Research Article
Neural Network Based Micro-grid Integration of Hybrid PV and Wind Energy
Diriba Gonfa Tolasa*
Issue:
Volume 14, Issue 2, April 2025
Pages:
20-27
Received:
4 March 2025
Accepted:
2 April 2025
Published:
19 May 2025
Abstract: The increasing demand for sustainable energy solutions has prompted significant interest in the integration of renewable energy sources into micro-grids. This paper presents a novel approach utilizing neural networks for the effective integration of hybrid photovoltaic (PV) and wind energy systems within micro-grids. The proposed framework addresses the inherent intermittency and variability associated with renewable energy sources, which can challenge grid stability and reliability. In recent years, there has been a growing recognition of the potential of neural networks to model complex non-linear relationships in energy generation and consumption. This study leverages advanced machine learning techniques to optimize the operation of micro-grids, enhancing the synergy between PV and wind energy systems. By employing a multi-layer perceptron (MLP) neural network, we are able to predict energy generation from both sources with high accuracy based on historical weather data and real-time operational parameters. The methodology involves a comprehensive analysis of the energy output from the hybrid system under varying climatic conditions. We utilize a combination of supervised learning algorithms to train the model on historical data, enabling it to forecast energy availability and optimize energy dispatch in real-time. Simulation results indicate a significant improvement in energy management efficiency, reducing reliance on conventional fossil fuel backup systems. Furthermore, the integration of energy storage systems is considered to mitigate fluctuations in power generation and ensure a stable energy supply. The results demonstrate that our neural network-driven approach can achieve a higher penetration of renewables in micro-grids, leading to enhanced economic viability and reduced greenhouse gas emissions. This study contributes to the field of sustainable energy by providing a robust framework for hybrid renewable energy integration, emphasizing the importance of advanced computational techniques. The findings underscore the potential of neural networks not only for predicting energy output but also for optimizing micro-grid operations, paving the way for more resilient and environmentally friendly energy systems. The implications of this research are significant for policymakers and energy planners seeking to implement effective strategies for renewable energy integration in micro-grid infrastructures. By fostering greater adoption of hybrid systems, we can move closer to realizing a sustainable energy future.
Abstract: The increasing demand for sustainable energy solutions has prompted significant interest in the integration of renewable energy sources into micro-grids. This paper presents a novel approach utilizing neural networks for the effective integration of hybrid photovoltaic (PV) and wind energy systems within micro-grids. The proposed framework addresse...
Show More
Research Article
Integration of Renewable Energy with Thermal-Based Power Systems: A Review of Grid Reliability, Optimization, and Storage
Stephen Adole Benson*,
Emmanuel Majiyebo Eronu
Issue:
Volume 14, Issue 2, April 2025
Pages:
28-44
Received:
8 April 2025
Accepted:
27 April 2025
Published:
29 May 2025
DOI:
10.11648/j.epes.20251402.12
Downloads:
Views:
Abstract: Thermal power system are major contributors to power generation and are mostly powered by natural gas, coal, and diesel, all of which are derivatives of petroleum. Aside from their inability to meet energy demands, they have led to growing environmental and economic challenges. Dependence on thermal based power system has further necessitated a transition to sustainable energy systems. This article presents a literature review and statistical analysis based on data obtained from 78 articles published between 2017 and 2025 addressing renewable energy, hybrid power systems, energy storage, optimization strategies, and grid stability. Analysis shows that 50% of the reviewed studies were published in 2024, reflecting a rising research interest. Lithium-ion batteries dominate energy storage (65%), followed by solid-state batteries (10%) and hydrogen fuel cells (6%). Optimization methods are increasingly being adopted, with artificial intelligence-based approaches accounting for 40% and metaheuristic algorithms such as genetic algorithms and particle swarm optimization comprising 30%. However, grid stability continues to be a central challenge as highlighted in 55% of the studies reviewed. Therefore, future work should focus on advanced optimization models to enhance system efficiency and stability. Promising approaches could include techniques that integrate voltage sensitivity analysis with artificial intelligence driven optimization models to improve grid resilience and enable real-time energy management. Furthermore, artificial intelligence driven predictive control, block-chain based energy trading, and IoT enabled smart grids are expected to advance energy networks. By leveraging these innovations, renewable energy sources and thermal power systems can be seamlessly integrated, ensuring a more resilient and sustainable energy future.
Abstract: Thermal power system are major contributors to power generation and are mostly powered by natural gas, coal, and diesel, all of which are derivatives of petroleum. Aside from their inability to meet energy demands, they have led to growing environmental and economic challenges. Dependence on thermal based power system has further necessitated a tra...
Show More
