AI and IoT for Smart Energy Forecasting

Dear Colleagues,

This Special Issue focuses on the convergence of artificial intelligence (AI) and Internet of Things (IoT) technologies in advancing smart energy forecasting. As energy systems undergo profound transformation driven by the large-scale integration of renewable energy sources, the proliferation of IoT-enabled sensing infrastructure, and the increasing complexity of demand-side behaviors, both the data landscape and the methodological requirements for energy forecasting are rapidly evolving. In particular, this publication targets the development of AI-driven forecasting strategies that go beyond predictive accuracy to address causality, interpretability, and real-world deployability under conditions of growing data heterogeneity and system uncertainty.

We invite original research articles and review papers addressing AI- and IoT-enabled modeling, analysis, and forecasting methods that align with the emerging needs of smart energy systems. Topics of interest include, but are not limited to, the following areas:

• AI and IoT integration for smart energy management;
• Short- and long-term electrical load and energy consumption forecasting;
• Photovoltaic and wind power generation prediction;
• Spatiotemporal modeling for energy forecasting across time and geographic scales;
• Large language models (LLMs) and text mining for energy data analysis;
• Causal inference for identifying drivers of energy demand and renewable generation variability;
• Explainable machine learning for transparent and trustworthy forecasting;
• IoT-based data acquisition, preprocessing, and feature engineering for energy applications;
• Demand response optimization and smart grid operation;
• Uncertainty quantification and probabilistic forecasting in energy systems.

With the rapid expansion of distributed IoT devices and renewable energy assets, energy forecasting is no longer confined to analyzing structured time-series data from conventional meters. Unstructured data sources, including weather reports, satellite imagery, and operational logs, are increasingly available and informative, yet they remain underutilized in mainstream forecasting pipelines. Meanwhile, the stochastic and spatially correlated nature of renewable generation and demand patterns calls for forecasting frameworks that jointly model temporal dynamics and geographic dependencies. As a result, the methodological frontier of smart energy forecasting is shifting from purely predictive modeling toward integrated approaches that incorporate causal understanding, contextual reasoning via LLMs, and model transparency through explainability. This Special Issue aims to provide a dedicated platform for academic exchange on these emerging challenges, grounded in real-world IoT data environments and engineering applications. We seek to attract cutting-edge research from both the energy systems and AI communities and to encourage interdisciplinary collaboration between academia and industry. We are particularly keen to publish contributions that combine advanced AI methodologies with practically relevant IoT data pipelines, with the goal of jointly advancing the accuracy, interpretability, and operational value of energy forecasting systems.

While previous studies have made considerable progress in applying conventional machine learning and deep learning models to energy forecasting, critical gaps persist. Existing work seldom integrates causal reasoning into forecasting workflows, limiting the ability to distinguish correlation from causation in energy demand analysis. The potential of large language models and text mining to leverage unstructured, context-rich data sources remains largely underexplored. Furthermore, spatiotemporal approaches capable of capturing cross-regional and cross-temporal dependencies are still underdeveloped relative to the complexity of modern smart grid systems. Meanwhile, model explainability is rarely treated as a first-class objective alongside predictive performance. This Special Issue contributes to the existing literature by positioning AI as a multifaceted analytical framework that encompasses causal inference, contextual language understanding, and interpretable decision support, with the goal of managing the complexity and uncertainty inherent in next-generation energy forecasting. By bridging IoT data infrastructure with domain-aware AI methodologies, we hope to enrich current knowledge and accelerate the development of forecasting systems that are accurate, trustworthy, and ready for real-world deployment.

We look forward to receiving your contributions.

Dr. Jiani Heng
Dr. Jianming Hu
Dr. Han Wu
Dr. Mingchen Li
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• smart energy forecasting
• Internet of Things (IoT)
• spatiotemporal modeling
• large language models (LLMs)
• text mining
• causal inference
• explainable machine learning
• demand response
• renewable energy prediction
• smart grid