Cheng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Cheng Zhang has a total of 64 co-authors. Here are the top co-authors by number of shared publications:
- Xiaofei Wang
Tianjin University
18 shared publications - Chao Qiu
Tianjin University
10 shared publications - Shaoyuan Huang
Tianjin University, Tianjin, China
5 shared publications - Shihao Shen
College of Intelligence and Computing, Tianjin University, Tianjin, China
5 shared publications - Tiancheng Zhang
College of Intelligence and Computing, Tianjin University, Tianjin, China
5 shared publications - Dawei Song
Beijing Institute of Technology, Beijing, China
3 shared publications
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (7) , 4239-4253
DynEformer: A Unified Framework for Robust Workload Prediction Under Dynamic Environment
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (7) , 4239-4253
DynEformer: A Unified Framework for Robust Workload Prediction Under Dynamic Environment
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 23, 402-416
Delay-Aware and Energy-Efficient Integrated Optimization System for 5G Networks
To meet the demands of high-capacity and low-delay services, Fifth Generation (5G) Base Stations (BSs) are typically deployed in ultra-dense configurations, especially in urban areas. While this densification enhances coverage and service quality, it also leads to substantially increased energy consumption. However, the dense deployment pattern makes BS workloads more responsive to the spatiotemporal variations in user behavior, offering opportunities for energy-saving strategies that dynamically adjust BS operation states. In this context, we propose a Delay-aware and Energy-efficient Integrated Optimization System (DEIS) based on Deep Reinforcement Learning (DRL), which jointly optimizes energy consumption and network delay while maintaining user satisfaction. DEIS leverages a real-world dataset collected from operational 5G BSs provided by partner network operators, containing both BS deployment data and high-volume user request logs. Extensive simulations demonstrate that DEIS can achieve a 41% reduction in energy consumption while ensuring reliable delay performance.
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 23, 402-416
Delay-Aware and Energy-Efficient Integrated Optimization System for 5G Networks
To meet the demands of high-capacity and low-delay services, Fifth Generation (5G) Base Stations (BSs) are typically deployed in ultra-dense configurations, especially in urban areas. While this densification enhances coverage and service quality, it also leads to substantially increased energy consumption. However, the dense deployment pattern makes BS workloads more responsive to the spatiotemporal variations in user behavior, offering opportunities for energy-saving strategies that dynamically adjust BS operation states. In this context, we propose a Delay-aware and Energy-efficient Integrated Optimization System (DEIS) based on Deep Reinforcement Learning (DRL), which jointly optimizes energy consumption and network delay while maintaining user satisfaction. DEIS leverages a real-world dataset collected from operational 5G BSs provided by partner network operators, containing both BS deployment data and high-volume user request logs. Extensive simulations demonstrate that DEIS can achieve a 41% reduction in energy consumption while ensuring reliable delay performance.
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (12) , 12784-12801
Enabling Real-Time Video Detection With Adaptive and Distributed Scheduling in Mobile Edge Computing
Real-time video detection is essential for many mobile visual applications, which brings the heavy computational burden of deep neural networks. Mobile edge computing offers a promising solution by deploying computational resources near mobile devices. However, achieving efficient video detection on mobile devices requires addressing challenges such as different performance requirements, diverse computing and network conditions, and system dynamics. We propose a real-time video detection framework in mobile edge computing, where multiple video streams from mobile devices are processed while balancing key performance metrics with consideration of grouping. A joint optimization problem of task scheduling, model selection, and resource provisioning is formulated for the system, where decisions are made on two timescales. To this end, we propose a window controller to unify decision-making at the time-slot level. We design an online scheduling algorithm based on multi-agent deep reinforcement learning to enable adaptive and distributed scheduling, while a masking-enhanced attention mechanism enables efficient explicit information exchange between mobile devices. Experimental evaluations across different numbers of mobile devices demonstrate that, in terms of average reward, the proposed algorithm outperforms local processing by 14.600%, fixed offloading by 10.007%, and four learning-based scheduling baselines by an average of 2.267%.
