首页|Short-term Residential Load Forecasting Based on K-shape Clustering and Domain Adversarial Transfer Network
Short-term Residential Load Forecasting Based on K-shape Clustering and Domain Adversarial Transfer Network
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
万方数据
维普
In recent years,the expansion of the power grid has led to a continuous increase in the number of consumers within the distribution network.However,due to the scarcity of historical data for these new consumers,it has become a com-plex challenge to accurately forecast their electricity demands through traditional forecasting methods.This paper proposes an innovative short-term residential load forecasting method that harnesses advanced clustering,deep learning,and transfer learning technologies to address this issue.To begin,this paper leverages the domain adversarial transfer network.It employs limited data as target domain data and more abundant data as source domain data,thus enabling the utilization of source do-main insights for the forecasting task of the target domain.Moreover,a K-shape clustering method is proposed,which effec-tively identifies source domain data that align optimally with the target domain,and enhances the forecasting accuracy.Sub-sequently,a composite architecture is devised,amalgamating at-tention mechanism,long short-term memory network,and seq2seq network.This composite structure is integrated into the domain adversarial transfer network,bolstering the perfor-mance of feature extractor and refining the forecasting capabili-ties.An illustrative analysis is conducted using the residential load dataset of the Independent System Operator to validate the proposed method empirically.In the case study,the relative mean square error of the proposed method is within 30 MW,and the mean absolute percentage error is within 2%.A signifi-cant improvement in accuracy,compared with other compara-tive experimental results,underscores the reliability of the pro-posed method.The findings unequivocally demonstrate that the proposed method advocated in this paper yields superior fore-casting results compared with prevailing mainstream forecast-ing methods.
万方数据
维普
