Simulation Framework for Substation Siting Integrating Load, Land Use, Neighborhood, and Cost Analysis

Related Work

Recent studies have explored various methodologies and tools to improve substation siting decisions. For instance, Zeng (2022) proposed a method for 110kV substation siting based on current distribution network and load conditions, emphasizing the importance of considering both technical and economic factors in the decision-making process. Similarly, Țiboacă-Ciupăgeanu and Țiboacă-Ciupăgeanu (2024) explored optimal substation placement through machine learning, presenting it as a sustainable solution for electrical grids.

Mirshekali et al. (2023) developed a deep learning-based framework for fault location in power distribution grids, emphasizing its potential in improving substation fault management. Yao et al. (2023) proposed a microscale substation siting framework utilizing spatial optimization and geospatial big data, underlining the significance of integrating machine learning in spatial decision making.

Li (2022) introduced an improved firefly algorithm for substation siting and capacity determination, highlighting its advantages in handling multiobjective optimization problems. Building on similar optimization techniques, Hrgović and Pavić (2024) developed a substation reconfiguration selection algorithm based on power transfer distribution factors and reinforcement learning, demonstrating its effectiveness in managing congestion. Garcia et al. (2022) employed machine learning to estimate circuit topology at the substation level, indicating its benefits in communication-limited environments.