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (12) , 12784-12801
Enabling Real-Time Video Detection With Adaptive and Distributed Scheduling in Mobile Edge Computing
Real-time video detection is essential for many mobile visual applications, which brings the heavy computational burden of deep neural networks. Mobile edge computing offers a promising solution by deploying computational resources near mobile devices. However, achieving efficient video detection on mobile devices requires addressing challenges such as different performance requirements, diverse computing and network conditions, and system dynamics. We propose a real-time video detection framework in mobile edge computing, where multiple video streams from mobile devices are processed while balancing key performance metrics with consideration of grouping. A joint optimization problem of task scheduling, model selection, and resource provisioning is formulated for the system, where decisions are made on two timescales. To this end, we propose a window controller to unify decision-making at the time-slot level. We design an online scheduling algorithm based on multi-agent deep reinforcement learning to enable adaptive and distributed scheduling, while a masking-enhanced attention mechanism enables efficient explicit information exchange between mobile devices. Experimental evaluations across different numbers of mobile devices demonstrate that, in terms of average reward, the proposed algorithm outperforms local processing by 14.600%, fixed offloading by 10.007%, and four learning-based scheduling baselines by an average of 2.267%.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 745-761
FLARE: Federated Lightweight Agents for Reinforcement Environments in Microgrids
With the development of smart grid, the significant role of artificial intelligence technologies in microgrid state analysis and energy scheduling is becoming increasingly evident. The microgrids constantly generate a massive amount of computational requests. However, the distributed architecture of microgrids poses challenges for processing computing requests, such as limited resources at single nodes and load imbalance. In this paper, we propose FLARE, an end-edge-cloud collaboration computing architecture in microgrids, to optimize request scheduling. The optimization objective of the scheduling algorithm is to maximize long-term comprehensive utility considering factors such as delay and energy consumption. We utilize Deep Reinforcement Learning (DRL) to tackle this NP-hard problem. To address the deployment and update issues of distributed schedulers on end devices, we introduce model pruning and Federated Learning (FL). Experimental results demonstrate that FLARE outperforms state-of-the-art heuristic and centralized algorithms in terms of performance and scalability.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 745-761
FLARE: Federated Lightweight Agents for Reinforcement Environments in Microgrids
With the development of smart grid, the significant role of artificial intelligence technologies in microgrid state analysis and energy scheduling is becoming increasingly evident. The microgrids constantly generate a massive amount of computational requests. However, the distributed architecture of microgrids poses challenges for processing computing requests, such as limited resources at single nodes and load imbalance. In this paper, we propose FLARE, an end-edge-cloud collaboration computing architecture in microgrids, to optimize request scheduling. The optimization objective of the scheduling algorithm is to maximize long-term comprehensive utility considering factors such as delay and energy consumption. We utilize Deep Reinforcement Learning (DRL) to tackle this NP-hard problem. To address the deployment and update issues of distributed schedulers on end devices, we introduce model pruning and Federated Learning (FL). Experimental results demonstrate that FLARE outperforms state-of-the-art heuristic and centralized algorithms in terms of performance and scalability.
- Open Access
Sentinel: Scheduling Live Streams with Proactive Anomaly Detection in Crowdsourced Cloud-Edge Platforms
With the rapid growth of live streaming services, Crowdsourced Cloud-edge service Platforms (CCPs) are playing an increasingly important role in meeting the increasing demand. Although stream scheduling plays a critical role in optimizing CCPs' revenue, most optimization strategies struggle to achieve practical results due to various anomalies in unstable CCPs. Additionally, the substantial scale of CCPs magnifies the difficulties of anomaly detection in time-sensitive scheduling. To tackle these challenges, this paper proposes Sentinel, a proactive anomaly detection-based scheduling framework. Sentinel models the scheduling process as a two-stage Pre-Post-Scheduling paradigm: in the pre-scheduling stage, Sentinel conducts anomaly detection and constructs a strategy pool; in the post-scheduling stage, upon request arrival, it triggers an appropriate scheduling based on a pre-generated strategy to implement the scheduling process. Extensive experiments on realistic datasets show that Sentinel significantly reduces anomaly frequency by 70%, improves revenue by 74%, and doubles the scheduling speed.
