Security event-triggered control for Markovian jump neural networks against actuator saturation and hybrid cyber attacks

Deng, Yahan; Lu, Hongqian; Zhou, Wuneng

doi:10.1016/j.jfranklin.2021.07.022

Cited by 27 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, such methods are not sufficient to deal with complex nonlinear load time series and are difficult to meet the needs of modern forecasting. With the development of artificial intelligence (AI) technology [11][12][13], machine learning is widely used in the field of power load forecasting due to its powerful non-linear processing capability [14].…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

A Combined Model Based on EOBL-CSSA-LSSVM for Power Load Forecasting

et al. 2021

View full text Add to dashboard Cite

Inaccurate electricity load forecasting can lead to the power sector gaining asymmetric information in the supply and demand relationship. This asymmetric information can lead to incorrect production or generation plans for the power sector. In order to improve the accuracy of load forecasting, a combined power load forecasting model based on machine learning algorithms, swarm intelligence optimization algorithms, and data pre-processing is proposed. Firstly, the original signal is pre-processed by the VMD–singular spectrum analysis data pre-processing method. Secondly, the noise-reduced signals are predicted using the Elman prediction model optimized by the sparrow search algorithm, the ELM prediction model optimized by the chaotic adaptive whale algorithm (CAWOA-ELM), and the LSSVM prediction model optimized by the chaotic sparrow search algorithm based on elite opposition-based learning (EOBL-CSSA-LSSVM) for electricity load data, respectively. Finally, the weighting coefficients of the three prediction models are calculated using the simulated annealing algorithm and weighted to obtain the prediction results. Comparative simulation experiments show that the VMD–singular spectrum analysis method and two improved intelligent optimization algorithms proposed in this paper can effectively improve the prediction accuracy. Additionally, the combined forecasting model proposed in this paper has extremely high forecasting accuracy, which can help the power sector to develop a reasonable production plan and power generation plans.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…This symmetric information will not only help the power sector to maintain a dynamic balance between power supply and consumption, but also to reduce the waste of resources. Symmetry 2021, 13…”

Section: Forecast Feedback System For Electricity Load Forecasting Modelsmentioning

confidence: 99%

A Combined Model Based on EOBL-CSSA-LSSVM for Power Load Forecasting

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…In practice, both attacks are stochastically considered together. Many results have been reported on various problems of neural networks, 28 thermostatically controlled loads, 14 T-S fuzzy systems, 13 and Markovian jump systems. 29 As a result, the focus of this article is on the development of a resilient memory/adaptive ET controller for NCSs in the face of randomly occurring multiple cyber-attacks in the sense of finite-time.…”

Section: Introductionmentioning

confidence: 99%

Finite‐time resilient control for networked control systems with multiple cyber‐attacks: Memory/adaptive event‐triggered scheme

Sathishkumar

Liu

2022

Adaptive Control & Signal

View full text Add to dashboard Cite

This article addresses the finite-time memory and finite-time adaptive event-triggered control issues for networked control systems (NCSs) with randomly occurring cyber-attacks. A comprehensive stochastic attack model is developed that includes false-data injection attacks and denial-of-service attacks. In our first problem, the purpose of the memory event-triggered scheme is used to release certain packets to establish new events contrasting with the existing event-triggered method. In this fashion, the event generator can make a more accurate decision and better control performance can be expected. On the other hand, our second problem introduces an adaptive event-triggered scheme to reduce unnecessary communication transmissions in a network with an adaptive varying-threshold while maintaining acceptable system performance. In both problems where malicious signals are injected by adversaries, a random variable is presented to relate cyber-attacks. Using Lyapunov stability theory, integral inequality and linear matrix inequality, a sufficient condition is constructed for both problems to achieve the exponentially mean-square finite-time boundedness for NCSs under stochastic attacks. Finally, three numerical examples are simulated to demonstrate the effectiveness of the proposed methods.

show abstract

“…In Liu et al [29] and Mmh et al [30], the security control problem under hybrid network attack is studied for linear systems. How to design an effective event trigger mechanism to save network resources under the hybrid network attack is studied in the literature [31,32]. Different from the above event-triggering mechanism, Murugesan and Liu [33] studies the elastic memory event-triggering scheme under the attack of deception and DoS, which enhances the flexibility of the system.…”

Section: Introductionmentioning

confidence: 99%

Resilient iterative learning control for a class of discrete‐time nonlinear systems under hybrid attacks

Zhao

Yin

2022

Asian Journal of Control

View full text Add to dashboard Cite

The security control problem for a class of unknown nonlinear systems is considered in this paper. For the nonlinear system running in the network environment, the measurement channel is subjected to hybrid attacks. Intermittent denial of service attacks and false data injection attacks are modeled as the hybrid attacks. According to the characteristics of the repetitive system, a resilient iterative learning control (ILC) algorithm under hybrid attacks is devised. Subsequently, the stability of the system is proved by mathematical derivation and theoretical analysis in the sense of mathematical expectation. The theoretical analysis results indicate that the resilient ILC algorithm can ensure the stability of the system, and the tracking error converges with the increased number of iterations. Finally, the validity of the algorithm is illustrated by numerical simulation and mobile robot simulation.

show abstract

Security event-triggered control for Markovian jump neural networks against actuator saturation and hybrid cyber attacks

Cited by 27 publications

References 28 publications

A Combined Model Based on EOBL-CSSA-LSSVM for Power Load Forecasting

A Combined Model Based on EOBL-CSSA-LSSVM for Power Load Forecasting

Finite‐time resilient control for networked control systems with multiple cyber‐attacks: Memory/adaptive event‐triggered scheme

Resilient iterative learning control for a class of discrete‐time nonlinear systems under hybrid attacks

Contact Info

Product

Resources

About