Power System Anomaly Detection Based on OCSVM Optimized by Improved Particle Swarm Optimization
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
This paper tries to solve anomaly detection, a very important issue in ensuring the safe and stable operation of power system. As the proportion of abnormal data in the operation of power system is very small, a one-class support vector machine (OCSVM) is adopted in this paper, which is suitable for classification of unbalanced data. However, the performance of OCSVM is sensitive to its parameters, and an unsuitable choice will decrease the classification accuracy and generalization ability of it. In this paper, particle swarm optimization (PSO) is used to optimize the parameters of OCSVM. The original PSO algorithm converges slowly and easily falls into local optimum. To overcome this issue, this paper proposes an improved PSO algorithm for parameters optimization, in which adaptive speed weighting and adaptive population splitting are introduced to improve the convergence speed of the algorithm and help the algorithm jump out of the local optimal position. Experiments on standard benchmarks and real power system experimental data sets demonstrate the effectiveness of the proposed algorithm.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures










Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“This problem is addressed by the author's modified PSO method for parameter optimization, which introduces adaptive population splitting and adaptive speed weighting to speed up convergence and aid in algorithmic escape from the local optimal location.”
From A Comprehensive Review on the Role of Artificial Intelligence in Power System Stability, Control, and Protection: Insights and Future Directions (2024) · cites this paper as [131]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A new optimizer using particle swarm theory
Eberhart, R., & Kennedy, J. (2002) · MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science · doi:10.1109/mhs.1995.494215 · Cited by 16,067
Estimating the Support of a High-Dimensional Distribution
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001) · Neural Computation · doi:10.1162/089976601750264965 · Cited by 6,168 · cited 1×
“first proposed the concept of one-class SVM in [8], which laid the foundation for the application and research of one-class SVM.”
BackgroundDistributed Online One-Class Support Vector Machine for Anomaly Detection Over Networks
Miao, X., Liu, Y., Zhao, H., & Li, C. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2804940 · Cited by 185 · cited 1×
“is used for anomaly data recognition in wireless sensor networks [18].”
MethodDeng, X., Jiang, P., Peng, X., & Mi, C. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2860568 · Cited by 116 · cited 1×
“used genetic algorithm to optimize parameters [21].”
Hydrological Time Series Anomaly Pattern Detection based on Isolation Forest
Qin, Y., & Lou, Y. (2019) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec.2019.8729405 · Cited by 54 · cited 1×
“Qin and Lou proposed a hydrological time series anomaly pattern detection algorithm based on isolation forest [6].”
BackgroundShort-Time Prediction of Traffic Flow Based on PSO Optimized SVM
Duan, M. (2018) · International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS) · doi:10.1109/icitbs.2018.00018 · Cited by 50 · cited 1×
“introduced particle swarm optimization to solve the parameter selection problem of support vector machine prediction model [13].”
MethodXue, H., Bai, Y., Hu, H., Xu, T. X., & Liang, H. (2019) · IEEE Access · doi:10.1109/access.2019.2897644 · Cited by 47 · cited 1×
“It effectively improves the classification accuracy and efficiency of the classifier [14].”
BackgroundShakya, S., & Sigdel, S. (2017) · International Conference on Computing, Communication and Automation · doi:10.1109/ccaa.2017.8229836 · Cited by 37 · cited 1×
“show a weighted hybrid model utilizing Support Vector Machine and Naive Bayes for anomaly discovery [4].”
MethodResearch on SVM improved algorithm for large data classification
Dai, H. (2018) · IEEE International Conference on Big Data Analysis (ICBDA) · doi:10.1109/icbda.2018.8367673 · Cited by 37 · cited 1×
“In 2018, Dai proposed a weighted Euclidean distance, radial integral kernel function SVM and dimensionality reduction algorithm for large data packet classification, which can effectively shorten the modeling time and improve the classification accuracy [7].”
