Bachelor's thesis Julian Vossen

 

Probabilistic forecasting of household electrical load using artificial neural networks

Copyright: EBC Forecast horizon, dataset granularity and lagged input

For optimizing the usage of electricity, home energy management systems require accurate fore- casts of the electrical load on a single-household level. As this load is subject to a high volatility and unpredictable human behavior, deterministic point-forecasting methods fail to provide accurate predictions. Towards overcoming this challenge, probabilistic forecasting methods are proposed in order to incorporate the uncertainty into the forecasts. In this thesis, we use Mixture Density Networks and Softmax Distribution Networks to predict the probability density over the electricity consumption one hour into the future. The models are evaluated on three smart meter datasets, the Smart*, a UCI and the UK-DALE dataset. Thereby, scoring functions such as the Continuous Ranked Probability Score are used to evaluate the predictive densities while the point-forecasting performance is measured in terms of the mean absolute error. The main finding is that both neu- ral network models generate reliable density forecasts which significantly outperform an uncondi- tional benchmarking model. When evaluating different model input configurations, conditioning models on lagged electrical load led to drastic performance gains. However, the models did not significantly benefit from increasing the length of the lagged input window, whereas decreasing the dataset granularity improved the forecasts. The results of this thesis pave the way to investigating if the availability of reliable probabilistic forecasts can result in a more effective optimization of household electricity consumption.