Short term load forecasting with markovian switching distributed deep belief networks

Abstract

In modern power systems, centralised short term load forecasting (STLF) methods raise concern on high communication requirements and reliability when a central controller undertakes the processing of massive load data solely. As an alternative, distributed methods avoid the problems mentioned above, whilst the possible issues of cyberattacks and uncertain forecasting accuracy still exist. To address the two issues, a novel distributed deep belief networks (DDBN) with Markovian switching topology is proposed for an accurate STLF, based on a completely distributed framework. Without the central governor, the load dataset is separated and the model is trained locally, while obtaining the updates through communication with stochastic neighbours under a designed consensus procedure, and therefore significantly reduced the training time. The overall network reliability against cyberattacks is enhanced by continually switching communication topologies. In the meanwhile, to ensure that the distributed structure is still stable under such a varying topology, the consensus controller gain is delicately designed, and the convergence of the proposed algorithm is theoretically analysed via the Lyapunov function. Besides, restricted Boltzmann machines (RBM) based unsupervised learning is employed for DDBN initialisation and thereby guaranteeing the success rate of STLF model training. GEFCom 2017 competition and ISO New England load datasets are applied to validate the accuracy and effectiveness of the proposed method. Experiment results demonstrate that the proposed DDBN algorithm can enhance around 19% better forecasting accuracy than centralised DBN algorithm.