In order to execute the energy-hungry computational intensive tasks, we can use the mobile resources of the other mobile user’s resources which are not in use. The idea is to deploy the virtual machines in the mobile device which helps in increasing the resources of the mobile for executing the tasks. In order deploy the virtual machine an algorithm called VM-ABC is proposed for efficient usage of the deployed virtual machines. This increases energy conservation and also reduces the transmission delay of the executed tasks (Ding& Xu& Wu, 2017).
Most of the time the users execute their tasks with the help of cellular networks. In that case, if the user is at the edge of the main cloud server and in between two cloud networks then the transmission delay occurs. So, in order to reduce the transmission delay, the modules send to the next cloud server to get the execution done as quickly as possible and send the modules back to the user without larger delays (Abraham& Al-khatib& Abdul, 2020).
Some of the algorithms that can reduce energy conservation by efficiently scheduling the tasks are the Greedy algorithm, Group Based task scheduling algorithm, and GA based task scheduling algorithm which are heuristic algorithms. In the above algorithms, the GA based task scheduling algorithm is given the best performance and efficiency while scheduling the tasks as the number of tasks increases when compared with the other two algorithms (Tang& Hao& Wei, 2018).
One of the methods proposed in one of the articles (Liu& Guo& Chang, 2019) to increase the performance and overall time consumption of the tasks is to get help from a cloudlet that is near the user network which helps in reducing the transmission delay while offloading the tasks to the cloud. The users can connect to the cloudlet using the SBS (Small cell Base) station and if the cloudlet overloads with tasks then the cloudlet sends the tasks to the main cloud server for execution.
In order to save energy and to use the offloading process efficiently some of the algorithms can be used. Those are CTTPO (Cost and Time constraint Task Partitioning and offloading) algorithm, which helps in calculating the time and cost for the application modules execution and decide whether to execute the task locally or on the cloud. The other algorithm is MTS (Multi-site task scheduling) algorithm which is based on a teaching and learning-based algorithm that optimizes the task offloading strategy. The other algorithm is the ESM (Energy Saving on Multi-sites) which uses DVS (Dynamic voltage scaling) technique that helps in switching the voltage from high to low when it is in an ideal state (Kumari& kaushal& chilamkurti, 2018).
As we all know that the mobile devices lack resources for executing the computational intensive tasks in a particular time and also loose the battery life if the whole task is performed on the mobile. So, in order save battery power and increase the speed of the task execution MCC is introduced which helps in offloading the computational intensive tasks to the cloud and perform the execution on the cloud. After execution the modules are sent back to the cloud.
Hi, I am Sai Akhil and I am currently pursuing Masters in Information technology with cloud computing specialization. I have been studying cloud computing for over a year now and I would like to research more about its architecture, infrastructure and other applications of it.