Mid-Term Residential Load Forecasting Based on Neighborhood Component Analysis Feature Selection

Residential load forecasting plays an important role in management and planning in modern smart grids. In planning to keep demand and supply balanced, accurate residential load forecasting is needed. This paper presents a mid-term residential load forecasting method based on feature selection for solving the linear regression problem. Utilization of neighborhood component analysis Method is proposed in this paper. For this purpose, an optimization problem is designed and the problem is solved using LBFGS algorithm. The AMPds2 dataset is used to implement the proposed method and the results were compared with the results of the other six forecasting methods. Comparisons were made by means of mean squared error, root mean squared error, and mean absolute percentage error. The simulation results confirm the effectiveness of the proposed method for accurate residential load forecasting.