Pub Date : 2024-09-05DOI: 10.1109/TSMC.2024.3448206
Ádám B. Csapó
This article addresses the challenge of efficiently managing datasets of various sizes through two key strategies: 1) dataset compression and 2) synthetic augmentation. This article introduces a novel framework, referred to as subsample, generate, and stack (SGS), which can be used to implement both of these strategies while maintaining the statistical characteristics of the original data. While SGS can be paired with a variety of generative methods, this article specifically demonstrates its application using the spiral discovery method (SDM)—an autoregressive data generation model that allows for the exploratory manipulation of numerical data. The uniqueness and widespread applicability of this approach stems from its support for the fine-grained optimization of exploration versus exploitation goals through an interpretable set of hyperparameters. The effectiveness of the SGS framework combined with SDM is validated on two benchmark examples—one focusing on compression and the other on augmentation—showcasing its potential as a tool for dataset management in engineering contexts.
{"title":"Subsample, Generate, and Stack Using the Spiral Discovery Method: A Framework for Autoregressive Data Compression and Augmentation","authors":"Ádám B. Csapó","doi":"10.1109/TSMC.2024.3448206","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3448206","url":null,"abstract":"This article addresses the challenge of efficiently managing datasets of various sizes through two key strategies: 1) dataset compression and 2) synthetic augmentation. This article introduces a novel framework, referred to as subsample, generate, and stack (SGS), which can be used to implement both of these strategies while maintaining the statistical characteristics of the original data. While SGS can be paired with a variety of generative methods, this article specifically demonstrates its application using the spiral discovery method (SDM)—an autoregressive data generation model that allows for the exploratory manipulation of numerical data. The uniqueness and widespread applicability of this approach stems from its support for the fine-grained optimization of exploration versus exploitation goals through an interpretable set of hyperparameters. The effectiveness of the SGS framework combined with SDM is validated on two benchmark examples—one focusing on compression and the other on augmentation—showcasing its potential as a tool for dataset management in engineering contexts.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142450949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-05DOI: 10.1109/TSMC.2024.3446635
Zong-Zhi Lin;Thomas D. Pike;Mark M. Bailey;Nathaniel D. Bastian
Network intrusion detection systems (NIDSs) to detect malicious attacks continue to meet challenges. NIDS are often developed offline while they face auto-generated port scan infiltration attempts, resulting in a significant time lag from adversarial adaption to NIDS response. To address these challenges, we use hypergraphs (HGs) focused on Internet protocol (IP) addresses and destination ports to capture evolving patterns of port scan attacks. The derived set of HG-based metrics are then used to train an ensemble machine learning (ML)-based NIDS that allows for real-time adaption in monitoring and detecting port scanning activities, other types of attacks, and adversarial intrusions at high accuracy, precision and recall performances. This ML adapting NIDS was developed through the combination of 1) intrusion examples; 2) NIDS update rules; 3) attack threshold choices to trigger NIDS retraining requests; and 4) a production environment with no prior knowledge of the nature of network traffic. 40 scenarios were auto-generated to evaluate the ML ensemble NIDS comprising three tree-based models. The resulting ML ensemble NIDS was extended and evaluated with the CIC-IDS2017 dataset. Results show that under the model settings of an Update-ALL-NIDS rule (specifically retrain and update all the three models upon the same NIDS retraining request) the proposed ML ensemble NIDS evolved intelligently and produced the best results with nearly 100% detection performance throughout the simulation.
