A new strategy is presented to solve robust multi-physics multi-objective optimization problem known as improved multi-objective collaborative optimization （IMOCO） and its extension improved multi-objective robust c...A new strategy is presented to solve robust multi-physics multi-objective optimization problem known as improved multi-objective collaborative optimization （IMOCO） and its extension improved multi-objective robust collaborative （IMORCO）. In this work, the proposed IMORCO approach combined the IMOCO method, the worst possible point （WPP） constraint cuts and the Genetic algorithm NSGA-II type as an optimizer in order to solve the robust optimization problem of multi-physics of microstructures with uncertainties. The optimization problem is hierarchically decomposed into two levels： a microstructure level, and a disciplines levels, For validation purposes, two examples were selected： a numerical example, and an engineering example of capacitive micro machined ultrasonic transducers （CMUT） type. The obtained results are compared with those obtained from robust non-distributed and distributed optimization approach, non-distributed multi-objective robust optimization （NDMORO） and multi-objective collaborative robust optimization （McRO）, respectively. Results obtained from the application of the IMOCO approach to an optimization problem of a CMUT cell have reduced the CPU time by 44% ensuring a Pareto front close to the reference non-distributed multi-objective optimization （NDMO） approach （mahalanobis distance, D2M =0.9503 and overall spread, So=0.2309）. In addition, the consideration of robustness in IMORCO approach applied to a CMUT cell of optimization problem under interval uncertainty has reduced the CPU time by 23% keeping a robust Pareto front overlaps with that obtained by the robust NDMORO approach （D2M =10.3869 and So=0.0537）.展开更多
深度强化学习算法以数据为驱动,且不依赖具体模型,能有效应对虚拟电厂运营中的复杂性问题。然而,现有算法难以严格执行操作约束,在实际系统中的应用受到限制。为了克服这一问题,提出了一种基于深度强化学习的改进深度Q网络(improved dee...深度强化学习算法以数据为驱动,且不依赖具体模型,能有效应对虚拟电厂运营中的复杂性问题。然而,现有算法难以严格执行操作约束,在实际系统中的应用受到限制。为了克服这一问题,提出了一种基于深度强化学习的改进深度Q网络(improved deep Q-network,MDQN)算法。该算法将深度神经网络表达为混合整数规划公式,以确保在动作空间内严格执行所有操作约束,从而保证了所制定的调度在实际运行中的可行性。此外,还进行了敏感性分析,以灵活地调整超参数,为算法的优化提供了更大的灵活性。最后,通过对比实验验证了MDQN算法的优越性能。该算法为应对虚拟电厂运营中的复杂性问题提供了一种有效的解决方案。展开更多
The industrial Internet of Things(IIoT)is a new indus-trial idea that combines the latest information and communica-tion technologies with the industrial economy.In this paper,a cloud control structure is designed for...The industrial Internet of Things(IIoT)is a new indus-trial idea that combines the latest information and communica-tion technologies with the industrial economy.In this paper,a cloud control structure is designed for IIoT in cloud-edge envi-ronment with three modes of 5G.For 5G based IIoT,the time sensitive network(TSN)service is introduced in transmission network.A 5G logical TSN bridge is designed to transport TSN streams over 5G framework to achieve end-to-end configuration.For a transmission control protocol(TCP)model with nonlinear disturbance,time delay and uncertainties,a robust adaptive fuzzy sliding mode controller(AFSMC)is given with control rule parameters.IIoT workflows are made up of a series of subtasks that are linked by the dependencies between sensor datasets and task flows.IIoT workflow scheduling is a non-deterministic polynomial(NP)-hard problem in cloud-edge environment.An adaptive and non-local-convergent particle swarm optimization(ANCPSO)is designed with nonlinear inertia weight to avoid falling into local optimum,which can reduce the makespan and cost dramatically.Simulation and experiments demonstrate that ANCPSO has better performances than other classical algo-rithms.展开更多
