Solar Power Interval Prediction via Lower and Upper Bound Estimation with a New Model Initialization Approach
This paper proposes a new model initialization approach for solar power prediction interval based on the lower and upper bound estimation (LUBE) structure. The linear regression interval estimation (LRIE) was first used to initialize the prediction interval and the extreme learning machine auto enco...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/12/21/4146 |
| _version_ | 1828150776429543424 |
|---|---|
| author | Peng Li Chen Zhang Huan Long |
| author_facet | Peng Li Chen Zhang Huan Long |
| author_sort | Peng Li |
| collection | DOAJ |
| description | This paper proposes a new model initialization approach for solar power prediction interval based on the lower and upper bound estimation (LUBE) structure. The linear regression interval estimation (LRIE) was first used to initialize the prediction interval and the extreme learning machine auto encoder (ELM-AE) is then employed to initialize the input weight matrix of the LUBE. Based on the initialized prediction interval and input weight matrix, the output weight matrix of the LUBE could be obtained, which was close to optimal values. The heuristic algorithm was employed to train the LUBE prediction model due to the invalidation of the traditional training approach. The proposed model initialization approach was compared with the point prediction initialization and random initialization approaches. To validate its performance, four heuristic algorithms, including particle swarm optimization (PSO), simulated annealing (SA), harmony search (HS), and differential evolution (DE), were introduced. Based on the experiment results, the proposed model initialization approach with different heuristic algorithms was better than the point prediction initialization and random initialization approaches. The PSO can obtain the best efficiency and effectiveness of the optimal solution searching in four heuristic algorithms. Besides, the ELM-AE can weaken the over-fitting phenomenon of the training model, which is brought in by the heuristic algorithm, and guarantee the model stable output. |
| first_indexed | 2024-04-11T21:48:06Z |
| format | Article |
| id | doaj.art-db9141430cd44bcc8e74eea932a98bba |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T21:48:06Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-db9141430cd44bcc8e74eea932a98bba2022-12-22T04:01:22ZengMDPI AGEnergies1996-10732019-10-011221414610.3390/en12214146en12214146Solar Power Interval Prediction via Lower and Upper Bound Estimation with a New Model Initialization ApproachPeng Li0Chen Zhang1Huan Long2State Grid Zhejiang Electrical Power Research Institute, Hangzhou 310014, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 211189, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 211189, ChinaThis paper proposes a new model initialization approach for solar power prediction interval based on the lower and upper bound estimation (LUBE) structure. The linear regression interval estimation (LRIE) was first used to initialize the prediction interval and the extreme learning machine auto encoder (ELM-AE) is then employed to initialize the input weight matrix of the LUBE. Based on the initialized prediction interval and input weight matrix, the output weight matrix of the LUBE could be obtained, which was close to optimal values. The heuristic algorithm was employed to train the LUBE prediction model due to the invalidation of the traditional training approach. The proposed model initialization approach was compared with the point prediction initialization and random initialization approaches. To validate its performance, four heuristic algorithms, including particle swarm optimization (PSO), simulated annealing (SA), harmony search (HS), and differential evolution (DE), were introduced. Based on the experiment results, the proposed model initialization approach with different heuristic algorithms was better than the point prediction initialization and random initialization approaches. The PSO can obtain the best efficiency and effectiveness of the optimal solution searching in four heuristic algorithms. Besides, the ELM-AE can weaken the over-fitting phenomenon of the training model, which is brought in by the heuristic algorithm, and guarantee the model stable output.https://www.mdpi.com/1996-1073/12/21/4146solar power predictioninterval predictionlower and upper bound estimationextreme learning machineheuristic algorithm |
| spellingShingle | Peng Li Chen Zhang Huan Long Solar Power Interval Prediction via Lower and Upper Bound Estimation with a New Model Initialization Approach Energies solar power prediction interval prediction lower and upper bound estimation extreme learning machine heuristic algorithm |
| title | Solar Power Interval Prediction via Lower and Upper Bound Estimation with a New Model Initialization Approach |
| title_full | Solar Power Interval Prediction via Lower and Upper Bound Estimation with a New Model Initialization Approach |
| title_fullStr | Solar Power Interval Prediction via Lower and Upper Bound Estimation with a New Model Initialization Approach |
| title_full_unstemmed | Solar Power Interval Prediction via Lower and Upper Bound Estimation with a New Model Initialization Approach |
| title_short | Solar Power Interval Prediction via Lower and Upper Bound Estimation with a New Model Initialization Approach |
| title_sort | solar power interval prediction via lower and upper bound estimation with a new model initialization approach |
| topic | solar power prediction interval prediction lower and upper bound estimation extreme learning machine heuristic algorithm |
| url | https://www.mdpi.com/1996-1073/12/21/4146 |
| work_keys_str_mv | AT pengli solarpowerintervalpredictionvialowerandupperboundestimationwithanewmodelinitializationapproach AT chenzhang solarpowerintervalpredictionvialowerandupperboundestimationwithanewmodelinitializationapproach AT huanlong solarpowerintervalpredictionvialowerandupperboundestimationwithanewmodelinitializationapproach |