The shift scheduling system of the transmission has an important effect on the dynamic and economic performance of hybrid vehicles. In this work, shift scheduling strategies are developed for parallel hybrid construct...The shift scheduling system of the transmission has an important effect on the dynamic and economic performance of hybrid vehicles. In this work, shift scheduling strategies are developed for parallel hybrid construction vehicles. The effect of power distribution and direction on shift characteristics of the parallel hybrid vehicle with operating loads is evaluated, which must be considered for optimal shift control. A power distribution factor is defined to accurately describe the power distribution and direction in various parallel hybrid systems. This paper proposes a Levenberg-Marquardt algorithm optimized neural network shift scheduling strategy. The methodology contains two objective functions, it is a dynamic combination of a dynamic shift schedule for optimal vehicle acceleration, and an energy-efficient shift schedule for optimal powertrain efficiency. The study is performed on a test bench under typical operating conditions of a wheel loader. The experimental results show that the proposed strategies offer effective and competitive shift performance.展开更多
The hybrid flow shop scheduling problem with unrelated parallel machine is a typical NP-hard combinatorial optimization problem, and it exists widely in chemical, manufacturing and pharmaceutical industry. In this wor...The hybrid flow shop scheduling problem with unrelated parallel machine is a typical NP-hard combinatorial optimization problem, and it exists widely in chemical, manufacturing and pharmaceutical industry. In this work, a novel mathematic model for the hybrid flow shop scheduling problem with unrelated parallel machine(HFSPUPM) was proposed. Additionally, an effective hybrid estimation of distribution algorithm was proposed to solve the HFSPUPM, taking advantage of the features in the mathematic model. In the optimization algorithm, a new individual representation method was adopted. The(EDA) structure was used for global search while the teaching learning based optimization(TLBO) strategy was used for local search. Based on the structure of the HFSPUPM, this work presents a series of discrete operations. Simulation results show the effectiveness of the proposed hybrid algorithm compared with other algorithms.展开更多
随着电动汽车的大规模入网,其无序充电使得负荷峰谷差距进一步激增,给电力系统的稳定运行带来了负面影响,因此提出1种计及电动汽车负荷和电池储能系统的削峰填谷两阶段优化调度策略。首先,以用户充电成本和负荷绝对峰谷差最小为目标建...随着电动汽车的大规模入网,其无序充电使得负荷峰谷差距进一步激增,给电力系统的稳定运行带来了负面影响,因此提出1种计及电动汽车负荷和电池储能系统的削峰填谷两阶段优化调度策略。首先,以用户充电成本和负荷绝对峰谷差最小为目标建立电动汽车有序充电调度模型,利用改进粒子群优化算法对模型进行求解,促使电动汽车避峰充电;其次,以负荷方差和储能寿命综合成本最小为目标建立储能系统削峰填谷优化调度模型,采用改进哈里斯鹰优化HHO(Harris Hawks optimization)算法对模型进行求解,从而减小负荷峰谷差,并通过削峰填谷评价指标对优化结果进行评估和分析;最后,以某电网实测负荷功率为例进行仿真实验,结果表明,所提两阶段优化调度策略使得负荷峰值降低了约147 k W,负荷谷值上升了约223 k W,峰谷差降低了约46.73%,能够有效改善负荷曲线,缓解负荷高峰期电力供应紧张的压力,保证了电网的安全、稳定运行。展开更多
随着新一代信息通信技术,如5G、云计算和人工智能的不断演进,世界正迅速迈入数字经济的快车道。针对数据中心中可再生能源和工作负载预测的不确定性,提出了一种基于多智能体近端策略网络的数据中心双层优化调度方法。首先,建立了数据中...随着新一代信息通信技术,如5G、云计算和人工智能的不断演进,世界正迅速迈入数字经济的快车道。针对数据中心中可再生能源和工作负载预测的不确定性,提出了一种基于多智能体近端策略网络的数据中心双层优化调度方法。首先,建立了数据中心双层时空优化调度框架,对数据中心工作负载、IT设备、空调设备进行详细建模;在此基础上,提出数据中心的双层优化调度模型,上层以互联网数据中心(Internet data center,IDC)运营管理商总运营成本最小为目标进行时间维度调度,下层以各IDC运行成本最低为目标进行空间维度调度;然后,介绍多智能体近端策略网络算法原理,设计数据中心双层优化调度模型的状态空间、动作空间和奖励函数。最后,针对算例进行离线训练和在线调度决策,仿真结果表明,所提模型和方法能够有效降低系统成本和能耗,实现工作负载的最佳分配,具有较好的经济性和鲁棒性。展开更多
