The complexity of cloud environments challenges secure resource management,especially for intrusion detection systems(IDS).Existing strategies struggle to balance efficiency,cost fairness,and threat resilience.This pa...The complexity of cloud environments challenges secure resource management,especially for intrusion detection systems(IDS).Existing strategies struggle to balance efficiency,cost fairness,and threat resilience.This paper proposes an innovative approach to managing cloud resources through the integration of a genetic algorithm(GA)with a“double auction”method.This approach seeks to enhance security and efficiency by aligning buyers and sellers within an intelligent market framework.It guarantees equitable pricing while utilizing resources efficiently and optimizing advantages for all stakeholders.The GA functions as an intelligent search mechanism that identifies optimal combinations of bids from users and suppliers,addressing issues arising from the intricacies of cloud systems.Analyses proved that our method surpasses previous strategies,particularly in terms of price accuracy,speed,and the capacity to manage large-scale activities,critical factors for real-time cybersecurity systems,such as IDS.Our research integrates artificial intelligence-inspired evolutionary algorithms with market-driven methods to develop intelligent resource management systems that are secure,scalable,and adaptable to evolving risks,such as process innovation.展开更多
Task assignment is critical for multiple unmanned aerial vehicles(UAVs)to perform suppressive jamming against radar network.However,under abrupt state changes of enemy radars,centralized methods often incur high compu...Task assignment is critical for multiple unmanned aerial vehicles(UAVs)to perform suppressive jamming against radar network.However,under abrupt state changes of enemy radars,centralized methods often incur high computational complexity and exhibit limited robustness,rendering them unsuitable for rapid task re-assignment.To address these challenges,an adaptive multi-UAV task assignment and re-assignment scheme for suppressive jamming against intermittent radar network is proposed.Specifically,the system is comprehensively modeled by integrating a motion model describing high-value target trajectory,a reconnaissance model detecting radar state transitions,and a suppressive jamming model characterizing the matching relationships between UAVs and radars.The problem is formulated as a dynamic integer program with time-varying constraints.To solve this,a distributed auction-based task assignment and re-assignment algorithm is proposed,enabling task assignment and re-assignment triggered by sudden radar activations or deactivations.Simulation results demonstrate that the proposed approach achieves jamming performance comparable to centralized methods,outperforms traditional fixed and random strategies,and enables re-assignment in response to abrupt radar state changes.展开更多
An improved genetic algorithm is proposed to solve the problem of bad real-time performance or inability to get a global optimal/better solution when applying single-item auction (SIA) method or combinatorial auctio...An improved genetic algorithm is proposed to solve the problem of bad real-time performance or inability to get a global optimal/better solution when applying single-item auction (SIA) method or combinatorial auction method to multi-robot task allocation. The genetic algorithm based combinatorial auction (GACA) method which combines the basic-genetic algorithm with a new concept of ringed chromosome is used to solve the winner determination problem (WDP) of combinatorial auction. The simulation experiments are conducted in OpenSim, a multi-robot simulator. The results show that GACA can get a satisfying solution in a reasonable shot time, and compared with SIA or parthenogenesis algorithm combinatorial auction (PGACA) method, it is the simplest and has higher search efficiency, also, GACA can get a global better/optimal solution and satisfy the high real-time requirement of multi-robot task allocation.展开更多
An extension of 2-D assignment approach is proposed for measurement-to-target association for improving multiple targets vector miss distance measurement accuracy.When the multiple targets move so closely,the measurem...An extension of 2-D assignment approach is proposed for measurement-to-target association for improving multiple targets vector miss distance measurement accuracy.When the multiple targets move so closely,the measurements can not be fully resolved due to finite resolution.The proposed method adopts an auction algorithm to compute the feasible measurement-to-target assignment with unresolved measurements for solving this 2-D assignment problem.Computer simulation results demonstrate the effectiveness and feasibility of this method.展开更多
Winner determination is one of the main challenges in combinatorial auctions. However, not much work has been done to solve this problem in the case of reverse auctions using evolutionary techniques. This has motivate...Winner determination is one of the main challenges in combinatorial auctions. However, not much work has been done to solve this problem in the case of reverse auctions using evolutionary techniques. This has motivated us to propose an improvement of a genetic algorithm based method, we have previously proposed, to address two important issues in the context of combinatorial reverse auctions: determining the winner(s) in a reasonable processing time, and reducing the procurement cost. In order to evaluate the performance of our proposed method in practice, we conduct several experiments on combinatorial reverse auctions instances. The results we report in this paper clearly demonstrate the efficiency of our new method in terms of processing time and procurement cost.展开更多
摘要The complexity of cloud environments challenges secure resource management,especially for intrusion detection systems(IDS).Existing strategies struggle to balance efficiency,cost fairness,and threat resilience.This paper proposes an innovative approach to managing cloud resources through the integration of a genetic algorithm(GA)with a“double auction”method.This approach seeks to enhance security and efficiency by aligning buyers and sellers within an intelligent market framework.It guarantees equitable pricing while utilizing resources efficiently and optimizing advantages for all stakeholders.The GA functions as an intelligent search mechanism that identifies optimal combinations of bids from users and suppliers,addressing issues arising from the intricacies of cloud systems.Analyses proved that our method surpasses previous strategies,particularly in terms of price accuracy,speed,and the capacity to manage large-scale activities,critical factors for real-time cybersecurity systems,such as IDS.Our research integrates artificial intelligence-inspired evolutionary algorithms with market-driven methods to develop intelligent resource management systems that are secure,scalable,and adaptable to evolving risks,such as process innovation.
