Fan Zhang

Dr. Fan Zhang


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
18 September 2023 in Energies
Verified
Journal Article
Open access
PDF file
MZMi Zhou
Mi Zhou
FLFusheng Li
Fusheng Li
FZFan Zhang
Fan Zhang
JZJunhao Zheng
Junhao Zheng
QMQianli D.Y. Ma
Qianli D.Y. Ma
The evolution of communication technology has driven the demand for intelligent power grids and data analysis in power systems. However, obtaining and annotating electrical data from intelligent terminals is time-consuming and challenging. We propose Meta In-Context Learning (M-ICL), a new approach that harnesses large language models to classify time series electrical data, which largely alleviates the need for annotated data when adapting to new tasks. The proposed M-ICL consists of two stages: meta-training and meta-testing. In meta-training, the model is trained on various tasks that have an adequate amount of training data. The meta-training stage aims to learn the mapping between electrical data and the embedding space of large language models. In the meta-testing stage, the trained model makes predictions on new tasks. By utilizing the in-context learning ability of large language models, M-ICL adapts models to new tasks effectively with only a few annotated instances (e.g., 1–5 training instances per class). Our contributions lie in the new application of large language models to electrical data classification and the introduction of M-ICL to improve the classification performance with the strong in-context learning ability of large language models. Furthermore, we conduct extensive experiments on 13 real-world datasets, and the experimental results show that the proposed M-ICL improves the average accuracy over all datasets by 19.06%, 12.06%, and 6.63% when only one, two, and five training instances for each class are available, respectively. In summary, M-ICL offers a promising solution to the challenges of electrical data classification.

12 September 2024 in Electronics
Verified
Journal Article
Open access
PDF file
NWNing Wu
Ning Wu
XLXiaoming Lin
Xiaoming Lin
JLJianbin Lu
Jianbin Lu
FZFan Zhang
Fan Zhang
WCWeidong Chen
Weidong Chen
JXJing Xiao
Jing Xiao
In the rapidly advancing domain of Intelligent Connected Vehicles (ICVs), multimodal Federated Learning (FL) presents a powerful methodology to harness diverse data sources, such as sensors, cameras, and Vehicle-to-Everything (V2X) communications, without compromising data privacy. Despite its potential, the presence of Byzantine adversaries–malicious participants who contribute incorrect or misleading updates–poses a significant challenge to the robustness and reliability of the FL process. This paper proposes a Byzantine-robust multimodal FL framework specifically designed for ICVs. Our framework integrates a robust aggregation mechanism to mitigate the influence of adversarial updates, a multimodal fusion strategy to effectively manage and combine heterogeneous input data, and a global optimization objective that accommodates the presence of Byzantine clients. The theoretical foundation of the framework is established through formal definitions and equations, demonstrating its ability to maintain reliable and accurate learning outcomes despite adversarial disruptions. Extensive experiments highlight the framework’s efficacy in preserving model performance and resilience in real-world ICV environments.

13 September 2024 in Electronics
Verified
Journal Article
Open access
PDF file
YXYong Xiao
Yong Xiao
XLXiaoming Lin
Xiaoming Lin
YLYiyong Lei
Yiyong Lei
YGYanzhang Gu
Yanzhang Gu
TJTang JianLin
Tang JianLin
BQBin Qian
Bin Qian
Electricity markets are intricate systems that facilitate efficient energy exchange within interconnected grids. With the rise of low-carbon transportation driven by environmental policies and tech advancements, energy trading has become crucial. This trend towards Electric Vehicles (EVs) is bolstered by the pivotal role played by EV charging operators in providing essential charging infrastructure and services for widespread EV adoption. This paper introduces a blockchain-assisted secure electricity trading framework between EV charging operators and the electricity market with renewable energy sources. We propose a single-leader, multi-follower Stackelberg game between the electricity market and EV charging operators. In the two-stage Stackelberg game, the electricity market acts as the leader, deciding the price of electric energy. The EV charging aggregator leverages blockchain technology to record and verify energy trading transactions securely. The EV charging operators, acting as followers, then decide their demand for electric energy based on the set price. To find the Stackelberg equilibrium, we employ a Deep Reinforcement Learning (DRL) algorithm that tackles non-stationary challenges through policy, action space, and reward function formulation. To optimize efficiency, we propose the integration of pruning techniques into DRL, referred to as Tiny DRL. Numerical results demonstrate that our proposed schemes outperform traditional approaches.

