A multi-input and dual-output wind speed interval forecasting system based on constrained multi-objective optimization problem and model averaging
[Display omitted] •A multi-input dual-output neural network is constructed to obtain the best interval.•Two constrained bi-objective optimization problems are established and solved.•An algorithm specifically solving constrained multi-objective problem is employed.•Coverage constraint is introduced...
Saved in:
| Published in: | Energy conversion and management Vol. 319; p. 118909 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Ltd
01.11.2024
|
| Subjects: | |
| ISSN: | 0196-8904 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | [Display omitted]
•A multi-input dual-output neural network is constructed to obtain the best interval.•Two constrained bi-objective optimization problems are established and solved.•An algorithm specifically solving constrained multi-objective problem is employed.•Coverage constraint is introduced to optimize the two optimal interval coefficients.•Model averaging is used to combine advantages to skillfully solve “no free lunch”
The uncertainty analysis of wind speed forecasting using the Lower Upper Bound Estimation (LUBE) is an advanced interval prediction method that does not require assumptions about data distribution. However, previous studies have primarily relied on single neural network models, overlooking the benefits of model averaging. Moreover, they assumed symmetric upper and lower bounds of true values in training data, which may not hold for real data with asymmetric features. To address these issues, we propose a multi-input dual-output wind speed interval forecasting system (MDWSIFS). Utilizing neural network models, we create two different outputs for each model by scaling the output values with interval scaling coefficients 1 + γ1 and 1 - γ2, respectively. Subsequently, we propose two constrained multi-objective optimization problems and introduce non-dominated sorting genetic algorithm II (NSGA-II), a method that has been proven to be highly suitable for solving constrained bi-objective optimization problems. By using NSGA-II to optimize a multi-objective problem with coverage probability constraints, the optimal coefficients γ1 and γ2 are determined, thereby the prediction interval is defined. Finally, through a model averaging strategy integrated with several neural network models, we use NSGA-II to optimize the weights of sub-models to achieve a more accurate final prediction interval. The test results indicate the superiority of MDWSIFS over existing models, with the metric reaching unprecedented levels across multiple datasets. These findings not only signify an advancement in wind speed forecasting but also promise improved efficiency in wind energy utilization and reduced operational costs for power systems. |
|---|---|
| AbstractList | [Display omitted]
•A multi-input dual-output neural network is constructed to obtain the best interval.•Two constrained bi-objective optimization problems are established and solved.•An algorithm specifically solving constrained multi-objective problem is employed.•Coverage constraint is introduced to optimize the two optimal interval coefficients.•Model averaging is used to combine advantages to skillfully solve “no free lunch”
The uncertainty analysis of wind speed forecasting using the Lower Upper Bound Estimation (LUBE) is an advanced interval prediction method that does not require assumptions about data distribution. However, previous studies have primarily relied on single neural network models, overlooking the benefits of model averaging. Moreover, they assumed symmetric upper and lower bounds of true values in training data, which may not hold for real data with asymmetric features. To address these issues, we propose a multi-input dual-output wind speed interval forecasting system (MDWSIFS). Utilizing neural network models, we create two different outputs for each model by scaling the output values with interval scaling coefficients 1 + γ1 and 1 - γ2, respectively. Subsequently, we propose two constrained multi-objective optimization problems and introduce non-dominated sorting genetic algorithm II (NSGA-II), a method that has been proven to be highly suitable for solving constrained bi-objective optimization problems. By using NSGA-II to optimize a multi-objective problem with coverage probability constraints, the optimal coefficients γ1 and γ2 are determined, thereby the prediction interval is defined. Finally, through a model averaging strategy integrated with several neural network models, we use NSGA-II to optimize the weights of sub-models to achieve a more accurate final prediction interval. The test results indicate the superiority of MDWSIFS over existing models, with the metric reaching unprecedented levels across multiple datasets. These findings not only signify an advancement in wind speed forecasting but also promise improved efficiency in wind energy utilization and reduced operational costs for power systems. |
