DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated Convolution

• Published in: Energies (Basel) Vol. 16; no. 22; p. 7662
• Main Authors: Anh, Le Hoang, Yu, Gwang-Hyun, Vu, Dang Thanh, Kim, Hyoung-Gook, Kim, Jin-Young
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-11-2023
• Subjects: Accuracy; Blackouts; Buildings; Computational linguistics; Datasets; Deep learning; Electricity; Energy consumption; Energy management; Forecasting; Language processing; Machine learning; Natural language interfaces; Neural networks; Regression analysis; temporal convolutional neural Network; Time series; time-delay; Use statistics; France; South Korea; Spain
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en16227662

In the face of increasing irregular temperature patterns and climate shifts, the need for accurate power consumption prediction is becoming increasingly important to ensure a steady supply of electricity. Existing deep learning models have sought to improve prediction accuracy but commonly require greater computational demands. In this research, on the other hand, we introduce DelayNet, a lightweight deep learning model that maintains model efficiency while accommodating extended time sequences. Our DelayNet is designed based on the observation that electronic series data exhibit recurring irregular patterns over time. Furthermore, we present two substantial datasets of electricity consumption records from South Korean buildings spanning nearly two years. Empirical findings demonstrate the model’s performance, achieving 21.23%, 43.60%, 17.05% and 21.71% improvement compared to recurrent neural networks, gated-recurrent units, temporal convolutional neural networks and ARIMA models, as well as greatly reducing model complexity and computational requirements. These findings indicate the potential for micro-level power consumption planning, as lightweight models can be implemented on edge devices.