Efficient Green Solution for a Balanced Energy Consumption and Delay in the IoT-Fog-Cloud Computing
Network Computing and Applications (NCA), 2017 IEEE 16th International Symposium on
Internet of Things (IoT) applications must fulfill certain crucial requirements such as low latency, mobility, and bandwidth constraints. Fog computing refers to a scalable, distributed computing architecture which extends the cloud computational tasks to the edge of the network, to be closer to the end-user. Hence over the last few years, attention has been drawn over the fog computing as a solution for IoT applications, with some focus on its energy consumption. In this work, an energy-efficient method is proposed in the context of latency-sensitive IoT applications. We start by building a new model to measure the energy consumed and the Quality of Service (QoS) in the fog. This model is used later to verify the performances of our solution. We then contribute a new centrilzed algorithm is based on Evolutionary Algorithms (EA) to find the optimal trade-off between the energy consumption and the service delay. The approach is validated conducting performance evaluation via simulation, while it is compared against energy-efficient and the traditional cloud solutions. The results show that the proposed approach is more efficient in terms of energy consumption and latency than the compared solutions.