Integrated Reliability Assessment and Optimal Reconfiguration of Islanded Microgrids Under Load Growth Using Fick’s Law Optimization Algorithm and Long Short-Term Memory Technique
This paper proposes an integrated framework for reliability assessment, load growth evaluation, and optimal reconfiguration of islanded microgrids under increasing electricity demand. The studied microgrid consists of solar photovoltaic (PV) panels, wind turbines, and diesel generators, operating in...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11114944/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This paper proposes an integrated framework for reliability assessment, load growth evaluation, and optimal reconfiguration of islanded microgrids under increasing electricity demand. The studied microgrid consists of solar photovoltaic (PV) panels, wind turbines, and diesel generators, operating independently from the main grid. First, as load demand grows over time, the microgrid must be reassessed to ensure that reliability metrics such as Loss of Load Probability (LOLP), Energy Not Supplied (ENS), and Loss of Power Supply Probability (LPSP) remain within acceptable limits. Second, a maximum allowable load growth is determined under current generation capacity constraints. Third, a long-term load forecasting model based on the Long Short-Term Memory (LSTM) technique is developed to predict future demand accurately. Fourth, if reliability thresholds are violated, the microgrid is reconfigured by optimally expanding generation capacity, focusing on diesel generators and battery storage units. To address the complex, mixed-variable nature of the reconfiguration problem, the Fick’s Law Optimization (FLO) algorithm is proposed. The FLO algorithm is compared with other metaheuristic algorithms such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO) algorithm, Non-dominated Sorting Genetic Algorithm II (NSGA-II), Artificial Bee Colony (ABC) algorithm, Grey Wolf Optimizer (GWO) algorithm, Equilibrium Optimizer (EO) algorithm, Runge-Kutta Optimizer (RUN) algorithm, and Honey Badger Algorithms (HBA) demonstrating superior performance in convergence speed, exploration–exploitation balance, and global optimality. Numerical results validate the proposed approach, confirming its effectiveness in ensuring reliable and cost-efficient microgrid operation under load growth scenarios. |
|---|---|
| ISSN: | 2169-3536 |