In an ordinary microgrid configuration, the required load changes from hour to hour. The power system firms determine the cost of energy at different times of day by considering the highest and lowest points of the consumption curve. This is referred to as time‐of‐use (TOU) pricing for power. The hourly basis load demand is divided into flexible and inflexible categories. Demand side management (DSM) lowers peak demand while rewarding customers for their participation based on load lowering. His rebuilds the whole load model on the pillars of demand cost movement. The research recommends a DSM methodology based on a combined intellect method to lower the total cost of employing loads in a microgrid (MG) structure while considering carbon tax as an unavoidable constraint to lower the emission of pollutants. This is because 40% of microgrid customers are willing to participate in the DSM scheme. The results obtained in each illustration demonstrate that the suggested DSM technique is suitable in terms of cost reduction. The generating cost was decreased from $15,488 to $15,354 when 0%–40% of clients engaged in the DSM programme. With just a 3% compromised increase in generation costs, a carbon price combined with economic emission dispatch reduced the pollutants emitted by up to 78%, from 70 to 15 tons.
{"title":"An optimal demand side management for microgrid cost minimization considering renewables","authors":"Swarupa Pinninti, Srinivasa Rao Sura","doi":"10.1002/oca.3205","DOIUrl":"https://doi.org/10.1002/oca.3205","url":null,"abstract":"In an ordinary microgrid configuration, the required load changes from hour to hour. The power system firms determine the cost of energy at different times of day by considering the highest and lowest points of the consumption curve. This is referred to as time‐of‐use (TOU) pricing for power. The hourly basis load demand is divided into flexible and inflexible categories. Demand side management (DSM) lowers peak demand while rewarding customers for their participation based on load lowering. His rebuilds the whole load model on the pillars of demand cost movement. The research recommends a DSM methodology based on a combined intellect method to lower the total cost of employing loads in a microgrid (MG) structure while considering carbon tax as an unavoidable constraint to lower the emission of pollutants. This is because 40% of microgrid customers are willing to participate in the DSM scheme. The results obtained in each illustration demonstrate that the suggested DSM technique is suitable in terms of cost reduction. The generating cost was decreased from $15,488 to $15,354 when 0%–40% of clients engaged in the DSM programme. With just a 3% compromised increase in generation costs, a carbon price combined with economic emission dispatch reduced the pollutants emitted by up to 78%, from 70 to 15 tons.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142257398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper introduces an adaptive optimal feedback control approach for discrete‐time anti‐linear systems (ALSs). The method utilizes sampling and measurable input–output data. By employing the Adaptive Dynamic Programming (ADP) technique, this study iteratively solves the discrete‐time algebraic Anti‐Riccati equation (AARE). Initially, an output feedback model is established for ALSs, and a model‐based algorithm is developed based on this model. The feasibility of this algorithm is based on the premise that the system dynamic information is completely known. Subsequently, for the scenario where the model is unknown, we further developed a model‐free ADP algorithm specifically designed to address optimal control problems in the presence of model uncertainty. With this algorithm, we achieve effective control optimization even in cases where detailed system dynamics information is lacking. Finally, through simulation experiments, we validated the feasibility and effectiveness of this algorithm.
