Haodong Zou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Haodong Zou has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Tian Wang
Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China
10 shared publications - Changfu Xu
Jiangxi University of Finance and Economics
8 shared publications - Jianxiong Guo
The Affiliated Brain Hospital, Guangzhou Medical University, Guangzhou, China
8 shared publications - Yuzhu Liang
Beijing Normal University
6 shared publications - Jiannong Cao
The Hong Kong Polytechnic University
5 shared publications - Yupeng Li
Department of Interactive Media, Hong Kong Baptist University, Hong Kong, China
4 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 19974-19987
Cooperative Edge Caching for Profit Maximization Based on Multi-Agent Deep Reinforcement Learning
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 19974-19987
Cooperative Edge Caching for Profit Maximization Based on Multi-Agent Deep Reinforcement Learning
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6021-6032
Attention Heads Hold the Key to Understanding Safety Mechanisms in Large Language Models
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6021-6032
Open AccessAttention Heads Hold the Key to Understanding Safety Mechanisms in Large Language Models
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 37 (7) , 1657-1670
Adaptive Image Batching and Slicing in Edge Networks for Delay-Critical Small Object Detection
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 37 (7) , 1657-1670
Adaptive Image Batching and Slicing in Edge Networks for Delay-Critical Small Object Detection
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 5271-5286
Fine-Grained Lifetime Control for Heterogeneous Service Provisioning in Energy-Constrained Edge-Edge Systems
To support delay-critical applications, migrating services from the cloud to edge servers (ESs) can effectively reduce service delay. However, in such a resource-constrained scenario, providing heterogeneous services to meet diverse user needs poses significant challenges. Specifically, ESs have limited computational resources and are often energy-constrained, complicating service placement and provisioning. Existing studies propose collaboration schemes to improve resource utilization and reduce service delay. Nevertheless, these works heavily depend on full-service coverage by the cloud or rely on coarse-grained (e.g., time-cycle level) strategies that inevitably waste energy in idle time slots, which are unsuitable for energy-constrained settings and dynamic edge environments. To address these challenges, we propose a novel edge-edge collaboration method tailored for heterogeneous edge service provisioning in energy-constrained networks. First, we formulate the heterogeneous service provisioning problem with the objective of delay minimization under energy constraints and prove its NP-hardness. Our framework leverages latest task statistics to decide the service lifetime in a fine-grained time slot level, so that enables edge collaboration to maximize resource utilization and adaptability in resource-limited conditions. Specifically, we decompose the problem into three subproblems: service placement, service lifetime decision, and task scheduling, and we design targeted lightweight solutions for each, ensuring low delay and efficient energy usage. Finally, we validate our method through comprehensive simulations on real-world datasets and implement it on a testbed with three ESs. Results demonstrate that our approach reduces service delays by an average of 69.6% across various energy-constrained scenarios.
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 5271-5286
Fine-Grained Lifetime Control for Heterogeneous Service Provisioning in Energy-Constrained Edge-Edge Systems
To support delay-critical applications, migrating services from the cloud to edge servers (ESs) can effectively reduce service delay. However, in such a resource-constrained scenario, providing heterogeneous services to meet diverse user needs poses significant challenges. Specifically, ESs have limited computational resources and are often energy-constrained, complicating service placement and provisioning. Existing studies propose collaboration schemes to improve resource utilization and reduce service delay. Nevertheless, these works heavily depend on full-service coverage by the cloud or rely on coarse-grained (e.g., time-cycle level) strategies that inevitably waste energy in idle time slots, which are unsuitable for energy-constrained settings and dynamic edge environments. To address these challenges, we propose a novel edge-edge collaboration method tailored for heterogeneous edge service provisioning in energy-constrained networks. First, we formulate the heterogeneous service provisioning problem with the objective of delay minimization under energy constraints and prove its NP-hardness. Our framework leverages latest task statistics to decide the service lifetime in a fine-grained time slot level, so that enables edge collaboration to maximize resource utilization and adaptability in resource-limited conditions. Specifically, we decompose the problem into three subproblems: service placement, service lifetime decision, and task scheduling, and we design targeted lightweight solutions for each, ensuring low delay and efficient energy usage. Finally, we validate our method through comprehensive simulations on real-world datasets and implement it on a testbed with three ESs. Results demonstrate that our approach reduces service delays by an average of 69.6% across various energy-constrained scenarios.
