Machine Learning and Data Based Optimization for Smart Energy Systems

Dear Colleagues,

Smart energy systems require a balanced component layout and an optimal control in order for electric components to deliver optimal results. Variable renewable supply from wind or solar will be combined with storage or diesel generators to match the load demand. As we combine various resources that are often subject to forecast uncertainty, finding the optimal solution for layout and control remains a complex task that requires broad and interdisciplinary technical knowledge. The assessment criteria are diverse and may include not only investment cost, but also multi-year operational cash flow as well as system lifetime, efficiency, and emissions. In the past, different approaches and methods have been applied to find the optimal solution, including simple rule-based strategies, optimization through linear programming, or meta-heuristic approaches. While these methods are well established, they are often not sufficient to model non-linear component behavior, or to deal with uncertainty and forecast errors, and are unable to execute quickly enough for both real-time control and multi-year lifetime assessment.

Machine learning (ML), artificial intelligence (AI), and applied data science methods offer a plethora of new tools to tackle complex non-linear problems that may involve uncertainty. While ML and AI have found broad application in, for example, the fields of robotics, autonomous driving, or image recognition, their usage in smart energy systems is still in its early stages. High-quality distributed data acquisition has become the new normal; the computing power of GPU-assisted data science computers can conduct complex calculations and execute deep learning techniques on multi-component systems, and the number of modelling frameworks with easily adaptable or ready-to-use interfaces for user-defined problems is increasing at a rapid pace.  

This Special Issue aims to collect, compare, and assess novel machine learning and data science techniques that can be used to address smart energy system challenges.

Topics of interest for publication include but are not limited to:

• Presentation of machine learning- and artificial intelligence-derived control strategies for smart energy systems.
• Data-analytics-derived methods for the sizing and layout of components in smart energy systems.
• Statistical analysis of prediction errors and data-based learning techniques for the stochastic optimization of electrical power dispatch with storage.
• Verification of new modelling approaches through field tests or assessments compared to traditional computational approaches (e.g., heuristics, linear and non-linear optimization).
• Assessment of the accuracy and computational speed of competing algorithms, computational frameworks, and solution techniques.

We look forward to your contributions!

Prof. Dr. Holger Hesse
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 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. 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.