BackgroundAn Anomaly Detection Algorithm of Cloud Platform Based on Self-Organizing Maps
Liu, J., Chen, S., Zhou, Z. Y., & Wu, T. (2016) · Mathematical Problems in Engineering · doi:10.1155/2016/3570305 · Cited by 36 · cited 1×
“proposed a dynamic and adaptive anomaly detection algorithm based on Self-Organizing Maps (SOM) for virtual machines [5].”
Method
Research works printed but not linked: 2
- wang, 2019, Prediction of output power of photovoltaic cells based on the improved particle swarm optimization support vector machine, Auto Electronics, 41, 63
- xu, 2019, Power consumption prediction model of least squares support vector machine based on adaptive Particl, Sci Technol Eng, 19, 136
Cited by
Alhamrouni, I., Abdul Kahar, N. H., Salem, M., Swadi, M., Zahroui, Y., Kadhim, D. J., Mohamed, F. A., & Alhuyi Nazari, M. (2024) · Applied Sciences · doi:10.3390/app14146214 · Cited by 217
“[131] attempted to resolve the problem of anomaly detection.”
BackgroundHealthcare insurance fraud detection using data mining
Hamid, Z., Khalique, F., Mahmood, S., Daud, A. Y., Bukhari, A. A., & Alshemaimri, B. K. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02512-4 · Cited by 116
“Wang [31] proposes an improved particle swarm optimization algorithm to enhance the accuracy of the OCSVM-based power system anomaly detection.”
MethodRecent advances in anomaly detection in Internet of Things: Status, challenges, and perspectives
Adhikari, D., Jiang, W., Zhan, J., Rawat, D. B., & Bhattarai, A. (2024) · Computer Science Review · doi:10.1016/j.cosrev.2024.100665 · Cited by 100
A Cloud Edge Collaborative Intelligence Method of Insulator String Defect Detection for Power IIoT
Song, C., Xu, W., Han, G., Zeng, P., Wang, Z., & Yu, S. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3039226 · Cited by 89
“The safe and stable operation of the power system is of great significance [10]–[12].”
BackgroundSelf-citationChaos Particle Swarm Optimization Enhancement Algorithm for UAV Safe Path Planning
Chu, H., Yi, J., & Yang, F. (2022) · Applied Sciences · doi:10.3390/app12188977 · Cited by 76
Applications of Artificial Intelligence in Distribution Power System Operation
Stock, S., Babazadeh, D., & Becker, C. U. (2021) · IEEE Access · doi:10.1109/access.2021.3125102 · Cited by 75
“In [105] Wang et al. combine the advantages of metaheuristics and machine learning by using a SVM for the classification of anomalies in generation control, optimized by an improved PSO algorithm.”
Anomaly detection methods based on GAN: a survey
Li, H., & Li, Y. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03905-6 · Cited by 54
“The representative method is OC-SVM [5].”
A survey of anomaly detection methods for power grids
Madabhushi, S., & Dewri, R. (2023) · International Journal of Information Security · doi:10.1007/s10207-023-00720-z · Cited by 43
Under frequency load shedding for low inertia grids utilizing smart loads
Darbandsari, A., & Amraee, T. (2021) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2021.107506 · Cited by 41
Power System Fault Classification and Prediction Based on a Three-Layer Data Mining Structure
Wang, Y., Wang, X., Wu, Y., & Guo, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3034365 · Cited by 28
Event Detection, Localization, and Classification Based on Semi-Supervised Learning in Power Grids
Yang, F., Ling, Z., Zhang, Y., He, X., Ai, Q., & Qiu, R. C. (2022) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2022.3209343 · Cited by 25
“In [7], an OCSVM is introduced to model normal measurements by a hyperplane hence to detect events.”
MethodDong, J., Song, C., Zhang, T., Li, Y., & Zheng, H. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/9233267 · Cited by 24
“[16] used differential privacy combined with deep learning to achieve privacy protection but did not consider robustness.”
BackgroundSelf-citationYe, T., Yan, J., Niu, E., Zhai, P., & Zhang, S. (2025) · Processes · doi:10.3390/pr13020549 · Cited by 22
Tian, H., Guo, J. Y., Xiao, H., Yan, K., & Sato, Y. (2022) · PLoS ONE · doi:10.1371/journal.pone.0271925 · Cited by 13
“PSO algorithms are widely applied in engineering like route planning [8, 9], data clustering [10, 11], feature selection [12, 13], image segmentation [14, 15], power system [16, 17], engineering areas [18–20], and so on.”
