Yitong Zhou

Yitong Zhou

Auto-generated profile, based on publicly available information

Yitong Zhou

Faculty of Computer Science, Dalhousie University, Halifax, Canada

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
24 September 2021 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
HHHui Huang
Hui Huang
Qiang YeQiang Ye
Qiang Ye
YZYitong Zhou
Yitong Zhou
Over the past years, computationally-intensive mobile applications, such as interactive games and augmented reality, have gained enormous popularity. This phenomenon has placed a serious burden on mobile devices with limited computation resources and constrained battery capacity. Multi-access Edge Computing (MEC) is proposed to solve the problem by offloading part of the computation tasks from mobile devices to edge servers. The fundamental challenge in MEC is how to effectively select a subset of computation tasks to be offloaded so that the application requirements are satisfied and the total energy consumption is minimized. The existing Deep Reinforcement Learning (DRL) based offloading schemes focus on either non-real-time tasks or real-time tasks with soft deadlines. In addition, the existing schemes do not work well when the information of the system environment is not complete. In this paper, we propose an innovative DRL-based task offloading method, PDMO, which guarantees that the deadlines of real-time tasks are met even when the system environment is only partially observable. Our experimental results indicate that PDMO works well in partially observable environments. In addition, it outperforms the existing offloading schemes in terms of energy consumption, deadline miss number and completion rate of non-real-time tasks.

22 March 2025 in ACM Transactions on Sensor Networks
Verified
Journal Article
Open access
HHHui Huang
Hui Huang
QYQiang Ye
Qiang Ye
YZYitong Zhou
Yitong Zhou
The proliferation of computation-intensive applications, such as autonomous driving, has urged mobile devices to alleviate their local computation pressure using external computing resources. As a promising solution, Multi-access Edge Computing tackles this problem by offloading computational tasks from mobile devices to edge servers. However, existing offloading schemes suffer from two fundamental limitations. First, they lack built-in measures to prevent deadline misses. For safety-critical applications, including autonomous driving, a deadline miss could result in catastrophic consequences. Second, existing schemes typically update offloading policies periodically. Namely, a policy based on the current system state is generated for a time window consisting of multiple time slots. Since system states could change from one time slot to the next one, the generated policy might not work well during the entire window. In this article, we propose a novel offloading scheme for safety-critical applications, Constrained Reinforcement Learning-based Offloading (CRLO). With CRLO, a safety layer is added to the learning-based policy generator, which effectively eliminates deadline misses. Furthermore, a long-sequence forecasting model, Informer, is utilized to predict temporally dependent system states, which helps to generate appropriate offloading policies. Our experimental results indicate that CRLO outperforms existing schemes in terms of deadline satisfaction and task completion time.

6 May 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
YZYitong Zhou
Yitong Zhou
Qiang YeQiang Ye
Qiang Ye
HHHui Huang
Hui Huang
Machine Learning (ML) has been widely applied to successfully address a variety of different problems across diverse domains, such as robotics, healthcare, and finance. However, high-complexity ML algorithms often require overlong computation time, which significantly impacts their feasibility. Distributed Machine Learning (DML) has been used to tackle the slow computation problem with high-complexity ML algorithms. Nevertheless, with DML, the computation results from all participating computing devices need to be collected in order to complete an ML task. When part of the participating devices, known as the stragglers, cannot return their results in time, the overall computation time will be extended. Distributed Coded Machine Learning (DCML) is a promising solution to mitigate the negative impact of the stragglers. With DCML, redundancy is injected into an ML task so that only a subset of the results from participating devices are required to finish the ML task. In DCML, how to select proper participating devices, referred to as workers, and how to allocate appropriate workloads to the selected workers are two challenging problems. In this paper, we consider a DCML scenario where numerous computing devices are available for an ML task. These devices are willing to offer their computation capacity in exchange for compensation. To encourage the computing devices to participate in the distributed computation, a reverse auction-based incentive mechanism is employed. With the objective of minimizing both the completion time of the ML task and the compensation for participating devices, we propose a Deep reinforcement learning based workload Allocation and worker Selection scheme for DCML, DAS. To our knowledge, this is the first attempt to simultaneously tackle both the workload allocation and worker selection issues in DCML. Our experimental results indicate that DAS outperforms the state-of-the-art schemes in terms of completion time and compensation.

25 September 2025 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
YZYitong Zhou
Yitong Zhou
Qiang YeQiang Ye
Qiang Ye
HHHui Huang
Hui Huang
Machine learning (ML) has been used in a wide range of applications. In recent years, the growing complexity of ML models has led to substantial computational demands. Distributed Machine Learning (DML) frameworks address this challenge by parallelizing computation across multiple devices. Yet, DML systems often suffer from the straggler effect, where the slowest devices delay task completion. Distributed Coded Machine Learning (DCML) mitigates this issue by injecting redundancy into subtasks, allowing partial results to suffice for completing the overall task. To fully exploit DCML, two critical problems, worker selection and workload allocation, must be addressed effectively, especially in large-scale edge networks characterized by unstable connectivity, dynamic device availability, and high-dimensional decision spaces. In this work, we propose a Multi-Agent Transformer-based workload Allocation and worker Selection (MAT-AS) scheme for DCML in large-scale edge networks. Technically, MAT-AS converts the multi-agent joint policy optimization problem into a sequential process to make robust decisions on worker selection and workload allocation. Experimental results demonstrate that MAT-AS significantly outperforms baseline approaches in task completion time and cost efficiency, making it a promising solution for efficient and adaptive DCML. Specifically, MAT-AS reduces task completion time by approximately 12% and computation cost by approximately 15% compared to the best baseline method.

1 January 2026 in IEEE Transactions on Cloud Computing
Verified
Journal Article
Closed access
HHHui Huang
Hui Huang
YZYitong Zhou
Yitong Zhou
Qiang YeQiang Ye
Qiang Ye