用于检测恶意攻击的网络入侵检测系统(NIDS)不断面临挑战。NIDS 通常是在离线状态下开发的,同时还要面对自动生成的端口扫描渗透尝试,这就导致从对手适应到 NIDS 响应之间存在明显的时间差。为了应对这些挑战,我们使用以互联网协议(IP)地址和目标端口为重点的超图(HG)来捕捉端口扫描攻击的演变模式。然后,基于超图的衍生指标集被用于训练基于机器学习(ML)的集合式 NIDS,该 NIDS 可在监控和检测端口扫描活动、其他类型的攻击和对抗性入侵时进行实时调整,并具有较高的准确度、精确度和召回率。这种基于 ML 学习的 NIDS 是通过以下几方面的结合开发出来的:1)入侵示例;2)NIDS 更新规则;3)用于触发 NIDS 再训练请求的攻击阈值选择;以及 4)事先不了解网络流量性质的生产环境。自动生成了 40 个场景,以评估由三个基于树的模型组成的 ML 集合 NIDS。利用 CIC-IDS2017 数据集对生成的 ML 集合 NIDS 进行了扩展和评估。结果表明,在更新-所有-NIDS 规则的模型设置下(特别是在同一 NIDS 重新训练请求中重新训练和更新所有三个模型),所提出的 ML 集合 NIDS 进行了智能进化,并在整个模拟过程中产生了最佳结果,检测性能接近 100%。
{"title":"A Hypergraph-Based Machine Learning Ensemble Network Intrusion Detection System","authors":"Zong-Zhi Lin;Thomas D. Pike;Mark M. Bailey;Nathaniel D. Bastian","doi":"10.1109/TSMC.2024.3446635","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3446635","url":null,"abstract":"Network intrusion detection systems (NIDSs) to detect malicious attacks continue to meet challenges. NIDS are often developed offline while they face auto-generated port scan infiltration attempts, resulting in a significant time lag from adversarial adaption to NIDS response. To address these challenges, we use hypergraphs (HGs) focused on Internet protocol (IP) addresses and destination ports to capture evolving patterns of port scan attacks. The derived set of HG-based metrics are then used to train an ensemble machine learning (ML)-based NIDS that allows for real-time adaption in monitoring and detecting port scanning activities, other types of attacks, and adversarial intrusions at high accuracy, precision and recall performances. This ML adapting NIDS was developed through the combination of 1) intrusion examples; 2) NIDS update rules; 3) attack threshold choices to trigger NIDS retraining requests; and 4) a production environment with no prior knowledge of the nature of network traffic. 40 scenarios were auto-generated to evaluate the ML ensemble NIDS comprising three tree-based models. The resulting ML ensemble NIDS was extended and evaluated with the CIC-IDS2017 dataset. Results show that under the model settings of an Update-ALL-NIDS rule (specifically retrain and update all the three models upon the same NIDS retraining request) the proposed ML ensemble NIDS evolved intelligently and produced the best results with nearly 100% detection performance throughout the simulation.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-04DOI: 10.1109/TSMC.2024.3450274
Yuhong Tang;Xiong Yang;Chaoxu Mu;Yongduan Song
This article develops an intermittent feedback optimal control scheme for nonlinear systems with asymmetric input saturation using a dynamic event-triggering mechanism. First, an infinite horizon nonquadratic value function with a novel integrand is formulated for the studied system to evaluate the performance, tackle the asymmetric input saturation, and remove certain rigorous assumptions in prior related studies. Second, a critic neural network (CNN) in the adaptive dynamic programming framework is constructed to obtain the optimal event-triggered control (ETC). An improved concurrent learning technique is then developed to update the CNN’s weights without requiring the persistence of excitation condition. Compared with the static ETC scheme, the present dynamic ETC strategy consumes fewer computational resources. Third, the uniform ultimate boundedness of the state, the weight estimation error, and the internal dynamic variable are assured, and the Zeno behavior is excluded. Finally, a rotational-translational actuator system is given to validate the developed intermittent feedback optimal control scheme.
