Electrical and Computer Engineering Publications

Document Type

Article

Publication Date

1-2021

Volume

4

Issue

1

Journal

Smart Cities

First Page

217

URL with Digital Object Identifier

10.3390/smartcities4010014

Last Page

240

Abstract

The development from traditional low voltage grids to smart systems has become extensive and adopted worldwide. Expanding the demand response program to cover the residential sector raises a wide range of challenges. Short term load forecasting for residential consumers in a neighbourhood could lead to a better understanding of low voltage consumption behaviour. Nevertheless, users with similar characteristics can present diversity in consumption patterns. Consequently, transfer learning methods have become a useful tool to tackle differences among residential time series. This paper proposes a method combining evolutionary algorithms for neural architecture search with transfer learning to perform short term load forecasting in a neighbourhood with multiple household load consumption. The approach centres its efforts on neural architecture search using evolutionary algorithms. The neural architecture evolution process retains the patterns of the centre-most house, and later the architecture weights are adjusted for each house in a multihouse set from a neighbourhood. In addition, a sensitivity analysis was conducted to ensure model performance. Experimental results on a large dataset containing hourly load consumption for ten houses in London, Ontario showed that the performance of the proposed approach performs better than the compared techniques. Moreover, the proposed method presents the average accuracy performance of 3.17 points higher than the state-of-the-art LSTM one shot method.

Notes

Gomez-Rosero, S.; Capretz, M.A.M.; Mir, S. Transfer Learning by Similarity Centred Architecture Evolution for Multiple Residential Load Forecasting. Smart Cities 2021, 4, 217-240. https://doi.org/10.3390/smartcities4010014

Find in your library

Share

COinS