| ArticleNumber | 118909 |
| Author | Lv, Mengzheng Gao, Jialu Wang, Jianzhou Wang, Kang Wang, Shuai Zhao, Yang |
| Author_xml | – sequence: 1 givenname: Mengzheng orcidid: 0000-0002-5035-4822 surname: Lv fullname: Lv, Mengzheng organization: School of Statistics, Dongbei University of Finance and Economics, Dalian 116025, China – sequence: 2 givenname: Jianzhou surname: Wang fullname: Wang, Jianzhou email: wangjz@dufe.edu.cn organization: School of Statistics, Dongbei University of Finance and Economics, Dalian 116025, China – sequence: 3 givenname: Shuai surname: Wang fullname: Wang, Shuai organization: School of Statistics, Dongbei University of Finance and Economics, Dalian 116025, China – sequence: 4 givenname: Yang surname: Zhao fullname: Zhao, Yang organization: School of Statistics, Dongbei University of Finance and Economics, Dalian 116025, China – sequence: 5 givenname: Jialu surname: Gao fullname: Gao, Jialu organization: Institute of Systems Engineering, Macau University of Science and Technology, Macau, 999078, China – sequence: 6 givenname: Kang surname: Wang fullname: Wang, Kang organization: School of Statistics, Dongbei University of Finance and Economics, Dalian 116025, China |
| BookMark | eNqFkM9OAyEQxjloYv3zCoYX2ArdLtsmHjSN_xITL3omAwyGZhc2QGvqY_jEslYvXnqaGfL9vmG-U3Lkg0dCLjmbcsbF1XqKXgffg5_O2Gw-5XyxZMsjMmF8KarSz0_IaUprxljdMDEhX7e033TZVc4Pm0zBG2o20FVhk8f5w5WHNCAa6nzGuIWO2hBRQ8rOv9O0Sxl7qiAVRfC07E45gvNl3PsGtUad3RZpGLLr3SdkV4RDDKor5LiwDwY7CluM8F5Mz8mxhS7hxW89I2_3d6-rx-r55eFpdftc6ZrPcgWiqVHxhmvWqpYpWJj5UihuwSJTjW6VbbFI0IAFY2phrBFKWLHAVqvG1Gfkeu-rY0gpopXa5Z_fjRd0kjM5ZirX8i9TOWYq95kWXPzDh-h6iLvD4M0exHLc1mGUSbuiRONKsFma4A5ZfANNeqB_ |
| CitedBy_id | crossref_primary_10_1016_j_apenergy_2025_126615 crossref_primary_10_1016_j_energy_2025_136060 crossref_primary_10_1016_j_energy_2024_133920 crossref_primary_10_1016_j_energy_2025_137229 crossref_primary_10_1016_j_ins_2025_122531 crossref_primary_10_1109_TSTE_2024_3478760 crossref_primary_10_1016_j_awe_2025_100055 crossref_primary_10_1111_mice_70049 crossref_primary_10_1016_j_asoc_2025_113829 |
| Cites_doi | 10.1109/TSTE.2021.3086851 10.1109/TII.2020.3006928 10.1109/4235.585893 10.1109/TNN.2010.2096824 10.1109/59.41700 10.1016/j.ijepes.2014.03.060 10.1109/72.97934 10.1016/j.enconman.2023.117868 10.1109/TNN.2003.809428 10.1109/5.726791 10.1080/07350015.1995.10524599 10.1109/TPWRS.2013.2287871 10.1016/j.apenergy.2022.118796 10.2307/2532360 10.1016/j.eswa.2022.118419 10.1049/iet-rpg.2018.5643 10.1016/j.jenvman.2022.116282 10.1007/s10489-024-05350-z 10.1016/j.eswa.2023.122924 10.1016/j.renene.2018.09.087 10.1016/j.ins.2022.11.145 10.1016/j.apenergy.2022.118938 10.1016/j.apm.2023.06.040 10.1016/j.enconman.2022.115583 10.1016/j.compeleceng.2022.108000 10.1109/4235.996017 10.1016/j.knosys.2021.107435 10.1016/j.eswa.2023.119539 10.1007/BF00114844 10.1093/biomet/asm068 10.1038/323533a0 10.1016/j.rser.2023.113497 10.1080/01621459.1972.10481224 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Ltd |
| Copyright_xml | – notice: 2024 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.enconman.2024.118909 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| ExternalDocumentID | 10_1016_j_enconman_2024_118909 S0196890424008501 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAHBH AAHCO AAIKJ AAKOC AALRI AAOAW AAQFI AARJD AAXKI AAXUO ABFNM ABFRF ABJNI ABMAC ACBEA ACDAQ ACGFO ACGFS ACIWK ACNCT ACRLP ADBBV ADEZE AEBSH AEFWE AEKER AENEX AFJKZ AFKWA AFRAH AFTJW AGHFR AGUBO AGYEJ AHHHB AHIDL AHJVU AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR BELTK BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W JARJE KOM LY6 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSR SST SSZ T5K TN5 XPP ZMT ~02 ~G- 29G 6TJ 8WZ 9DU A6W AAQXK AATTM AAYWO AAYXX ABDPE ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADMUD ADNMO AEIPS AEUPX AFFNX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EFLBG EJD FEDTE FGOYB G-2 HVGLF HZ~ H~9 R2- SAC WUQ ~HD |