本文介绍了离散时间反线性系统（ALS）的自适应优化反馈控制方法。该方法利用采样和可测量的输入输出数据。通过采用自适应动态编程（ADP）技术，本研究对离散时间代数反里卡提方程（AARE）进行了迭代求解。首先，建立了 ALS 的输出反馈模型，并在此基础上开发了基于模型的算法。该算法的可行性建立在系统动态信息完全已知的前提下。随后，针对模型未知的情况，我们进一步开发了一种无模型 ADP 算法，专门用于解决模型不确定情况下的最优控制问题。有了这种算法，即使在缺乏详细系统动态信息的情况下，我们也能实现有效的控制优化。最后，我们通过仿真实验验证了该算法的可行性和有效性。
{"title":"Output feedback control of anti‐linear systems using adaptive dynamic programming","authors":"Li Yu, Hai Wang","doi":"10.1002/oca.3203","DOIUrl":"https://doi.org/10.1002/oca.3203","url":null,"abstract":"This paper introduces an adaptive optimal feedback control approach for discrete‐time anti‐linear systems (ALSs). The method utilizes sampling and measurable input–output data. By employing the Adaptive Dynamic Programming (ADP) technique, this study iteratively solves the discrete‐time algebraic Anti‐Riccati equation (AARE). Initially, an output feedback model is established for ALSs, and a model‐based algorithm is developed based on this model. The feasibility of this algorithm is based on the premise that the system dynamic information is completely known. Subsequently, for the scenario where the model is unknown, we further developed a model‐free ADP algorithm specifically designed to address optimal control problems in the presence of model uncertainty. With this algorithm, we achieve effective control optimization even in cases where detailed system dynamics information is lacking. Finally, through simulation experiments, we validated the feasibility and effectiveness of this algorithm.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article suggests the methods to estimate the reachable set of Markovian jump neural networks (MJNNs) with time‐varying delays. By building up improved Lyapunov–Krasovskii functionals, the conditions that have less conservatism for the delay‐dependent can be obtained. Integral inequalities are employed to estimate the reachable set of MJNNs, resulting in more effective and conservative outcomes regarding time delays. Moreover, some mathematical techniques, the augmented zero equality approach, improve the results and eliminated the free variables. Two numerical examples and figures demonstrated that the proposed method was effective and provided less conservative results than previous research.
{"title":"Reachable set estimation of delayed Markovian jump neural networks based on an augmented zero equality approach","authors":"S. H. Kim, Y. J. Kim, S. H. Lee, O. M. Kwon","doi":"10.1002/oca.3206","DOIUrl":"https://doi.org/10.1002/oca.3206","url":null,"abstract":"This article suggests the methods to estimate the reachable set of Markovian jump neural networks (MJNNs) with time‐varying delays. By building up improved Lyapunov–Krasovskii functionals, the conditions that have less conservatism for the delay‐dependent can be obtained. Integral inequalities are employed to estimate the reachable set of MJNNs, resulting in more effective and conservative outcomes regarding time delays. Moreover, some mathematical techniques, the augmented zero equality approach, improve the results and eliminated the free variables. Two numerical examples and figures demonstrated that the proposed method was effective and provided less conservative results than previous research.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohamed Abd‐El‐Hakeem Mohamed, Salah Kamel, Hamed Zeinoddini‐Meymand
This article focuses on utilizing intelligent H‐∞ synthesis to create a controller for a wind generation system linked to a power system via a static VAR compensator. The purpose of the control approach is twofold: firstly, to enhance the system's dynamic reactions to turbulent wind variations, and secondly, to elevate the quality of power generation. To achieve optimal control of the system, an Artificial Neural Network (ANN) is combined with the H‐∞ control method. This integration leverages the strengths of both ANN, which excels in modeling and optimization, and H‐∞, which prioritizes robustness to enhance dynamic performance. The resultant control strategy, connecting ANN and H‐∞, demonstrates the capability to deliver superior performance, precise tracking, and minimal overshooting. This approach is adaptive to changing control signals and exhibits robust characteristics, effectively managing uncertainties and disturbances. Through a simulation study, the effectiveness of this presented technique is showcased in enhancing the dynamic response of the system when compared to alternative control strategies.