- Top Cited Papers
- 19 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 20583-20599
A Comprehensive Survey on Large Language Model Compression for Artificial Intelligence Applications in Edge Systems
Large language models (LLMs) have achieved remarkable performance across various artificial intelligence (AI) applications. However, current LLMs cannot be deployed directly on edge nodes due to their large number of parameters. Fortunately, model compression technology has been proposed to reduce the computational workload and memory usage of LLMs, enabling further edge-based LLM services. However, existing research typically concentrates on isolated compression algorithms and lacks a comprehensive perspective on how to leverage these techniques for practical, end-to-end LLM deployment in edge environments. In this survey, we review edge-oriented LLM compression techniques and software–hardware codesign strategies to enable efficient LLM deployment on resource-constrained edge systems and guide future research in this area. First, we analyze techniques for LLM compression from the perspective of cloud–edge collaborative intelligence, including model quantization, parameter pruning, and knowledge distillation (KD). Second, we present several hybrid model frameworks tailored to dynamic, heterogeneous edge environments, based on model architecture, application scenarios, and combination selection. Third, we further refine a four-layer software–hardware codesign and an overhead-aware LLM deployment optimization. Finally, we discuss the challenges of current model compression approaches and offer insights into future research directions, with a focus on edge-based LLM services.
- 19 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 20583-20599
Top Cited PapersA Comprehensive Survey on Large Language Model Compression for Artificial Intelligence Applications in Edge Systems
Large language models (LLMs) have achieved remarkable performance across various artificial intelligence (AI) applications. However, current LLMs cannot be deployed directly on edge nodes due to their large number of parameters. Fortunately, model compression technology has been proposed to reduce the computational workload and memory usage of LLMs, enabling further edge-based LLM services. However, existing research typically concentrates on isolated compression algorithms and lacks a comprehensive perspective on how to leverage these techniques for practical, end-to-end LLM deployment in edge environments. In this survey, we review edge-oriented LLM compression techniques and software–hardware codesign strategies to enable efficient LLM deployment on resource-constrained edge systems and guide future research in this area. First, we analyze techniques for LLM compression from the perspective of cloud–edge collaborative intelligence, including model quantization, parameter pruning, and knowledge distillation (KD). Second, we present several hybrid model frameworks tailored to dynamic, heterogeneous edge environments, based on model architecture, application scenarios, and combination selection. Third, we further refine a four-layer software–hardware codesign and an overhead-aware LLM deployment optimization. Finally, we discuss the challenges of current model compression approaches and offer insights into future research directions, with a focus on edge-based LLM services.
- 2 January 2026
- Published by Springer Nature
- p. 510-523
EC-MADRL: AI-Enhanced Edge Cooperation Caching Based on Multi-agent Deep Reinforcement Learning
- 2 January 2026
- Published by Springer Nature
- p. 510-523
EC-MADRL: AI-Enhanced Edge Cooperation Caching Based on Multi-agent Deep Reinforcement Learning
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (4) , 4747-4761
Logical Correction Enabled Collaborative Person Detection Inference in Edge Networks
Person detection in videos is vital for area admission and public safety. Existing studies have made significant progress in improving the accuracy of this task on the cloud.Meanwhile, with people’s increasing awareness of privacy protection, there is a surging demand for privacy not being transmitted and processed by the cloud. Thus, providing services on edges becomes a promising solution. The dilemma is that edges are typically resource-constrained and cannot support the deployment of large models. However, tiny models that fit resource-constrained edges generally have unsatisfactory performance in accuracy and efficiency. To this end, we propose a Logical Correction Enabled Collaborative Person Detection Inference (LC-CPDI) framework for resource-constrained edges. First, we formulate the problem studied with a delay minimization objective. Second, we design a logical correction scheme to perceive abnormal predictions and perform corrections to improve accuracy. Third, a hybrid position prediction algorithm is proposed to replace time-consuming inference for simple scenarios. Finally, we design a collaborative inference scheme that enables frame outsourcing to idle edges to reduce the inference delay. We implemented LC-CPDI on a testbed designed with commercial edges. The experiments on real-world datasets show the effectiveness of LC-CPDI with up to 41.8% delay reduction on average and near 2% recall improvement.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (4) , 4747-4761
