With the steady increase in the use of renewable energy sources in the energy sector, new challenges arise, especially the unpredictability of these energy sources. This uncertainty complicates the management, planning, and development of energy systems. An effective solution to these challenges is short-term forecasting of the output of photovoltaic power plants. In this paper, a novel method for short-term production prediction was explored which involves continuous photography of the sky above the photovoltaic power plant. By analyzing a series of sky images, patterns can be identified to help predict future photovoltaic power generation. A hybrid model that integrates both a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) for short-term production forecasting was developed and tested. This model effectively detects spatial and temporal patterns from images and power output data, displaying considerable prediction accuracy. In particular, a 74% correlation was found between the model’s predictions and actual future production values, demonstrating the model’s efficiency. The results of this paper suggest that the hybrid CNN-LSTM model offers an improvement in prediction accuracy and practicality compared to traditional forecasting methods. This paper highlights the potential of Deep Learning in improving renewable energy practices, particularly in power prediction, contributing to the overall sustainability of power systems.

Visions of energy transition focus on activating end users, meaning that numerous flexible-distribution network-level devices become active participants in power-system operations. This implies a fast, reliable, and secure exchange of data, enabling the distribution-system operators to maintain, or even improve, the quality and delivery of service. With the introduction of the International Electrotechnical Commission (IEC) 61850 standard, the path is set for a single communication topology covering all substation levels. The standard has the potential to change the way substations are designed, built, tested, and maintained. This means that the key segment of the substation, its protection system, will go through a transition period with the end goal of having a digitized substation where all information exchange is performed over an Ethernet communication bus. This paper analyzes the performance impact of the IEC 61850-9-2LE on the protection system. To do this, a laboratory hardware-in-the-loop test setup was developed representing traditional-, hybrid-, and digital-substation topology. The setup serves to simulate faults and create transient waveforms in an extended IEEE 123-node test system, which is then used to detect the reaction times of protection relay devices. To verify the results, a significant number of tests was performed clearly showing the benefits of digitalizing the distribution system.

Advancements in new technologies, a reduction in CO₂ emissions, and the rising demand for energy are causing a growth in the share of renewable energy sources. In distribution networks, an increasing number of distributed generators (DGs) makes the utility grid’s protection complex and demanding. Vector surge and rate-of-change-of-frequency are the established anti-islanding protection methods, recognizing that the standard paradigm for protection, involving distributed generation, cannot be set only once but has to be continuously updated following the requirements and changes in the system. One of the requirements is active participation in the preservation of system frequency and voltage, which can be interrupted if the DG trips and disconnects from the utility grid. Anti-islanding protection and spurious tripping can be avoided by implementing new algorithms and techniques. This paper presents a novel protection scheme based on a voltage frequency differential. The proposed algorithm employs remote and local frequency measurements in such a manner that, for the occurrence of a frequency difference, it is assumed that the DG is in an islanding state. In this article, we demonstrate the feasibility of the algorithm through numerical analysis of grid events and laboratory testing emulating real grid-measured values. The test results show that the algorithm is resilient to false tripping for non-islanding events and more reliable than conventional methods in islanding detection. The algorithm can be set to low-frequency differential values, drastically reducing the non-detection zone in any DG type, regardless of its size and voltage level at the point of common coupling. Unlike standard anti-islanding methods, the algorithm supports the ability of the DG to fault-ride through demand.

This work shows genetic algorithm approach to the optimum wire busbar design. Parameters of the wire busbar are mapped into a chromosome like a string. This includes insulator string type, wire conductor type and number, bundle wire...

Original methodology for the calculation of island operation event occurrence possibility is proposed for the photovoltaic power plants connected to medium voltage grid. Within the methodology description, event fault tree with number of pairs of basic initial events is discussed, where probability for the basic events are defined and flow chart for the proposed calculation is given. The novelty in the approach for probability calculation includes also proposal for development of frequency distribution functions for concerned power generation and consumption variables which have to be modelled for the probability calculations, for which the triangular distributions curves have been chosen. Being boundary conditions for definition of non-detected island event, borders of non-detection zones are defined for the common island detection protection functions: over frequency and under frequency, over voltage and under voltage and rate of change of frequency functions. Comparison of the island event probability is presented on case study example, with conclusion that standard voltage and frequency protection alone are not satisfying, but ROCOF protection could be suitable, subject to particular local grid characteristic and calculative verification of probability.