Optimizing Distributed Generation Placement In Distribution Systems: A Comparative Study Of AI, Machine Learning, And Deep Learning Algorithms
Year: 2024
Type: article
Abstract: Optimizing Distributed Generation (DG) placement in power distribution systems is crucial for minimizing power losses, enhancing voltage stability, and improving overall system efficiency. This study presents a comprehensive analysis and comparison of various Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) algorithms for optimizing DG placement and sizing in distribution networks. While traditional methods such as Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) have limitations in terms of computational efficiency and scalability, this paper evaluates more advanced algorithms, including “K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Random Forest (RF), Gradient Boosting Machines (GBM), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Deep Q-Learning (DQL)”. The performance of these algorithms is tested on standard IEEE 33-bus and 69-bus radial distribution systems, focusing on key metrics such as power loss reduction, voltage profile improvement, computational time, and scalability. Results demonstrate that deep learning techniques, particularly CNN and LSTM, are highly effective in handling complex grid data, while machine learning models like KNN and SVM offer superior computational efficiency, making them ideal for real-time applications. This analysis provides valuable insights into the strengths and trade-offs of various AI, ML, and DL algorithms, offering guidance for selecting the most appropriate approach to optimize DG placement in different power distribution networks.
Source: Nanotechnology Perceptions
Authors: Dr. Harish S. Avchat, Amit B. Kasar, Dr. Prakash P. Rokade, Dr. Hafiz M. Shaikh, Dr. Pravin D. Gunaware, Dr. Pravin D. Gunaware, Dr. Sandip P. Gath
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4403685671