Large Model-Driven Task Generation and Multidimensional Verification for Power Grid Operation
DOI:
https://doi.org/10.4108/ew.11803Keywords:
Large model-driven, Power grid operation task generation, Multidimensional verification, Edge computing, Rule engineAbstract
INTRODUCTION: The generation technology of power grid operation tasks is crucial for ensuring the stable operation of the power system, and the accuracy and safety of task generation are even more critical. Traditional task generation methods are difficult to fully consider various factors such as grid load and reactive power, and suffer from poor adaptability and limited optimization capabilities.
OBJECTIVES: The research aims to solve the bottleneck problems of traditional methods in inaccurate power grid state judgment, lagging rule updates, difficult data fusion, and low verification efficiency, and provide efficient decision support for operation and maintenance personnel in complex power grid regulation scenarios.
METHODS: A hybrid approach combining rule engines and large model drivers is proposed. First, a power grid business rule library is constructed based on a rule engine, separating business rules from code to achieve fast matching and evaluation of real-time voltage, current, and other data; Then, using a large model to learn historical operational data and actual experience, predict the power grid status and generate multiple decision options; Finally, edge computing algorithm is introduced to process and schedule real-time data locally, reducing bandwidth pressure and improving response speed.
RESULTS: When the research method was iterated 82 times, the recognition accuracy was 94.35%, and the recognition accuracy increased with the increase of iteration times. Additionally, empirical analysis of the proposed intelligent generation technology for power grid operation tasks revealed that when tested on node 1, the operation response time was 8.2ms, the transmission rate was 22.1Mbit/s, and the overall operation response speed was fast.
CONCLUSION: The research method can effectively improve the feature recognition accuracy and task generation efficiency of power grid data, significantly reduce operational risks, and has high practicality and reliability.
Downloads
References
[1] Zhigang X, Xin S, Siyang X, Jing C. Providing robust and low-cost edge computing in smart grid: An energy harvesting based task scheduling and resource management framework. China Communications, 2025, 22(2):226-240.
[2] Sadeque F, Gursoy M, Mirafzal B. Grid-forming inverters in a microgrid: Maintaining power during an outage and restoring connection to the utility grid without communication. IEEE Transactions on Industrial Electronics, 2024, 71(10):11796-11805.
[3] Odonkor E N, Moses P M, Akumu A O. Intelligent ANFIS-based distributed generators energy control and power dispatch of grid-connected microgrids integrated into distribution network. International Journal of Electrical and Electronic Engineering & Telecommunications, 2024, 13(2):112-124.
[4] Li Y, Ding Y, He S, Hu F, Duan J, Wen G, Zeng Z. Artificial intelligence-based methods for renewable power system operation. Nature Reviews Electrical Engineering, 2024, 1(3):163-179.
[5] Naderi E, Mirzaei L, Pourakbari-Kasmaei M, Cerna F V, Lehtonen M. Optimization of active power dispatch considering unified power flow controller: Application of evolutionary algorithms in a fuzzy framework. Evolutionary Intelligence, 2024, 17(3):1357-1387.
[6] Lin Y, Wang J, Liu K, Min H. Grounding rod hanging and removing robot with hand-eye self-calibration capability in substation. Complex & Intelligent Systems, 2024, 10(5):6491-6507.
[7] Qu Z, Zhang Z, Qu N, Zhou Y, Li Y, Jiang T, Long C. Extraction of typical operating scenarios of new power system based on deep time series aggregation. CAAI Transactions on Intelligence Technology, 2025, 10(1):283-299.
[8] Bhadani U. Pillars of power system and security of smart grid. International journal of innovative research in science engineering and technology, 2024, 13(13888):10-15680.
[9] Zabihia A, Parhamfarb M. Empowering the grid: toward the integration of electric vehicles and renewable energy in power systems. International Journal of Energy Security and Sustainable Energy, 2024, 2(1):1-14.
[10] Xu L, Feng K, Lin N, Perera A T D, Poor H V, Xie L, O’Malley M. Resilience of renewable power systems under climate risks. Nature reviews electrical engineering, 2024, 1(1):53-66.
[11] Dong Y, Li Z, Li X, Li X. Using ontology and rules to retrieve the semantics of disaster remote sensing data. Journal of Systems Engineering and Electronics, 2024, 35(5):1211-1218.
[12] Dey S, Deb M, Das P K. Application of fuzzy-assisted grey Taguchi approach for engine parameters optimization on performance-emission of a CI engine. Energy sources, part a: recovery, utilization, and environmental effects, 2024, 46(1):4330-4346.
[13] Eze S C, Chinedu-Eze V C, Awa H O, Asiyanbola T A. Multi-dimensional framework of the information behaviour of SMEs on emerging information communication technology (EICT) adoption. Journal of Science and Technology Policy Management, 2023, 14(6):1006-1036.
[14] Chen Z, Li X, Wang H, Chen Z, Zhang Q, Wu Z. Multi-dimensional information sensing of complex surfaces based on fringe projection profilometry. Optics Express, 2023, 31(25):41374-41390.
[15] Liu H, Matthies M, Russo J, Rovigatti L, Narayanan R P, Diep T, Šulc P. Inverse design of a pyrochlore lattice of DNA origami through model-driven experiments. Science, 2024, 384(6697):776-781.
[16] Seymour K, Held M, Stolz B, Georges G, Boulouchos K. Future costs of power-to-liquid sustainable aviation fuels produced from hybrid solar PV-wind plants in Europe. Sustainable Energy & Fuels, 2024, 8(4):811-825.
[17] Ntantis E L, Xezonakis V. Optimization of electric power prediction of a combined cycle power plant using innovative machine learning technique. Optimal Control Applications and Methods, 2024, 45(5):2218-2230.
[18] Ali A, Khan L, Javaid N, Aslam M, Aldegheishem A, Alrajeh N. Exploiting machine learning to tackle peculiar consumption of electricity in power grids: A step towards building green smart cities. IET Generation, Transmission & Distribution, 2024, 18(3):413-445.
[19] Law R M, Ardo J. Using a discrete global grid system for a scalable, interoperable, and reproducible system of land-use mapping. Big Earth Data, 2025, 9(1):29-46.
[20] Ahsan F, Dana N H, Sarker S K, Li L, Muyeen S M, Ali M F, Das P. Data-driven next-generation smart grid towards sustainable energy evolution: techniques and technology review. Protection and Control of Modern Power Systems, 2023, 8(3):1-42.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Weijian Lai, Chao Hu, Shuan Liu, Jingguang Li, Xinwei Duan
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
