Publication Year: 2020 Publication Type : JournalArticle

Abstract:

Nowadays the ever-increasing energy consumption in buildings has caused supply shortages and adverse environmental impacts. The accurate prediction of energy consumption in smart buildings may help to monitor and control energy usage. As energy consumption is inevitably affected by exogenous factors such as temperature and wind speed, it is fundamentally important to select the informative channels of the factors, to extract the valuable features from the selected channels applied to the optimal-configured model, to improve prediction accuracy. However, existing work considers these parts in an almost disjoint way and lacks a model taking them into account, which may decrease prediction performance. Motivated by this challenge, an end-to-end prediction framework, called evolutionary model construction (EMC), is proposed to focus on performing these parts jointly. To implement EMC, a two-step evolutionary algorithm (EA) is designed, where one EA is firstly used to focus on exploiting the informative channels, while a new algorithm is proposed to concentrate on selecting the suitable feature extraction methods and respective time window sizes applied to the selected channels, and selecting the parameters in the predictor. The implementation of EMC chooses neural network with random weights as the predictor due to its highly recognized efficacy. We evaluate EMC in comparison with the existing approaches on a realworld electricity consumption dataset with various auxiliary factors. The superiority of EMC is further proved by analyzing and discussing the result according to the days in 1 week, time stamps in 1 day and month information on test samples.

BibTex:

Cite: