李晓露,吴钉捷,陆一鸣.基于生成对抗网络和联邦学习的非侵入式负荷分解方法[J].电测与仪表,2022,59(6):37-45. Li Xiaolu,Wu Dingjie,Lu Yiming.Non-intrusive load disaggregation based on GAN and federated learning[J].Electrical Measurement & Instrumentation,2022,59(6):37-45.
基于生成对抗网络和联邦学习的非侵入式负荷分解方法
Non-intrusive load disaggregation based on GAN and federated learning
Non-intrusive load disaggregation is an important means of sensing the power demand. Traditional methods have low accuracy of appliance identification and power disaggregation. Load disaggregation model based on GAN is proposed. The generative network deconstructs the total power signal by constructing a convolutional self-encoder to generate the power sequence of the appliance, and the discrimination network is used to identify the authenticity of the generated sequence. The two oppose each other to get a more realistic sequence. In view of the shortcomings of centralized model training methods, this paper uses deep separable convolution instead of traditional convolution, so that it can be applied to edge devices, and proposes a network model implementation solution based on federated learning. Training the model in a cloud-side collaborative manner reduces communication transmission pressure and protects user privacy and data security. The method is verified based on public data sets.
