zhenyi wang

Dr. zhenyi wang


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
26 June 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
WLWenkai Lv
Wenkai Lv
PYPengfei Yang
Pengfei Yang
TZTianyang Zheng
Tianyang Zheng
CLChengmin Lin
Chengmin Lin
ZWzhenyi wang
zhenyi wang
QWQuan Wang
Quan Wang
Microservice architecture is a design philosophy that achieves decoupling by decomposing a monolithic application into multiple lightweight microservices. Meanwhile, edge computing can significantly reduce service latency and network congestion by extending computation and storage resources to the network edge. Therefore, in the microservice-oriented edge computing platform, a fundamental problem is how to efficiently deploy microservices with complex dependencies on the resource-constrained edge servers to satisfy the Quality of Service (QoS) constraints of users. Most of the existing studies ignore multiple call graphs with differentiated dependencies for an application, which often result in the violation of QoS. To address this issue, in this article, we first model the request response time of multiple instances and multiple call graphs scenario with service conflicts. Then, different from the existing heuristic or approximation algorithms which rely heavily on expert knowledge, we propose a graph-reinforcement-learning-based deployment (GRLD) framework. GRLD uses a graph convolutional network (GCN) to extract the graph data required for multiple call graphs with messages passing and aggregation, and the generated feature is fed into the underlying network of deep-reinforcement-learning (DRL). Experimental results show that GRLD outperforms counterparts in reducing service deployment overhead while satisfying QoS constraints of multiple call graphs.

4 September 2023 in Neural Networks
Verified
Journal Article
Closed access
CLChengmin Lin
Chengmin Lin
PYPengfei Yang
Pengfei Yang
QWQuan Wang
Quan Wang
ZQZeyu Qiu
Zeyu Qiu
WLWenkai Lv
Wenkai Lv
ZWzhenyi wang
zhenyi wang

22 November 2023 in Neural Networks
Verified
Journal Article
Closed access
ZWzhenyi wang
zhenyi wang
PYPengfei Yang
Pengfei Yang
LHLinwei Hu
Linwei Hu
BZBowen Zhang
Bowen Zhang
CLChengmin Lin
Chengmin Lin
QWQuan Wang
Quan Wang

16 October 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
CLChengmin Lin
Chengmin Lin
PYPengfei Yang
Pengfei Yang
QWQuan Wang
Quan Wang
YGYitong Guo
Yitong Guo
ZWzhenyi wang
zhenyi wang
In hardware-aware neural architecture search (NAS), accurately assessing a model’s inference efficiency is crucial for search optimization. Traditional approaches, which measure numerous samples to train proxy models, are impractical across varied platforms due to the extensive resources needed to remeasure and rebuild models for each platform. To address this challenge, we propose a multihardware-aware NAS method that enhances the generalizability of proxy models across different platforms while reducing the required sample size. Our method introduces a multihardware adaptive latency prediction (MHLP) model that leverages one-hot encoding for hardware parameters and multihead attention mechanisms to effectively capture the intricate interplay between hardware attributes and network architecture features. Additionally, we implement a two-stage sampling mechanism based on probability density weighting to ensure the representativeness and diversity of the sample set. By adopting a dynamic sample allocation mechanism, our method can adjust the adaptive sample size according to the initial model state, providing stronger data support for devices with significant deviations. Evaluations on NAS benchmarks demonstrate the MHLP predictor’s excellent generalization accuracy using only 10 samples, guiding the NAS search process to identify optimal network architectures.

11 July 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
ZWzhenyi wang
zhenyi wang
PYPengfei Yang
Pengfei Yang
BZBowen Zhang
Bowen Zhang
LHLinwei Hu
Linwei Hu
WLWenkai Lv
Wenkai Lv
QWQuan Wang
Quan Wang
For heterogeneous multiprocessor system-on-chips (HMPSoCs), a reasonable pipeline design can significantly improve the inference performance of deep learning (DL) models. The pipeline design optimization can be modeled as a search problem where an accurate prediction model can efficiently speed up the search process. However, the performance prediction of DL models for the pipeline inference strategy is challenging because of the interlayer effect, inference details, and variety of model structures. In this article, we propose TPPNet, a transformer-based model for predicting the inference performance of various DL models with the pipeline inference strategy. TPPNet represents the DL model as an execution sequence with operators and hardware details to extract the hidden factors between layers. Moreover, we apply the multitask learning (MTL) method to accurately predict throughput and latency metrics by constructing a predictive model. To the best of our knowledge, this is the first study dedicated to pipeline inference performance prediction for the DL model on HMPSoCs. We evaluate TPPNet on six well-known DL models using RK3399. The experimental outcomes affirm the high accuracy of TPPNet and its capability to significantly reduce the time overhead associated with pipeline exploration.

29 May 2024 in Information Sciences
Verified
Journal Article
Closed access
CLChengmin Lin
Chengmin Lin
PYPengfei Yang
Pengfei Yang
CLChengcheng Li
Chengcheng Li
FCFei Cheng
Fei Cheng
WLWenkai Lv
Wenkai Lv
QWQuan Wang
Quan Wang