<abstract xmlns="http://www.w3.org/1999/xhtml">

Generation of photovoltaic power plants is growing rapidly in the last ten years in the world. One of the key factors for the construction of floating photovoltaic power plants is to provide space for their construction. This paper presents statistical indicators of installed capacities of floating photovoltaic power plants, as well as a detailed description of the components of these power plants. Approaches to construction and maintenance recommendations are described in more detail. The basic results of simulations are presented on a concrete example of a floating photovoltaic 1 MW power plant on Lake Modrac. The available areas of artificial lakes in Bosnia and Herzegovina were analysed, and it was shown that the installation of floating photovoltaic power plants on 5% of the surface of artificial lakes would provide around 10% of the total electricity consumption in Bosnia and Herzegovina.
</abstract>

Floating Photovoltaic Power Plant and Estimation of Potential in Bosnia and Herzegovina

<abstract xmlns="http://www.w3.org/1999/xhtml">

The final paper presents an approach to solving the problem of optimal use of electrical energy in the production process. An analysis of all important parameters, limitations, and goals was performed, after which a mathematical model was created and used in writing Matlab code to solve the problems. It is the basis for further upgrading following the needs of each organization and because of that, it can be very significant.
</abstract>

The Energy Management System According to the Norm ISO 50001

<abstract xmlns="http://www.w3.org/1999/xhtml">

This paper describes charging of battery stack using model predictive control (MPC) algorithm. Temperature model and hybrid electrical model are used in algorithm. The battery stack consists of four serially connected valve-regulated lead-acid (VRLA) batteries. The objective of the optimization is to charge the proposed battery stack without violating the constraints in order to maintain the battery health. Validation of MPC algorithm for battery charging is performed using comparison between closed-loop MPC simulations and obtained characteristics of actual MPC charging. Previously, the conventional constant current constant voltage (CCCV) algorithm was proved as good, taking into account the degradation effects but not considering the speed of the charging. The comparison between charging of proposed battery stack using MPC algorithm and CCCV algorithm is performed and the comparison in charging proves MPC algorithm as better compared to the CCCV algorithm.
</abstract>

Comparison of Two Different Battery Charging Methods

<abstract xmlns="http://www.w3.org/1999/xhtml">

Reinforcement learning (RL) is area of Machine Learning (ML) and part of wide-range portfolio of the Artificial intelligence (AI) methods. Besides the explanations of the concepts and principles of RL, in the paper are presented practical RL models for control and optimizing operation of power system – controlling tap-changers for maintain voltage levels and model for techno-economical optimizing operation of energy storages of households in microgrid. Trained RL agent in the practical example synchronizes operation of tap-changers to maintain satisfactory voltage level for the consumers, even in the network with distributed generation. Energy storages are in wide use in households, especially in the combination with PV. In the second example, microgrid’s energy management system (EMS) RL agent after learning process act in the simulated environment with variable electrical energy prices, variable load profiles and efficiency of PV modules of households to maximize profit for the houseowners in the microgrid. Agent controls charging and discharging of energy storages and obtain maximal benefit in randomly determined conditions of microgrid operation and different tariff situations. Models are implemented in the Python programming environment Python with specialized power system simulation software (Pandapower) and RL libraries (RLib, OpenAI).
</abstract>

Reinforcement Learning in Power System Control and Optimization

<abstract xmlns="http://www.w3.org/1999/xhtml">

This paper aims to provide objective quality metrics assessment for cloud gaming using machine learning algorithms. Three classification algorithms (i.e., Random Forest, Random Three and J-48) have been used for the development of models for objective quality assessment of two metrics: blurriness and blockiness. The results indicate that Random Forest has the best performance in this experimental case of objective quality metrics assessment for cloud gaming. Future research activities will cover comparison of a broad range of objective quality metrics and machine learning algorithms while using larger dataset to enhance the results significance.
</abstract>

Objective Quality Metrics Assessment for Cloud Gaming

AHEAD OF PRINT

Volume 17 (2023): Issue 2 (December 2023)

Volume 17 (2023): Issue 1 (July 2023)

Volume 17 (2023): Issue s1 (December 2023)

Volume 16 (2022): Issue s1 (December 2022) Advanced materials for engineering applications

Volume 16 (2022): Issue 2 (December 2022)

Volume 16 (2022): Issue 1 (July 2022)

Volume 15 (2021): Issue 2 (December 2021)

Volume 15 (2021): Issue 1 (October 2021) Research trends in interrupting and switching in HV and MV switchgear

Volume 14 (2020): Issue 2 (December 2020)

Volume 14 (2020): Issue s1 (October 2020) Special Issue: Computational, Numerical and Mathematical Methods in Electrical Engineering

Volume 13 (2019): Issue 1 (December 2019)

B&H Electrical Engineering

B&amp;H Electrical Engineering (ISSN: 2566-3143, e-ISSN: 2566-3151) is an international, double blind peer reviewed, non-commercial, open access journal.   The Committee for Bosnia and Herzegovina International Council on Large Electric Systems – CIGRE is the journal publisher.   The aim of the Journal is to publish high-quality papers in a wide area of electrical engineering, computer sciences and information technology.   However, papers in the field of technology, ecology, energy efficiency, industry applications, economy, management and other engineering and social science fields will also be published if they are associated with the field of electrical engineering, computer science and information technology.   Examples of relevant areas can be (but are not limited to):    Power engineering  Automation  Electronics  Robotics  Telecomunications  Signal procesing  Mechatronics  Applied Artificial Inteligence  Energy Engineering  Materials in Electrical Engineering  Applied Mathematics  Biomedical Engineering  Database and Data mining  IT security and Criptology  Data Processing  Buissness Informatics   Type of papers   In addition to original and review scientific papers, the Journal will also consider professional and conference papers.   Language   The Journal accepts only English-language papers.  Publication Fee  No fee is charged from authors for papers accepted for publishing.  Archiving  Sciendo archives the contents of this journal in Portico - digital long-term preservation service of scholarly books, journals and collections.  Plagiarism Policy  The editorial board is participating in a growing community of Similarity Check System's in order to ensure that the content published is original and trustworthy. Similarity Check is a medium that allows for comprehensive manuscripts screening, aimed to eliminate plagiarism and provide a high standard and quality peer-review process. 