Adaptive Optimal Greedy Clustering-Based Monthly Electricity Consumption Forecasting Method

Accurate monthly electricity consumption forecasting (MECF) is important for electricity retailers to mitigate trading risks in the electricity market. Clustering is commonly used to improve the accuracy of MECF. However, in the existing clustering-based forecasting methods, clustering and forecasting are independently performed and lack coordination, which limits the further improvement of forecasting accuracy. To address this issue, an adaptive optimal greedy clustering-based MECF method is proposed in this article. First, a metric of predictability is defined based on the goodness of fit and the cluster's average electricity consumption. Under a predefined number of clusters, the greedy clustering algorithm achieves the optimal division of individuals with the goal of maximizing predictability. Then, an adaptive method is designed to select the optimal number of clusters from a variety of clustering scenarios according to the prediction accuracy on the validation dataset. The effectiveness and superiority of the proposed method have been verified on a real-world dataset.