论文标题
朝着雾环境的自适应点对点监测
Towards Self-Adaptive Peer-to-Peer Monitoring for Fog Environments
论文作者
论文摘要
监视是雾环境中的关键组成部分：它迅速提供了有关系统行为的见解，揭示服务水平协议（SLA）违规，实现服务和平台的自主编排，呼吁进行操作员的干预以及触发自我完成的动作。 在这样的环境中，监视解决方案必须应对雾中存在的设备和平台的异质性，网络边缘可用的有限资源以及整个云之间连续体的高动力。 本文解决了通过自适应对等（P2P）监视解决方案准确有效地监视雾的挑战，该解决方案可以根据利用基于规则的专家系统的收集数据来进行机会主义地调整其行为。 经验结果表明，适应性可以提高监视精度，同时以更高的记忆消耗为代价减少网络和功耗。
Monitoring is a critical component in fog environments: it promptly provides insights about the behavior of systems, reveals Service Level Agreements (SLAs) violations, enables the autonomous orchestration of services and platforms, calls for the intervention of operators, and triggers self-healing actions. In such environments, monitoring solutions have to cope with the heterogeneity of the devices and platforms present in the Fog, the limited resources available at the edge of the network, and the high dynamism of the whole Cloud-to-Thing continuum. This paper addresses the challenge of accurately and efficiently monitoring the Fog with a self-adaptive peer-to-peer (P2P) monitoring solution that can opportunistically adjust its behavior according to the collected data exploiting a lightweight rule-based expert system. Empirical results show that adaptation can improve monitoring accuracy, while reducing network and power consumption at the cost of higher memory consumption.
