Power Load Forecasting Method Based on Improved Federated Learning Algorithm

被引：0

作者：

Sun, Jing ^{[1
]}

Peng, Yonggang ^{[1
]}

Ni, Yini ^{[1
]}

Wei, Wei ^{[1
]}

Cai, Tiantian ^{[2
]}

Xi, Wei ^{[2
]}

机构：

[1] Department of Electrical Engineering, Zhejiang University, Hangzhou

[2] Research Institute of China Southern Power Grid, Guangzhou

来源：

Gaodianya Jishu/High Voltage Engineering | 2024年 / 50卷 / 07期

关键词：

CNN-LSTM; cosine similarity; federated learning; FedSTA algorithm; neural network; power load forecasting;

D O I：

10.13336/j.1003-6520.hve.20230484

中图分类号：

TP181 [自动推理、机器学习];

学科分类号：

摘要：

Aiming at the problem of load prediction for power users under the protection of data privacy, we propose a power load prediction method based on improved federated learning algorithm. Firstly, a multi-user power load prediction framework based on lateral federated learning is constructed. On this basis, the traditional federated learning algorithm is not accurate enough and is vulnerable to malicious attacks, thus an innovative FedSTA (federated similarity training and aggregation) algorithm based on cosine similarity to optimize the local model update process and global model weighted aggregation is innovatively proposed. The calculation example results using actual load data show that the global model trained by the framework proposed in this paper has considerable prediction accuracy and certain generalization ability. In addition, compared with the FedAvg algorithm and the FedAdp algorithm, the FedSTA algorithm proposed in this paper significantly improves the accuracy of the global model trained. Finally, this paper verifies the robustness of the FedSTA algorithm and its ability to identify attacked clients. The results show that the algorithm can accurately identify the attacked clients and assign them a smaller aggregation weight. Compared with the FedAvg algorithm, the impact of the global model prediction accuracy is significantly reduced. © 2024 Science Press. All rights reserved.

引用

页码：3039 / 3049

页数：10

共 25 条

[1]

KANG Chongqing, XIA Qing, LIU Mei, Power system load forecasting, (2017)

[2]

LUO Fengzhang, ZHANG Xu, YANG Xin, Et al., Load analysis and prediction of integrated energy distribution system based on deep learning, High Voltage Engineering, 47, 1, pp. 23-32, (2021)

[3]

TANG Xianlun, CHEN Hongxu, XIONG Deyi, Et al., Short-term power load forecasting based on extreme gradient boosting and temporal convolutional network, High Voltage Engineering, 48, 8, pp. 3059-3067, (2022)

[4]

WANG Yuchen, DOU Yinke, MENG Runquan, Forecasting model for multicore neural network short-term load based on fuzzy C-mean clustering-variational modal decomposition and chaotic swarm intelligence optimization, High Voltage Engineering, 48, 4, pp. 1308-1319, (2022)

[5]

HOCHREITER S, SCHMIDHUBER J., Long short-term memory, Neural Computation, 9, 8, pp. 1735-1780, (1997)

[6]

KONG W C, DONG Z Y, JIA Y W, Et al., Short-term residential load forecasting based on LSTM recurrent neural network, IEEE Transactions on Smart Grid, 10, 1, pp. 841-851, (2019)

[7]

LIU Yahui, ZHAO Qian, Ultra-short-term power load forecasting based on cluster empirical mode decomposition of CNN-LSTM, Power System Technology, 45, 11, pp. 4444-4451, (2021)

[8]

LUO Shuxin, MA Minhua, JIANG Lin, Et al., Medium and long-term load forecasting method considering multi-time scale data, Proceedings of the CSEE, 40, pp. 11-19, (2020)

[9]

SAVI M, OLIVADESE F., Short-term energy consumption forecasting at the edge: a federated learning approach, IEEE Access, 9, pp. 95949-95969, (2021)

[10]

CHEN Xiaojiang, LIU Ye, ZHANG Jinbo, Et al., Short-term power load forecasting based on smart concentrator, Proceedings of the CSU-EPSA, 32, 6, pp. 140-145, (2020)

← 1 2 3 →