Dynamic ensemble wind speed prediction model based on hybrid deep reinforcement learning

Prediction of wind speed can provide a reference for the reliable utilization of wind energy. This study focuses on 1-hour, 1-step ahead deterministic wind speed prediction with only wind speed as input. To consider the time-varying characteristics of wind speed series, a dynamic ensemble wind speed prediction model based on deep reinforcement learning is proposed. It includes ensemble learning, multi-objective optimization, and deep reinforcement learning to ensure effectiveness. In part A, deep echo state network enhanced by real-time wavelet packet decomposition is used to construct base models with different vanishing moments. The variety of vanishing moments naturally guarantees the diversity of base models. In part B, multi-objective optimization is adopted to determine the combination weights of base models. The bias and variance of ensemble model are synchronously minimized to improve generalization ability. In part C, the non-dominated solutions of combination weights are embedded into a deep reinforcement learning environment to achieve dynamic selection. By reasonably designing the reinforcement learning environment, it can dynamically select non-dominated solution in each prediction according to the time-varying characteristics of wind speed. Four actual wind speed series are used to validate the proposed dynamic ensemble model. The results show that: (a) The proposed dynamic ensemble model is competitive for wind speed prediction. It significantly outperforms five classic intelligent prediction models and six ensemble methods; (b) Every part of the proposed model is indispensable to improve the prediction accuracy.     

Hierarchical control for cornering stability of dual-motor RWD vehicles with electronic differential system using PSO optimized SOSMC method

This paper proposes a novel control scheme with a three-layer hierarchical structure to improve the cornering stability of the dual-motor rear-wheel drive (RWD) vehicles with the electronic differential system (EDS). The proposed hierarchical structure for the control system includes the observing layer, control layer, and actuation layer. In the observing layer, the driver model is designed to obtain the nominal steering angle, and the state observer is designed to obtain the yaw angle which cannot be easily measured. Then, particle swarm optimization (PSO) and second order sliding mode control (SOSMC) are employed in the control layer. The SOSMC part is used to design the control law to eliminate the chattering problem in the sliding mode algorithm, and the PSO part is used to obtain the optimal weights in the sliding mode surface to meet the minimum sideslip angle error and yaw rate error. The actuation layer allocates the corrected yaw moment by distributing the driving force to each independent driving wheel. Finally, the numerical tests are carried out under the double line change (DLC) maneuver. The results show that the proposed control system can effectively improve the cornering stability of the dual-motor RWD vehicles and reduce their motor power consumption.     

Guaranteeing performance for uncertain nonlinear systems with bounded state constraint and mismatching condition

The control design problem for the uncertain nonlinear system with bounded state constraint and mismatching condition is considered in this paper. The uncertainty in the system, which may be due to unknown system parameters and external disturbance, is nonlinear and time‐varying. The state of the system is constrained to be bounded. The system does not satisfy the (global) matching condition. A creative one‐to‐one state transformation is proposed by converting the bounded states into the unbounded ones. A step‐by‐step state transformation is proposed to convert the mismatched system into a matched system. The robust control is then proposed based on the transformed system. The control is demonstrated to be able to guarantee the uniform boundedness and uniform ultimate boundedness of the system in the presence of uncertainty, while the state constraint can be always guaranteed.     

基于RISC-V处理器的卷积加速SoC系统设计

为提高卷积神经网络（CNN）的计算效率和能效,以8 bit定点数据作为输入,设计一个支持激活、批标准化以及池化等CNN网络中常见计算类型的卷积加速器,优化循环计算顺序并将其与数据复用技术相结合,以提高卷积计算的效率。基于软硬件协同设计思想,构建包含RISC-V处理器和卷积加速器的SoC系统,RISC-V处理器基于开源的指令集标准,可以根据具体的设计需求扩展指令功能。将该SoC系统部署在Xilinx ZCU102开发板上,RISC-V处理器和卷积加速器分别工作在100 MHz和300 MHz频率下,测试结果表明,该加速器的算力达到153.6 GOP/s,运行VGG16网络进行图片推理计算时加速效果较好。     

基于改进NSGA-II算法求解多目标资源受限项目调度问题

资源受限项目调度问题(resource constrained project scheduling problem, RCPSP)要求在满足相关约束的条件下安排各活动开始时间,从而达到某一目标的最优,具有很强的应用背景,并受到众多学者的广泛关注.经典的RCPSP模型以最小化项目工期为单一目标,忽略了资源使用率等因素对项目整体的影响,使其与实际应用仍有较大差距.基于经典的RCPSP模型,引入最优资源均衡为另一目标,将模型扩展为多目标模型,丰富了RCPSP模型的应用场景.同时,考虑到新模型中各活动间存在大量的控制关系,使用传统的启发式多目标算法需要耗费大量的时间对不可行解进行判断,求解性能较低,提出一种新的算法框架NSGA-IIs.该算法框架基于活动间控制关系将各活动分成若干子集,并在初始化和交叉变异等阶段以子集为基本单位产生新的个体,能够较好地避免不可行解的产生,提高算法的效率.使用解集覆盖度作为评价指标,通过实例数据集的实验表明,与已有的求解RCPSP的经典算法相比,所提出的算法具有明显的优越性.     

