The limited nature of fossil resources and their unsustainable characteristics have led to increased interest in renewable sources. However, significant work remains to be carried out to fully integrate these systems into existing power distribution networks, both technically and legally. While reliability holds great potential for improving energy production sustainability, the dependence of solar energy production plants on weather conditions can complicate the realization of consistent production without incurring high storage costs. Therefore, the accurate prediction of solar power production is vital for efficient grid management and energy trading. Machine learning models have emerged as a prospective solution, as they are able to handle immense datasets and model complex patterns within the data. This work explores the use of metaheuristic optimization techniques for optimizing recurrent forecasting models to predict power production from solar substations. Additionally, a modified metaheuristic optimizer is introduced to meet the demanding requirements of optimization. Simulations, along with a rigid comparative analysis with other contemporary metaheuristics, are also conducted on a real-world dataset, with the best models achieving a mean squared error (MSE) of just 0.000935 volts and 0.007011 volts on the two datasets, suggesting viability for real-world usage. The best-performing models are further examined for their applicability in embedded tiny machine learning (TinyML) applications. The discussion provided in this manuscript also includes the legal framework for renewable energy forecasting, its integration, and the policy implications of establishing a decentralized and cost-effective forecasting system.

The problem we tried to solve relates to the application of artificial intelligence in the legal and judicial system. Given the fact that artificial intelligence (AI) is increasingly taking precedence in various areas of human existence and work, it is an undoubted fact that the legal and judicial systems have not been left out either. It is precisely for this reason that the current state of the use of artificial intelligence in the judicial system, as well as potential new solutions, was first reviewed. In addition to the current one, we focused on the application of artificial intelligence in the legal and judicial system, especially in the domain of decision-making. In this regard, in this paper we propose the use of explainable artificial intelligence, which increasingly takes place when dealing with systems in which the precision and clarity of the parameters on the basis of which a decision is made are of great importance. Looking at the advantages of using explainable artificial intelligence in the decision-making process, one gets the impression that the application of such a model of neural networks can provide the necessary and sufficient conditions for the legal system to accept the use of artificial intelligence in decision-making in the judicial system.

The development of real-time communication systems has become increasingly important for educational institutions seeking flexible, scalable, and cost-effective digital learning environments. This paper presents the design, implementation, and performance evaluation of a cloud-based WebRTC Voice over IP application deployed through Docker container technology and integrated into an educational e-learning system. The proposed solution enables secure browser-based audio and video communication between instructors and students, as well as among students, without requiring additional plugins or native software installation. The application architecture is based on multiple containerized microservices, including database, WebSocket, Apache, and Nginx components, hosted within the Microsoft Azure cloud environment. To assess the efficiency of the proposed model, performance testing was conducted across three deployment infrastructures: bare-metal server, virtual server, and Docker-based platform. The evaluation included application deployment time, startup time, system restart time, and response time under different numbers of concurrent sessions. The results indicate that the Docker-based implementation achieved the best overall performance, with substantially shorter deployment and startup times and lower response latency compared with both bare-metal and virtualized alternatives. These findings confirm that containerized WebRTC infrastructure can improve scalability, maintainability, and responsiveness in educational communication systems. The study contributes a practical implementation model for integrating real-time VoIP and video communication into e-learning platforms, particularly for institutions seeking open-source, cloud-ready, and resource-efficient communication solutions.

Energetska tranzicija u klimatski neutralnom društvu zahteva masovno uvođenje sistema za skladištenje električne energije kako bi se premostio jaz između proizvodnje i potrošnje. Ovaj rad se bavi tehnološko-ekonomskom analizom primenom litijum-jonskih i protočnih baterija na nivou distributivne mreže, kao i potencijalom korišćenja viškova zelene energiјe za proizvodnju vodonika kroz elektrolizu. Rezultati pokazuju da sinergija kratkoročnog (baterije) i dugoročnog (vodonik) skladištenja dramatično smanjuje potrebu za angažovanjem konvensionalnih termoelektrana i ubrzava proces dekarbonizacije industrije.

Savremena regulativa sve više prepoznaje krajnje kupce kao aktivne učesnike na tržištu električne energije. Ovaj rad istražuje trenutni pravni i regulatorni okvir koji uređuje status kupaca-proizvođača i energetskih zajednica. Analiziraju se ekonomski podsticaji, tehničke barijere za njihovo povezivanje na niskonaponsku mrežu, kao i direktan uticaj lokalne proizvodnje iz biomase i solarnih panela na podizanje opšte energetske efikasnosti ruralnih i urbanih sredina. Na kraju, rad nudi preporuke za unapređenje domaćeg zakonodavstva po uzoru na najbolje prakse Evropske unije.

Modern power systems are facing increasing demands for sustainability and reduction of harmful gas emissions, leading to a higher share of renewable energy sources in electricity generation. However, the integration of these sources, primarily solar and wind power plants, brings challenges in terms of intermittent generation, grid instability, and the need for flexible energy management. This paper analyzes the key technical and systemic aspects of renewable energy integration, including energy storage systems, smart grids, and production forecasting methods. Special focus is placed on the stability of the power system, load balancing, and network operation optimization. The results show that successful integration requires a combination of advanced technologies, digitalization, and appropriate regulatory frameworks. It is concluded that system flexibility and resilience are key factors for a sustainable energy transition.