Renli Zhang

Renli Zhang

Auto-generated profile, based on publicly available information

Renli Zhang

Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
20 February 2024 in IEEE/ACM Transactions on Networking
Verified
Journal Article
Closed access
RZRenli Zhang
Renli Zhang
Ruiting ZhouRuiting Zhou
Ruiting Zhou
YWYufeng Wang
Yufeng Wang
Haisheng TanHaisheng Tan
Haisheng Tan
KHKun He
Kun He
Unmanned aerial vehicles (UAVs) have emerged as a promising technology to provide low-latency mobile edge computing (MEC) services. To fully utilize the potential of UAV-assisted MEC in practice, both technical and economic challenges need to be addressed: how to optimize UAV trajectory for online task offloading and incentivize the participation of UAVs without compromising the privacy of user equipment (UE). In this work, we consider unique features of UAVs, i.e., high mobility as well as limited energy and computing capacity, and propose privacy-preserving auction frameworks, Ptero, to schedule offloading tasks on the fly and incentivize UAVs’ participation. Specifically, Ptero first decomposes the online task offloading problem into a series of one-round problems by scaling the UAV’s energy constraint into the objective. To protect UE’s privacy, Ptero calculates UAV’s coverage based on subset-anonymity. At each round, Ptero schedules UAVs greedily, computes remuneration for working UAVs, and processes unserved tasks in the cloud to maximize the system’s utility ( i.e., minimize social cost). Theoretical analysis proves that Ptero achieves truthfulness, individual rationality, computational efficiency, privacy-preserving and a nontrivial competitive ratio. Trace-driven evaluations further verify that Ptero can reduce the social cost by up to $116\%$ compared with four state-of-the-art algorithms.

13 February 2025 in IEEE Transactions on Services Computing
Verified
Journal Article
Closed access
Ruiting ZhouRuiting Zhou
Ruiting Zhou
YHYifeng Huang
Yifeng Huang
YWYufeng Wang
Yufeng Wang
LJLei Jiao
Lei Jiao
Haisheng TanHaisheng Tan
Haisheng Tan
Libing WuLibing Wu
Libing Wu
Unmanned aerial vehicles (UAVs) have emerged as a new and flexible paradigm to offer low-latency and diverse mobile edge computing (MEC) services for user equipment (UE). To minimize the service delay, caching is introduced in UAV-assisted MEC networks to bring service contents closer to UEs. However, UAV-assisted MEC is challenged by the heavy communication overhead introduced by service caching and UAV’s limited energy capacity. In this article, we propose an online algorithm, OOA, that jointly optimizes caching and offloading decisions for UAV-assisted MEC networks, to minimize the overall service delay. Specifically, to improve the caching effectiveness and reduce the caching overhead, OOA employs a greedy algorithm to dynamically make caching decisions based on UEs’ preferences on services and UAVs’ historical trajectories, with the goal of maximizing the probability of successful offloading. To realize the rational utilization of energy from a long-term perspective, OOA decomposes the online problem into a series of single-slot problems by scaling the UAV’s energy constraint into the objective, and iteratively optimizes UAV trajectory and task offloading at each time slot. Theoretical analysis proves that OOA converges to a suboptimal solution with polynomial time complexity. Extensive simulations based on real world data further show that OOA can reduce the service delay by up to 33% while satisfying the UAV’s energy constraint, compared to three state-of-the-art algorithms.

18 July 2024 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
ZHZiyi Han
Ziyi Han
Ruiting ZhouRuiting Zhou
Ruiting Zhou
CXChengzhong Xu
Chengzhong Xu
YZYifan Zeng
Yifan Zeng
RZRenli Zhang
Renli Zhang
As the applications of AI proliferate, it is critical to increase the throughput of online DNN inference services. Multi-process service (MPS) improves the utilization rate of GPU resources by spatial-sharing, but it also brings unique challenges. First, interference between co-located DNN models deployed on the same GPU must be accurately modeled. Second, inference tasks arrive dynamically online, and each task needs to be served within a bounded time to meet the service-level objective (SLO). Third, the problem of fragments has become more serious. To address the above three challenges, we propose an In telligent S cheduling orchestrator for multi-GPU inference servers with spatio-temporal S haring ( InSS ), aiming to maximize the system throughput. InSS exploits two key innovations: i) An interference-aware latency analytical model which estimates the task latency. ii) A two-stage intelligent scheduler is tailored to jointly optimize the model placement, GPU resource allocation and adaptively decides batch size by coupling the latency analytical model. Our prototype implementation on four NVIDIA A100 GPUs shows that InSS can improve the throughput by up to 86% compared to the state-of-the-art GPU schedulers, while satisfying SLOs. We further show the scalability of InSS on 64 GPUs.

