Data Selection for Short Term load forecasting
This work addresses data selection for power load forecasting, a domain-specific incremental improvement.
The authors tackled the problem of selecting appropriate training data for short-term load forecasting by developing a fully automatic Bayesian methodology, which they validated on real U.S. power load data.
Power load forecast with Machine Learning is a fairly mature application of artificial intelligence and it is indispensable in operation, control and planning. Data selection techniqies have been hardly used in this application. However, the use of such techniques could be beneficial provided the assumption that the data is identically distributed is clearly not true in load forecasting, but it is cyclostationary. In this work we present a fully automatic methodology to determine what are the most adequate data to train a predictor which is based on a full Bayesian probabilistic model. We assess the performance of the method with experiments based on real publicly available data recorded from several years in the United States of America.