Logical Correction Enabled Collaborative Person Detection Inference in Edge Networks
Person detection in videos is vital for area admission and public safety. Existing studies have made significant progress in improving the accuracy of this task on the cloud.Meanwhile, with people’s increasing awareness of privacy protection, there is a surging demand for privacy not being transmitted and processed by the cloud. Thus, providing services on edges becomes a promising solution. The dilemma is that edges are typically resource-constrained and cannot support the deployment of large models. However, tiny models that fit resource-constrained edges generally have unsatisfactory performance in accuracy and efficiency. To this end, we propose a Logical Correction Enabled Collaborative Person Detection Inference (LC-CPDI) framework for resource-constrained edges. First, we formulate the problem studied with a delay minimization objective. Second, we design a logical correction scheme to perceive abnormal predictions and perform corrections to improve accuracy. Third, a hybrid position prediction algorithm is proposed to replace time-consuming inference for simple scenarios. Finally, we design a collaborative inference scheme that enables frame outsourcing to idle edges to reduce the inference delay. We implemented LC-CPDI on a testbed designed with commercial edges. The experiments on real-world datasets show the effectiveness of LC-CPDI with up to 41.8% delay reduction on average and near 2% recall improvement.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (12) , 12983-12998
Enhancing QoE in Collaborative Edge Systems With Feedback Diffusion Generative Scheduling
Collaborative edge computing is a promising approach for delivering low-delay services to computation-intensive Internet of Things applications. Deep Reinforcement Learning (DRL) has become an effective way to solve task scheduling decisions in edge systems due to its adaptive learning ability to interact with the environment. However, current DRL-based task scheduling methods still face several challenges, such as limited exploration, sample inefficiency, and performance instability, which can lead to degraded user Quality of Experience (QoE). To address these challenges, we observe that diffusion models, famous for their performance in image generation, exhibit strong exploration, data efficiency, and performance stability. This inspires us to propose FDEdge, a novel feedback diffusion generative scheduling method for enhancing user QoE in collaborative edge systems. We first design an innovative Feedback Diffusion (FDN) model by leveraging historical action probability information during the denoising process. We then incorporate the FDN model into DRL, forming an effective and efficient framework for task scheduling in collaborative edge systems. We also present a probability derivation to ensure the FDEdge’s rationality. Extensive experimental results demonstrate that our FDEdge method significantly reduces service delays by 45.42% to 87.57% and speeds up training episode durations by$2.5\times$ times for a higher QoE than state-of-the-art methods.- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (12) , 12983-12998
Enhancing QoE in Collaborative Edge Systems With Feedback Diffusion Generative Scheduling
Collaborative edge computing is a promising approach for delivering low-delay services to computation-intensive Internet of Things applications. Deep Reinforcement Learning (DRL) has become an effective way to solve task scheduling decisions in edge systems due to its adaptive learning ability to interact with the environment. However, current DRL-based task scheduling methods still face several challenges, such as limited exploration, sample inefficiency, and performance instability, which can lead to degraded user Quality of Experience (QoE). To address these challenges, we observe that diffusion models, famous for their performance in image generation, exhibit strong exploration, data efficiency, and performance stability. This inspires us to propose FDEdge, a novel feedback diffusion generative scheduling method for enhancing user QoE in collaborative edge systems. We first design an innovative Feedback Diffusion (FDN) model by leveraging historical action probability information during the denoising process. We then incorporate the FDN model into DRL, forming an effective and efficient framework for task scheduling in collaborative edge systems. We also present a probability derivation to ensure the FDEdge’s rationality. Extensive experimental results demonstrate that our FDEdge method significantly reduces service delays by 45.42% to 87.57% and speeds up training episode durations by$2.5\times$ times for a higher QoE than state-of-the-art methods.