本文的重点是利用智能 H-∞ 综合法为通过静态 VAR 补偿器与电力系统相连的风力发电系统创建一个控制器。该控制方法有两个目的：一是增强系统对风力湍流变化的动态响应，二是提高发电质量。为了实现系统的最优控制，人工神经网络（ANN）与 H-∞ 控制方法相结合。人工神经网络擅长建模和优化，而 H-∞ 则优先考虑鲁棒性，以提高动态性能。将 ANN 和 H-∞ 相结合的控制策略能够提供卓越的性能、精确的跟踪和最小的过冲。这种方法能适应不断变化的控制信号，并表现出鲁棒性特征，能有效管理不确定性和干扰。通过模拟研究，与其他控制策略相比，该技术在增强系统动态响应方面的有效性得到了展示。
{"title":"Intelligent integration of ANN and H‐infinity control for optimal enhanced performance of a wind generation unit linked to a power system","authors":"Mohamed Abd‐El‐Hakeem Mohamed, Salah Kamel, Hamed Zeinoddini‐Meymand","doi":"10.1002/oca.3199","DOIUrl":"https://doi.org/10.1002/oca.3199","url":null,"abstract":"This article focuses on utilizing intelligent H‐∞ synthesis to create a controller for a wind generation system linked to a power system via a static VAR compensator. The purpose of the control approach is twofold: firstly, to enhance the system's dynamic reactions to turbulent wind variations, and secondly, to elevate the quality of power generation. To achieve optimal control of the system, an Artificial Neural Network (ANN) is combined with the H‐∞ control method. This integration leverages the strengths of both ANN, which excels in modeling and optimization, and H‐∞, which prioritizes robustness to enhance dynamic performance. The resultant control strategy, connecting ANN and H‐∞, demonstrates the capability to deliver superior performance, precise tracking, and minimal overshooting. This approach is adaptive to changing control signals and exhibits robust characteristics, effectively managing uncertainties and disturbances. Through a simulation study, the effectiveness of this presented technique is showcased in enhancing the dynamic response of the system when compared to alternative control strategies.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
An adaptive neural network (NN) based optimal saturation control scheme is investigated for single‐phase grid‐connected photovoltaic (PV) systems by incorporating dynamic surface control (DSC) and adaptive dynamic programming (ADP) based on the backstepping control design framework. For each backstepping step, a critic‐actor architecture is constructed via reinforcement learning (RL), and the PV system is optimized according to the cost function in the architecture. Due to the nonlinearity, it is difficult to solve the Hamilton–Jacobi–Bellman (HJB) equation. The neural networks (NNs) are employed to approximate the solution of the HJB equation such that the optimal virtual control and the actual controller are obtained. By considering control input symmetric saturation nonlinearity link, constraints on pulse width modulation (PWM) are ensured. On this basis, the combination of backstepping control design and dynamic surface technique is used to overcome the shortcomings of “differential explosion” and simplify calculations. Based on the Lyapunov method, the stability analysis proves that all signals of the closed‐loop PV systems are semiglobally uniformly ultimately bounded (SGUUB). Simulation experiments and comparative results are given to verify the efficacy of the studied control strategy.
{"title":"Adaptive neural network dynamic surface optimal saturation control for single‐phase grid‐connected photovoltaic systems","authors":"Hongyang Zhang, Tiechao Wang","doi":"10.1002/oca.3204","DOIUrl":"https://doi.org/10.1002/oca.3204","url":null,"abstract":"An adaptive neural network (NN) based optimal saturation control scheme is investigated for single‐phase grid‐connected photovoltaic (PV) systems by incorporating dynamic surface control (DSC) and adaptive dynamic programming (ADP) based on the backstepping control design framework. For each backstepping step, a critic‐actor architecture is constructed via reinforcement learning (RL), and the PV system is optimized according to the cost function in the architecture. Due to the nonlinearity, it is difficult to solve the Hamilton–Jacobi–Bellman (HJB) equation. The neural networks (NNs) are employed to approximate the solution of the HJB equation such that the optimal virtual control and the actual controller are obtained. By considering control input symmetric saturation nonlinearity link, constraints on pulse width modulation (PWM) are ensured. On this basis, the combination of backstepping control design and dynamic surface technique is used to overcome the shortcomings of “differential explosion” and simplify calculations. Based on the Lyapunov method, the stability analysis proves that all signals of the closed‐loop PV systems are semiglobally uniformly ultimately bounded (SGUUB). Simulation experiments and comparative results are given to verify the efficacy of the studied control strategy.