| ID | FETCH-LOGICAL-c312t-a653eb151c07b70ba8d496b1fafe0b5c7bf7e53eedafadd36dfd6b6f68e7cb5d3 |
| ISICitedReferencesCount | 10 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001302022900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0196-8904 |
| IngestDate | Sat Nov 29 04:26:14 EST 2025 Tue Nov 18 22:00:31 EST 2025 Tue Dec 03 03:44:28 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Dual-output neural network Constrained multi-objective optimization problem Lower and upper bound estimation Wind speed interval forecasting Model averaging |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c312t-a653eb151c07b70ba8d496b1fafe0b5c7bf7e53eedafadd36dfd6b6f68e7cb5d3 |
| ORCID | 0000-0002-5035-4822 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_enconman_2024_118909 crossref_primary_10_1016_j_enconman_2024_118909 elsevier_sciencedirect_doi_10_1016_j_enconman_2024_118909 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-11-01 2024-11-00 |
| PublicationDateYYYYMMDD | 2024-11-01 |
| PublicationDate_xml | – month: 11 year: 2024 text: 2024-11-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Energy conversion and management |
| PublicationYear | 2024 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | An, Yin, Wu, She, Chen (b0005) 2021 Jones, Henderson (b0045) 2007 El-Dakkak, Feng, Wahbah, EL-Fouly, Zahawi (b0075) 2019 Specht (b0230) 1991 Zhang, Wang, Li, Zeng, Huang (bib281) 2022 Chung J, Gulcehre C, Cho K, Bengio Y. Gated feedback recurrent neural networks. 32nd International Conference on Machine Learning, ICML 2015, 2015. Xing, Wang, Lu, Wang (b0140) 2022; 263 Wang, Wang, Li, Lu, Jiang, Xing (b0130) 2023 Wang, Wang, Zeng, Lu (b0255) 2022; 313 Zhang, Yan, Liu, Gao, Han, Li (b0015) 2021 Zhao, Wang, Niu, Wang, Lv (b0275) 2024 Lian, Zeng, Wang, Yao, Su, Tang (b0105) 2020 Li, Wang, Zhang (b0090) 2021; 231 Gao, Wang, Zhou, Lv, Wei (b0125) 2024; 244 Bin, Zhu, Siew (b0220) 2006 Rumelhart, Hinton, Williams (b0215) 1986 Khosravi, Nahavandi (b0060) 2014 Odell, Anderson, D’Agostino (b0040) 1992 Heskes (b0050) 1997 Wolpert, Macready (b0260) 1997 Winkler (b0280) 1972 GWEC. Global Wind Report 2023. Global Wind Energy Council 2023. Liu C, Zhu H, Ren Y, Wang Z. A Novel Intelligent Forecasting Framework for Quarterly or Monthly Energy Consumption. IEEE Transactions on Industrial Informatics 2023;PP:1–12. 10.1109/TII.2023.3330299. Choi, Park, Choi, Lee, Lee (b0020) 2023 Almutairi, Alrumayh (b0095) 2022; 101 Yang, Hao, Hao (b0030) 2023; 622 Wang, Wang, Zeng, Lu (b0080) 2022; 314 Wang, Lv, Li, Zeng (b0265) 2023 Wang, Zhang, Liu, Huang (b0115) 2023 Seo, Oh, Kwak (b0070) 2019 Lv, Li, Niu, Wang (b0135) 2022; 52 Wan, Xu, Pinson, Dong, Wong (b0085) 2014 Zhao, Ye, Pinson, Tang, Lu (b0025) 2018 Nix, Weigend (b0035) 1994 Deb, Pratap, Agarwal, Meyarivan (b0170) 2002 Jaeger H. Adaptive Nonlinear System Identification with Echo State Networks. NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems, 2002. Elman (b0225) 1991 Gao, Wang, Wei, Jiang (b0160) 2023; 123 Diebold, Mariano (b0270) 1995; 13 Ding, He (b0065) 2003 Zheng, Wang (b0155) 2024 Khosravi, Nahavandi, Creighton, Atiya (b0055) 2011; 22 Wang, Qian, Zhang, Wang, Zhang (b0145) 2024 Wang, Li, Zhang, Wang (b0110) 2023; 211 Wang, Zhou, Jiang (b0100) 2023; 217 Moghram, Rahman (b0120) 1989 LeCun, Bottou, Bengio, Haffner (b0245) 1998 Hao, Wang, Wang, Yang (b0150) 2024; 299 Heskes (10.1016/j.enconman.2024.118909_b0050) 1997 Lian (10.1016/j.enconman.2024.118909_b0105) 2020 Deb (10.1016/j.enconman.2024.118909_b0170) 2002 LeCun (10.1016/j.enconman.2024.118909_b0245) 1998 Wang (10.1016/j.enconman.2024.118909_b0130) 2023 Wang (10.1016/j.enconman.2024.118909_b0265) 2023 Khosravi (10.1016/j.enconman.2024.118909_b0060) 2014 Choi (10.1016/j.enconman.2024.118909_b0020) 2023 El-Dakkak (10.1016/j.enconman.2024.118909_b0075) 2019 10.1016/j.enconman.2024.118909_b0235 10.1016/j.enconman.2024.118909_b0210 Gao (10.1016/j.enconman.2024.118909_b0125) 2024; 244 10.1016/j.enconman.2024.118909_b0010 Odell (10.1016/j.enconman.2024.118909_b0040) 1992 Jones (10.1016/j.enconman.2024.118909_b0045) 2007 Wang (10.1016/j.enconman.2024.118909_b0080) 2022; 314 Xing (10.1016/j.enconman.2024.118909_b0140) 2022; 263 Zhang (10.1016/j.enconman.2024.118909_bib281) 2022 Wang (10.1016/j.enconman.2024.118909_b0100) 2023; 217 Seo (10.1016/j.enconman.2024.118909_b0070) 2019 Nix (10.1016/j.enconman.2024.118909_b0035) 1994 Wang (10.1016/j.enconman.2024.118909_b0145) 2024 Ding (10.1016/j.enconman.2024.118909_b0065) 