MethodSchindler, T. F., Schlicht, S., & Thoben, K. (2023) · Computers · doi:10.3390/computers12120253 · Cited by 12
Comparison of Isolation Forest and One Class SVM in Anomaly Detection of Gas Pipeline Operation
Lukito, K., Ihsan, A. F., & Hasmawati, H. (2023) · International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) · doi:10.1109/icicyta60173.2023.10428838 · Cited by 12
“Conversely, for the One-Class SVM, the corresponding hyperplane is depicted as a continuous black line [15].”
BackgroundKatbi, A., & Ksantini, R. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105153 · Cited by 12
Abnormal Sound Detection in Pipes Using a Wireless Microphone and Machine Learning
Notani, K., Hayashi, T., & Mori, N. (2022) · MATERIALS TRANSACTIONS · doi:10.2320/matertrans.mt-i2022001 · Cited by 11
Multi-bit Data Flow Error Detection Method Based on SDC Vulnerability Analysis
Yan, Z., Zhuang, Y., Zheng, W., & Gu, J. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3572838 · Cited by 9
“According to literature[29], the model is developed for the classiication of high multi-bit SDC vulnerability instructions, as shown in equation 4 f (F ) = sдn(ω · φ (F ) − ρ) (4) where f (F ) is a classiication function for a one-class support vector machine dividing the SDC vulnerability of an instruction; F is a mu…”
MethodInfusing k-means for securing IoT services in edge computing
Sakirin, T., & Asif, I. (2023) · Mesopotamian Journal of Computer Science · doi:10.58496/mjcsc/2023/007 · Cited by 9
Li, J., Liu, X., Wu, X., Wang, D., Xu, K., & Li, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112269 · Cited by 8
A Comprehensive Study on Anomaly Detection Methods Using Traditional and Machine Learning Approaches
Raj, A., & Sharma, S. (2024) · International journal of high school research · doi:10.36838/v6i11.2 · Cited by 8
Robust Anomaly Detection of Rotating Machinery with Contaminated Data
Wen, J., Ren, J., Zhao, Z., & Chen, X. (2025) · Journal of Dynamics Monitoring and Diagnostics · doi:10.37965/jdmd.2025.855 · Cited by 7
Garg, K., Gill, K. S., Aggarwal, P., Rawat, R. S., & Banerjee, D. (2024) · International Conference for Innovation in Technology (INOCON) · doi:10.1109/inocon60754.2024.10511525 · Cited by 7
Gao, Z. T., Fang, K., Zhu, Y., Wang, Z., & Guo, K. (2021) · Remote Sensing · doi:10.3390/rs13214327 · Cited by 7
“Due to the fact that only vector inputs can be imported into the OCSVM, onedimension time series cannot be applied directly [26].”
BackgroundMethodSelf-citationResearch on Automatic Identification of Power Big Data Anomalies Based on Improved Decision Tree
Zheng, S., Wang, J., & Gong, Y. (2025) · International Journal of High Speed Electronics and Systems · doi:10.1142/s0129156425403341 · Cited by 5
Xie, R., Zhou, D., Yang, Y., Chen, S., & Li, H. (2025) · International Journal of High Speed Electronics and Systems · doi:10.1142/s0129156425402979 · Cited by 5
Fan, L., Zhang, J., Mao, W., & Cao, F. (2023) · Entropy · doi:10.3390/e25010123 · Cited by 5
“As can be seen from the two tables above, the detection results of the OCSVM algorithm on several accessory demand data perform poorly relative to other methods, This is because it is difficult to train a suitable support vector to classify demand samples from a short length and large fluctuation.”
