Application of SOM neural networks to short-term load forecasting: The Spanish electricity market case study

The use of neural networks in load forecasting has been a popular research topic over the last decade. However, the use of Kohonen's self-organizing maps (SOM) for this purpose remains yet mostly unexplored. This paper presents a forecasting model based on this particular type of neural network. The scope of this study is not only to prove that SOM neural networks can be effectively used in load forecasting but to provide a deep and thorough analysis of the prediction and a real-world application. The data used to assess the validity of the model corresponds to Spain energy consumption from 2001 to 2010. Also meteorological data from this period has been used. The analysis comprises the study of the significance of different meteorological variables, the relevance of these meteorological data when recent load values are used as input and the effect of using different patterns to select the days to train the map. In addition, the evaluation of the frequency components of the data has provided an explanation to why apparently similar data sets allow different forecasting performances of the model. In order to build an application to the Spanish electricity market, the model was adjusted to timely forecast a load profile for each session of the daily and intra-daily markets. These forecasts are intended as an input to a decision support system for any commercializing company bidding on the market.

► Short-term load forecasting application of SOM neural network is proposed.
► The model is tested with real load and weather data for the whole country of Spain.
► The input is optimized hourly through an algorithm that excludes insignificant variables from the available input.
► The result of forecasting day-ahead 24 hours load profiles is a MAPE of 2.18%.
► The model is fitted to the different sessions of the Spanish electricity market. The tests yield a MAPE from 2.32% to 1.84%.