Edge Server Placement for Service Offloading in Internet of Things

Abstract

With the rapid development of the Internet of Things, a large number of smart devices are being connected to the Internet while the data generated by these devices have put unprecedented pressure on existing network bandwidth and service operations. Edge computing, as a new paradigm, places servers at the edge of the network, effectively relieving bandwidth pressure and reducing delay caused by long-distance transmission. However, considering the high cost of deploying edge servers, as well as the waste of resources caused by the placement of idle servers or the degradation of service quality caused by resource conflicts, the placement strategy of edge servers has become a research hot spot. To solve this problem, an edge server placement method orienting service offloading in IoT called EPMOSO is proposed. In this method, Genetic Algorithm and Particle Swarm Optimization are combined to obtain a set of edge server placements strategies, and Simple Additive Weighting Method is utilized to determine the most balanced edge server placement, which is measured by minimum delay and energy consumption while achieving the load balance of edge servers. Multiple experiments are carried out, and results show that EPMOSO fulfills the multiobjective optimization with an acceptable convergence speed.

Energy-aware edge server placement using the improved butterfly optimization algorithm

“…The authors improved and adapted it for server placement that has a discrete nature. Also, in [12], using PSO and genetic algorithm(GA), a new method of edge server placement has been introduced with the objectives of energy consumption optimization and better load balancing of servers. GA and PSO have been used in service offloading and optimization of optimal server placement strategy, respectively.…”

“…Local search is used to further explore the search space, avoiding greedy search and forcing the algorithm to more random behavior. Equation (12) updates the position of a candidate location, where j and s are two random locations to which the current position randomly moves toward them. After the first step of the proposed method, i.e., finding the optimal location of the server in each area, it is time for the second step of the proposed method.…”

Multi-Objective Edge Server Placement Using the Whale Optimization Algorithm and Game Theory

“…And finally, the simulated annealing algorithm is used for more exploration of the algorithm. In another similar work [11], using particle swarm optimization and genetic algorithms as well as Simple Additive Weighting Method, a model of server placement to balance the user's workload on mobile servers has been introduced. Genetic algorithms and particle swarm optimization algorithms have been used for service offloading and optimization of resource placement strategy, respectively.…”

Multi objectives Edge Server Placement in Mobile Edge computing Using Trees Social Relations Optimization Algorithm and DVFS technique

“…Genetic algorithm, hill climbing, and Simulated annealing are used to calculate the value of candidate solutions, determine the input state, and more exploration, respectively. In [16], genetic and PSO algorithms have introduced a new server placement method to determine the best resource balancing strategy. Server balancing is done using the criterion of minimum latency and minimum energy consumption.…”

“…Three state-of-the-art algorithms and a random method have been used to evaluate the proposed method. EPMOSO [16] is used as a similar algorithm to compare the proposed method. This multi-objective algorithm uses the combination of two evolutionary and metaheuristic algorithms, i.e., GA and PSO, with goals similar to the proposed method.…”