多时空配送任务驱动的无人车队车辆数优化方法

为解决快递终端配送多时空任务驱动下的最小无人车队车辆数配置问题,提出一种随机优化方法。首先,分析服务时长和等待时长对无人车队行驶路线规划的影响,从而构建最短路径模型;然后,基于二维时空网络构造服务序列网络;其次,通过网络转换将最小无人车队车辆数配置问题转化为网络最大流问题,并建立以车队车辆数最小为目标的最小车队模型;最后,针对模型特征设计一种融合Dijkstra算法和Dinic算法的Dijkstra-Dinic算法来对最小无人车队车辆数配置问题进行求解。在四种不同规模的服务网络中进行仿真实验,实验结果表明：在不同成功服务率下,最小无人车队车辆数与服务网络规模呈正相关,但随等待时长的增加而减少并趋向于稳定;所提算法中所引入的One-stop算子大大提高了搜索效率,所提模型和算法适用于大规模服务网络中的最小车队计算。     

面向制造任务的云制造虚拟车间构造方法

针对云制造模式下快速选择和组织相关制造资源、保证制造任务执行的问题,提出一种面向制造任务的云制造虚拟车间构造方法。该方法将制造过程抽象为制造任务执行链,链中的节点对应制造设备云服务或检验云服务,链中的有向边对应物流云服务;并通过行业域、地域和类型域来组织管理云服务,以构造规模较小的候选云服务集,同时减少功能匹配、性能匹配、价格匹配和时间匹配的计算量,达到快速构建云制造虚拟车间的目的。算例分析表明,相比其他方法,该方法能够在更短的时间内完成云服务的选择,并保证所选云服务的服务质量（QoS）在相关域中是更好的。     

横向整合战略下异质车辆库存路径优化模型

以实现供货商联盟期望物流成本最小化为目标,针对需求随机波动下的多供货商多产品库存路径问题（IRP）进行了研究。基于横向整合战略,设计了供货商联盟成员间车辆配送成本的合理分摊方式。考虑零售商配送软硬时间窗和库存服务水平要求,构建了多供货商多产品的异质车辆库存路径混合整数随机规划模型,并利用需求累积分布逆函数将其转化为确定型规划模型。然后设计改进遗传算法求解该确定型规划模型。算例分析结果显示,使用异质车辆配送可以比使用同质重型和轻型车辆分别降低供货商联盟总成本8.3%和11.92%,分别提升配送车辆装载率24%和17%。敏感性分析结果表明,无论供货商供货数量占联盟总供货数量比例和零售商商品需求变异系数如何变化,采用异质车辆配送的供货商联盟总成本都能得到有效降低;且需求变异系数越大,采用异质车辆配送的优势越明显。     

应急通信网络中基于粒子群优化的信道分配算法

当前应急通信亟需解决的问题,在于如何快速有效地满足突发性增长的网络需求,以保证网络传输质量。无线mesh网络以其部署快速、结构灵活、鲁棒性等优点,成为了新一代灾后应急通信网络架构的优秀解决方案。文中提出了一种基于粒子群算法的信道分配优化算法PWCA,在降低全局网络干扰的前提下,考虑了不同链路对整体网络表现的影响,通过其邻接链路的数量来决定信道分配的优先级。在迭代优化的过程中,该算法利用信道分离度细分了不同信道之间的干扰程度以作为优化的评判标准。实验结果表明,该算法可以显著降低网络干扰,保障网络性能,相比传统的粒子群信道分配算法,其在优化速度以及多节点网络环境下的表现均有明显提升。     

云存储多异构文件联合延迟尾概率凸优化分析

随着擦除码技术的流行,分布式存储中高数据可靠性和高空间效率存储性能逐渐实现,但是降低尾部延迟仍然是一个有待解决的问题。为此,提出一种量化和优化擦除编码存储系统尾延迟的算法框架。对于任意服务时间分布和异构文件,推导给出尾部延迟上界。提出了一个优化模型,使得所有文件在服务器上放置的加权延迟尾概率和访问请求文件的服务器选择共同最小化,并证明了其非凸问题特性,以便采用一种高效的交替优化算法求解。此外,通过描述延迟分布尾部的渐近行为,以闭合形式对任意擦除编码存储的服务延迟的尾部指数进行数学量化,证明了基于概率调度的算法是（渐近）最优的。实验结果表明,在实际工作负载下擦除编码存储系统的尾部延迟显著降低。