MethodInfluentialOutlier Detection Method of Three Rate Value Based on One Class SVM
Ma, Z., Lu, S., Zhang, R., Yu, H., & Wang, X. (2021) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac53711.2021.9486516 · Cited by 4
Hot-Pressing Furnace Current Monitoring and Predictive Maintenance System in Aerospace Applications
Chen, H., Chao-Tung, Y., Zhang, J.-H., Wang, Y.-C., Chang, H.-C., & King, J.-K. (2022) · Sensors · doi:10.3390/s23042230 · Cited by 4
“improved the effectiveness of a real power system experimentally with parameters optimization particle swarm optimization (PSO) algorithms [14].”
BackgroundA Survey on Different Techniques for Anomaly Detection
Pawar, P. P., & Phadke, A. C. (2023) · Algorithms for intelligent systems · doi:10.1007/978-981-99-2854-5_31 · Cited by 4
Diner: Interpretable Anomaly Detection for Seasonal Time Series in Web Services
Jing, Y., Wang, J., Qi, J., Qi, Q., He, B., Zhuang, Z., Wu, N., & Liao, J. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3422894 · Cited by 4
“Due to the difficulty of obtaining adequate labels, researchers have focused on unsupervised learning methods, such as One-Class SVM [32], K-means [33], DBSCAN [8], GAN [34] and deep Autoencoder [35], etc.”
MethodAnomaly Detection with Partially Observed Anomaly Types
Zhang, W., Gao, L., Li, S., & Li, W. (2021) · International Conference on Computer Communication and Network Security (CCNS) · doi:10.1109/ccns53852.2021.00028 · Cited by 4
A gas pipeline leakage detection method based on multichannel acoustic signals
Cao, Y., Zhu, M., Gao, J., Li, H., Ma, T., Li, Z., Liu, F., Li, Q., Zhang, C., & Tang, B. (2023) · International Conference on Electrical Engineering and Mechatronics Technology (ICEEMT) · doi:10.1109/iceemt59522.2023.10263263 · Cited by 4
“OCSVM first maps samples nonlinearly from the original sample space into a high-dimensional feature space F .”
MethodInfluentialA Study on Anomaly Detection with Deep Learning Models for IoT Time Series Sensor Data
Sachdeva, U., & Vamsi, P. R. (2022) · 2022 8th International Conference on Signal Processing and Communication (ICSC) · doi:10.1109/icsc56524.2022.10009580 · Cited by 4
“According to [11], particle swarm optimization is used to optimize the OCSVM’s parameters (PSO).”
MethodHao, G., Ruan, H., Li, Y., Liu, Q., Liu, C., Wang, Z., Li, X., Yu, J., & Juan, G. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114124 · Cited by 3
Self-citationATS: A Fully Automatic Troubleshooting System with Efficient Anomaly Detection and Localization
Yuan, L., Meng, Y., Sun, J., Zhuang, S., Liu, Y., Geng, L., & Huang, W. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36030-5_38 · Cited by 3
“Although OCSVM [38] and CBLOF [12] have relatively good performance, we do not choose them due to time consumption.”
Cai, H., Liu, B., & Pan, S. L. (2020) · IEEE Access · doi:10.1109/access.2020.3009429 · Cited by 3
“Constrained Optimization Problems (COPs) exist widely in the real-world applications [1], [2].”
BackgroundPradeep, K. V., Gowrishankar, K., Sivanantham, E., Rao, K. S., Kiran, N., & Vimal, A. (2023) · International Conference on Artificial Intelligence and Smart Energy (ICAIS) · doi:10.1109/icais56108.2023.10073820 · Cited by 3
“The voltage and current measurements undergo signal processing in order to reflect the inputs to detect the fault occurrence in the system [4].”
BackgroundYang, F., Ling, Z., Zhang, Y., He, X., Ai, Q., & Qiu, R. C. (2022) · Frontiers in Energy Research · doi:10.3389/fenrg.2022.858665 · Cited by 1
“In this section, the PL-based approach is compared with other approaches for event classi fi cation, including CNN (Li and Wang, 2019), deep neural network (DNN) (Yadav et al., 2019), and LSTM (Li et al., 2021).”
BackgroundMethodInfluentialZhao, S., Du, Y., He, S., Bian, J., & Shi, J. (2024) · Scalable Computing Practice and Experience · doi:10.12694/scpe.v25i5.3088 · Cited by 1
“Therefore, the daily load curve is used to analyze electric power data [9].”