{"title":"Intermittent Feedback Optimal Control of Saturated-Input Nonlinear Systems via Adaptive Dynamic Programming","authors":"Yuhong Tang;Xiong Yang;Chaoxu Mu;Yongduan Song","doi":"10.1109/TSMC.2024.3450274","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3450274","url":null,"abstract":"This article develops an intermittent feedback optimal control scheme for nonlinear systems with asymmetric input saturation using a dynamic event-triggering mechanism. First, an infinite horizon nonquadratic value function with a novel integrand is formulated for the studied system to evaluate the performance, tackle the asymmetric input saturation, and remove certain rigorous assumptions in prior related studies. Second, a critic neural network (CNN) in the adaptive dynamic programming framework is constructed to obtain the optimal event-triggered control (ETC). An improved concurrent learning technique is then developed to update the CNN’s weights without requiring the persistence of excitation condition. Compared with the static ETC scheme, the present dynamic ETC strategy consumes fewer computational resources. Third, the uniform ultimate boundedness of the state, the weight estimation error, and the internal dynamic variable are assured, and the Zeno behavior is excluded. Finally, a rotational-translational actuator system is given to validate the developed intermittent feedback optimal control scheme.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142450950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-04DOI: 10.1109/TSMC.2024.3443290
Jin-Xi Zhang;Tianyou Chai
This article is concerned with the problem of tracking control with discontinuous references for the strict-feedback systems with both multiplicative and additive nonlinearities as well as unmatched disturbances. In contrast with the existing studies, it is focused on the cases where the system nonlinearities are radially unbounded; the system dynamics or its bounding functions are unknown; and the reference derivatives are unavailable. They significantly challenge the existing control solutions under discontinuous references which are based on filtering, guidance, or impulsive systems. To conquer this obstruction, a novel hybrid control scheme is devised in this article, which consists of a robust constraint-handling controller and a proportional controller. It steers the system output to track the discontinuous reference with tunable setting time and accuracy, without violation of the prescribed constraint. Moreover, the controller exhibits a significant simplicity. While it is independent of the specific model information of the plant or the derivatives of the intermediate control signals, no effort is paid for parameter identification, function approximation, command filtering, or disturbance estimation. Finally, three simulation studies are conducted to substantiate the theoretical result.
{"title":"Robust Tracking Control of Unknown Nonlinear Systems With Discontinuous References Under Output Constraints","authors":"Jin-Xi Zhang;Tianyou Chai","doi":"10.1109/TSMC.2024.3443290","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3443290","url":null,"abstract":"This article is concerned with the problem of tracking control with discontinuous references for the strict-feedback systems with both multiplicative and additive nonlinearities as well as unmatched disturbances. In contrast with the existing studies, it is focused on the cases where the system nonlinearities are radially unbounded; the system dynamics or its bounding functions are unknown; and the reference derivatives are unavailable. They significantly challenge the existing control solutions under discontinuous references which are based on filtering, guidance, or impulsive systems. To conquer this obstruction, a novel hybrid control scheme is devised in this article, which consists of a robust constraint-handling controller and a proportional controller. It steers the system output to track the discontinuous reference with tunable setting time and accuracy, without violation of the prescribed constraint. Moreover, the controller exhibits a significant simplicity. While it is independent of the specific model information of the plant or the derivatives of the intermediate control signals, no effort is paid for parameter identification, function approximation, command filtering, or disturbance estimation. Finally, three simulation studies are conducted to substantiate the theoretical result.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traditional knowledge-based situation awareness (SA) modes struggle to adapt to the escalating complexity of today’s Energy Internet of Things (EIoT), necessitating a pivotal paradigm shift. In response, this work introduces a pioneering data-driven SA framework, termed digital twin-based SA (DT-SA), aiming to bridge existing gaps between data and demands, and further to enhance SA capabilities within the complex EIoT landscape. First, we redefine the concept of digital twin (DT) within the EIoT context, aligning it with data-intensive scientific discovery paradigm (the Fourth Paradigm) so as to waken EIoT’s sleeping data; this contextual redefinition lays the cornerstone of our DT-SA framework for EIoT. Then, the framework is comprehensively explored through its four fundamental steps: digitalization, simulation, informatization, and intellectualization. These steps initiate a virtual ecosystem conducive to a continuously self-adaptive, self-learning, and self-evolving big model (BM), further contributing to the evolution and effectiveness of DT-SA in engineering. Our framework is characterized by the incorporation of system theory and Fourth Paradigm as guiding ideologies, DT as data engine, and BM as intelligence engine. This unique combination forms the backbone of our approach. This work extends beyond engineering, stepping into the domain of data science—DT-SA not only enhances management practices for EIoT users/operators, but also propels advancements in pattern analysis and machine intelligence (PAMI) within the intricate fabric of a complex system. Numerous real-world cases validate our DT-SA framework.