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The expedience of materials processing is of great significance and increased the industrial interest in meeting the needs of contemporary engineering applications. The inspection of mechanical properties is extensively explored by scientists, but the prediction of properties with the deep model is limited. This article presents an optimized deep residual network (DRN) to predict mechanical properties of materials. The quantile normalization is applied for improved processing. The DRN is pre‐trained with an optimization model for initializing the best set of attributes and tuning the parameters of the model. Here, Taylor‐Smart Flower Optimization Algorithm (Taylor‐SFOA) is adapted for training DRN by tuning optimum weights. The proposed Taylor‐SFOA helps to effectively offer precise mapping amidst mechanical properties and processing parameters. The optimal features are selected with the Ruzicka and Motyka. The selected features are fused with a dice coefficient to choose distinct features for attaining effective performance. The method yielded better outcomes with improved generalization. The Taylor‐SFOA‐based DRN provided better outcomes with smallest Mean absolute error (MAE) of 0.049, Mean square error (MSE) of 0.116, Root Mean square error (RMSE) of 0.340, memory footprint of 37.700 MB, and training time of 9.633 Sec.
{"title":"Taylor‐based smart flower optimization algorithm with the deep residual network to predict mechanical materials properties","authors":"Oshin Sharma, Deepak Sharma","doi":"10.1002/oca.3195","DOIUrl":"https://doi.org/10.1002/oca.3195","url":null,"abstract":"The expedience of materials processing is of great significance and increased the industrial interest in meeting the needs of contemporary engineering applications. The inspection of mechanical properties is extensively explored by scientists, but the prediction of properties with the deep model is limited. This article presents an optimized deep residual network (DRN) to predict mechanical properties of materials. The quantile normalization is applied for improved processing. The DRN is pre‐trained with an optimization model for initializing the best set of attributes and tuning the parameters of the model. Here, Taylor‐Smart Flower Optimization Algorithm (Taylor‐SFOA) is adapted for training DRN by tuning optimum weights. The proposed Taylor‐SFOA helps to effectively offer precise mapping amidst mechanical properties and processing parameters. The optimal features are selected with the Ruzicka and Motyka. The selected features are fused with a dice coefficient to choose distinct features for attaining effective performance. The method yielded better outcomes with improved generalization. The Taylor‐SFOA‐based DRN provided better outcomes with smallest Mean absolute error (MAE) of 0.049, Mean square error (MSE) of 0.116, Root Mean square error (RMSE) of 0.340, memory footprint of 37.700 MB, and training time of 9.633 Sec.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
SummaryIn this article, an event‐triggered optimal control method based on prescribed performance is investigated for a constrained two‐link robotic manipulator system. To satisfy the performance constraints of the system, an equated error model of the dynamics model is established by means of two auxiliary functions and the prescribed performance technique. A predictive controller based on an adaptive event triggering mechanism is obtained by solving a constraint optimization problem for this transformed error model, and the triggering threshold can be adjusted based on real‐time changes of the system. This controller realizes the tracking of the joint angle with the desired angle and meets the prescribed performance conditions. Finally, the control algorithm is shown to be an effective method for improving control performance through numerical simulations and comparison with other prescribed performance functions.
