Abstract
The Edge computing extension of the Cloud services towards the network boundaries raises important placement challenges for IoT applications running in a heterogeneous environment with limited computing capacities. Unfortunately, existing works only partially address this challenge by optimizing a single or aggregate objective (e.g., response time), and not considering the edge devices’ mobility and resource constraints. To address this gap, we propose a novel mobility-aware multi-objective IoT application placement (mMAPO) method in the Cloud – Edge Continuum that optimizes completion time, energy consumption, and economic cost as conflicting objectives. mMAPO utilizes a Markov model for predictive analysis of the Edge device mobility and constrains the optimization to devices that do not frequently move through the network. We evaluate the quality of the mMAPO placements using simulation and real-world experimentation on two IoT applications. Compared to related work, mMAPO reduces the economic cost by 28 percent and decreases the completion time by 80 percent while maintaining a stable energy consumption.
Highlights
Internet of Things (IoT) is a disruptive technology that sparked a revolution in terms of connectivity and reachability of the daily used devices
We evaluated the benefits of mobility-aware multi-objective IoT application placement (mMAPO) for application placement compared to the following complementary state-ofthe-art methods: 1) Fog Service Placement Problem (FSPP) [9] based on linear integer programming model focused on reducing the economic cost and improving resources utilization; 2) Edge-ward delay-priority (EW-DP) [10] that implements a hierarchical best-fit algorithm to cope with users’ mobility; and 3) Best-fit Queue (BQ) [11] as a queuing algorithm that uses the Min-Max heuristic [38] to reduce the completion time by giving preference to the Edge devices
We introduced mMAPO, a mobility-aware multi-objective method integrated within the C3 environment that considers the computation, communication, and mobility aspects for placing and executing IoT applications in the Cloud – Edge Continuum. mMAPO employs a genetic algorithm that optimizes three conflicting objective functions, constrained through a Markov chain model characterizing Edge devices’ mobility
Summary
Internet of Things (IoT) is a disruptive technology that sparked a revolution in terms of connectivity and reachability of the daily used devices. A 10% likelihood for the three devices (r1, r2, r3) to leave the network produces a failure probability of 27.8% based on the serial reliability model [7] This further aggravates the application placement problem, especially in heterogeneous environments with hundreds of devices. To address this problem, we present a novel mobilityaware multi-objective method for IoT application placement in the Cloud – Edge Continuum (mMAPO) for IoT applications mod-. We apply a generation-based multi-objective optimization algorithm that approximates the Pareto set of possible application placements in the Cloud – Edge Continuum using completion time, energy consumption, and economic cost as conflicting criteria. A multi-objective IoT application placement model that allocates Cloud – Edge resources to multiple IoT application components based on their characteristics;.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