2003 Wang (10.1016/j.enconman.2024.118909_b0115) 2023 Zhang (10.1016/j.enconman.2024.118909_b0015) 2021 Bin (10.1016/j.enconman.2024.118909_b0220) 2006 Zhao (10.1016/j.enconman.2024.118909_b0025) 2018 Moghram (10.1016/j.enconman.2024.118909_b0120) 1989 Gao (10.1016/j.enconman.2024.118909_b0160) 2023; 123 Wang (10.1016/j.enconman.2024.118909_b0110) 2023; 211 Zhao (10.1016/j.enconman.2024.118909_b0275) 2024 Wang (10.1016/j.enconman.2024.118909_b0255) 2022; 313 Wolpert (10.1016/j.enconman.2024.118909_b0260) 1997 Winkler (10.1016/j.enconman.2024.118909_b0280) 1972 Rumelhart (10.1016/j.enconman.2024.118909_b0215) 1986 Li (10.1016/j.enconman.2024.118909_b0090) 2021; 231 Lv (10.1016/j.enconman.2024.118909_b0135) 2022; 52 Hao (10.1016/j.enconman.2024.118909_b0150) 2024; 299 Diebold (10.1016/j.enconman.2024.118909_b0270) 1995; 13 Wan (10.1016/j.enconman.2024.118909_b0085) 2014 Zheng (10.1016/j.enconman.2024.118909_b0155) 2024 10.1016/j.enconman.2024.118909_b0240 Elman (10.1016/j.enconman.2024.118909_b0225) 1991 Almutairi (10.1016/j.enconman.2024.118909_b0095) 2022; 101 An (10.1016/j.enconman.2024.118909_b0005) 2021 Khosravi (10.1016/j.enconman.2024.118909_b0055) 2011; 22 Yang (10.1016/j.enconman.2024.118909_b0030) 2023; 622 Specht (10.1016/j.enconman.2024.118909_b0230) 1991 |
| References_xml | – year: 2024 ident: b0155 article-title: Short-term wind speed forecasting based on recurrent neural networks and Levy crystal structure algorithm publication-title: Energy – volume: 263 year: 2022 ident: b0140 article-title: Research of a novel short-term wind forecasting system based on multi-objective Aquila optimizer for point and interval forecast publication-title: Energ Conver Manage – reference: Liu C, Zhu H, Ren Y, Wang Z. A Novel Intelligent Forecasting Framework for Quarterly or Monthly Energy Consumption. IEEE Transactions on Industrial Informatics 2023;PP:1–12. 10.1109/TII.2023.3330299. – year: 1994 ident: b0035 article-title: Estimating the mean and variance of the target probability distribution publication-title: IEEE International Conference on Neural Networks - Conference Proceedings – year: 1972 ident: b0280 article-title: A decision-theoretic approach to interval estimation publication-title: J Am Stat Assoc – reference: Jaeger H. Adaptive Nonlinear System Identification with Echo State Networks. NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems, 2002. – volume: 101 year: 2022 ident: b0095 article-title: An intelligent deep learning based prediction model for wind power generation publication-title: Comput Electr Eng – volume: 217 year: 2023 ident: b0100 article-title: A novel interval forecasting system based on multi-objective optimization and hybrid data reconstruct strategy publication-title: Expert Syst Appl – volume: 13 start-page: 253 year: 1995 end-page: 263 ident: b0270 article-title: Comparing predictive accuracy publication-title: J Bus Econ Stat – year: 2014 ident: b0060 article-title: An optimized mean variance estimation method for uncertainty quantification of wind power forecasts publication-title: Int J Electr Power Energy Syst – year: 1989 ident: b0120 article-title: Analysis and evaluation of five short-term load forecasting techniques publication-title: IEEE Trans Power Syst – volume: 52 year: 2022 ident: b0135 article-title: Novel deterministic and probabilistic combined system based on deep learning and self-improved optimization algorithm for wind speed forecasting publication-title: Sustainable Energy Technol Assess – volume: 231 year: 2021 ident: b0090 article-title: A wind speed interval forecasting system based on constrained lower upper bound estimation and parallel feature selection publication-title: Knowl-Based Syst – reference: Chung J, Gulcehre C, Cho K, Bengio Y. Gated feedback recurrent neural networks. 32nd International Conference on Machine Learning, ICML 2015, 2015. – volume: 22 start-page: 337 year: 2011 end-page: 346 ident: b0055 article-title: Lower upper bound estimation method for construction of neural network-based prediction intervals publication-title: IEEE Trans Neural Netw – year: 2023 ident: b0265 article-title: Multivariate selection-combination short-term wind speed forecasting system based on convolution-recurrent network and multi-objective chameleon swarm algorithm publication-title: Expert Syst Appl – year: 2002 ident: b0170 article-title: A fast and elitist multiobjective genetic algorithm: NSGA-II publication-title: IEEE Trans Evol Comput – year: 