No abstract

No abstract

No abstract

No abstract

SummaryTo extend the reach of cloud computing, the concept of edge computing and dew computing is introduced to execute various Internet of things (IoT) application with minimized delay in real time. The requested tasks are allocated computing resources that best suits their purpose. In this work, a novel hybrid hierarchical dew based edge to cloud architecture is developed. The objective of the study is to provide a detailed analysis and validation of real‐time scheduling of IoT application in this hybrid hierarchical ecosystem. The problem of optimally mapping requested tasks to the computing layers is mathematically formulated based on several quality of service factors and solved using the proposed hybrid adaptive metaheuristic algorithm. This is a combination of learning‐based adaptive particle swarm optimization and genetic algorithm. The exploitative and exploratory feature of the proposed algorithm helps in achieving better global optima compared with other existing metaheuristic algorithms.

No abstract

No abstract

SummaryThe evolution of 5th Generation wireless technology introduced Mobile Edge Computing, where edge servers are placed at the edge of the network, and are associated with evolved Node Base Stations (eNBs). This enables mobile users to offload their resource‐intensive tasks to these servers and improve network performance by reducing end‐to‐end delay. However, frequent user mobility leads to frequent re‐planning of network and increases network load. This demands dynamic Virtual Machine (VM) migration in Mobile Edge paradigm for an improved Quality of Service (QoS). For an enhanced VM migration process, an optimal pair of migrating VMs and destination edge servers needs to be chosen. In this paper, we propose an optimized decision‐making policy that chooses such optimal pairs. Several decision parameters such as average wait time, processing delay, migration delay, transmission power, and processing power are modeled. A profit function is developed using these modeled decision parameters that chooses the optimal pairs. This function is maximized using the proposed hybrid evolutionary algorithm, which combines the advantages of PSO and GA. The pairs are chosen in such a manner, that the selection guarantees high network throughput, reduced service delay, and energy consumption which is reflected in the simulation.