{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T17:15:25Z","timestamp":1771002925959,"version":"3.50.1"},"reference-count":35,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:00:00Z","timestamp":1745625600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational Methods in Sciences and Engineering"],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Existing LSTM-based power quality (PQ) prediction models primarily rely on historical information, which limits their ability to fully capture contextual dependencies. Furthermore, these models process inputs sequentially without accounting for the varying importance of different time steps, leading to significant prediction inaccuracies. To address these limitations, this study proposes an enhanced PQ prediction model that integrates Bidirectional Long Short-Term Memory (BiLSTM) with a Self-Attention (SA) mechanism. The BiLSTM module is introduced to model both forward and backward temporal dependencies, enabling a more comprehensive capture of long-term patterns in time series data. The SA mechanism dynamically adjusts the importance of different time steps through weighted summation, enhancing the model\u2019s ability to focus on critical features and improving its capacity to model nonlinear relationships. The weighted features from the SA layer are then mapped to a fully connected layer to generate the final prediction outputs. Experiments were conducted using power quality data from Nanchang as the primary dataset, with additional datasets from Nanjing, Wuhan, Changsha, and Beijing used for generalization testing. The results demonstrate that the BiLSTM-SA model outperforms traditional LSTM models across all PQ metrics, achieving a mean absolute error (MAE) of 0.09 for voltage deviation, a 0.05 improvement over single-layer LSTM. Notably, the model maintains robust performance in complex power supply scenarios, with a generalized MAE of only 0.2 in Beijing. These findings highlight the effectiveness of combining BiLSTM with the SA mechanism in reducing prediction errors and ensuring the stability of power supply quality, offering a significant advancement in PQ prediction methodologies.<\/jats:p>","DOI":"10.1177\/14727978251337953","type":"journal-article","created":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T11:36:00Z","timestamp":1745667360000},"page":"4061-4073","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Power supply quality prediction method based on LSTM and self-attention mechanism"],"prefix":"10.1177","volume":"25","author":[{"given":"Yan","family":"Yang","sequence":"first","affiliation":[{"name":"Power Supply Service Command Center, State Grid Wuhan Power Supply Company, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5946-5234","authenticated-orcid":false,"given":"Chang","family":"Yu","sequence":"additional","affiliation":[{"name":"Power Supply Service Command Center, State Grid Wuhan Power Supply Company, Wuhan, China"}]}],"member":"179","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3274504"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1049\/enc2.12087"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/s24082465"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2024.10.057"},{"issue":"1","key":"e_1_3_3_6_2","first-page":"10","article-title":"Impact of solar penetrations in conventional power systems and generation of harmonic and power quality issues: a review","volume":"1","author":"Liyakat KKS","year":"2024","unstructured":"Liyakat KKS. Impact of solar penetrations in conventional power systems and generation of harmonic and power quality issues: a review. Adv Res Power Electr Dev 2024; 1(1): 10\u201316.","journal-title":"Adv Res Power Electr Dev"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.3390\/app12178423"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/su152015055"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2023.01.060"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12020389"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13462-2"},{"issue":"6","key":"e_1_3_3_12_2","first-page":"889","article-title":"Improved deep learning model for forecasting short-term load based on random forest algorithm and rough set theory","volume":"44","author":"Yu F","year":"2023","unstructured":"Yu F, Youbin S, Sheng JIN, et al. Improved deep learning model for forecasting short-term load based on random forest algorithm and rough set theory. Power Gener Technol 2023; 44(6): 889\u2013895.","journal-title":"Power Gener Technol"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.3390\/en16093627"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.3390\/su151511667"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12163441"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2024.2314350"},{"issue":"1","key":"e_1_3_3_17_2","first-page":"1","article-title":"Short-term voltage stability prediction based on a Bidirectional Gated Recurrent Unit neural network using phasor measurement data in power systems","volume":"15","author":"Babaali A","year":"2024","unstructured":"Babaali A, Ameli MT. Short-term voltage stability prediction based on a Bidirectional Gated Recurrent Unit neural network using phasor measurement data in power systems. Comput Intell Electr Eng 2024; 15(1): 1\u201316.","journal-title":"Comput Intell Electr Eng"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12224652"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3266783"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.3390\/app132212479"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.3390\/en17184699"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3321301"},{"issue":"1","key":"e_1_3_3_23_2","first-page":"1","article-title":"A systematic review of real-time detection and classification of power quality disturbances","volume":"8","author":"Caicedo JE","year":"2023","unstructured":"Caicedo JE, Agudelo-Mart\u00ednez D, Rivas-Trujillo E, et al. A systematic review of real-time detection and classification of power quality disturbances. Protect Control of Modern Power Sys 2023; 8(1): 1\u201337.","journal-title":"Protect Control of Modern Power Sys"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.3390\/en17133193"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1049\/gtd2.13026"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.3390\/en17102312"},{"issue":"1","key":"e_1_3_3_27_2","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1080\/00051144.2022.2118101","article-title":"Hybrid power generation forecasting using CNN based BILSTM method for renewable energy systems","volume":"64","author":"Anu Shalini T","year":"2023","unstructured":"Anu Shalini T, Sri Revathi B. Hybrid power generation forecasting using CNN based BILSTM method for renewable energy systems. Automatika: casopis za automatiku, mjerenje, elektroniku, racunarstvo i komunikacije 2023; 64(1): 127\u2013144.","journal-title":"Automatika: casopis za automatiku, mjerenje, elektroniku, racunarstvo i komunikacije"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2024.09.043"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.3390\/app13021165"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.23919\/PCMP.2023.000296"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2023.3266369"},{"issue":"1","key":"e_1_3_3_32_2","first-page":"22","article-title":"Global attention-based LSTM for noisy power quality disturbance classification","volume":"14","author":"Chiam DH","year":"2023","unstructured":"Chiam DH, Lim KH, Law KH. Global attention-based LSTM for noisy power quality disturbance classification. Int J Syst Control Commun 2023; 14(1): 22\u201339.","journal-title":"Int J Syst Control Commun"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08568-z"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.3390\/math11061360"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3356731"},{"issue":"1","key":"e_1_3_3_36_2","first-page":"13","article-title":"Research on the effectiveness of different outlier detection methods in common data distribution types","volume":"1","author":"Song Q","year":"2024","unstructured":"Song Q, Xia S. Research on the effectiveness of different outlier detection methods in common data distribution types. J Comp Technol Appli Math 2024; 1(1): 13\u201325.","journal-title":"J Comp Technol Appli Math"}],"container-title":["Journal of Computational Methods in Sciences and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14727978251337953","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/14727978251337953","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14727978251337953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T16:31:03Z","timestamp":1771000263000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/14727978251337953"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,26]]},"references-count":35,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["10.1177\/14727978251337953"],"URL":"https:\/\/doi.org\/10.1177\/14727978251337953","relation":{},"ISSN":["1472-7978","1875-8983"],"issn-type":[{"value":"1472-7978","type":"print"},{"value":"1875-8983","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,26]]}}}