{"title":"Event‐triggered optimal control based on prescribed performance for a two‐link robotic manipulator","authors":"Xinying Chen, Baili Su","doi":"10.1002/oca.3200","DOIUrl":"https://doi.org/10.1002/oca.3200","url":null,"abstract":"SummaryIn this article, an event‐triggered optimal control method based on prescribed performance is investigated for a constrained two‐link robotic manipulator system. To satisfy the performance constraints of the system, an equated error model of the dynamics model is established by means of two auxiliary functions and the prescribed performance technique. A predictive controller based on an adaptive event triggering mechanism is obtained by solving a constraint optimization problem for this transformed error model, and the triggering threshold can be adjusted based on real‐time changes of the system. This controller realizes the tracking of the joint angle with the desired angle and meets the prescribed performance conditions. Finally, the control algorithm is shown to be an effective method for improving control performance through numerical simulations and comparison with other prescribed performance functions.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chong Liu, Yalun Li, Zhongxing Duan, Zhousheng Chu, Zongfang Ma
This article solves the robust tracking problem (RTP) for a type of partially unknown nonlinear systems with asymmetric constrained‐input by utilizing an improved adaptive dynamic programming (ADP) method based on experience replay (ER) technique and critic‐only neural network (NN). Initially, an identifier neural network (INN) is used to identify the unknown part of the system dynamics. Subsequently, the tracking error and the desired trajectory are used to construct an augmented system, so that the robust tracking problem (RTP) is transformed into a constrained optimal control problem (OCP). It is proved that the designed control policy of OCP can make the tracking error to be uniformly ultimately bounded (UUB). Then, using the framework of ADP and critic‐only NN to solve the derived Hamilton–Jacobi–Bellman equation (HJBE). The NN weight regulation law is partially derived by using gradient descent algorithm (GDA) and then is improved by using the ER technique and the Lyapunov stability theory, which no longer need the conditions of persistence of excitation (PE) and the initial admissible control. Besides, the total system states and NN weights are proved to be closed‐loop stable by utilizing the Lyapunov technique. Finally, through two simulation examples, it is demonstrated that the proposed control scheme is effective.
本文利用基于经验重放（ER）技术和纯批判神经网络（NN）的改进型自适应动态编程（ADP）方法，解决了具有非对称约束输入的部分未知非线性系统的鲁棒跟踪问题（RTP）。首先，使用识别器神经网络（INN）来识别系统动态的未知部分。随后，利用跟踪误差和期望轨迹构建一个增强系统，从而将鲁棒跟踪问题（RTP）转化为约束最优控制问题（OCP）。研究证明，所设计的 OCP 控制策略能使跟踪误差最终均匀受限（UUB）。然后，利用 ADP 和唯批判 NN 框架求解推导出的汉密尔顿-雅各比-贝尔曼方程（HJBE）。利用梯度下降算法（GDA）推导出部分 NN 权重调节规律，然后利用 ER 技术和 Lyapunov 稳定性理论对其进行改进，使其不再需要激励持续性（PE）和初始容许控制等条件。此外，利用 Lyapunov 技术证明了系统总状态和 NN 权重的闭环稳定性。最后，通过两个仿真实例证明了所提出的控制方案是有效的。
{"title":"Experience replay based online adaptive robust tracking control for partially unknown nonlinear systems with asymmetric constrained‐input","authors":"Chong Liu, Yalun Li, Zhongxing Duan, Zhousheng Chu, Zongfang Ma","doi":"10.1002/oca.3202","DOIUrl":"https://doi.org/10.1002/oca.3202","url":null,"abstract":"This article solves the robust tracking problem (RTP) for a type of partially unknown nonlinear systems with asymmetric constrained‐input by utilizing an improved adaptive dynamic programming (ADP) method based on experience replay (ER) technique and critic‐only neural network (NN). Initially, an identifier neural network (INN) is used to identify the unknown part of the system dynamics. Subsequently, the tracking error and the desired trajectory are used to construct an augmented system, so that the robust tracking problem (RTP) is transformed into a constrained optimal control problem (OCP). It is proved that the designed control policy of OCP can make the tracking error to be uniformly ultimately bounded (UUB). Then, using the framework of ADP and critic‐only NN to solve the derived Hamilton–Jacobi–Bellman equation (HJBE). The NN weight regulation law is partially derived by using gradient descent algorithm (GDA) and then is improved by using the ER technique and the Lyapunov stability theory, which no longer need the conditions of persistence of excitation (PE) and the initial admissible control. Besides, the total system states and NN weights are proved to be closed‐loop stable by utilizing the Lyapunov technique. Finally, through two simulation examples, it is demonstrated that the proposed control scheme is effective.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
SummaryThe article aims at solving a cooperative hunting problem for multiple unmanned surface vehicles (USVs) subject to constrained kinematics. In order to cooperatively trap the evader into the hunting domain, a velocity model with control variable for the pursuers is firstly proposed according to the Apollonius circle. Then, a flexible self‐organizing control strategy is developed, which enables the pursuers to approach the evader while forming an encirclement. The pursuers can dynamically adapt their strategies in real‐time by choosing the optimal control variable. Additionally, take into account the limitation imposed on the vessel's motion, the optimal control variable with constraint can be obtained by using the particle swarm optimization with log‐barrier method. The simulation results ultimately demonstrate the validity and superiority of the proposed cooperative hunting algorithm.
