An optimal workflow scheduling method in cloud-fog computing using three-objective Harris-Hawks algorithm

Today, the Internet of Things (IoT) use to collect data by sensors, and store and process them. As the IoT has limited processing and computing power, we are turning to integration of cloud and IoT. Cloud computing processes large data at high speed, but sending this large data requires a lot of bandwidth. Therefore, we use fog computing, which is close to IoT devices. In this case, the delay is reduced. Both cloud and fog computing are used to increasing performance of IoT. Job scheduling of IoT workflow requests based on cloud-fog computing plays a key role in responding to these requests. Job scheduling in order to reduce makespan time, is very important in realtime system. Also, one way to improve system performance is to reduce energy consumption. In this article, three-objective Harris Hawks Optimizer (HHO) scheduling algorithm is proposed in order to reduce makespan time, energy consumption and increase reliability. Also, dynamic voltage frequency scaling (DVFS) has been used to reduce energy consumption, which reduces frequency of the processor. Then HHO is compared with other algorithms such as Whale Optimization Algorithm (WOA), Firefly Algorithm (FA) and Particle Swarm Optimization (PSO) and proposed algorithm shows better performance on experimental data. The proposed method has achieved an average reliability of 83%, energy consumption of 14.95 KJ, and makespan of 272.5 seconds.