{"title":"Redefinition of Digital Twin and Its Situation Awareness Framework Designing Toward Fourth Paradigm for Energy Internet of Things","authors":"Xing He;Yuezhong Tang;Shuyan Ma;Qian Ai;Fei Tao;Robert Qiu","doi":"10.1109/TSMC.2024.3407061","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3407061","url":null,"abstract":"Traditional knowledge-based situation awareness (SA) modes struggle to adapt to the escalating complexity of today’s Energy Internet of Things (EIoT), necessitating a pivotal paradigm shift. In response, this work introduces a pioneering data-driven SA framework, termed digital twin-based SA (DT-SA), aiming to bridge existing gaps between data and demands, and further to enhance SA capabilities within the complex EIoT landscape. First, we redefine the concept of digital twin (DT) within the EIoT context, aligning it with data-intensive scientific discovery paradigm (the Fourth Paradigm) so as to waken EIoT’s sleeping data; this contextual redefinition lays the cornerstone of our DT-SA framework for EIoT. Then, the framework is comprehensively explored through its four fundamental steps: digitalization, simulation, informatization, and intellectualization. These steps initiate a virtual ecosystem conducive to a continuously self-adaptive, self-learning, and self-evolving big model (BM), further contributing to the evolution and effectiveness of DT-SA in engineering. Our framework is characterized by the incorporation of system theory and Fourth Paradigm as guiding ideologies, DT as data engine, and BM as intelligence engine. This unique combination forms the backbone of our approach. This work extends beyond engineering, stepping into the domain of data science—DT-SA not only enhances management practices for EIoT users/operators, but also propels advancements in pattern analysis and machine intelligence (PAMI) within the intricate fabric of a complex system. Numerous real-world cases validate our DT-SA framework.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-04DOI: 10.1109/TSMC.2024.3445881
Te Yang;Keqing Bu;Guoliang Chen;Xiang-Peng Xie;Jianwei Xia
The concept of reachable set and state space ellipsoid is used in this article to determine the optimal safe range of the truck-trailer driving by allowing the constrained variables to move freely within a given range. A method of returning the truck to the desired position is proposed by analysing the movement trajectory of the truck. Two results are certified. The first result considers the issue of reachable set estimation (RSE) for the multirate sampled-data (MRSD) system in the aperiodic sampled-data framework based on the model knowledge. By constructing loop-based Lyapunov functional (LBLF), we obtain the sufficient condition that all the state trajectories are confined to target ellipsoid. This article also provides a computational method for an MRSD controller considering RSE. The second result provides the data-driven control tactics for the unknown sampled-data system to consider the RSE problem for the aperiodic sampled-data system, using only the noisy data. In addition, this article extends the data-driven control scheme to the design of MRSD controllers and ensures the stability of the system in agreement with the measured data. Simulation results show that the MRSD controller under both the model-driven method and the data-driven method is valid and achieves better control effect compared to the single-rate sampled-data (SRSD).