电热气互联能源系统(integrated power,heat and natural gas energy system,IPHNGES)对促进多能协同互补互济、实现系统低碳经济运行、提高系统灵活性调度潜力具有重要意义,已成为能源互联网的重要发展方向。综合考虑了多异构能源系统...电热气互联能源系统(integrated power,heat and natural gas energy system,IPHNGES)对促进多能协同互补互济、实现系统低碳经济运行、提高系统灵活性调度潜力具有重要意义,已成为能源互联网的重要发展方向。综合考虑了多异构能源系统多元化互联方式,在传统能源转换单元基础上建立多种改进的具有连续调节能力、灵活性潜质更高的设备模型,模型更加精细化、实用化。提出了计及电力、热力、天然气子异构能源系统的统一稳态潮流模型,以IPHNGES碳排放、运行经济成本最小化为目标,基于多目标模糊优化方法对IPHNGES进行动态环保经济协同灵活性调度。最后,IPHNGES算例结果表明所提模型与方法的合理性与可行性。展开更多
文摘A new strategy is presented to solve robust multi-physics multi-objective optimization problem known as improved multi-objective collaborative optimization （IMOCO） and its extension improved multi-objective robust collaborative （IMORCO）. In this work, the proposed IMORCO approach combined the IMOCO method, the worst possible point （WPP） constraint cuts and the Genetic algorithm NSGA-II type as an optimizer in order to solve the robust optimization problem of multi-physics of microstructures with uncertainties. The optimization problem is hierarchically decomposed into two levels： a microstructure level, and a disciplines levels, For validation purposes, two examples were selected： a numerical example, and an engineering example of capacitive micro machined ultrasonic transducers （CMUT） type. The obtained results are compared with those obtained from robust non-distributed and distributed optimization approach, non-distributed multi-objective robust optimization （NDMORO） and multi-objective collaborative robust optimization （McRO）, respectively. Results obtained from the application of the IMOCO approach to an optimization problem of a CMUT cell have reduced the CPU time by 44% ensuring a Pareto front close to the reference non-distributed multi-objective optimization （NDMO） approach （mahalanobis distance, D2M =0.9503 and overall spread, So=0.2309）. In addition, the consideration of robustness in IMORCO approach applied to a CMUT cell of optimization problem under interval uncertainty has reduced the CPU time by 23% keeping a robust Pareto front overlaps with that obtained by the robust NDMORO approach （D2M =10.3869 and So=0.0537）.
文摘深度强化学习算法以数据为驱动,且不依赖具体模型,能有效应对虚拟电厂运营中的复杂性问题。然而,现有算法难以严格执行操作约束,在实际系统中的应用受到限制。为了克服这一问题,提出了一种基于深度强化学习的改进深度Q网络(improved deep Q-network,MDQN)算法。该算法将深度神经网络表达为混合整数规划公式,以确保在动作空间内严格执行所有操作约束,从而保证了所制定的调度在实际运行中的可行性。此外,还进行了敏感性分析,以灵活地调整超参数,为算法的优化提供了更大的灵活性。最后,通过对比实验验证了MDQN算法的优越性能。该算法为应对虚拟电厂运营中的复杂性问题提供了一种有效的解决方案。
文摘The industrial Internet of Things(IIoT)is a new indus-trial idea that combines the latest information and communica-tion technologies with the industrial economy.In this paper,a cloud control structure is designed for IIoT in cloud-edge envi-ronment with three modes of 5G.For 5G based IIoT,the time sensitive network(TSN)service is introduced in transmission network.A 5G logical TSN bridge is designed to transport TSN streams over 5G framework to achieve end-to-end configuration.For a transmission control protocol(TCP)model with nonlinear disturbance,time delay and uncertainties,a robust adaptive fuzzy sliding mode controller(AFSMC)is given with control rule parameters.IIoT workflows are made up of a series of subtasks that are linked by the dependencies between sensor datasets and task flows.IIoT workflow scheduling is a non-deterministic polynomial(NP)-hard problem in cloud-edge environment.An adaptive and non-local-convergent particle swarm optimization(ANCPSO)is designed with nonlinear inertia weight to avoid falling into local optimum,which can reduce the makespan and cost dramatically.Simulation and experiments demonstrate that ANCPSO has better performances than other classical algo-rithms.
文摘电热气互联能源系统(integrated power,heat and natural gas energy system,IPHNGES)对促进多能协同互补互济、实现系统低碳经济运行、提高系统灵活性调度潜力具有重要意义,已成为能源互联网的重要发展方向。综合考虑了多异构能源系统多元化互联方式,在传统能源转换单元基础上建立多种改进的具有连续调节能力、灵活性潜质更高的设备模型,模型更加精细化、实用化。提出了计及电力、热力、天然气子异构能源系统的统一稳态潮流模型,以IPHNGES碳排放、运行经济成本最小化为目标,基于多目标模糊优化方法对IPHNGES进行动态环保经济协同灵活性调度。最后,IPHNGES算例结果表明所提模型与方法的合理性与可行性。
