Machine Learning Techniques for Energy Systems

Dear Colleagues,

With the rapid development of computational power in the last ten years, machine learning techniques based on the neural networks of the past have been given new life since they now can be studied and utilized using many layers. This has led to the discovery of so-called deep learning techniques that have numerous potential applications to many real physical and/or artificial (manmade) systems. The use of machine learning technique in all areas of science and engineering appears to be the imperative of modern times, especially in the past three to four years. Supervised and unsupervised machine learning techniques can be used to solve numerous classification, regression, and clustering problems. Various machine learning techniques (convolutional neural networks, spiking neural networks, support vector machines, reinforcement learning, etc.) have already been utilized to improve the processes and operations of energy systems. It is important to emphasize that the reinforcement learning technique represents an approximate dynamic programming method—the method that together with the calculus of variations was used to develop algorithms for the optimal control of dynamic systems.

Although many journal papers have been published on the use of machine learning in energy systems, a lot of research opportunities still exist in this area. The time has come for researchers in energy systems to systematically use machine learning techniques and algorithms to make energy systems more efficient, better controlled and stabilized, better managed, more ecologically friendly, more user friendly, and provide guidelines for how to build future energy systems for various applications in diverse engineering and scientific fields.

Prof. Dr. Zoran Gajic
Guest Editor

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. Energies 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 2600 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.

• machine learning
• neural networks
• deep learning
• reinforcement learning
• support vector machines
• energy systems (solar, wind, fuel cells, power systems, smart grids, batteries, ultra-capacitors, thermal energy, nuclear energy, tidal energy, wave energy, magnetic energy)
• applications