2007 ident: b0045 article-title: Miscellanea kernel-type density estimation on the unit interval publication-title: Biometrika – year: 2014 ident: b0085 article-title: Probabilistic forecasting of wind power generation using extreme learning machine publication-title: IEEE Trans Power Syst – year: 1997 ident: b0050 article-title: Practical confidence and prediction intervals publication-title: Adv Neural Inf Proces Syst – volume: 299 year: 2024 ident: b0150 article-title: A new perspective of wind speed forecasting: Multi-objective and model selection-based ensemble interval-valued wind speed forecasting system publication-title: Energ Conver Manage – year: 2019 ident: b0075 article-title: Combinatorial method for bandwidth selection in wind speed kernel density estimation publication-title: IET Renew Power Gener – year: 2023 ident: b0020 article-title: Evaluating offshore wind power potential in the context of climate change and technological advancement: Insights from Republic of Korea publication-title: Renew Sustain Energy Rev – year: 2019 ident: b0070 article-title: Wind turbine power curve modeling using maximum likelihood estimation method publication-title: Renew Energy – year: 1991 ident: b0230 article-title: A general regression neural network publication-title: IEEE Trans Neural Netw – year: 1992 ident: b0040 article-title: Maximum likelihood estimation for interval-censored data using a weibull- based accelerated failure time model publication-title: Biometrics – year: 2023 ident: b0115 article-title: Tourism demand interval forecasting amid COVID-19: A hybrid model with a modified multi-objective optimization algorithm publication-title: J Hosp Tour Res – year: 1986 ident: b0215 article-title: Learning representations by back-propagating errors publication-title: Nature – reference: GWEC. Global Wind Report 2023. Global Wind Energy Council 2023. – volume: 622 start-page: 560 year: 2023 end-page: 586 ident: b0030 article-title: Innovative ensemble system based on mixed frequency modeling for wind speed point and interval forecasting publication-title: Inf Sci – volume: 314 year: 2022 ident: b0080 article-title: An integrated power load point-interval forecasting system based on information entropy and multi-objective optimization publication-title: Appl Energy – year: 2006 ident: b0220 article-title: Extreme learning machine: Theory and applications publication-title: Neurocomputing – year: 2024 ident: b0275 article-title: A novel fuzzification - forecasting - optimization ensemble system for wind speed based on fuzzy theory and a multiobjective optimizer publication-title: Appl Intell – volume: 211 year: 2023 ident: b0110 article-title: A deep-learning wind speed interval forecasting architecture based on modified scaling approach with feature ranking and two-output gated recurrent unit publication-title: Expert Syst Appl – year: 2018 ident: b0025 article-title: Correlation-constrained and sparsity-controlled vector autoregressive model for spatio-temporal wind power forecasting publication-title: IEEE Trans Power Syst – year: 1998 ident: b0245 article-title: Gradient-based learning applied to document recognition publication-title: Proc IEEE – year: 2021 ident: b0015 article-title: Multi-source and temporal attention network for probabilistic wind power prediction publication-title: IEEE Trans Sustainable Energy – start-page: 1 year: 2023 end-page: 11 ident: b0130 article-title: A Multitask integrated deep-learning probabilistic prediction for load forecasting publication-title: IEEE Trans Power Syst – year: 2024 ident: b0145 article-title: A novel wind power forecasting system integrating time series refining, nonlinear multi-objective optimized deep learning and linear error correction publication-title: Energ Conver Manage – volume: 313 year: 2022 ident: b0255 article-title: A novel ensemble probabilistic forecasting system for uncertainty in wind speed publication-title: Appl Energy – year: 2003 ident: b0065 article-title: Backpropagation of pseudoerrors: Neural networks that are adaptive to heterogeneous noise publication-title: IEEE Trans Neural Netw – year: 2020 ident: b0105 article-title: Jou rna lP publication-title: Neural Netw – year: 2021 ident: b0005 article-title: Multisource wind speed fusion method for short-term wind power prediction publication-title: IEEE Trans Ind Inf – year: 2022 ident: bib281 article-title: Uncertainty quantification of PM2.5 concentrations using a hybrid model based on