基金Project(51805200)supported by the National Natural Science Foundation of ChinaProject(20170520096JH)supported by the Science and Technology Development Plan of Jilin Province,ChinaProject(2016YFC0802900)supported by the National Key R&D Program of China
文摘The shift scheduling system of the transmission has an important effect on the dynamic and economic performance of hybrid vehicles. In this work, shift scheduling strategies are developed for parallel hybrid construction vehicles. The effect of power distribution and direction on shift characteristics of the parallel hybrid vehicle with operating loads is evaluated, which must be considered for optimal shift control. A power distribution factor is defined to accurately describe the power distribution and direction in various parallel hybrid systems. This paper proposes a Levenberg-Marquardt algorithm optimized neural network shift scheduling strategy. The methodology contains two objective functions, it is a dynamic combination of a dynamic shift schedule for optimal vehicle acceleration, and an energy-efficient shift schedule for optimal powertrain efficiency. The study is performed on a test bench under typical operating conditions of a wheel loader. The experimental results show that the proposed strategies offer effective and competitive shift performance.
基金Projects(61573144,61773165,61673175,61174040)supported by the National Natural Science Foundation of ChinaProject(222201717006)supported by the Fundamental Research Funds for the Central Universities,China
文摘The hybrid flow shop scheduling problem with unrelated parallel machine is a typical NP-hard combinatorial optimization problem, and it exists widely in chemical, manufacturing and pharmaceutical industry. In this work, a novel mathematic model for the hybrid flow shop scheduling problem with unrelated parallel machine(HFSPUPM) was proposed. Additionally, an effective hybrid estimation of distribution algorithm was proposed to solve the HFSPUPM, taking advantage of the features in the mathematic model. In the optimization algorithm, a new individual representation method was adopted. The(EDA) structure was used for global search while the teaching learning based optimization(TLBO) strategy was used for local search. Based on the structure of the HFSPUPM, this work presents a series of discrete operations. Simulation results show the effectiveness of the proposed hybrid algorithm compared with other algorithms.
文摘随着电动汽车的大规模入网,其无序充电使得负荷峰谷差距进一步激增,给电力系统的稳定运行带来了负面影响,因此提出1种计及电动汽车负荷和电池储能系统的削峰填谷两阶段优化调度策略。首先,以用户充电成本和负荷绝对峰谷差最小为目标建立电动汽车有序充电调度模型,利用改进粒子群优化算法对模型进行求解,促使电动汽车避峰充电;其次,以负荷方差和储能寿命综合成本最小为目标建立储能系统削峰填谷优化调度模型,采用改进哈里斯鹰优化HHO(Harris Hawks optimization)算法对模型进行求解,从而减小负荷峰谷差,并通过削峰填谷评价指标对优化结果进行评估和分析;最后,以某电网实测负荷功率为例进行仿真实验,结果表明,所提两阶段优化调度策略使得负荷峰值降低了约147 k W,负荷谷值上升了约223 k W,峰谷差降低了约46.73%,能够有效改善负荷曲线,缓解负荷高峰期电力供应紧张的压力,保证了电网的安全、稳定运行。
文摘随着新一代信息通信技术,如5G、云计算和人工智能的不断演进,世界正迅速迈入数字经济的快车道。针对数据中心中可再生能源和工作负载预测的不确定性,提出了一种基于多智能体近端策略网络的数据中心双层优化调度方法。首先,建立了数据中心双层时空优化调度框架,对数据中心工作负载、IT设备、空调设备进行详细建模;在此基础上,提出数据中心的双层优化调度模型,上层以互联网数据中心(Internet data center,IDC)运营管理商总运营成本最小为目标进行时间维度调度,下层以各IDC运行成本最低为目标进行空间维度调度;然后,介绍多智能体近端策略网络算法原理,设计数据中心双层优化调度模型的状态空间、动作空间和奖励函数。最后,针对算例进行离线训练和在线调度决策,仿真结果表明,所提模型和方法能够有效降低系统成本和能耗,实现工作负载的最佳分配,具有较好的经济性和鲁棒性。
