haijin wang

Dr. haijin wang

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
10 November 2022 in Scientific Data
Verified
Journal Article
Open access
PDF file
DHDa Huo
Da Huo
KLKai Liu
Kai Liu
JLJianwu Liu
Jianwu Liu
YHYingjian Huang
Yingjian Huang
TSTaochun Sun
Taochun Sun
ZLZhu Liu
Zhu Liu
Cities in China are on the frontline of low-carbon transition which requires monitoring city-level emissions with low-latency to support timely climate actions. Most existing CO2emission inventories lag reality by more than one year and only provide annual totals. To improve the timeliness and temporal resolution of city-level emission inventories, we present Carbon Monitor Cities-China (CMCC), a near-real-time dataset of daily CO2emissions from fossil fuel and cement production for 48 major high-emission cities in China. This dataset provides territory-based emission estimates from 2020-01-01 to 2021-12-31 for five sectors: power generation, residential (buildings and services), industry, ground transportation, and aviation. CMCC is developed based on an innovative framework that integrates bottom-up inventory construction and daily emission estimates from sectoral activities and models. Annual emissions show reasonable agreement with other datasets, and uncertainty ranges are estimated for each city and sector. CMCC provides valuable daily emission estimates that enable low-latency mitigation monitoring for cities in China.

20 April 2022 in Energy Conversion and Economics
Verified
Journal Article
Open access
HWhaijin wang
haijin wang
CSCaomingzhe Si
Caomingzhe Si
GLGuolong Liu
Guolong Liu
JZJunhua Zhao
Junhua Zhao
FWFushuan Wen
Fushuan Wen
YXYusheng Xue
Yusheng Xue
Non‐intrusive load monitoring (NILM) is essential for understanding consumer power consumption patterns and may have wide applications such as in carbon emission reduction and energy conservation. Determining NILM models requires massive load data containing different types of appliances. However, inadequate load data and the risk of power consumer privacy breaches may be encountered by local data owners when determining the NILM model. To address these problems, a novel NILM method based on federated learning (FL) called Fed‐NILM is proposed. In Fed‐NILM, instead of local load data, local model parameters are shared among multiple data owners. The global NILM model is obtained by averaging the parameters with the appropriate weights. Experiments based on two measured load datasets are performed to explore the generalization capability of Fed‐NILM. In addition, a comparison of Fed‐NILM with locally trained NILM models and the centrally trained NILM model is conducted. Experimental results show that the Fed‐NILM exhibits superior performance in terms of scalability and convergence. Fed‐NILM out performs locally trained NILM models operated by local data owners and approaches the centrally trained NILM model, which is trained on the entire load dataset without privacy protection. The proposed Fed‐NILM significantly improves the co‐modelling capabilities of local data owners while protecting the privacy of power consumers.

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZPZibin Pan
Zibin Pan
SWShuyi Wang
Shuyi Wang
CLChi Li
Chi Li
HWhaijin wang
haijin wang
XTXiaoying Tang
Xiaoying Tang
JZJunhua Zhao
Junhua Zhao
Fairness has been considered as a critical problem in federated learning (FL). In this work, we analyze two direct causes of unfairness in FL - an unfair direction and an improper step size when updating the model. To solve these issues, we introduce an effective way to measure fairness of the model through the cosine similarity, and then propose a federated multiple gradient descent algorithm with fair guidance (FedMDFG) to drive the model fairer. We first convert FL into a multi-objective optimization problem (MOP) and design an advanced multiple gradient descent algorithm to calculate a fair descent direction by adding a fair-driven objective to MOP. A low-communication-cost line search strategy is then designed to find a better step size for the model update. We further show the theoretical analysis on how it can enhance fairness and guarantee the convergence. Finally, extensive experiments in several FL scenarios verify that FedMDFG is robust and outperforms the SOTA FL algorithms in convergence and fairness. The source code is available at https://github.com/zibinpan/FedMDFG.

