Previous studies have shown that residential energy consumption prediction accuracy can be improved when households energy data are fused with residents' socioeconomic information. In this article we propose an architecture for the prediction of residential energy consumption using past energy consumption from other/neighboring households in combination with socioeconomic information of the corresponding residents. The architecture is based on a Long Short Term Memory model and was evaluated using a large-scale dataset monitoring households of London. The proposed approach significantly improves the accuracy of the energy consumption predictor reducing the mean absolute error up to 25.2% with prediction error rate equal to 5.4%.
|Publication status||Published - 18 Dec 2020|
|Event||28th European Signal Processing Conference, EUSIPCO 2020 - |
Duration: 18 Jan 2021 → …
|Conference||28th European Signal Processing Conference, EUSIPCO 2020|
|Period||18/01/21 → …|