Yi Dong

Yi Dong

Auto-generated profile, based on publicly available information

Yi Dong

Department of Computer Science, University of Liverpool, Liverpool, U.K.

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
16 June 2020 in IEEE Transactions on Sustainable Energy
Verified
Journal Article
Closed access
ZDZhen Dong
Zhen Dong
Zhongguo LiZhongguo Li
Zhongguo Li
YDYi Dong
Yi Dong
SJShuoying Jiang
Shuoying Jiang
Zhengtao DingZhengtao Ding
Zhengtao Ding
A system-level consensus-based deloading operation is proposed for DFIG-based wind farm (WF) participating in system active power regulation. Rotor overspeeding control (ROC) and pitch angle control (PAC) are coordinated for load sharing among each wind turbine (WT). For ROC, a novel fully-distributed consensus protocol is developed for fair load sharing control without the need to know the total active power capacity. Considering the influences of wind turbines' individual differences and rotor speed limit, the amount of WTs involved in consensus protocal are dynamically adjusted according to their varying operating points. Further, a distributed optimization strategy is designed for active power setting-points allocation to curtail the utilization of WF's pitch angle during PAC. As the result, the proposed strategy can fully and quickly extract the available rotor overspeeding margin for a high kinetic energy storage and a better dynamic performance in ROC stage, and further minimize the dependency on pitch angle when facing deeper deloading operation. Case studies demonstrate the effectiveness of the proposed scheme.

20 April 2023 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
YDYi Dong
Yi Dong
WHWei Huang
Wei Huang
VBVibhav Bharti
Vibhav Bharti
VCVictoria Cox
Victoria Cox
ABAlec Banks
Alec Banks
Xiaowei HuangXiaowei Huang
Xiaowei Huang
The increasing use of Machine Learning (ML) components embedded in autonomous systems—so-called Learning-Enabled Systems (LESs)—has resulted in the pressing need to assure their functional safety. As for traditional functional safety, the emerging consensus within both, industry and academia, is to use assurance cases for this purpose. Typically assurance cases support claims of reliability in support of safety, and can be viewed as a structured way of organising arguments and evidence generated from safety analysis and reliability modelling activities. While such assurance activities are traditionally guided by consensus-based standards developed from vast engineering experience, LESs pose new challenges in safety-critical application due to the characteristics and design of ML models. In this article, we first present an overall assurance framework for LESs with an emphasis on quantitative aspects, e.g., breaking down system-level safety targets to component-level requirements and supporting claims stated in reliability metrics. We then introduce a novel model-agnostic Reliability Assessment Model (RAM) for ML classifiers that utilises the operational profile and robustness verification evidence. We discuss the model assumptions and the inherent challenges of assessing ML reliability uncovered by our RAM and propose solutions to practical use. Probabilistic safety argument templates at the lower ML component-level are also developed based on the RAM. Finally, to evaluate and demonstrate our methods, we not only conduct experiments on synthetic/benchmark datasets but also scope our methods with case studies on simulated Autonomous Underwater Vehicles and physical Unmanned Ground Vehicles.

5 February 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
YDYi Dong
Yi Dong
YWYingjie Wang
Yingjie Wang
MGMariana Gama
Mariana Gama
Mustafa MustafaMustafa Mustafa
Mustafa Mustafa
Geert DeconinckGeert Deconinck
Geert Deconinck
Xiaowei HuangXiaowei Huang
Xiaowei Huang
In the realm of power systems, the increasing involvement of residential users in load forecasting applications has heightened concerns about data privacy. Specifically, the load data can inadvertently reveal the daily routines of residential users, thereby posing a risk to their property security. While federated learning (FL) has been employed to safeguard user privacy by enabling model training without the exchange of raw data, these FL models have shown vulnerabilities to emerging attack techniques, such as deep leakage from gradients and poisoning attacks. To counteract these, we initially employ a secure-aggregation (SecAgg) algorithm that leverages multiparty computation cryptographic techniques to mitigate the risk of gradient leakage. However, the introduction of SecAgg necessitates the deployment of additional subcenter servers for executing the MPC protocol, thereby escalating computational complexity and reducing system robustness, especially in scenarios where one or more subcenters are unavailable. To address these challenges, we introduce a Markovian switching-based distributed training framework, the convergence of which is substantiated through rigorous theoretical analysis. The distributed Markovian switching (DMS) topology shows strong robustness toward the poisoning attacks as well. Case studies employing real-world power system load data validate the efficacy of our proposed algorithm. It not only significantly minimizes communication complexity but also maintains accuracy levels comparable to traditional FL methods, thereby enhancing the scalability of our load forecasting algorithm.

1 September 2011 in Combinatorial Chemistry & High Throughput Screening
Verified
Journal Article
Closed access
PDF file
LLLianzhu Lin
Lianzhu Lin
YDYi Dong
Yi Dong
BYBao Yang
Bao Yang
Mouming ZhaoMouming Zhao
Mouming Zhao
The application of Isodon species in Chinese folk medicine has a long histroy, especially the ones called ‘Xihuangcao’ in Chinese. ‘Xihuangcao’ has been successfully applied to treat acute hepatitis, cholecystitis, enteritis, dysentery and trauma. The original species of ‘Xihuangcao’ is Isodon lophanthoides (Buch.-Ham.ex D.Don). However, there are five sources of Chinese medicinal herb ‘Xihuangcao’ due to their similar morphology and close pharmaceutical activity. Each source belongs to Isodon. However, their chemical composition and bioactivities are significantly different. In order to differentiate these sources of ‘Xihuangcao’ and to know their pharmaceutical effects, this review summarizes the chemical constituents, bioactive properties of ‘Xihuangcao’ and their available application.

9 February 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YDYi Dong
Yi Dong
Xingyu ZhaoXingyu Zhao
Xingyu Zhao
SWSen Wang
Sen Wang
Xiaowei HuangXiaowei Huang
Xiaowei Huang
Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS). A key challenge to its deployment in real-life operations is the presence of spuriously unsafe DRL policies. Unexplored states may lead the agent to make wrong decisions that could result in hazards, especially in applications where DRL-trained end-to-end controllers govern the behaviour of RAS. This letter proposes a novel quantitative reliability assessment framework for DRL-controlled RAS, leveraging verification evidence generated from formal reliability analysis of neural networks. A two-level verification framework is introduced to check the safety property with respect to inaccurate observations that are due to, e.g., environmental noise and state changes. Reachability verification tools are leveraged locally to generate safety evidence of trajectories. In contrast, at the global level, we quantify the overall reliability as an aggregated metric of local safety evidence, corresponding to a set of distinct tasks and their occurrence probabilities. The effectiveness of the proposed verification framework is demonstrated and validated via experiments on real RAS.

22 August 2025 in Chinese Journal of Aeronautics
Verified
Journal Article
Open access
JHJinwei Hu
Jinwei Hu
YDYi Dong
Yi Dong
Zhengtao DingZhengtao Ding
Zhengtao Ding
XHXiaowei Huang
Xiaowei Huang