8 June 2022 in IEEE Journal on Selected Areas in Communications
Verified
Journal Article
Closed access
NWNe Wang
Ne Wang
Ruiting ZhouRuiting Zhou
Ruiting Zhou
LJLei Jiao
Lei Jiao
RZRenli Zhang
Renli Zhang
BLBo Li
Bo Li
ZLZongpeng Li
Zongpeng Li
Recent advances in 5G and edge computing enable rapid development and deployment of edge-cloud systems, which are ideal for delay-sensitive machine learning (ML) applications such as autonomous driving and smart city. Distributed ML jobs often need to train a large model with enormous datasets, which can only be handled by deploying a distributed set of workers in an edge-cloud system. One common approach is to employ a parameter server (PS) architecture, in which training is carried out at multiple workers, while PSs are used for aggregation and model updates. In this architecture, one of the fundamental challenges is how to dispatch ML jobs to workers and PSs such that the average job completion time (JCT) can be minimized. In this work, we propose a novel online preemptive scheduling framework to decide the location and the execution time window of concurrent workers and PSs upon each job arrival. Specifically, our proposed scheduling framework consists of: i) a job dispatching and scheduling algorithm that assigns each ML job to workers and decides the schedule to train each data chunk; ii) a PS assignment algorithm that determines the placement of PS. We prove theoretically that our proposed algorithm is $D_{max}(1+1/\epsilon)$ -competitive with $(1 + \epsilon)$ -speed augmentation, where $D_{max}$ is the maximal number of data chunks in any job. Extensive testbed experiments and trace-driven simulations show that our algorithm can reduce the average JCT by up to 30% compared with state-of-the-art baselines.

29 November 2023 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
JPJinlong Pang
Jinlong Pang
ZHZiyi Han
Ziyi Han
Ruiting ZhouRuiting Zhou
Ruiting Zhou
RZRenli Zhang
Renli Zhang
JLJohn C.S. Lui
John C.S. Lui
HCHao Chen
Hao Chen
The emergence of edge intelligence has made smart IoT services ( e.g., video/audio surveillance, autonomous driving and smart city) a reality. To ensure the quality of service, edge service providers train unbiased models of distributed machine learning jobs over the local datasets collected by edge networks, and usually adopt the parameter server (PS) architecture. However, the training of unbiased distributed learning (UDL) depends on geo-distributed data and edge resources, bringing a new challenge for service providers: how to effectively schedule and price UDL jobs such that the long-term system utility ( i.e., social welfare) can be maximized. In this paper, we propose an online auction-based scheduling algorithm Eris , which determines the data workload, the number and the placement of concurrent workers and PSs for each arriving UDL job, and dynamically prices limited edge resources based on current resource consumption. Eris applies a primal-dual framework which calls an efficient dual subroutine to schedule UDL jobs, achieving a good competitive ratio and pseudo-polynomial time complexity. To evaluate the effectiveness of Eris , we implement both a testbed and a large-scaled simulator. The results demonstrate that Eris outperforms and achieves up to 44% more social welfare compared to state-of-the-art algorithms in today's cloud system.

9 February 2023 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
RZRenli Zhang
Renli Zhang
Ruiting ZhouRuiting Zhou
Ruiting Zhou
Containers are more lightweight and agile, which are merging as an alternative to virtual machines to provide efficient cloud computing services. For cloud service providers, there are two main challenges for provisioning container clusters: i) Design an optimal placement scheme while considering the communication between containers; ii) Flexible pricing mechanism, which not only meets the market demand but also maximizes the social welfare or provider's profit. To solve the above challenges, this paper proposes an efficient auction that achieves truthfulness and computational efficiency, targeting social welfare and provider's profit maximization. We first model the problem into a non-conventional integer linear program (ILP), considering both inter-container traffic flow and resources consumed in containers. We then introduce auxiliary variables and reformulate them to a classical packing-type ILP. Second, we apply the primal-dual technique to design an effective online auction algorithm, based on the number of consumed resources to ensure the flexible supply of resources while obtaining maximum social welfare. Third, we use a randomized reduction algorithm to convert the optimization objective to the provider's profit maximization. We prove that the competitive ratio of the two auctions are $\ln \lambda$ and $O(\ln \lambda +\log _{2}\kappa)$ , and verify that our auctions perform well in various settings through simulations.