Learning from Scarcity: A Review of Deep Learning Strategies for Cold-Start Energy Time-Series Forecasting
Jihoon Moon*
Department of Data Science, Duksung Women’s University, Seoul, 01369, Republic of Korea
* Corresponding Author: Jihoon Moon. Email: 
(This article belongs to the Special Issue: Deep Learning for Energy Systems)
Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2025.071052
Received 30 July 2025; Accepted 10 December 2025; Published online 29 December 2025
Abstract
Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data, a challenge that becomes especially pronounced when commissioning new facilities where operational records are scarce. This review aims to synthesize recent progress in data-efficient deep learning approaches for addressing such “cold-start” forecasting problems. It primarily covers three interrelated domains—solar photovoltaic (PV), wind power, and electrical load forecasting—where data scarcity and operational variability are most critical, while also including representative studies on hydropower and carbon emission prediction to provide a broader systems perspective. To this end, we examined trends from over 150 predominantly peer-reviewed studies published between 2019 and mid-2025, highlighting advances in zero-shot and few-shot meta-learning frameworks that enable rapid model adaptation with minimal labeled data. Moreover, transfer learning approaches combined with spatiotemporal graph neural networks have been employed to transfer knowledge from existing energy assets to new, data-sparse environments, effectively capturing hidden dependencies among geographic features, meteorological dynamics, and grid structures. Synthetic data generation has further proven valuable for expanding training samples and mitigating overfitting in cold-start scenarios. In addition, large language models and explainable artificial intelligence (XAI)—notably conversational XAI systems—have been used to interpret and communicate complex model behaviors in accessible terms, fostering operator trust from the earliest deployment stages. By consolidating methodological advances, unresolved challenges, and open-source resources, this review provides a coherent overview of deep learning strategies that can shorten the data-sparse ramp-up period of new energy infrastructures and accelerate the transition toward resilient, low-carbon electricity grids.
Keywords
Cold-start forecasting; zero-shot learning; few-shot meta-learning; transfer learning; spatiotemporal graph neural networks; energy time series; large language models; explainable artificial intelligence (XAI)
Open Access
Login
Register
Submit a Paper
Propose a Special lssue
Download PDF
Downloads
Citation Tools