{"title":"Model-Driven and Data-Driven Reachable Set Estimation for Multirate Sampled-Data Truck-Trailer System","authors":"Te Yang;Keqing Bu;Guoliang Chen;Xiang-Peng Xie;Jianwei Xia","doi":"10.1109/TSMC.2024.3445881","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3445881","url":null,"abstract":"The concept of reachable set and state space ellipsoid is used in this article to determine the optimal safe range of the truck-trailer driving by allowing the constrained variables to move freely within a given range. A method of returning the truck to the desired position is proposed by analysing the movement trajectory of the truck. Two results are certified. The first result considers the issue of reachable set estimation (RSE) for the multirate sampled-data (MRSD) system in the aperiodic sampled-data framework based on the model knowledge. By constructing loop-based Lyapunov functional (LBLF), we obtain the sufficient condition that all the state trajectories are confined to target ellipsoid. This article also provides a computational method for an MRSD controller considering RSE. The second result provides the data-driven control tactics for the unknown sampled-data system to consider the RSE problem for the aperiodic sampled-data system, using only the noisy data. In addition, this article extends the data-driven control scheme to the design of MRSD controllers and ensures the stability of the system in agreement with the measured data. Simulation results show that the MRSD controller under both the model-driven method and the data-driven method is valid and achieves better control effect compared to the single-rate sampled-data (SRSD).","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-04DOI: 10.1109/TSMC.2024.3444007
Liang Cao;Yingnan Pan;Hongjing Liang;Choon Ki Ahn
This study explored the issue of decentralized adaptive event-triggered neural network (NN) control for nonlinear interconnected large-scale systems (LSSs) subjected to unknown measurement sensitivity and nonconstant control gains. Due to the impact of unknown measurement sensitivity, the real states of LSSs cannot be directly utilized. To overcome this difficulty, an effective adaptive feedback control scheme was developed. Subsequently, NNs were exploited to address the nonlinear terms and unknown nonconstant control gains. A modified first-order compensation system was developed to enhance the control performance in the presence of saturation nonlinearity. Furthermore, a significant dynamic event-triggered control (DETC) protocol was developed based on the saturation controller and measurement error, which reduced the number of controller updates. According to the Lyapunov stability theory, the proposed DETC-based decentralized adaptive protocol demonstrated that all signals were semiglobally uniformly ultimately bounded. The simulation examples illustrate the validity of the presented control protocol.
本研究探讨了在未知测量灵敏度和非恒定控制增益条件下,非线性互联大规模系统(LSS)的分散自适应事件触发神经网络(NN)控制问题。由于未知测量灵敏度的影响,无法直接利用 LSS 的真实状态。为了克服这一困难,我们开发了一种有效的自适应反馈控制方案。随后,利用 NN 解决了非线性项和未知非定常控制增益问题。开发了一种改进的一阶补偿系统,以提高饱和非线性情况下的控制性能。此外,基于饱和控制器和测量误差,还开发了一种重要的动态事件触发控制(DETC)协议,减少了控制器的更新次数。根据 Lyapunov 稳定性理论,所提出的基于 DETC 的分散自适应协议证明了所有信号都是半全局均匀最终有界的。仿真实例说明了所提出的控制协议的有效性。
{"title":"Event-Based Adaptive Neural Network Control for Large-Scale Systems With Nonconstant Control Gains and Unknown Measurement Sensitivity","authors":"Liang Cao;Yingnan Pan;Hongjing Liang;Choon Ki Ahn","doi":"10.1109/TSMC.2024.3444007","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3444007","url":null,"abstract":"This study explored the issue of decentralized adaptive event-triggered neural network (NN) control for nonlinear interconnected large-scale systems (LSSs) subjected to unknown measurement sensitivity and nonconstant control gains. Due to the impact of unknown measurement sensitivity, the real states of LSSs cannot be directly utilized. To overcome this difficulty, an effective adaptive feedback control scheme was developed. Subsequently, NNs were exploited to address the nonlinear terms and unknown nonconstant control gains. A modified first-order compensation system was developed to enhance the control performance in the presence of saturation nonlinearity. Furthermore, a significant dynamic event-triggered control (DETC) protocol was developed based on the saturation controller and measurement error, which reduced the number of controller updates. According to the Lyapunov stability theory, the proposed DETC-based decentralized adaptive protocol demonstrated that all signals were semiglobally uniformly ultimately bounded. The simulation examples illustrate the validity of the presented control protocol.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-04DOI: 10.1109/TSMC.2024.3446624
Yingwei Li;Xiang Feng;Huiqun Yu
Large-scale sparse multiobjective optimization problems (SMOPs) exist widely in real-world applications, and solving them requires algorithms that can handle high-dimensional decision space while simultaneously discovering the sparse distribution of Pareto optimal solutions. However, it is difficult for most existing multiobjective evolutionary algorithms (MOEAs) to get satisfactory results. To address this problem, this article proposes a dynamic knowledge-guided coevolutionary algorithm, which employs a cooperative coevolutionary framework tailored for large-scale SMOPs. Specifically, variable selection is performed initially for the dimension reduction, and two populations are evolved in the original and reduced decision spaces, respectively. After offspring generation, variable replacement is performed to precisely identify the sparse distribution of Pareto optimal solutions. Furthermore, a dynamic score update mechanism is designed based on the discovered sparsity knowledge, which aims to adjust the direction of evolution dynamically. The superiority of the proposed algorithm is demonstrated by applying it to a variety of benchmark test instances and real-world test instances with the comparison of five other state-of-the-art MOEAs.
