Abstract
As information technology continues to evolve, the intelligence level of the power system is also constantly increasing. However, there are problems such as insufficient timeliness and low accuracy in the abnormal detection and interval prediction of power load data. Therefore, the research proposes an anomaly detection algorithm that combines generalized range testing with local anomaly factors, as well as an interval prediction model that improves the Transformer model. This method uses a sliding window to improve the generalized range test, optimizes local anomaly factors using reachable distance, and then combines it with the generalized range test for detection. The research uses time series generative adversarial networks to enhance load data and sparse self attention to reduce the complexity of Transformer models. Experiments indicate that the maximum anomaly detection accuracy of the fusion algorithm is 0.981, which is 0.081 higher than the second best local anomaly factor. The detection accuracy and detection time are 0.982 and 13.02 ms, respectively. The prediction accuracy, precision, root mean square error, and mean absolute error of the improved Transformer model are 0.972, 0.975, 0.305, and 0.152, respectively. Predicting the power load curve results in a greater level of alignment with actual power load data. From this, it can be inferred that the proposed approach has the capacity to substantially enhance the accuracy of anomaly detection and interval prediction of power loads, ensuring the reliable operation of the power system.
References
Wang X, Wang H, Bhandari B, Cheng L. AI-empowered methods for smart energy consumption: A review of load forecasting, anomaly detection and demand response. International Journal of Precision Engineering and Manufacturing-Green Technology. 2024, 11(3): 963–993.
Lee S, Nengroo SH, Xi H, Doh Y, Lee C, Heo T, Har D. Anomaly detection of smart metering system for power management with battery storage system/electric vehicle. ETRI Journal. 2023, 45(4):650–665.
Yang Q, Gultekin MA, Seferian V, Pattipati K, Bazzi AM, Palmieri FA, Ukegawa H. Incipient residual-based anomaly detection in power electronic devices. IEEE Transactions on Power Electronics. 2022, 37(6):7315–7332.
Yu J, Cheng H, Zhang J, Li Q, Wu S, Zhong W, Ma P. CONGO2
: Scalable Online Anomaly Detection and Localization in Power Electronics Networks. IEEE Internet of Things Journal. 2022, 9(15):13862–13875.
Mahi-al-Rashid A, Hossain F, Anwar A, Azam S. False data injection attack detection in smart grid using energy consumption forecasting. Energies. 2022, 15(13):4877-4892.
Takiddin A, Ismail M, Serpedin E. Robust data-driven detection of electricity theft adversarial evasion attacks in smart grids. IEEE Transactions on Smart Grid. 2022, 14(1):663–676.
Takiddin A, Ismail M, Zafar U, Serpedin E. Deep autoencoder-based anomaly detection of electricity theft cyberattacks in smart grids. IEEE Systems Journal. 2022, 16(3):4106–4117.
Khan IU, Javaid N, Taylor CJ, Ma X. Robust data driven analysis for electricity theft attack-resilient power grid. IEEE Transactions on Power Systems. 2022, 38(1):537–548.
Mestav KR, Wang X, Tong L. A deep learning approach to anomaly sequence detection for high-resolution monitoring of power systems. IEEE Transactions on Power Systems. 2022, 38(1):4–13.
Baker M, Fard AY, Althuwaini H, Shadmand MB. Real-time AI-based anomaly detection and classification in power electronics dominated grids. IEEE Journal of Emerging and Selected Topics in Industrial Electronics. 2022, 4(2):549–559.
Yong L, Tang Y, Mao S, Liu H, Meng K, Dong Z, Qian F. A two-level energy management strategy for multi-microgrid systems with interval prediction and reinforcement learning. IEEE Transactions on Circuits and Systems I: Regular Papers. 2022, 69(4):1788–1799.
Dong X, Deng S, Wang D. A short-term power load forecasting method based on k-means and SVM. Journal of Ambient Intelligence and Humanized Computing. 2022, 13(11):5253–5267.
Veeramsetty V, Reddy KR, Santhosh M, Mohnot A, Singal G. Short-term electric power load forecasting using random forest and gated recurrent unit. Electrical Engineering. 2022, 104(1):307–329.
Zeng W, Li J, Sun C, Cao L, Tang X, Shu S, Zheng J. Ultra short-term power load forecasting based on similar day clustering and ensemble empirical mode decomposition. Energies. 2023, 16(4):1989–2011.
Habbak H, Mahmoud M, Metwally K, Fouda MM, Ibrahem MI. Load forecasting techniques and their applications in smart grids. Energies. 2023, 16(3):1480–1495.
Liao W, Wang S, Bak-Jensen B, Pillai JR, Yang Z, Liu K. Ultra-short-term interval prediction of wind power based on graph neural network and improved bootstrap technique. Journal of Modern Power Systems and Clean Energy. 2023, 11(4):1100–1114.
Choudhuri S, Adeniye S, Sen A. Distribution Alignment Using Complement Entropy Objective and Adaptive Consensus-Based Label Refinement For Partial Domain Adaptation. Artificial Intelligence and Applications. 2023, 1(1): 43–51.
Herrera-Casanova R, Conde A, Santos-Pé rez C. Hour-Ahead Photovoltaic Power Prediction Combining BiLSTM and Bayesian Optimization Algorithm, with Bootstrap Resampling for Interval Predictions. Sensors. 2024, 24(3):882–107.
Geng G, He Y, Zhang J, Qin T, Yang B. Short-term power load forecasting based on PSO-optimized VMD-TCN-attention mechanism. Energies. 2023, 16(12):4616–4631.
Veeramsetty V, Chandra DR, Grimaccia F, Mussetta M. Short term electric power load forecasting using principal component analysis and recurrent neural networks. Forecasting. 2022, 4(1):149–164.
Minghui Gao, Zhijun Zhang, Liangliang Cui, Sibo Feng, Jingyi Liu, Yongzhen Jiang, Temporal and Topological Enhanced Graph Neural Networks for Traffic Anomaly Detection. Journal of Cyber Security and Mobility, 2025, 14 (2), 457–474.
Lei Zhang, Implementing RGCN Model in Network Security Big Data Analysis, Journal of Cyber Security and Mobility, 2025, 14 (2), 505–530.
Qiang Wu, Network Security Maintenance and Detection Based on Diversified Features and Knowledge Graph, Journal of Cyber Security and Mobility, 2025, 14 (2), 339–364.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Journal of Cyber Security and Mobility