Neural Network Algorithm with Reinforcement Learning for Microgrid Techno-Economic Optimization
Hybrid energy systems (HESs) are gaining prominence as a practical solution for powering remote and rural areas, overcoming limitations of conventional energy generation methods, and offering a blend of technical and economic benefits. This study focuses on optimizing the sizes of an autonomous micr...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/2/280 |
| _version_ | 1827371568028712960 |
|---|---|
| author | Hassan M. Hussein Farh |
| author_facet | Hassan M. Hussein Farh |
| author_sort | Hassan M. Hussein Farh |
| collection | DOAJ |
| description | Hybrid energy systems (HESs) are gaining prominence as a practical solution for powering remote and rural areas, overcoming limitations of conventional energy generation methods, and offering a blend of technical and economic benefits. This study focuses on optimizing the sizes of an autonomous microgrid/HES in the Kingdom of Saudi Arabia, incorporating solar photovoltaic energy, wind turbine generators, batteries, and a diesel generator. The innovative reinforcement learning neural network algorithm (RLNNA) is applied to minimize the annualized system cost (ASC) and enhance system reliability, utilizing hourly wind speed, solar irradiance, and load behavior data throughout the year. This study validates RLNNA against five other metaheuristic/soft-computing approaches, demonstrating RLNNA’s superior performance in achieving the lowest ASC at USD 1,219,744. This outperforms SDO and PSO, which yield an ASC of USD 1,222,098.2, and MRFO, resulting in an ASC of USD 1,222,098.4, while maintaining a loss of power supply probability (LPSP) of 0%. RLNNA exhibits faster convergence to the global solution than other algorithms, including PSO, MRFO, and SDO, while MRFO, PSO, and SDO show the ability to converge to the optimal global solution. This study concludes by emphasizing RLNNA’s effectiveness in optimizing HES sizing, contributing valuable insights for off-grid energy systems in remote regions. |
| first_indexed | 2024-03-08T10:42:19Z |
| format | Article |
| id | doaj.art-754723f85d424029b6d4a8244985b0a6 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-08T10:42:19Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-754723f85d424029b6d4a8244985b0a62024-01-26T17:32:52ZengMDPI AGMathematics2227-73902024-01-0112228010.3390/math12020280Neural Network Algorithm with Reinforcement Learning for Microgrid Techno-Economic OptimizationHassan M. Hussein Farh0Electrical Engineering Department, College of Engineering, Imam Mohammad Ibn Saud Islamic University, Riyadh 11564, Saudi ArabiaHybrid energy systems (HESs) are gaining prominence as a practical solution for powering remote and rural areas, overcoming limitations of conventional energy generation methods, and offering a blend of technical and economic benefits. This study focuses on optimizing the sizes of an autonomous microgrid/HES in the Kingdom of Saudi Arabia, incorporating solar photovoltaic energy, wind turbine generators, batteries, and a diesel generator. The innovative reinforcement learning neural network algorithm (RLNNA) is applied to minimize the annualized system cost (ASC) and enhance system reliability, utilizing hourly wind speed, solar irradiance, and load behavior data throughout the year. This study validates RLNNA against five other metaheuristic/soft-computing approaches, demonstrating RLNNA’s superior performance in achieving the lowest ASC at USD 1,219,744. This outperforms SDO and PSO, which yield an ASC of USD 1,222,098.2, and MRFO, resulting in an ASC of USD 1,222,098.4, while maintaining a loss of power supply probability (LPSP) of 0%. RLNNA exhibits faster convergence to the global solution than other algorithms, including PSO, MRFO, and SDO, while MRFO, PSO, and SDO show the ability to converge to the optimal global solution. This study concludes by emphasizing RLNNA’s effectiveness in optimizing HES sizing, contributing valuable insights for off-grid energy systems in remote regions.https://www.mdpi.com/2227-7390/12/2/280hybrid energy systemsrenewable energy fractionannualized system costloss of power supply probabilityreinforcement learning neural network algorithm (RLNNA)soft-computing algorithms |
| spellingShingle | Hassan M. Hussein Farh Neural Network Algorithm with Reinforcement Learning for Microgrid Techno-Economic Optimization Mathematics hybrid energy systems renewable energy fraction annualized system cost loss of power supply probability reinforcement learning neural network algorithm (RLNNA) soft-computing algorithms |
| title | Neural Network Algorithm with Reinforcement Learning for Microgrid Techno-Economic Optimization |
| title_full | Neural Network Algorithm with Reinforcement Learning for Microgrid Techno-Economic Optimization |
| title_fullStr | Neural Network Algorithm with Reinforcement Learning for Microgrid Techno-Economic Optimization |
| title_full_unstemmed | Neural Network Algorithm with Reinforcement Learning for Microgrid Techno-Economic Optimization |
| title_short | Neural Network Algorithm with Reinforcement Learning for Microgrid Techno-Economic Optimization |
| title_sort | neural network algorithm with reinforcement learning for microgrid techno economic optimization |
| topic | hybrid energy systems renewable energy fraction annualized system cost loss of power supply probability reinforcement learning neural network algorithm (RLNNA) soft-computing algorithms |
| url | https://www.mdpi.com/2227-7390/12/2/280 |
| work_keys_str_mv | AT hassanmhusseinfarh neuralnetworkalgorithmwithreinforcementlearningformicrogridtechnoeconomicoptimization |