Research On Optimization Of Task Scheduling On Cloud-Fog Computing Framework

The rapid development of IoT applications,along with the far distance between intelligent networking devices and cloud computing datacenter,the cloud-only framework faces the challenge,which has promoted a novel distributed computing framework based on collaboration between cloud computing and fog computing.Fog computing helps to reduce transmission latency and provides pleased service to support delay-sensitive applications that require almost real-time responses.The cooperation of the fog computing and cloud computing is considered to be a promising architecture,which efficiently handles IoT's data processing and communications requirements.With the continuous expansion of the data center and the proliferation of smart terminal devices,it is primary problem faced by task scheduling in the cloud-fog computing framework to meet the real-time processing needs of users while reducing energy consumption.The advanced task scheduling strategy is of great significance which can adapt to the real-time demand of the IoT and reduce the energy consumption of the cloud and fog nodes.Considering the task deadline and energy consumption,this dissertation mainly studies the scheduling problems of independent tasks and associated tasks on the cloud-fog computing framework.(1)Considering the advantages of cloud computing and fog computing,in order to collaboratively utilize cloud and fog resources,this dissertation describes the system architecture of the cloud-fog computing framework and introduces the task scheduling model in detail.According to the different attribute of cloud and fog resources,the energy consumption model is established to provide calculation basis.(2)For the scheduling problem of independent tasks on cloud-fog computing framework,considering the task deadline and reducing the total energy consumption of processing tasks,a task scheduling strategy based on ant colony algorithm is proposed.Compared with other algorithms,the experimental results show that the proposed algorithm can reduce the total energy consumption of processing tasks while meeting the deadline of tasks.(3)For the scheduling problems of complex tasks with priority constraints in IoT applications,a task scheduling strategy is proposed,which is the combination of laxity-based priority algorithm and ant colony system.In the process of calculating the priority,the limitation of the task deadline is considered.In order to enhance the sensitivity of task delay,the laxity-based priority algorithm is adopted to construct a task scheduling sequence with reasonable priority.At the same time,in order to minimize the total energy consumption,the constrained optimization algorithm based on ant colony system algorithm is used to obtain the approximate optimal scheduling scheme in the global.Compared with other algorithms,the experimental results show that the proposed algorithm can effectively reduce the energy consumption of processing all tasks,while ensuring reasonable scheduling length and reducing the failure rate of associated tasks scheduling with mixed deadlines.