{"title":"A Dynamic Knowledge-Guided Coevolutionary Algorithm for Large-Scale Sparse Multiobjective Optimization Problems","authors":"Yingwei Li;Xiang Feng;Huiqun Yu","doi":"10.1109/TSMC.2024.3446624","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3446624","url":null,"abstract":"Large-scale sparse multiobjective optimization problems (SMOPs) exist widely in real-world applications, and solving them requires algorithms that can handle high-dimensional decision space while simultaneously discovering the sparse distribution of Pareto optimal solutions. However, it is difficult for most existing multiobjective evolutionary algorithms (MOEAs) to get satisfactory results. To address this problem, this article proposes a dynamic knowledge-guided coevolutionary algorithm, which employs a cooperative coevolutionary framework tailored for large-scale SMOPs. Specifically, variable selection is performed initially for the dimension reduction, and two populations are evolved in the original and reduced decision spaces, respectively. After offspring generation, variable replacement is performed to precisely identify the sparse distribution of Pareto optimal solutions. Furthermore, a dynamic score update mechanism is designed based on the discovered sparsity knowledge, which aims to adjust the direction of evolution dynamically. The superiority of the proposed algorithm is demonstrated by applying it to a variety of benchmark test instances and real-world test instances with the comparison of five other state-of-the-art MOEAs.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article addresses the secure control issue for cyber-physical systems (CPSs) under aperiodic denial-of-service (DoS) attacks. Malicious DoS attacks disrupt the communication between the controller and the actuator. The finite attack resources of malevolent attackers are taken into consideration, and the DoS attacks are characterized using an aperiodic model. In contrast to prior results, the present study tackles the issues of security analysis and secure controller design by considering the attributes of the DoS attacks, instead of employing a switched system approach to address the aforementioned concerns. First, under aperiodic DoS attacks, sufficient criteria are established to guarantee that the closed-loop CPSs can attain asymptotical stability. Second, within a time-varying attack period, the relationship between the attack active interval and the attack silent interval is derived, if this relation is not satisfied, the stability of the system will deteriorate. Finally, a unified framework is developed to address the external disturbances and aperiodic DoS attacks. Sufficient criteria are introduced for evaluating the security of CPSs, and a corresponding secure control scheme is also designed. To verify the efficacy of the derived theory, a wheeled mobile robot system under aperiodic DoS attacks is illustrated.
