Edge Computing Resource Allocation for Dynamic Networks

物联网时代丰富的传感器、执行器和通信所提供的潜力受到本地节点有限的计算能力的阻碍，使得计算在时间和空间上的分布成为必要。为了优化和共同利用网络、计算和存储资源，同时保证时间关键型和任务关键型任务的可行性，需要解决几个关键挑战。我们的研究通过在需求快速变化的情况下动态分配资源来应对这些挑战。我们首先提出了资源、提供的工作负载和网络环境的分析数学动态模型，该模型结合了无线通信、移动边缘计算数据中心和网络拓扑中遇到的现象。我们还为不断更新模型参数的工作负载和资源时变概要提出了一组新的估计器。在这个框架的基础上，我们的目标是开发新的资源分配机制，明确地考虑到服务差异和上下文感知，最重要的是，为定义良好的QoS/QoE指标提供正式的保证。通过将资源分配机制纳入决策策略本身，我们的研究远远超出了网络物理系统（CPS）控制算法设计的最新水平。我们提出了新一代控制器，由网络和计算资源利用的协同设计理念驱动。这种模式有可能在工程的关键领域引起巨大的飞跃，例如工业4.0、协作机器人、物流、多智能体系统等。为了实现这些突破，我们利用并结合了自动机和图论、机器学习、现代控制理论和网络理论等领域的工具，这些领域的联盟拥有国际领先的专业知识。尽管来自计算机和网络科学、控制工程和应用数学的研究人员已经提出了各种方法来解决上述挑战，但我们的研究构成了第一个真正全面的、多学科的方法，它结合并扩展了最近来自上述所有领域的零散结果，从而弥合了不同社区之间的努力差距。我们开发的理论将在参与实体的现有实验测试平台基础设施上进行广泛测试。将在涉及物联网环境中移动自主代理的三个复杂用例下测试和评估整个拟议框架的效率：(i)一组具有复杂规格的移动机器人的分布式远程路径规划，（ii）在灾难场景中快速部署用于分布式计算目的的移动代理，以及（iii）具有预定义性能指标的拥挤区域的移动性感知资源分配。

The potential offered by the abundance of sensors, actuators and communications in IoT era is hindered by the limited computational capacity of local nodes, making the distribution of computing in time and space a necessity. Several key challenges need to be addressed in order to optimally and jointly exploit the network, computing, and storage resources, guaranteeing at the same time feasibility for time-critical and mission-critical tasks. Our research takes upon these challenges by dynamically distributing resources when the demand is rapidly time varying. We first propose an analytic mathematical dynamical modelling of the resources, offered workload, and networking environment, that incorporates phenomena met in wireless communications, mobile edge computing data centres, and network topologies. We also propose a new set of estimators for the workload and resources time-varying profiles that continuously update the model parameters. Building on this framework, we aim to develop novel resource allocation mechanisms that take explicitly into account service differentiation and context-awareness, and most importantly, provide formal guarantees for well-defined QoS/QoE metrics. Our research goes well beyond the state of the art also in the design of control algorithms for cyber-physical systems (CPS), by incorporating resource allocation mechanisms to the decision strategy itself. We propose a new generation of controllers, driven by a co-design philosophy both in the network and computing resources utilization. This paradigm has the potential to cause a quantum leap in crucial fields in engineering, e.g., Industry 4.0, collaborative robotics, logistics, multi-agent systems etc. To achieve these breakthroughs, we utilize and combine tools from Automata and Graph theory, Machine Learning, Modern Control Theory and Network Theory, fields where the consortium has internationally leading expertise. Although researchers from Computer and Network Science, Control Engineering and Applied Mathematics have proposed various approaches to tackle the above challenges, our research constitutes the first truly holistic, multidisciplinary approach that combines and extends recent, albeit fragmented results from all aforementioned fields, thus bridging the gap between efforts of different communities. Our developed theory will be extensively tested on available experimental testbed infrastructures of the participating entities. The efficiency of the overall proposed framework will be tested and evaluated under three complex use cases involving mobile autonomous agents in IoT environments: (i) distributed remote path planning of a group of mobile robots with complex specifications, (ii) rapid deployment of mobile agents for distributed computing purposes in disaster scenarios and (iii) mobility-aware resource allocation for crowded areas with pre-defined performance indicators to reach.