A comprehensive review on deep learning approaches for short-term load forecasting

• Published in: Renewable & sustainable energy reviews 2024-01, Vol.189, p.114031, Article 114031
• Main Authors: Eren, Yavuz, Küçükdemiral, İbrahim
• Format: Article
• Language: English
• Subjects: Dataset; Deep-learning; Demand response; Online forecasting; Short term load forecasting; Uncertainty awareness
• ISSN: 1364-0321; 1879-0690
• DOI: 10.1016/j.rser.2023.114031

The balance between supplied and demanded power is a crucial issue in the economic dispatching of electricity energy. With the emergence of renewable sources and data-driven approaches, demand-side or demand response (DR) programs have been applied to maintain this balance as accurately as possible. Short-term load forecasting (STLF) has a decisive impact on the success, sustainability, and performance of those programs. Forecasting customers’ consumption over short or long time horizons allows distribution companies to establish new policies or modify strategies in terms of energy management, infrastructure planning, and budgeting. Deep learning (DL)-based approaches for STLF have been referenced for a long time, considering factors such as accuracy, various performance measures, volatility, and adverse effects of uncertainties in load demand. Hence, in this review, DL-based studies for the STLF problem have been considered. The studies have been classified by several titles, such as the provided method and main ideas, dataset specifications, uncertain-aware approaches, online solutions, and practical extensions to DR programs. The main contribution of this review is the ongoing exploration of STLF with DL models to reveal the research direction of the load forecasting problem in terms of the future-oriented integration of the key concepts of online, robustness, and feasibility. [Display omitted] •A review of STLF using DL models.•Classification of techniques, idea, dataset, uncertainty, and online methods.•Information on STLF and examination of LF and DR studies.•Concise description of frequently referenced DL-based LF techniques.•Recent compilation of various LD datasets.