2 September 2025 in International Journal of Computational Intelligence Systems
Verified
Journal Article
Open access
PDF file
YXYong Xiao
Yong Xiao
TJTang JianLin
Tang JianLin
XLXiaoming Lin
Xiaoming Lin
XFXiangyong Feng
Xiangyong Feng
BQBin Qian
Bin Qian
FZFan Zhang
Fan Zhang
This study develops a centralized reinforcement learning framework, employing Q-learning, for efficient vehicle-to-grid (V2G) scheduling of large electric vehicle (EV) fleets. To address scalability challenges and inherent uncertainties in user behavior, the framework utilizes an aggregated state representation. This state captures the time-of-day, the distribution of the fleet’s state of charge (SOC) across discrete bins, and an estimated user adherence factor. The central agent learns a control policy based on this aggregated state to dynamically issue charging, discharging, or idle commands to EVs grouped within specific SOC bins. The primary objectives are to enhance power grid stability by minimizing the peak-to-average ratio (PAR) and to improve the economic viability of V2G participation for EV owners. Simulations conducted under a 40% EV penetration level (relative to a 300,000 vehicle base fleet) demonstrate the proposed method’s effectiveness: it reduced the grid PAR to 1.0683, compared to 1.0729 for a baseline uncontrolled charging scenario. Critically, the proposed method transformed the economic outcome, achieving positive average daily earnings of $1.17 per EV, in stark contrast to an average daily loss of $6.75 per EV under the baseline. These results validate the potential of the proposed intelligent, centralized control strategy using aggregated information to effectively manage large-scale V2G systems, enhance grid stability, and provide economic benefits under practical behavioral assumptions.

23 March 2025 in Processes
Verified
Journal Article
Open access
PDF file
JTJianlin Tang
Jianlin Tang
BQBin Qian
Bin Qian
YLYi Luo
Yi Luo
XLXiaoming Lin
Xiaoming Lin
MZMi Zhou
Mi Zhou
HWHaolin Wang
Haolin Wang
China’s power generation system has undergone reforms, leading to a competitive electricity market where independent producers participate through competitive bidding. With the rise of low-carbon policies, producers must optimize bidding strategies while reducing carbon emissions, creating complex interactions with local governments. Evolutionary game theory (EGT) is well-suited to analyze these dynamics. This study begins by summarizing the fundamental concepts of electricity trading markets, including transaction models, bidding mechanisms, and carbon reduction strategies. Existing research on the application of evolutionary game theory in power markets is reviewed, with a focus on theoretical constructs such as evolutionary stable strategies and replicator dynamics. Based on this foundation, the study conducts a detailed mathematical analysis of symmetric and asymmetric two-group evolutionary game models in general market scenarios. Building upon these models, a three-group evolutionary game framework is developed to analyze interactions within power producer groups and between producers and regulators under low-carbon mechanisms. A core innovation of this study is the incorporation of a case study based on China’s electricity market, which examines the evolutionary dynamics between local governments and power producers regarding carbon reduction strategies. This includes analyzing how regulatory incentives, market-clearing prices, and demand-side factors influence producers’ bidding and emission reduction behaviors. The study also provides a detailed analysis of the bidding strategies for small, medium, and large power producers, revealing the significant impact of carbon pricing and market-clearing prices on strategic decision-making. Specifically, the study finds that small producers tend to adopt more conservative bidding strategies, aligning closely with market-clearing prices, while large producers take advantage of economies of scale, adjusting their strategies at higher capacities. The study explores the conditions under which carbon emission reduction strategies achieve stable equilibrium, as well as the implications of these equilibria for both market efficiency and environmental sustainability. The study reveals that integrating carbon reduction strategies into power market dynamics significantly impacts bidding behaviors and long-term market stability, especially under the influence of governmental penalties and incentives. The findings provide actionable insights for both power producers and policymakers, contributing to the advancement of low-carbon market theories and supporting the global transition to sustainable energy systems.

21 September 2023 in Electronics
Verified
Journal Article
Open access
PDF file
ZWZhenshang Wang
Zhenshang Wang
MZMi Zhou
Mi Zhou
YZYuming Zhao
Yuming Zhao
FZFan Zhang
Fan Zhang
JWJing Wang
Jing Wang
QMQianli D.Y. Ma
Qianli D.Y. Ma
In the context of electrical power systems, modeling the edge-end interaction involves understanding the dynamic relationship between different components and endpoints of the system. However, the time series of electrical power obtained by user terminals often suffer from low-quality issues such as missing values, numerical anomalies, and noisy labels. These issues can easily reduce the robustness of data mining results for edge-end interaction models. Therefore, this paper proposes a time–frequency noisy label classification (TF-NLC) model, which improves the robustness of edge-end interaction models in dealing with low-quality issues. Specifically, we employ two deep neural networks that are trained concurrently, utilizing both the time and frequency domains. The two networks mutually guide each other’s classification training by selecting clean labels from batches within small loss data. To further improve the robustness of the classification of time and frequency domain feature representations, we introduce a time–frequency domain consistency contrastive learning module. By classifying the selection of clean labels based on time–frequency representations for mutually guided training, TF-NLC can effectively mitigate the negative impact of noisy labels on model training. Extensive experiments on eight electrical power and ten other different realistic scenario time series datasets show that our proposed TF-NLC achieves advanced classification performance under different noisy label scenarios. Also, the ablation and visualization experiments further demonstrate the robustness of our proposed method.