{"title":"Self‐organizing cooperative hunting for unmanned surface vehicles with constrained kinematics","authors":"Qun Deng, Yan Peng, Tingke Mo, Jinduo Wang, Dong Qu, Yangmin Xie","doi":"10.1002/oca.3194","DOIUrl":"https://doi.org/10.1002/oca.3194","url":null,"abstract":"SummaryThe article aims at solving a cooperative hunting problem for multiple unmanned surface vehicles (USVs) subject to constrained kinematics. In order to cooperatively trap the evader into the hunting domain, a velocity model with control variable for the pursuers is firstly proposed according to the Apollonius circle. Then, a flexible self‐organizing control strategy is developed, which enables the pursuers to approach the evader while forming an encirclement. The pursuers can dynamically adapt their strategies in real‐time by choosing the optimal control variable. Additionally, take into account the limitation imposed on the vessel's motion, the optimal control variable with constraint can be obtained by using the particle swarm optimization with log‐barrier method. The simulation results ultimately demonstrate the validity and superiority of the proposed cooperative hunting algorithm.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142219643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Christina Schenk, Aditya Vasudevan, Maciej Haranczyk, Ignacio Romero
Mathematical and computational tools have proven to be reliable in decision‐making processes. In recent times, in particular, machine learning‐based methods are becoming increasingly popular as advanced support tools. When dealing with control problems, reinforcement learning has been applied to decision‐making in several applications, most notably in games. The success of these methods in finding solutions to complex problems motivates the exploration of new areas where they can be employed to overcome current difficulties. In this article, we explore the use of automatic control strategies to initial boundary value problems in thermal and disease transport. Specifically, in this work, we adapt an existing reinforcement learning algorithm using a stochastic policy gradient method and we introduce two novel reward functions to drive the flow of the transported field. The new model‐based framework exploits the interactions between a reaction‐diffusion model and the modified agent. The results show that certain controls can be implemented successfully in these applications, although model simplifications had to be assumed.
{"title":"Model‐based reinforcement learning control of reaction‐diffusion problems","authors":"Christina Schenk, Aditya Vasudevan, Maciej Haranczyk, Ignacio Romero","doi":"10.1002/oca.3196","DOIUrl":"https://doi.org/10.1002/oca.3196","url":null,"abstract":"Mathematical and computational tools have proven to be reliable in decision‐making processes. In recent times, in particular, machine learning‐based methods are becoming increasingly popular as advanced support tools. When dealing with control problems, reinforcement learning has been applied to decision‐making in several applications, most notably in games. The success of these methods in finding solutions to complex problems motivates the exploration of new areas where they can be employed to overcome current difficulties. In this article, we explore the use of automatic control strategies to initial boundary value problems in thermal and disease transport. Specifically, in this work, we adapt an existing reinforcement learning algorithm using a stochastic policy gradient method and we introduce two novel reward functions to drive the flow of the transported field. The new model‐based framework exploits the interactions between a reaction‐diffusion model and the modified agent. The results show that certain controls can be implemented successfully in these applications, although model simplifications had to be assumed.","PeriodicalId":501055,"journal":{"name":"Optimal Control Applications and Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141946346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：