Machine Learning and Data-Driven Approaches to Photovoltaic and Solar Forecasting

Dear Colleagues,

To comply with the ever-challenging constraints imposed by environmental impact reduction policies, electricity generation from renewable electricity sources has grown rapidly since the last decade and is expected to continue to grow. However, a big family of renewable sources have the peculiarity of being non-programmable, variable throughout hours and seasons. Among these, the photovoltaic (PV) sources are the ones that have developed more rapidly. The variability of PV power generation creates different negative impacts on the electric grid system, such as the stability, reliability, and planning of the operation, aside from the economic benefits.

Therefore, solar and PV forecasts are in general significant for planning the operations of power plants which convert renewable energies into electricity. In particular, regarding the grid, connected PV plants the possibility to predict solar irradiance and the power can became fundamental in making power dispatching plans, in ensuring grid stability and in enabling an optimal unit commitment and economical dispatch. In addition, with reference to stand-alone and hybrid systems, PV forecasting can be a useful reference for improving the control algorithms of charge controllers.

Machine learning (ML), or more generally Artificial Intelligence, and other methods capable of deriving insights from data are nowadays being applied in almost every aspect of human life, ranging from self-driving cars to cancer detection. In the last decade, researchers in AI have developed many advanced ML models able to forecast energy production from renewable sources, also characterizing the uncertainty related to the produced forecast such as probabilistic solar power and load forecasting.

This Special Issue will cover recent advances in ML and photovoltaic and solar forecasts in order to provide a broad overview of current advanced techniques to academics and practitioners. We welcome submissions in the field of forecasting that use data-driven methods. Priority will be given to research articles that present significant advances in their field of application or propose methods never applied in the renewable forecasting field.

We especially seek submissions that advance their field with empirical findings, new methods, or can produce new insights in applied methods (e.g., machine learning interpretability).

Dr. Cristina Ventura
Dr. Sergio Ferlito
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 100 words) can be sent to the Editorial Office for announcement on this website.

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. Forecasting is an international peer-reviewed open access quarterly 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 1800 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.

• forecasting
• artificial intelligence
• ensemble methods
• probabilistic forecasting
• time series
• renewable forecasting
• photovoltaic power forecasting
• solar forecasting
• machine learning