Demand forecasting in residential distribution feeders in the context of smart grids

Investments on smarter solutions for power systems are currently growing and many large Smart Grid projects are underway throughout the world. With photovoltaic and wind power generation, consumers will also be able to produce and sell energy. This distributed generation will require a very efficient management of the power system. In this context, smart meters will be crucial tools to measure and monitor the system's performance. Each house will have a smart meter acquiring data uninterruptedly, creating a large amount of data, which will have to be processed into useful information for strategic decisions. This paper analyses the forecasting of residential load demand, using Auto Regressive with Exogenous Inputs (ARX), Artificial Neural Networks (ANN) and Artificial Neural Networks optimized by Genetic Algorithm (ANN-GA). The procedure that achieved best predictions was ANN working with GA.