29 February 2024 in IEEE Transactions on Smart Grid
Verified
Journal Article
Closed access
CSCaomingzhe Si
Caomingzhe Si
HWhaijin wang
haijin wang
LCLei Chen
Lei Chen
JZJunhua Zhao
Junhua Zhao
YMYong Min
Yong Min
FXFei Xu
Fei Xu
Short-term load forecasting (STLF) can support strategies for power retailers. Training based on aggregate load datasets can yield more precise STLF models. In real scenarios, however, retailers can only access the consumer information they serve. The aggregation of their data for centralized forecasting requires access to private local data, which may lead to potential security concerns. This paper proposes a method namely Privacy-Preserving ${k}$ -means Federated Learning (PPK-Fed), to facilitate STLF co-modeling among retailers. Federated Learning (FL) is founded on the assumption of data consistency, which does not necessarily exist in real datasets. PPK-Fed incorporates ${k}$ -means clustering together with convolutional neural networks into FL. PPK-Fed is proven to reduce the impact of potential data incongruence embedded in retailer local datasets. Besides, to address the sensitivity of the ${k}$ -means prototype to the potential anomalies in the real dataset, PPK-Fed fuses density-based anomaly detection into ${k}$ -means clustering under FL to improve robustness. For further model security, a secure multi-party computation (SMPC) scheme is designed in PPK-Fed. The model validity, privacy-preserving features, and robustness to anomalies have been verified using a real load dataset.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZPZibin Pan
Zibin Pan
CLChi Li
Chi Li
FYFangchen Yu
Fangchen Yu
SWShuyi Wang
Shuyi Wang
HWhaijin wang
haijin wang
JZJunhua Zhao
Junhua Zhao
Fairness has become an important concern in Federated Learning (FL). An unfair model that performs well for some clients while performing poorly for others can reduce the willingness of clients to participate. In this work, we identify a direct cause of unfairness in FL - the use of an unfair direction to update the global model, which favors some clients while conflicting with other clients’ gradients at the model and layer levels. To address these issues, we propose a layer-wise fair Federated Learning algorithm (FedLF). Firstly, we formulate a multi-objective optimization problem with an effective fair-driven objective for FL. A layer-wise fair direction is then calculated to mitigate the model and layer-level gradient conflicts and reduce the improvement bias. We further provide the theoretical analysis on how FedLF can improve fairness and guarantee convergence. Extensive experiments on different learning tasks and models demonstrate that FedLF outperforms the SOTA FL algorithms in terms of accuracy and fairness. The source code is available at https://github.com/zibinpan/FedLF.

28 June 2024 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
HWhaijin wang
haijin wang
SXShuangshuang Xing
Shuangshuang Xing
CSCaomingzhe Si
Caomingzhe Si
ZPZibin Pan
Zibin Pan
JZJunhua Zhao
Junhua Zhao
Zhaoyang DongZhaoyang Dong
Zhaoyang Dong
Short-term load forecasting (STLF) is essential in power system research. In scenarios where multiple distribution system operators are involved in cooperative forecasting, it is important to uphold the fairness of multi-party cooperation and drive the parity of model gains among parties under the premise of privacy protection. In this context, this paper proposes a short-term load forecasting method namely Multi-Gradient-Descent Federated Learning with Parity Long-short Term Memory (MGD-FLP-LSTM) under a federated learning framework. First, MGD-FLP-LSTM transforms cooperative STLF into a Multi-Objective Optimization (MOO) problem with parity-driven ob-jective. The designed algorithm optimizes multiple objectives simultaneously and incorporates Karush-Kuhn-Tucker (KKT) conditions in solving the dual form of the problem, thus acceler-ating the global model convergence. Second, MGD-FLP-LSTM constitutes a parity-driven objective with cosine similarity in the MOO iteration. The objective allows all local loss functions to have similar descents on the common gradient descending direc-tion. Third, MGD-FLP-LSTM constructs a Performance Pari-ty Control (PPC) scheme that enables an active moderate trade-off between forecasting accuracy and parity. Experiments on real-measured load dataset highlight the method's enhanced ac-curacy, efficiency, and performance while maintaining consumer privacy.