Architecture of a Trusted Artificial Intelligence System for Time Series Forecasting in Power Industry

Pavel Matrenin

Abstract


As energy consumption increases and distributed generation develops, the need for reliable and explainable forecasting systems becomes critical. The new article presents the architecture of a trusted artificial intelligence system for time series forecasting in power industry. Unlike existing solutions that primarily focus on model accuracy, the proposed approach implements system-level trust based on ontological models, information security, and natural language explanation generation. The developed architecture includes modules for input data integrity control, model verification, data drift detection, automatic model adaptation, and a dedicated explanation module. The latter employs a language model trained on a corpus of human-authored explanations aligned with Shapley values. The ontological model, integrated with a common information model, ensures semantic consistency across system components. The paper substantiates the key requirements for trusted AI systems in time series forecasting for the power sector, including security, explainability, protection against model degradation, and compatibility with enterprise information systems. The proposed solutions can be applied to load forecasting, renewable generation prediction, and decision support in power system planning and operation. The results demonstrate the practical feasibility of implementing AI systems that foster trust—both at the level of individual users and across the industry—by relying on the principles of ontological modeling.

Full Text:

PDF (Russian)

References


I.D. Morgoyev, A. E. Dzgoyev, R. V. Klyuyev, and A. D. Morgoyeva, “Prognozirovaniye potrebleniya elektroenergii predpriyatiyami narodnokhozyaystvennogo kompleksa v usloviyakh nepolnoty informatsii [Forecasting electricity consumption by enterprises of the national economic complex in conditions of incomplete information],” Izvestiya Kabardino-Balkarskogo nauchnogo tsentra RAN [Bulletin of the Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences], vol. 3 (107), pp. 9–20, 2022.

B. I. Makoklyuyev, “Metody i programmnyye sredstva planirovaniya elektropotrebleniya [Methods and software for planning electricity consumption],” Energiya yedinoy seti [Energy of the unified network], vol. 2, pp. 58–69, 2022.

N. Ahmad, Y. Ghadi, M. Adnan and M. Ali, “Load Forecasting Techniques for Power System: Research Challenges and Survey,” IEEE Access, vol. 10, pp. 71054-71090, 2022.

A. V.Blokhin, A. S. Gritsay, and A. Y. Gorshenin, “Issledovaniye faktorov, vliyayushchikh na potrebleniye elektroenergii kommercheskim predpriyatiyem [Study of factors influencing electricity consumption by a commercial enterprise // Mathematical structures and modeling.],” Matematicheskiye struktury i modelirovaniye [Mathematical structures and modeling], vol. 3(63), pp. 39–47, 2022.

A. S. Glazyrin, E. V. Bolovin , O.V. Arkhipova [et al] “Adaptive short-term forecasting of electricity consumption by autonomous power systems of small northern settlements based on retrospective regression analysis methods,” Bulletin of the Tomsk Polytechnic University. Geo Аssets Engineering, vol. 334, no. 4, рр.231–248, 2023.

P. V. Matrenin and N. N. Sergeyev, “Obzor mezhdunarodnogo opyta v prognozirovanii generatsii vozobnovlyayemykh istochnikov energii s pomoshch'yu metodov mashinnogo obucheniya [Review of international experience in forecasting the generation of renewable energy sources using machine learning methods],” iPolytech Journal, vol. 27(2), pp. 354–369, 2023.

A. Y. Gorshenin, “Formirovaniye vyborki iskhodnykh dannykh dlya mashinnogo obucheniya modeli kratkosrochnogo prognozirovaniya elektropotrebleniya [Formation of a sample of initial data for machine learning of a short-term forecasting model of electricity consumption],” Avtomatizatsiya v promyshlennosti [Automation in industry], vol. 10, pp. 37–41, 2023.

L. Baur, K. Ditschuneit, and M. Schambach [et al], “Explainability and Interpretability in Electric Load Forecasting Using Machine Learning Techniques – A Review,” Energy and AI, vol. 16, art. 100358, 2024.

P. V. Matrenin and A. I. Stepanova, “Enhancing the interpretability of electricity consumption forecasting models for mining enterprises using SHapley Additive exPlanations,” Journal of Mining Institute, vol. 271, pp. 154–167, 2025.

A. Rebei, M. Amayri, N. Bouguila, “Affinity-Driven Transfer Learning for Load Forecasting,” Sensors, vol. 24 (17), art. 5802, 2024.

