Abstract
Denial of Service (DoS) attack blocks the transmission of the power system measurements by the interference, which greatly degrades the performance of power system state estimation performance. In order to reduce the impact of DoS attacks on estimated performance, it is necessary to compensate for lost measurements. In this paper, a hybrid compensation model based on deep neural networks is proposed for power system state estimation under DoS attacks. In this compensation model, the advantages of Convolutional Neural Network (CNN) and Long-Short Term Memory Neural Networks (LSTM) are respectively utilized in the automatic feature extraction and long-term prediction of measurements. The spatio features of the measurements are fully figured out by squeeze-and-excitation blocks in the CNN, which enables the characteristic response of the input channel can be adaptively adjusted. Moreover, an autoregressive is applied for dealing with the problem of the scale insensitivity of neural network models. The proposed model is validated in a Cubature Kalman Filtering (CKF) state estimation algorithm on the IEEE-30 and IEEE-118 bus test systems. Simulation results illustrate that the CKF algorithm with the proposed model withstands the DoS attacks and performs a higher estimation accuracy than that with the LSTM, CNN, and the Multilayer Perceptron (MLP).
Similar content being viewed by others
References
Gunasekaran N, Ali MS, Pavithra S (2019) Finite-time L\(\infty \) performance state estimation of recurrent neural networks with sampled-data signals. Neural Process Lett 51:1379–1392
Ali MS (2018) Sampled-data state estimation of Markovian jump static neural networks with interval time-varying delays. J Comput Appl Math 343:217–229
Ali MS, Gunasekaran N, Joo YH (2018) Sampled-data state estimation of neutral type neural networks with mixed time-varying delays[J]. Neural Process Lett 50:357–378
Ali MS, Gunasekaran N, Zhu Q (2017) State estimation of T-S fuzzy delayed neural networks with Markovian jumping parameters using sampled-data control. Fuzzy Sets Syst 306:87–104
Teixeira A, Amin S, Sandberg H, Johansson KH, Sastry SS (2010) Cyber security analysis of state estimators in electric power systems. In: 49th IEEE conference on decision and control (CDC), pp 5991–5998
Chen J, Dou C, Xiao L, Wang Z (2019) Fusion state estimation for power systems under dos attacks: a switched system approach. IEEE Trans Syst, Man, Cybern Syst 49:1679–1687
Liang G, Zhao J, Luo F, Weller SR, Dong ZY (2017) A review of false data injection attacks against modern power systems. IEEE Trans Smart Grid 8:1630–1638
Chao Y, Wen Y, Shi H (2018) Dos attack in centralised sensor network against state estimation. IET Control Theory Appl 12:1244–1253
Zhang Y, Du L, Lewis FL (2020) Stochastic dos attack allocation against collaborative estimation in sensor networks. IEEE/CAA J Automatica Sinica 7:1225–1234
Zhou Y, Miao Z (2016) Cyber attacks, detection and protection in smart grid state estimation. In: north American power symposium, pp 1–6
Chen W, Ding D, Dong H, Wei G (2019) Distributed resilient filtering for power systems subject to denial-of-service attacks. IEEE Trans Syst, Man Cybern: Syst 49:1688–1697
Luca SCHENATO (2009) To zero or to hold control inputs with lossy links? IEEE Trans Autom Control 54:1093–1099
Sun S (2013) Optimal linear filters for discrete-time systems with randomly delayed and lost measurements with/without time stamps. IEEE Trans Autom Control 58:1551–1556
Yang H, Li H, Xia Y, Li L (2018) Nonuniform sampling kalman filter for networked systems with markovian packets dropout. J Franklin Inst 355:4218–4240
Lu X, Li H (2020) An improved stability theorem for nonlinear systems on time scales with application to multi-agent systems. IEEE Transactions on Circuits and Systems II: Express Briefs 67:3277–3281
X Lu, H Li. (2020) A hybrid control approach to H\(\infty \) problem of nonlinear descriptor systems with actuator saturation. IEEE Transactions on Automatic Control
Broersen Mt P (2009) Modified durbin method for accurate estimation of moving-average models. IEEE Trans Instrum Meas 58:1361–1369
Wang Z, Lou Y (2019) Hydrological time series forecast model based on wavelet de-noising and arima-lstm. In: 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), pp 1697–1701
Nezhad SMT, Nazari M, Gharavol E (2016) A novel dos and ddos attacks detection algorithm using arima time series model and chaotic system in computer networks. IEEE Commun Lett 20:700–703
Demidova L, Ivkina M (2020) Development and research of the forecasting models based on the time series using the random forest algorithm. 2020 2nd International Conference on Control Systems. Mathematical Modeling, Automation and Energy Efficiency (SUMMA), pp 359–364
