaya
TETarek El-Ghazawi
Tarek El-Ghazawi

3 December 2021 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
Zheyi ChenZheyi Chen
Zheyi Chen
Jia HuJia Hu
Jia Hu
Geyong  MinGeyong Min
Geyong Min
CLChunbo Luo
Chunbo Luo
TETarek El-Ghazawi
Tarek El-Ghazawi
The ever-expanding scale of cloud datacenters necessitates automated resource provisioning to best meet the requirements of low latency and high energy-efficiency. However, due to the dynamic system states and various user demands, efficient resource allocation in cloud faces huge challenges. Most of the existing solutions for cloud resource allocation cannot effectively handle the dynamic cloud environments because they depend on the prior knowledge of a cloud system, which may lead to excessive energy consumption and degraded Quality-of-Service (QoS). To address this problem, we propose an adaptive and efficient cloud resource allocation scheme based on Actor-Critic Deep Reinforcement Learning (DRL). First, the actor parameterizes the policy (allocating resources) and chooses actions (scheduling jobs) based on the scores assessed by the critic (evaluating actions). Next, the resource allocation policy is updated by using gradient ascent while the variance of policy gradient is reduced with an advantage function, which improves the training efficiency of the proposed method. We conduct extensive simulation experiments using real-world data from Google cloud datacenters. The results show that our method can obtain the superior QoS in terms of latency and job dismissing rate with enhanced energy-efficiency, compared to two advanced DRL-based and five classic cloud resource allocation methods.

26 February 2021 in IEEE Access
Verified
Journal Article
Open access
HCHuilin Chen
Huilin Chen
Zheyi ChenZheyi Chen
Zheyi Chen
FLFeiting Lin
Feiting Lin
PZPeifen Zhuang
Peifen Zhuang
In agri-food supply chains (ASCs), consumers pay for agri-food products produced by farmers. During this process, consumers emphasize the importance of agri-food safety while farmers expect to increase their profits. Due to the complexity and dynamics of ASCs, the effective traceability and management for agri-food products face huge challenges. However, most of the existing solutions cannot well meet the requirements of traceability and management in ASCs. To address these challenges, we first design a blockchain-based ASC framework to provide product traceability, which guarantees decentralized security for the agri-food tracing data in ASCs. Next, a Deep Reinforcement learning based Supply Chain Management (DR-SCM) method is proposed to make effective decisions on the production and storage of agri-food products for profit optimization. The extensive simulation experiments are conducted to demonstrate the effectiveness of the proposed blockchain-based framework and the DR-SCM method under different ASC environments. The results show that reliable product traceability is well guaranteed by using the proposed blockchain-based ASC framework. Moreover, the DR-SCM can achieve higher product profits than heuristic and Q-learning methods.

3 May 2024 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
Zheyi ChenZheyi Chen
Zheyi Chen
BXBing Xiong
Bing Xiong
XCXing Chen
Xing Chen
Geyong  MinGeyong Min
Geyong Min
Jie LiJie Li
Jie Li
Through deploying computing resources at the network edge, Mobile Edge Computing (MEC) alleviates the contradiction between the high requirements of intelligent mobile applications and the limited capacities of mobile End Devices (EDs) in smart communities. However, existing solutions of computation offloading and resource allocation commonly rely on prior knowledge or centralized decision-making, which cannot adapt to dynamic MEC environments with changeable system states and personalized user demands, resulting in degraded Quality-of-Service (QoS) and excessive system overheads. To address this important challenge, we propose a novel Personalized Federated deep Reinforcement learning based computation Offloading and resource Allocation method (PFR-OA). This innovative PFR-OA considers the personalized demands in smart communities when generating proper policies of computation offloading and resource allocation. To relieve the negative impact of local updates on global model convergence, we design a new proximal term to improve the manner of only optimizing local Q-value loss functions in classic reinforcement learning. Moreover, we develop a new partial-greedy based participant selection mechanism to reduce the complexity of federated aggregation while endowing sufficient exploration. Using real-world system settings and testbed, extensive experiments demonstrate the effectiveness of the PFR-OA. Compared to benchmark methods, the PFR-OA achieves better trade-offs between delay and energy consumption and higher task execution success rates under different scenarios.

3 October 2024 in IEEE Journal on Selected Areas in Communications
Verified
Journal Article
Closed access
Zheyi ChenZheyi Chen
Zheyi Chen
JZJunjie Zhang
Junjie Zhang
Geyong  MinGeyong Min
Geyong Min
Zhaolong NingZhaolong Ning
Zhaolong Ning
Jie LiJie Li
Jie Li
The emerging Space-Air-Ground Integrated Networks (SAGIN) empower Mobile Edge Computing (MEC) with wider communication coverage and more flexible network access. However, the fluctuating user traffic and constrained computing architecture seriously hinder the Quality-of-Service (QoS) and resource utilization in SAGIN. Existing solutions generally depend on prior knowledge or adopt static resource provisioning, lacking adaptability and resulting in serious system overheads. To address these important challenges, we propose THOAS , a novel Traffic-aware lightweight Hierarchical Offloading framework towards Adaptive Slicing-enabled SAGIN. First, we innovatively separate SAGIN into Communication Access Platforms (CAPs) and Computation Offloading Platforms (COPs). Next, we design a new self-attention-based prediction method to accurately capture the traffic changes on each platform, enabling adaptive slice resource adjustments. Finally, we develop an improved deep reinforcement learning method based on proximal clipping with dynamic confidence intervals to reach optimal offloading. Notably, we employ knowledge distillation to compress offloading policies into lightweight networks, enhancing their adaptability in resource-limited SAGIN. Using real-world datasets of user traffic, extensive experiments are conducted. The results show that the THOAS can accurately predict traffic and make adaptive resource adjustments and offloading decisions, which outperforms other benchmark methods on multiple metrics under various scenarios.