M. H. Bin Kamilin, S. Yamaguchi, and M. A. Bin Ahmadon, “Radian Scaling and Its Application to Enhance Electricity Load Forecasting in Smart Cities Against Concept Drift,” Smart Cities, vol. 7, pp. 3412–3436, 2024.

P. V. Matrenin and R. N. Khamitov, “Algoritm formirovaniya strategii avtomaticheskogo obnovleniya modeley iskusstvennogo intellekta v zadachakh prognozirovaniya v elektroenergetike [Algorithm for forming a strategy for automatic updating of artificial intelligence models in forecasting problems in the electric power industry],” Inzhenernyy vestnik Dona [Engineering Bulletin of the Don], 2025.

M. R. Habibi, S. Golestan, Y. Wu, J. M. Guerrero, and J. C. Vasquez, “Electrical load forecasting in power systems based on quantum computing using time series-based quantum artificial intelligence,” Scientific Reports, vol 15, art. 7429 (2025).

A. Miraki, P. Parviainen, and R. Arghandeh, “Electricity demand forecasting at distribution and household levels using explainable causal graph neural network,” Energy and AI, vol. 16, art. 100368, 2024.

A. Y. Gorshenin, “Razrabotka i verifikatsiya programmnogo obespecheniya sistemy kratkosrochnogo prognozirovaniya elektropotrebleniya [Development and verification of software for a short-term forecasting system for electricity consumption],” Izvestiya Tul'skogo gosudarstvennogo universiteta. Tekhnicheskiye nauki [Bulletin of Tula State University. Technical sciences], vol. 7, pp. 253–259, 2024.

G. Antonesi, T. Cioara, L. Toderean, I. Anghel, and C. De Mulder, “A Machine Learning Pipeline to Forecast the Electricity and Heat Consumption in a City District,” Buildings, vol 13, art. 1407, 2023.

H. Xu, F. Hu, and X. Liang, “A framework for electricity load forecasting based on attention mechanism time series depthwise separable convolutional neural network,” Energy, vol. 299, art. 131258, 2024.

A. Khalyasmaa and P. Matrenin, “Initial Data Corruption Impact on Machine Learning Models' Performance in Energy Consumption Forecast,” 2021 Ural-Siberian Smart Energy Conference (USSEC), Novosibirsk, Russian Federation, 2021.

S. Pelekis, E. Karakolis, T. Pountridis [et al], “DeepTSF: Codeless machine learning operations for time series forecasting,” URL https://arxiv.org/abs/2308.00709 (access date: 23.04.2025).

H. Wicaksono, M. Trat, A. Bashyal [et al], “Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes,” The International Journal of Advanced Manufacturing Technology, vol. 138, pp. 247–271, 2025.

L. V. Massel and A. G. Massel, “Semanticheskoye modelirovaniye pri postroyenii tsifrovykh dvoynikov energeticheskikh obyektov i sistem [Semantic modeling in constructing digital twins of energy objects and systems],” Ontologiya proyektirovaniya [Design Ontology], vol. 1(13), pp. 44-52, 2023.

D. E. Namiot and E. A. Ilyushin, “Monitoring sdviga dannykh v modelyakh mashinnogo obucheniya [Monitoring data shift in machine learning models],” International Journal of Open Information Technologies, vol. 10 (12), pp. 84–93, 2022.

Xue L., Constant N., Roberts A. [et al.], “mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer,” 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, pp. 483–498.

P. V. Matrenin, A. I. Khalyasmaa, V. V. Gamaley [et al], “Improving of the Generation Accuracy Forecasting of Photovoltaic Plants Based on k-Means and k-Nearest Neighbors Algorithms,” Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, vol. 66(4), pp. 305–321, 2023.

Z. Zhang, C. Wang, X. Peng [et al], “Solar Radiation Intensity Probabilistic Forecasting Based on K-Means Time Series Clustering and Gaussian Process Regression,” IEEE Access, vol. 9, pp. 89079-89092, 2021.

A. I. Khalyasmaa and P. V. Matrenin, “New software architecture for visualization, transformation, and analysis of equipment images,” International Journal of Open Information Technologies, 2025, Vol. 13 (5), pp. 34–40.

F. Arrano-Vargas and G. Konstantinou, “Modular Design and Real-Time Simulators Toward Power System Digital Twins Implementation,” IEEE Transactions on Industrial Informatics, 2023, vol. 19(1), pp. 52–61.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность ИБП для ЦОД СНЭ

ISSN: 2307-8162