基金supported by Qianyuan Laboratoryby the China Scholarship Council(CSC)(Grant No.202506070040)by the National Key Research and Development Program of China(Grant No.2022YFB3902400)。
摘要Task assignment is critical for multiple unmanned aerial vehicles(UAVs)to perform suppressive jamming against radar network.However,under abrupt state changes of enemy radars,centralized methods often incur high computational complexity and exhibit limited robustness,rendering them unsuitable for rapid task re-assignment.To address these challenges,an adaptive multi-UAV task assignment and re-assignment scheme for suppressive jamming against intermittent radar network is proposed.Specifically,the system is comprehensively modeled by integrating a motion model describing high-value target trajectory,a reconnaissance model detecting radar state transitions,and a suppressive jamming model characterizing the matching relationships between UAVs and radars.The problem is formulated as a dynamic integer program with time-varying constraints.To solve this,a distributed auction-based task assignment and re-assignment algorithm is proposed,enabling task assignment and re-assignment triggered by sudden radar activations or deactivations.Simulation results demonstrate that the proposed approach achieves jamming performance comparable to centralized methods,outperforms traditional fixed and random strategies,and enables re-assignment in response to abrupt radar state changes.
基金Sponsored by Excellent Young Scholars Research Fund of Beijing Institute of Technology(00Y03-13)
摘要An improved genetic algorithm is proposed to solve the problem of bad real-time performance or inability to get a global optimal/better solution when applying single-item auction (SIA) method or combinatorial auction method to multi-robot task allocation. The genetic algorithm based combinatorial auction (GACA) method which combines the basic-genetic algorithm with a new concept of ringed chromosome is used to solve the winner determination problem (WDP) of combinatorial auction. The simulation experiments are conducted in OpenSim, a multi-robot simulator. The results show that GACA can get a satisfying solution in a reasonable shot time, and compared with SIA or parthenogenesis algorithm combinatorial auction (PGACA) method, it is the simplest and has higher search efficiency, also, GACA can get a global better/optimal solution and satisfy the high real-time requirement of multi-robot task allocation.
摘要An extension of 2-D assignment approach is proposed for measurement-to-target association for improving multiple targets vector miss distance measurement accuracy.When the multiple targets move so closely,the measurements can not be fully resolved due to finite resolution.The proposed method adopts an auction algorithm to compute the feasible measurement-to-target assignment with unresolved measurements for solving this 2-D assignment problem.Computer simulation results demonstrate the effectiveness and feasibility of this method.
摘要Winner determination is one of the main challenges in combinatorial auctions. However, not much work has been done to solve this problem in the case of reverse auctions using evolutionary techniques. This has motivated us to propose an improvement of a genetic algorithm based method, we have previously proposed, to address two important issues in the context of combinatorial reverse auctions: determining the winner(s) in a reasonable processing time, and reducing the procurement cost. In order to evaluate the performance of our proposed method in practice, we conduct several experiments on combinatorial reverse auctions instances. The results we report in this paper clearly demonstrate the efficiency of our new method in terms of processing time and procurement cost.