Jwa B, Xin SA, Qian CA, Quan CA (2020) An innovative random forest-based nonlinear ensemble paradigm of improved feature extraction and deep learning for carbon price forecasting. Sci Total Environ 762:143099
Zhao X, Nie X (2020) Prediction error and forecasting interval analysis of decision trees with an application in renewable energy supply forecasting. Complexity, 2020
Lim B, Zohren S (2021) Time-series forecasting with deep learning: a survey. Philos Trans Royal Soci Math Phys Eng Sci 379:20200209
Jiao Z, Hu P, Xu H, Wang Q (2020) Machine learning and deep learning in chemical health and safety: a systematic review of techniques and applications. J Chem Health Saf 27:316–334
Ploysuwan T(2019) Deep cnn and lstm network for appliances energy forecasting in residential houses using iot sensors. In: 2019 7th international electrical engineering congress (iEECON), pp 1-4
Wang Y, Wang Z, Wang H, Junfeng Z, Feng R (2019) Prediction of passenger flow based on cnn-lstm hybrid model. In: 2019 12th international symposium on computational intelligence and design (ISCID) 2:132-135
Cirstea RG, Micu DV, Muresan GM, Guo C, Yang B (2018) Correlated time series forecasting using Deep neural networks: a summary of results arXiv preprint arXiv:1808.09794
Bao T, Zaidi S, Xie S, Yang P, Zhang ZQ (2020) A cnn-lstm hybrid model for wrist kinematics estimation using surface electromyography. IEEE Trans Instrum Meas 70:1–9
Bishop CM (1995) Regularization and complexity control in feed-forward networks. In proceedings international conference on artificial neural networks 1:141–148
Goodfellow I, Bengio Y, Courville A (2016) Deep learning MIT press
Zhang R, Yin J, Peng F (2019) Situational awareness for dynamic power system based on UKF-driven residual matrix analysis. In: 2019 IEEE innovative smart grid technologies-Asia, pp 964-969
Qi J, Kai S, Wang J (2018) Dynamic state estimation for multi-machine power system by unscented kalman filter with enhanced numerical stability. IEEE Trans Smart Grid 9:1184–1196
Rouhani A, Abur A (2015) Real-time dynamic parameter estimation for an exponential dynamic load model. IEEE Trans Smart Grid 7:1530–1536
Sun J, Li P, Wang C (2021) Optimise transient control against DoS attacks on ESS by input convex neural networks in a game. Sustain Energy, Grids Netw 28:100535
Zhao H, Tian T (2014) Dynamic state estimation for power system based on an adaptive unscented kalman filter. Power Syst Technol 38:188–192
Bhattacharya S, BasAr T (2010) Game-theoretic analysis of an aerial jamming attack on a uav communication network. In: proceedings of the 2010 American control conference, pp 818-823
Ding K, Ren X, Quevedo DE, Subhrakanti D, Shi L (2018) Dos attacks on remote state estimation with asymmetric information. IEEE Trans Control Netw Syst 6:653–666
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780
Jie H, Li S, Gang S (2018) Squeeze-and-excitation networks. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132-7141
Lai G, Chang WC, Yang Y, Liu H (2018) Modeling long- and short-term temporal patterns with deep neural networks. In: The 41st International ACM SIGIR Conference on Research and Development in information retrieval, pp 95-104
Karim F, Majumdar S, Darabi H, Harford S (2018) Multivariate lstm-fcns for time series classification. Neural Netw 116:237–245
Arasaratnam I, Haykin S (2009) Cubature kalman filters. IEEE Trans Autom Control 54:1254–1269
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366
Hornik K, Stinchcombe M, White H (1990) Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Netw 3:551–560
Bergmeir C, Benítez J (2012) On the use of cross-validation for time series predictor evaluation. Inf Sci 191:192–213
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. Journal Mach Learn Res 15:1929–1958
Karim F, Majumdar S, Darabi H (2019) Multivariate LSTM-FCNs for time series classification. Neural Netw 116:237–245
Acknowledgements
This work is jointly supported by National Natural Science Foundation of China under Grant 61703347; Fundamental Research Funds for the Central Universities (Grant XDJK2020B010); Chongqing special fund for technological innovation and application development (Grant cstc2019jscx-fxydX0017); Natural science foundation of chongqing, grant no. stc2021jcyj-msxmX0416.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xu, X., Sun, J., Wang, C. et al. A Novel Hybrid CNN-LSTM Compensation Model Against DoS Attacks in Power System State Estimation. Neural Process Lett 54, 1597–1621 (2022). https://doi.org/10.1007/s11063-021-10696-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-021-10696-3