characteristic decomposition and fuzzy granulation publication-title: J Environ Manage – year: 1991 ident: b0225 article-title: Distributed representations, simple recurrent networks and grammatical structure publication-title: Mach Learn – volume: 123 start-page: 566 year: 2023 end-page: 589 ident: b0160 article-title: Combined interval prediction algorithm based on optimal relevancy publication-title: Redundancy and Synergy Applied Mathematical Modelling – year: 1997 ident: b0260 article-title: No free lunch theorems for optimization publication-title: IEEE Trans Evol Comput – volume: 244 year: 2024 ident: b0125 article-title: Enhancing investment performance of Black-Litterman model with AI hybrid system: Can it be done? publication-title: Expert Syst Appl – year: 2021 ident: 10.1016/j.enconman.2024.118909_b0015 article-title: Multi-source and temporal attention network for probabilistic wind power prediction publication-title: IEEE Trans Sustainable Energy doi: 10.1109/TSTE.2021.3086851 – year: 2021 ident: 10.1016/j.enconman.2024.118909_b0005 article-title: Multisource wind speed fusion method for short-term wind power prediction publication-title: IEEE Trans Ind Inf doi: 10.1109/TII.2020.3006928 – year: 1997 ident: 10.1016/j.enconman.2024.118909_b0260 article-title: No free lunch theorems for optimization publication-title: IEEE Trans Evol Comput doi: 10.1109/4235.585893 – start-page: 1 year: 2023 ident: 10.1016/j.enconman.2024.118909_b0130 article-title: A Multitask integrated deep-learning probabilistic prediction for load forecasting publication-title: IEEE Trans Power Syst – volume: 22 start-page: 337 year: 2011 ident: 10.1016/j.enconman.2024.118909_b0055 article-title: Lower upper bound estimation method for construction of neural network-based prediction intervals publication-title: IEEE Trans Neural Netw doi: 10.1109/TNN.2010.2096824 – ident: 10.1016/j.enconman.2024.118909_b0010 – year: 1989 ident: 10.1016/j.enconman.2024.118909_b0120 article-title: Analysis and evaluation of five short-term load forecasting techniques publication-title: IEEE Trans Power Syst doi: 10.1109/59.41700 – year: 2014 ident: 10.1016/j.enconman.2024.118909_b0060 article-title: An optimized mean variance estimation method for uncertainty quantification of wind power forecasts publication-title: Int J Electr Power Energy Syst doi: 10.1016/j.ijepes.2014.03.060 – year: 1991 ident: 10.1016/j.enconman.2024.118909_b0230 article-title: A general regression neural network publication-title: IEEE Trans Neural Netw doi: 10.1109/72.97934 – volume: 299 year: 2024 ident: 10.1016/j.enconman.2024.118909_b0150 article-title: A new perspective of wind speed forecasting: Multi-objective and model selection-based ensemble interval-valued wind speed forecasting system publication-title: Energ Conver Manage doi: 10.1016/j.enconman.2023.117868 – year: 2003 ident: 10.1016/j.enconman.2024.118909_b0065 article-title: Backpropagation of pseudoerrors: Neural networks that are adaptive to heterogeneous noise publication-title: IEEE Trans Neural Netw doi: 10.1109/TNN.2003.809428 – ident: 10.1016/j.enconman.2024.118909_b0210 – year: 1998 ident: 10.1016/j.enconman.2024.118909_b0245 article-title: Gradient-based learning applied to document recognition publication-title: Proc IEEE doi: 10.1109/5.726791 – volume: 13 start-page: 253 year: 1995 ident: 10.1016/j.enconman.2024.118909_b0270 article-title: Comparing predictive accuracy publication-title: J Bus Econ Stat doi: 10.1080/07350015.1995.10524599 – year: 2014 ident: 10.1016/j.enconman.2024.118909_b0085 article-title: Probabilistic forecasting of wind power generation using extreme learning machine publication-title: IEEE Trans Power Syst doi: 10.1109/TPWRS.2013.2287871 – volume: 313 year: 2022 ident: 10.1016/j.enconman.2024.118909_b0255 article-title: A novel ensemble probabilistic forecasting system for uncertainty in wind speed publication-title: Appl Energy doi: 10.1016/j.apenergy.2022.118796 – year: 1992 ident: 10.1016/j.enconman.2024.118909_b0040 article-title: Maximum likelihood estimation for interval-censored data using a weibull- based accelerated failure time model publication-title: Biometrics doi: 10.2307/2532360 – volume: 211 year: 2023 ident: 10.1016/j.enconman.2024.118909_b0110 article-title: A deep-learning wind speed interval forecasting architecture based on modified scaling approach with feature ranking and two-output gated recurrent unit publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2022.118419 – ident: 10.1016/j.enconman.2024.118909_b0235 – year: 2019 ident: 10.1016/j.enconman.2024.118909_b0075 article-title: Combinatorial method for bandwidth selection in wind speed kernel density estimation publication-title: IET Renew Power Gener doi: 10.1049/iet-rpg.2018.5643 – ident: 10.1016/j.enconman.2024.118909_b0240 – year: 2022 ident: 10.1016/j.enconman.2024.118909_bib281 article-title: Uncertainty quantification of PM2.5 concentrations using a hybrid model based on characteristic decomposition and fuzzy granulation publication-title: J Environ Manage doi: 10.1016/j.jenvman.2022.116282 – year: 2024 ident: 10.1016/j.enconman.2024.118909_b0275 article-title: A novel fuzzification - forecasting - optimization ensemble system for wind speed based on fuzzy theory and a multiobjective optimizer publication-title: Appl Intell doi: 10.1007/s10489-024-05350-z – volume: 244 year: 2024 ident: 10.1016/j.enconman.2024.118909_b0125 article-title: Enhancing investment performance of Black-Litterman model with AI hybrid system: Can it be done? publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2023.122924 – year: 2019 ident: 10.1016/j.enconman.2024.118909_b0070 article-title: Wind turbine power curve modeling using maximum likelihood estimation method publication-title: Renew Energy doi: 10.1016/j.renene.2018.09.087 – volume: 622 start-page: 560 year: 2023 ident: 10.1016/j.enconman.2024.118909_b0030 article-title: Innovative ensemble system based on mixed frequency modeling for wind speed point and interval forecasting publication-title: Inf Sci doi: 10.1016/j.ins.2022.11.145 – volume: 314 year: 2022 ident: 10.1016/j.enconman.2024.118909_b0080 article-title: An integrated power load point-interval forecasting system based on information entropy and multi-objective optimization publication-title: Appl Energy doi: 10.1016/j.apenergy.2022.118938 – volume: 123 start-page: 566 year: 2023 ident: 10.1016/j.enconman.2024.118909_b0160 article-title: Combined interval prediction algorithm based on optimal relevancy publication-title: Redundancy and Synergy Applied Mathematical Modelling doi: 10.1016/j.apm.2023.06.040 – year: 2023 ident: 10.1016/j.enconman.2024.118909_b0265 article-title: Multivariate selection-combination short-term wind speed forecasting system based on convolution-recurrent network and multi-objective chameleon swarm algorithm publication-title: Expert Syst Appl – volume: 263 year: 2022 ident: 10.1016/j.enconman.2024.118909_b0140 article-title: Research of a novel short-term wind forecasting system based on multi-objective Aquila optimizer for point and interval forecast publication-title: Energ Conver Manage doi: 10.1016/j.enconman.2022.115583 – volume: 101 year: 2022 ident: 10.1016/j.enconman.2024.118909_b0095 article-title: An intelligent deep learning based prediction model for wind power generation publication-title: Comput Electr Eng doi: 10.1016/j.compeleceng.2022.108000 – volume: 52 year: 2022 ident: 10.1016/j.enconman.2024.118909_b0135 article-title: Novel deterministic and probabilistic combined system based on deep learning and self-improved optimization algorithm for wind speed forecasting publication-title: Sustainable Energy Technol Assess – year: 2020 ident: 10.1016/j.enconman.2024.118909_b0105 article-title: Jou rna lP publication-title: Neural Netw – year: 2024 ident: 10.1016/j.enconman.2024.118909_b0155 article-title: Short-term wind speed forecasting based on recurrent neural networks and Levy crystal structure algorithm publication-title: Energy – year: 2002 ident: 10.1016/j.enconman.2024.118909_b0170 article-title: A fast and elitist multiobjective genetic algorithm: NSGA-II publication-title: IEEE Trans Evol Comput doi: 10.1109/4235.996017 – volume: 231 year: 2021 ident: 10.1016/j.enconman.2024.118909_b0090 article-title: A wind speed interval forecasting system based on constrained lower upper bound estimation and parallel feature selection publication-title: Knowl-Based Syst doi: 10.1016/j.knosys.2021.107435 – volume: 217 year: 2023 ident: 10.1016/j.enconman.2024.118909_b0100 article-title: A novel interval forecasting system based on multi-objective optimization and hybrid data reconstruct strategy publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2023.119539 – year: 2018 ident: 10.1016/j.enconman.2024.118909_b0025 article-title: Correlation-constrained and sparsity-controlled vector autoregressive model for spatio-temporal wind power forecasting publication-title: IEEE Trans Power Syst – year: 2024 ident: 10.1016/j.enconman.2024.118909_b0145 article-title: A novel wind power forecasting system integrating time series refining, nonlinear multi-objective optimized deep learning and linear error correction publication-title: Energ Conver Manage – year: 1991 ident: 10.1016/j.enconman.2024.118909_b0225 article-title: Distributed representations, simple recurrent networks and grammatical structure publication-title: Mach Learn doi: 10.1007/BF00114844 – year: 1994 ident: 10.1016/j.enconman.2024.118909_b0035 article-title: Estimating the mean and variance of the target probability distribution publication-title: IEEE International Conference on Neural Networks - Conference Proceedings – year: 2007 ident: 10.1016/j.enconman.2024.118909_b0045 article-title: Miscellanea kernel-type density estimation on the unit interval publication-title: Biometrika doi: 10.1093/biomet/asm068 – year: 2023 ident: 10.1016/j.enconman.2024.118909_b0115 article-title: Tourism demand interval forecasting amid COVID-19: A hybrid model with a modified multi-objective optimization algorithm publication-title: J Hosp Tour Res – year: 1986 ident: 10.1016/j.enconman.2024.118909_b0215 article-title: Learning representations by back-propagating errors publication-title: Nature doi: 10.1038/323533a0 – year: 2006 ident: 10.1016/j.enconman.2024.118909_b0220 article-title: Extreme learning machine: Theory and applications publication-title: Neurocomputing – year: 2023 ident: 10.1016/j.enconman.2024.118909_b0020 article-title: Evaluating offshore wind power potential in the context of climate change and technological advancement: Insights from Republic of Korea publication-title: Renew Sustain Energy Rev doi: 10.1016/j.rser.2023.113497 – year: 1972 ident: 10.1016/j.enconman.2024.118909_b0280 article-title: A decision-theoretic approach to interval estimation publication-title: J Am Stat Assoc doi: 10.1080/01621459.1972.10481224 – year: 1997 ident: 10.1016/j.enconman.2024.118909_b0050 article-title: Practical confidence and prediction intervals publication-title: Adv Neural Inf Proces Syst |
| SSID | ssj0003506 |
| Score | 2.501351 |
| Snippet | [Display omitted]
•A multi-input dual-output neural network is constructed to obtain the best interval.•Two constrained bi-objective optimization problems are... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 118909 |
| SubjectTerms | Constrained multi-objective optimization problem Dual-output neural network Lower and upper bound estimation Model averaging Wind speed interval forecasting |
| Title | A multi-input and dual-output wind speed interval forecasting system based on constrained multi-objective optimization problem and model averaging |
| URI | https://dx.doi.org/10.1016/j.enconman.2024.118909 |
| Volume | 319 |
| WOSCitedRecordID | wos001302022900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0196-8904 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0003506 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ba9swFBYh3cP2MHZl3Q097C24cyzLlh7D6NhGKYN2kD0ZSZaXhFYOaZyV_ow-9tfu6GLHawvdGHsxsciRYn-fdY5PzgWhd6WQWUWVjJKkTKNUZHEkhVDwxDOZ0AreGHzXkoP88JBNp_zrYHDV5sJsTnJj2Pk5X_5XqGEMwLaps38BdzcpDMBnAB2OADsc_wj4iQ8SjOZm2fjwcZtuFdXN2p7_nFtH-RJ0lqsUsdr4BEatxJkLgPaVnUdWuZX2jwRl7UfbRgJO_by1XPhNclTDdnMa8jhHoTONW9C11xkJuHWuB9Jv3n-fa-iC3Z2nzgvcCMI52DhXrTY_LmY6TOH8_iGCGFh9Maub6-NHs0bMe85w5wj-LsIEwbuRpCHNr3O5tWk32xgn5wXlWcS471vcbuPEb703VIL3Tiz2bF1QA5ezZ5cBTQHyfKsEu9DEIzu5ndsG1zJqUwN3kpxyNkQ7k8_70y-dnifUdW7tfkwv__z21W43fXrmzPEj9DC8h-CJ589jNNDmCXrQq075FF1OcI9JGHDCPSZhyyTsmIRbJuEek7BnEnZMwrXBPSbha0zCfSbhwCS3oGMS7pj0DH37uH_84VMUWnhEioyTdSQySsAaoGMV5zKPpWBlyjM5rkSlY0lVLqtcw1d0KSrQtCQrqzKD3SNjOleSluQ5Gpra6BcIw43kKkmquCICtDsgohWRTJE0VUzGahfR9u4WKtS3t1d1UrSBjIuiRaWwqBQelV30vpNb-govd0rwFrwi2Kne_iyAc3fIvvwH2Vfo_vYReY2G61Wj36B7arOen63eBnr-AlUUx_I |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+multi-input+and+dual-output+wind+speed+interval+forecasting+system+based+on+constrained+multi-objective+optimization+problem+and+model+averaging&rft.jtitle=Energy+conversion+and+management&rft.au=Lv%2C+Mengzheng&rft.au=Wang%2C+Jianzhou&rft.au=Wang%2C+Shuai&rft.au=Zhao%2C+Yang&rft.date=2024-11-01&rft.pub=Elsevier+Ltd&rft.issn=0196-8904&rft.volume=319&rft_id=info:doi/10.1016%2Fj.enconman.2024.118909&rft.externalDocID=S0196890424008501 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-8904&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-8904&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-8904&client=summon |