本文探讨了网络物理系统(CPS)在非周期性拒绝服务(DoS)攻击下的安全控制问题。恶意 DoS 攻击会破坏控制器与执行器之间的通信。本研究考虑了恶意攻击者的有限攻击资源,并使用非周期性模型对 DoS 攻击进行了描述。与之前的研究结果不同,本研究通过考虑 DoS 攻击的属性来解决安全分析和安全控制器设计问题,而不是采用开关系统方法来解决上述问题。首先,在非周期性 DoS 攻击下,建立了充分的标准来保证闭环 CPS 达到渐近稳定性。其次,在时变攻击周期内,推导出攻击活跃间隔和攻击沉默间隔之间的关系,如果该关系不满足,系统的稳定性将恶化。最后,建立了一个统一的框架来解决外部干扰和非周期性 DoS 攻击问题。引入了评估 CPS 安全性的充分标准,并设计了相应的安全控制方案。为了验证推导理论的有效性,演示了在非周期性 DoS 攻击下的轮式移动机器人系统。
{"title":"Secure Control for Cyber–Physical Systems Subject to Aperiodic DoS Attacks","authors":"Liyuan Yin;Chengwei Wu;Hongming Zhu;Yucheng Chen;Quanqi Zhang","doi":"10.1109/TSMC.2024.3448395","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3448395","url":null,"abstract":"This article addresses the secure control issue for cyber-physical systems (CPSs) under aperiodic denial-of-service (DoS) attacks. Malicious DoS attacks disrupt the communication between the controller and the actuator. The finite attack resources of malevolent attackers are taken into consideration, and the DoS attacks are characterized using an aperiodic model. In contrast to prior results, the present study tackles the issues of security analysis and secure controller design by considering the attributes of the DoS attacks, instead of employing a switched system approach to address the aforementioned concerns. First, under aperiodic DoS attacks, sufficient criteria are established to guarantee that the closed-loop CPSs can attain asymptotical stability. Second, within a time-varying attack period, the relationship between the attack active interval and the attack silent interval is derived, if this relation is not satisfied, the stability of the system will deteriorate. Finally, a unified framework is developed to address the external disturbances and aperiodic DoS attacks. Sufficient criteria are introduced for evaluating the security of CPSs, and a corresponding secure control scheme is also designed. To verify the efficacy of the derived theory, a wheeled mobile robot system under aperiodic DoS attacks is illustrated.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-04DOI: 10.1109/TSMC.2024.3446822
Zhuanlian Ding;Lei Chen;Dengdi Sun;Xingyi Zhang;Wei Liu
Due to the curse of dimensionality and the unknown sparsity of search spaces, evolutionary algorithms face immense challenges in approximating optimal solutions for widely studied sparse large-scale multiobjective optimization problems (SLMOPs). Most bilevel encoding scheme (BLES)-based algorithms primarily focus on exploring sparsity in the binary layer, neglecting the real layer. Moreover, the interactions between two layers may be disregarded in these algorithms, thus the latent gap between the two encoding scales could lead to evolutionary ambiguity and performance limitations. To tackle the above issues, this article proposes a novel BLES-based collaborative algorithm using cross-scale knowledge fusion for SLMOPs. The algorithm integrates dual grouping and dual dimension reduction techniques via two subpopulations in a coevolutionary manner. Additionally, the interaction strategy is designed for each technique, leveraging the binary layer to guide the real layer, thus facilitating sufficient cross-scale cooperation. Extensive experiments on benchmark SLMOPs and four real-world applications validate the proposed algorithm’s strong competitiveness in solving SLMOPs compared to state-of-the-art algorithms.
{"title":"Efficient Sparse Large-Scale Multiobjective Optimization Based on Cross-Scale Knowledge Fusion","authors":"Zhuanlian Ding;Lei Chen;Dengdi Sun;Xingyi Zhang;Wei Liu","doi":"10.1109/TSMC.2024.3446822","DOIUrl":"https://doi.org/10.1109/TSMC.2024.3446822","url":null,"abstract":"Due to the curse of dimensionality and the unknown sparsity of search spaces, evolutionary algorithms face immense challenges in approximating optimal solutions for widely studied sparse large-scale multiobjective optimization problems (SLMOPs). Most bilevel encoding scheme (BLES)-based algorithms primarily focus on exploring sparsity in the binary layer, neglecting the real layer. Moreover, the interactions between two layers may be disregarded in these algorithms, thus the latent gap between the two encoding scales could lead to evolutionary ambiguity and performance limitations. To tackle the above issues, this article proposes a novel BLES-based collaborative algorithm using cross-scale knowledge fusion for SLMOPs. The algorithm integrates dual grouping and dual dimension reduction techniques via two subpopulations in a coevolutionary manner. Additionally, the interaction strategy is designed for each technique, leveraging the binary layer to guide the real layer, thus facilitating sufficient cross-scale cooperation. Extensive experiments on benchmark SLMOPs and four real-world applications validate the proposed algorithm’s strong competitiveness in solving SLMOPs compared to state-of-the-art algorithms.","PeriodicalId":48915,"journal":{"name":"IEEE Transactions on Systems Man Cybernetics-Systems","volume":null,"pages":null},"PeriodicalIF":8.6,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}