Demand Side Data Generating Based on Conditional Generative Adversarial Networks

With the technological advancement in the fields of advanced metering infrastructure (AM11), a massive amount of customers' electricity consumption data is collected. Meanwhile, the energy providers need to make informed decisions based on power consumption strategy of demand side to reduce overall operational cost. So how to generate demand side load data based on historical energy consumption data or customer attribute is a pressing issue. In this paper, we propose a data-driven approach to generate new power consumption data based on intrinsic property of load pattern learnt from demand side using conditional generative adversarial networks (cGANs), which is based on two interconnected deep neural networks known as generator and discriminator. By using several representative labels from the responded surveys and the load data from demand side to train the models, the generator is able to generate realistic power consumption data by given labels which can be used for energy management and scheduling, the discriminator is capable of detecting abnormal power consumption and system error from the smart meter data. Copyright 2018 Elsevier Ltd. All rights reserved.