边缘网络下多无人机协同计算和资源分配联合优化策略

针对边缘网络环境下多人机之间存在计算负载不均，造成卸载任务失败的问题，提出了一种多无人机间协作的智能任务卸载方案。通过联合考虑多无人机任务分配、计算资源分配和无人机飞行轨迹，引入公平性指数建立了无人机公平负载最大化和能量消耗最小化问题。基于多智能体深度强化学习框架，提出了融合轨迹规划和任务卸载的分布式算法。仿真结果表明，所提出的多无人机协作方案可以显著提高任务完成率和负载公平度，并且有效适用于大规模用户设备场景。     

Comparison study of ductile iron produced with Martian regolith harvested iron from ionic liquids and Bosch byproduct carbon for in-situ resource utilization versus commercially available 65-45-12 ductile iron

As researchers continue to study methods to facilitate long-term missions beyond low-Earth orbit, the ability to manufacture high-quality mechanical and structural components on the Lunar and Martian surfaces remains a crucial piece to the puzzle for a sustained presence. Due to the immense cost of sending supplies to extraterrestrial bodies, in-situ resource utilization (ISRU) methods are critical for the success and feasibility of these habitation missions. Ionic liquids (ILs) are currently being studied at NASA’s Marshall Space Flight Center (MSFC) to harvest elemental metals from meteorites and regolith minerals. Additionally, the Bosch process is being explored as a life support system at MSFC for oxygen (O₂) regeneration, rendering a byproduct of elemental carbon (C). In this investigation, the viability of casting ductile iron (DI) using IL-sourced iron (IL-Fe) and Bosch C was studied given the range of applications and performance of DI as an as-cast alloy. Ingots were produced using commercial elements to simulate the use of IL-Fe with C sourced from the byproduct C of the Bosch process. Samples were cast and compared to commercially available 65–45-12 DI with phase transformation diagrams, microstructures, and hardness. Results showed that IL-sourced elements are a viable source of elemental alloying materials for a range of DI alloys, with some limitations.     

Sequential dynamic resource allocation in multi-beam satellite systems:A learning-based optimization method

Multi-beam antenna and beam hopping technologies are an effective solution for scarce satellite frequency resources. One of the primary challenges accompanying with Multi-Beam Satellites(MBS) is an efficient Dynamic Resource Allocation(DRA) strategy. This paper presents a learning-based Hybrid-Action Deep Q-Network(HADQN) algorithm to address the sequential decision-making optimization problem in DRA. By using a parameterized hybrid action space,HADQN makes it possible to schedule the beam patte...     

机场飞行区资源调度问题研究(一)：基本概念与框架

世界航空运输系统的一体化、协同化和智能化发展对机场飞行区资源调度精细化管理和空中交通运行高效化管控提出了高要求。本文聚焦机场飞行区资源调度的基本概念与框架问题,是飞行区资源调度问题研究系列之一。从国际公约、理论研究和行业规范视角界定飞行区的基本概念,分析飞行区的一般运行过程和资源调度内涵。对飞行区资源调度体系涉及的理论方法、系统工具、管理机制等要素及逻辑关系进行系统总结。研究成果旨在为机场运行管理理论与应用的可持续发展提供科学指引。     

机场飞行区资源调度问题研究(三)：研究热点与挑战

全球航空运输需求的持续和迅猛增长,使得诸多大型繁忙机场正面临高频次飞行冲突、大范围空域拥堵、大面积航班延误等一系列严峻问题。本文聚焦飞行区资源调度的研究热点与挑战问题,为机场飞行区资源调度问题研究系列之三。从多维视角对飞行区资源调度问题进行详细分类,梳理近几年在容量预测、跑道配置、态势感知、空地调度、性能权衡等方面的研究热点,并对该领域目前面临的主要挑战进行综合分析。研究成果旨在为机场运行管理理论与应用的可持续发展提供科学指引。     

网格远程调度系统的设计与实现

阐明了在多集群的网格中，资源调度和任务的分配受到网络和通信延迟的限制。采用元调度机制有效的将作业分配到不同集群计算机中，进一步，义采用动态绑定机制来减少作业分配的延迟。这一机制是绑定相似的请求来组成复合请求分配到网格资源。在不同的服务负载下应用了这些机制，结果显示这些机制能够帮助获得负载均衡和减少作业分配的延迟，同时也能减少程序的运行时间。     

基于改进非支配排序遗传算法 的维修资源优化配置

针对在武器装备维修保障过程中出现的资源短缺、资源冲突等问题,构建了多目标的维修资源优化配置模型,并且基于加权思想将多目标转化为单目标以方便求解。针对遗传算法求解多目标优化问题存在的解空间过大、收敛速度慢、计算效率低等问题,提出了基于约束的改进非支配排序遗传算法对资源优化配置模型进行求解。实例分析结果验证了模型及算法的可行性和有效性。     

非战争军事行动中装备维修保障资源需求计算模型

精确、高效、稳定、可靠的维修保障是海军非战争军事行动顺利实施的必要条件。文章建立了维修设施设备、备品备件、保障专业人员等维修保障资源的需求量化计算模型,并结合实例说明了模型的实际应用。