Distributed Photovoltaic Power Energy Generation Prediction Based on Improved Multi-objective Particle Algorithm
Accurate prediction of distributed photovoltaic (DPV) power generation is crucial for stable grid operation, yet existing methods struggle with the non-linear, intermittent nature of solar power, and traditional machine learning models face hyperparameter selection and overfitting challenges. This s...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
European Alliance for Innovation (EAI)
2025-03-01
|
| Series: | EAI Endorsed Transactions on Energy Web |
| Subjects: | |
| Online Access: | https://publications.eai.eu/index.php/ew/article/view/8901 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850226687675990016 |
|---|---|
| author | Yuanzheng Xiao Huawei Hong Feifei Chen Xiaorui Qian Ming Xu Hanbin Ma |
| author_facet | Yuanzheng Xiao Huawei Hong Feifei Chen Xiaorui Qian Ming Xu Hanbin Ma |
| author_sort | Yuanzheng Xiao |
| collection | DOAJ |
| description | Accurate prediction of distributed photovoltaic (DPV) power generation is crucial for stable grid operation, yet existing methods struggle with the non-linear, intermittent nature of solar power, and traditional machine learning models face hyperparameter selection and overfitting challenges. This study developed a highly accurate DPV power prediction method by optimizing a Long Short-Term Memory (LSTM) network's hyperparameters using an improved Multi-Objective Particle Swarm Optimization (MO-PSO) algorithm. A hybrid LSTM-PSO model was created, where the LSTM network served as the core prediction model, and the improved MO-PSO algorithm optimized its hyperparameters, enhancing generalization and avoiding overfitting. The LSTM-PSO model significantly improved prediction accuracy compared to traditional methods. Key results from two power stations included a maximum deviation of 6.2 MW at Power Station A, a peak time deviation of less than 0.1 MW at Power Station B, and a prediction interval error controlled below 30 MW at an 80% confidence level. The optimized LSTM-PSO model effectively captures DPV power generation dynamics, and the superior performance metrics demonstrate its potential for intelligent grid management. However, limitations include prediction accuracy under extreme weather and computational efficiency for large datasets. Future work will focus on broader applicability and more efficient algorithm variants.
|
| format | Article |
| id | doaj-art-68a78a52843146939284e1bc1ff5ece2 |
| institution | OA Journals |
| issn | 2032-944X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | European Alliance for Innovation (EAI) |
| record_format | Article |
| series | EAI Endorsed Transactions on Energy Web |
| spelling | doaj-art-68a78a52843146939284e1bc1ff5ece22025-08-20T02:04:59ZengEuropean Alliance for Innovation (EAI)EAI Endorsed Transactions on Energy Web2032-944X2025-03-011210.4108/ew.8901Distributed Photovoltaic Power Energy Generation Prediction Based on Improved Multi-objective Particle AlgorithmYuanzheng Xiao0Huawei Hong1Feifei Chen2Xiaorui Qian3Ming Xu4Hanbin Ma5State Grid Fujian Marketing Service CenterState Grid Fujian Marketing Service CenterState Grid Fujian Marketing Service CenterState Grid Fujian Marketing Service CenterState Grid Fujian Marketing Service CenterState Grid Info-Telecom Great Power Science and Technology Co LtdAccurate prediction of distributed photovoltaic (DPV) power generation is crucial for stable grid operation, yet existing methods struggle with the non-linear, intermittent nature of solar power, and traditional machine learning models face hyperparameter selection and overfitting challenges. This study developed a highly accurate DPV power prediction method by optimizing a Long Short-Term Memory (LSTM) network's hyperparameters using an improved Multi-Objective Particle Swarm Optimization (MO-PSO) algorithm. A hybrid LSTM-PSO model was created, where the LSTM network served as the core prediction model, and the improved MO-PSO algorithm optimized its hyperparameters, enhancing generalization and avoiding overfitting. The LSTM-PSO model significantly improved prediction accuracy compared to traditional methods. Key results from two power stations included a maximum deviation of 6.2 MW at Power Station A, a peak time deviation of less than 0.1 MW at Power Station B, and a prediction interval error controlled below 30 MW at an 80% confidence level. The optimized LSTM-PSO model effectively captures DPV power generation dynamics, and the superior performance metrics demonstrate its potential for intelligent grid management. However, limitations include prediction accuracy under extreme weather and computational efficiency for large datasets. Future work will focus on broader applicability and more efficient algorithm variants. https://publications.eai.eu/index.php/ew/article/view/8901Particle AlgorithmDistributed photovoltaic power generationPower predictionLong short-term memory networkIntelligent Power Grid |
| spellingShingle | Yuanzheng Xiao Huawei Hong Feifei Chen Xiaorui Qian Ming Xu Hanbin Ma Distributed Photovoltaic Power Energy Generation Prediction Based on Improved Multi-objective Particle Algorithm EAI Endorsed Transactions on Energy Web Particle Algorithm Distributed photovoltaic power generation Power prediction Long short-term memory network Intelligent Power Grid |
| title | Distributed Photovoltaic Power Energy Generation Prediction Based on Improved Multi-objective Particle Algorithm |
| title_full | Distributed Photovoltaic Power Energy Generation Prediction Based on Improved Multi-objective Particle Algorithm |
| title_fullStr | Distributed Photovoltaic Power Energy Generation Prediction Based on Improved Multi-objective Particle Algorithm |
| title_full_unstemmed | Distributed Photovoltaic Power Energy Generation Prediction Based on Improved Multi-objective Particle Algorithm |
| title_short | Distributed Photovoltaic Power Energy Generation Prediction Based on Improved Multi-objective Particle Algorithm |
| title_sort | distributed photovoltaic power energy generation prediction based on improved multi objective particle algorithm |
| topic | Particle Algorithm Distributed photovoltaic power generation Power prediction Long short-term memory network Intelligent Power Grid |
| url | https://publications.eai.eu/index.php/ew/article/view/8901 |
| work_keys_str_mv | AT yuanzhengxiao distributedphotovoltaicpowerenergygenerationpredictionbasedonimprovedmultiobjectiveparticlealgorithm AT huaweihong distributedphotovoltaicpowerenergygenerationpredictionbasedonimprovedmultiobjectiveparticlealgorithm AT feifeichen distributedphotovoltaicpowerenergygenerationpredictionbasedonimprovedmultiobjectiveparticlealgorithm AT xiaoruiqian distributedphotovoltaicpowerenergygenerationpredictionbasedonimprovedmultiobjectiveparticlealgorithm AT mingxu distributedphotovoltaicpowerenergygenerationpredictionbasedonimprovedmultiobjectiveparticlealgorithm AT hanbinma distributedphotovoltaicpowerenergygenerationpredictionbasedonimprovedmultiobjectiveparticlealgorithm |