MethodOptimizing Renewable Energy Distribution Networks with AI Techniques: The A-IsolE Project
Soma, G. G., Pasquarelli, M. G., Pentolini, M., Dore, C., Martini, F., Bagnasco, A., Vinci, A., Valfrè, G., Bessone, E., Mosaico, G., et al. (2026) · Energies · doi:10.3390/en19071718 · Cited by 1
Anomaly Detection in Multivariate Time Series: Combining LSTM Autoencoders with Contrastive Learning
Seo, S., Jang, S., & Min, M. (2026) · Hawaii International Conference on System Sciences (HICSS) · doi:10.24251/hicss.2026.157 · Cited by 1
Motor online novelty detection scheme based on one-class hyperdisk
Yang, B., He, Z., Shao, H., & Xu, X. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad490e · Cited by 1
“Wang et al [23] exploited the optimal selection of the OCSVM parameters using particle swarm optimization.”
Hsiao, S., & Sung, W. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.060056 · Cited by 1
Particle Swarm Optimization Enhanced with Kernel Principal Component Analysis
Wang, Y., Huang, W. C., & Wang, J. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533971
“Scholars' research on PSO is mainly divided into the following categories: theoretical analysis [2-3], algorithm structure [4-5], parameter setting [6-7], topology structure [8-9], mixed strategy [10-11], and engineering application [12-13].”
BackgroundZhang, Q., Gou, X., Zhang, Q., & Yu, G. (2024) · Research Square · doi:10.21203/rs.3.rs-4958971/v1
Electric Data Anomaly Detection Method Based on an Auto-Encoder Algorithm
She, Y., Ni, H., Zhang, Z., & Du, J. (2025) · International Conference on Computers, Information Processing and Advanced Education (CIPAE) · doi:10.1109/cipae66821.2025.00061
A Training-Free Anomaly Detection Framework for Photovoltaic Panels Using DINO-Based Memory Banks
Lin, C. E., Lv, H., Zhang, Y., & Gong, Y. (2025) · International Conference on Intelligent Power and Systems (ICIPS) · doi:10.1109/icips67876.2025.11331993
“Early efforts leveraged classical machine learning (ML) techniques like One-Class Support Vector Machines (OCSVM) [26] and observer-based models [3] for anomaly identification.”
Particle Swarm Optimization for Feature Selection in IoT Sensor Anomaly Detection
Ghazal, T. M., Ibrahim, A. M., Aruna, V., Abbas, A., Azizova, F., & Jana, M. (2025) · doi:10.1109/iceei68459.2025.11330683
“Wang et al. [34] sought to use the enhanced PSO to identify unusual standards in energy systems.”
Anomaly Detection Method for Smart Grids Integrating State Estimation and LightGBM
Yang, X. J., Yuan, S., Pan, L., Wei, X., & Xue, H. (2025) · doi:10.1109/epee67527.2025.11428577
Metadata
- Authors
- Wang, Z., Fu, Y., Song, C., Zeng, P., & Qiao, L.
- Affiliations
- Shenyang Institute of Automation (CN)
- State Grid Liaoning Electric Power Company (China) (CN)
- Venue
- IEEE Access
- Published
- 2019
- Volume
- 7
- Pages
- 181580-181588
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2995769985
- Cited by
- 47
- References
- 21
- Citations by year
- 2026: 1 · 2025: 10 · 2024: 8 · 2023: 9 · 2022: 10 · 2021: 6 · 2020: 3
- FWCI
- 2.19
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- SIA OpenIR (Chinese Academy of Sciences) (submittedVersion)
- Funders
- State Grid Corporation Science and Technology Project (SGLNXT00YJJS1800110)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Power System Optimization and Stability
- Physical Sciences › Computer Science › Artificial Intelligence › Metaheuristic Optimization Algorithms Research
- Keywords
- one-class support vector machine, particle swarm optimization, parameter optimization, improved PSO algorithm, local optima avoidance, convergence rate
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.