RPL Protocol Enhancement using Artificial Neural Network (ANN) for IoT Applications

In near future, IoT will revolutionize human lifestyle. IoT is categorized as low power lossy network since it employs devices with constrained power, memory and processing capability which are interconnected over lossy links. The efficiency of such networks largely depends on the design of the routing protocol. To cater specific routing needs of such networks, the IETF has proposed IPv6 routing protocol for LLNs (RPL) as a de facto routing standard. In RPL, routing decision is based on a single parameter which leads to the selection of inefficient paths and affects network lifetime. This work primarily focuses on improving the RPL protocol by overcoming the single metric limitation. In this work, a novel version of RPL is proposed which uses a Multilayer Feed Forward Neural Network to make the routing decision based on multiple metrics. Four routing parameters namely, hop count, delay, residual energy and link quality of candidate neighbors are fed as input to ANN in order to compute the fitness of each candidate and the one with highest value is designated as the most suitable parent to route packets towards sink node. This technique lowers energy consumption by 15%, improves Packet Delivery Ratio by 3%, lowers delay by 17% and reduces the control overhead by 48% as compared to standard RPL implementation.