Deep learning based forecasting of individual residential loads using recurrence plots

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

High penetration of renewable energy resources in distribution systems brings more uncertainty for system control and management due their intermittent behaviour. In this context, besides generation side, demand side should be also controlled and managed. Since demand side has variant flexibility over time, in order to timely facilitate Demand Response (DR), distribution system operators (DSO) should be aware of DR potential in advance to see whether it is sufficient for different services, and how much and when to send DR signals. This indeed requires accurate short-term or medium-term load forecasting. There are many methods for predicting aggregated loads, but more effective DR schemes should involve individual residential households which would require load forecasting of single residential loads. This is much more challenging due to high volatility in load curves of single customers. In this paper, we present a novel method of forecasting individual household power consumption using recurrence plots and deep learning. We use Convolutional Neural Network (CNN) for such a two-dimensional deep learning approach, and compare it with one-dimensional CNN, as well as Support Vector Machine (SVM) and Artificial Neural Network (ANN). Demonstrating some experimental tests on a real case proved that our approach outperforms the other existing solutions.