USING CLUSTERING ALGORITHM AND FOG COMPUTING FOR EN-ROUTE FILTERING IN LOW POWER AND LOSS NETWORKS

Due to trustless link quality in Wireless Mesh Networks (WMNs), Power Outage Notification (PON) and Power Restoration Notification (PRN) messages are often dropped or delayed en-route, which may fail to satisfy customer requirements in practice. Therefore, proposed herein are techniques that use machine learning and Fog computing to efficiently deduce missing PON/PRN messages. DETAILED DESCRIPTION Vendors are developing multi-hop wireless mesh networks (WMNs) for smart grid business use and to provide interoperability for with Advantaged Metering Infrastructure (AMI) and Distributed Automation (DA) devices. These WMNs utilize IPv6 Routing Protocol for LLNs (RPL) to establish a tree-based multi-hop topology network based on the RF and PLC medium by using IEEE802.15.4g and P1901.2 protocols. In general, the networks are usually constrained with limited power/energy, bandwidth, and memory resources, are often deployed in hostile environments, and utilize wireless communication. In WMNs, there are two en-route filtering problems that must be considered. The first problem is that most of the nodes can be easily compromised by an attacker, who can then inject false report and launch path-based DoS (PDoS) attacks. For example, a compromised node will frequently send joining requests to neighbors (e.g., Eapol requests), and then the receivers will forward these requests to the border router (BR) because they could not verify the legitimacy for these requests. This problem is shown below in Figure 1. 2 Zhang et al.: USING CLUSTERING ALGORITHM AND FOG COMPUTING FOR EN-ROUTE FILTERI Published by Technical Disclosure Commons, 2020