Open AccessSentinel: Scheduling Live Streams with Proactive Anomaly Detection in Crowdsourced Cloud-Edge Platforms
With the rapid growth of live streaming services, Crowdsourced Cloud-edge service Platforms (CCPs) are playing an increasingly important role in meeting the increasing demand. Although stream scheduling plays a critical role in optimizing CCPs' revenue, most optimization strategies struggle to achieve practical results due to various anomalies in unstable CCPs. Additionally, the substantial scale of CCPs magnifies the difficulties of anomaly detection in time-sensitive scheduling. To tackle these challenges, this paper proposes Sentinel, a proactive anomaly detection-based scheduling framework. Sentinel models the scheduling process as a two-stage Pre-Post-Scheduling paradigm: in the pre-scheduling stage, Sentinel conducts anomaly detection and constructs a strategy pool; in the post-scheduling stage, upon request arrival, it triggers an appropriate scheduling based on a pre-generated strategy to implement the scheduling process. Extensive experiments on realistic datasets show that Sentinel significantly reduces anomaly frequency by 70%, improves revenue by 74%, and doubles the scheduling speed.
- 25 April 2025
- Published by Oxford University Press (OUP) in The Computer Journal
Unravelling the semantic mysteries of transformers layer by layer
Despite the significant success of transformer models and their successors in various natural language processing (NLP) applications, their internal workings are still not fully understood. Much of the current interpretability research has focused primarily on numerical components, often missing the complex semantic layers within these models. To fill this gap, this study explores the interpretability of the transformer model, a cornerstone of modern NLP, by addressing the semantic complexities of its multi-layer architecture. We identify three key questions: (i) the influence of the multi-layer structure on semantic processing, (ii) the unique contributions of each layer to model performance, and (iii) methodologies for determining optimal layer counts for the encoder and decoder. To tackle these issues, we introduce the semantic interpreter for transformer hierarchy, an innovative framework that employs convex hull metrics to visualize and assess semantic quality and quantity. Our contributions include novel methods for semantic assessment, a dual analytical framework that integrates cumulative and layer-to-layer perspectives, and insights into the dynamics of encoding and decoding. This comprehensive approach aims to enhance the understanding of Transformer models, ultimately guiding their refinement for improved interpretability and effectiveness in natural language tasks.
- 25 April 2025
- Published by Oxford University Press (OUP) in The Computer Journal
Unravelling the semantic mysteries of transformers layer by layer
Despite the significant success of transformer models and their successors in various natural language processing (NLP) applications, their internal workings are still not fully understood. Much of the current interpretability research has focused primarily on numerical components, often missing the complex semantic layers within these models. To fill this gap, this study explores the interpretability of the transformer model, a cornerstone of modern NLP, by addressing the semantic complexities of its multi-layer architecture. We identify three key questions: (i) the influence of the multi-layer structure on semantic processing, (ii) the unique contributions of each layer to model performance, and (iii) methodologies for determining optimal layer counts for the encoder and decoder. To tackle these issues, we introduce the semantic interpreter for transformer hierarchy, an innovative framework that employs convex hull metrics to visualize and assess semantic quality and quantity. Our contributions include novel methods for semantic assessment, a dual analytical framework that integrates cumulative and layer-to-layer perspectives, and insights into the dynamics of encoding and decoding. This comprehensive approach aims to enhance the understanding of Transformer models, ultimately guiding their refinement for improved interpretability and effectiveness in natural language tasks.
- 29 March 2025
- Published by Springer Nature
- p. 435-447
QDPformer: Quantum-Driven Workload Prediction Model Based on Transformer
- 29 March 2025
- Published by Springer Nature
- p. 435-447
QDPformer: Quantum-Driven Workload Prediction Model Based on Transformer
- 29 March 2025
- Published by Springer Nature
- p. 409-420
MTEE: Multiscale Temporal Entropy Evaluation Paradigm for Heterogeneous Complex Datasets
- 29 March 2025
- Published by Springer Nature
- p. 409-420
MTEE: Multiscale Temporal Entropy Evaluation Paradigm for Heterogeneous Complex Datasets
- 29 March 2025
- Published by Springer Nature
- p. 297-309
AnaNET: Anatomical Network for Aggregated Time Series Forecasting in Multi-layered Architecture
- 29 March 2025
- Published by Springer Nature
- p. 297-309
AnaNET: Anatomical Network for Aggregated Time Series Forecasting in Multi-layered Architecture