article · Results in Engineering
Managing energy distribution within renewable microgrid networks requires rapid, accurate control decisions across multiple components, including batteries, fuel cells, super-capacitors, and the main grid. A comparative assessment evaluated the capability of two machine learning techniques, k-Nearest Neighbours and Random Forest, to guide decision-making in systems integrated with hydrogen storage. Across all evaluated switching relays, Random Forest substantially outperformed k-Nearest Neighbours. It achieved macro average precision ratings between 82 and 90 percent and F1-scores between 85 and 90 percent, whereas k-Nearest Neighbours attained precision scores of only 14 to 30 percent. The Random Forest method demonstrated high resilience when handling imbalanced operational data, showing that it can reliably manage the complexities of energy routing among diverse storage units and renewable generation sources.
Renewable microgrids combine fluctuating power sources with multiple storage units like batteries and hydrogen cells. Operating them efficiently requires automated systems that decide instantly when to charge, store, or feed power into the grid. Demonstrating that Random Forest algorithms can reliably make these relay decisions, even with skewed operational data, provides a clearer path towards stable, automated green energy management.
This algorithmic benchmarking could inform control software for developers and operators of hybrid renewable microgrids integrating hydrogen and electrical storage. Because the abstract reports algorithmic evaluation across component relays rather than hardware integration or field testing, the work represents early-stage decision-support research. Commercial energy management providers would need to conduct live or simulated trials before implementing these algorithms.
AI-generated from the published abstract. Always read the original work before citing.
This study addresses the critical issue of energy management in micro-grid (MG) systems incorporating renewable energy sources and hydrogen storage. The research introduces an innovative approach by conducting a comparative analysis of two machine learning methods, namely k-Nearest Neighbors (k-NN) and Random Forest (RF), to optimize micro-grid decision-making. The investigation reveals the consistent superiority of Random Forest, particularly in precision and F1-scores, across key micro-grid components such as the fuel cell relay, battery relay, super-capacitor relay, and grid system relay. The results demonstrate that the RF method consistently achieves high macro average precision factors (90%, 86%, 84%, 82%) and impressive macro average F1-scores (90%, 87%, 88%, 85%), surpassing the performance of k-NN, which yields notably lower precision factors (30%, 15%, 14%, 28%) and F1-scores (41%, 23%, 26%, 34%). This superior performance positions RF as a robust machine learning method for micro-grid decision-making, specifically in the realm of energy storage and renewable sources. The novelty of this work lies in establishing Random Forest as a reliable tool capable of handling the intricacies of micro-grid decision-making, thereby enhancing sustainable energy management processes. Additionally, the resilience of RF to imbalanced data adds to its effectiveness in diverse operational scenarios. This research sheds light on the potential of RF to contribute significantly to the advancement of sustainable energy solutions in micro-grid systems.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.rineng.2024.101888
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
