Dynamic Deployment and Scheduling Strategy for Dual-Service Pooling Based Hierarchical Cloud Service System in Intelligent Buildings
ABSTARCT :
Due to the excessive concentration of computing resources in the traditional centralized cloud service system, there will be three prominent problems of management confusion, construction cost and network delay. Therefore, we propose to virtualize regional edge computing resources in intelligent buildings as edge service pooling, then presents a hierarchical cloud platform with dual-service pooling structure and a dynamic strategy for the proposed model. The analytic hierarchy process (AHP) based quality of service (QoS) evaluation mechanism and the dynamic normal distribution selection method are adopted for service deployment. And the dynamic inertia particle swarm optimization (DI-PSO) algorithm is employed to realize task scheduling. Furthermore, the cloud platform and existing terminal server group are used to conduct platform structure comparison experiments, and the popular task scheduling algorithms are selected for simulation experiments. Experimental results of platform measurement show that the average service response time of different services can be improved by about 17.3% to 37.4%. The average occupancy ratio of computing resources can be reduced by about 5%. The simulation results show that the earliest completion time of single task list can be decreased by 11.3% to 20.9%, and the makespan of 100 task lists can be improved by 0.3 times.
EXISTING SYSTEM :
? Many of these algorithms are novel or are developed on the top of some existing methods incorporating more scheduling parameters to improve the performance.
? It includes the execution time and delay caused by the cloud system. Minimizing completion time of tasks is considered by many of the existing scheduling algorithms.
? It helps to identify the scheduling attributes which are considered most and which all is less significant in different algorithms so that better algorithms can be developed by including least considered metrics or combining them with other metrics in existing algorithms to get a good overall performance.
? Fault tolerance and reliability are also considered in fewer amounts in existing methods.
DISADVANTAGE :
? In this paper we introduce a classification of the scheduling problem in distributed systems by presenting a taxonomy that incorporates recent developments, especially those in cloud computing.
? We first introduce the problem of scheduling in distributed systems, covering advances in scheduling in cluster and grid computing.
? The scheduling problem is NP-Complete, although there exist polynomial time solutions for few scenarios.
? we present how the scheduling problem in cloud computing has been developed, and discuss scheduling peculiarities and major challenges in cloud computing.
? With billions of devices data streams realizing a set of operations, the scale of the scheduling problem can make current decision making methods unfeasible.
PROPOSED SYSTEM :
• In an algorithm is proposed based on the divisible load theory which aims to reduce the overall processing time of the tasks.
• In they propose an algorithm which is a modification done on the improved max-min algorithm.
• It is based on the expected execution time in which it assigns a task with average execution time on the machine which gives minimum completion time.
• In they propose a green energy efficient method of scheduling using the DVFS technique.
• Using Dynamic Voltage Frequency Scaling method it reduces the power consumption of infrastructure.
ADVANTAGE :
? Multimedia and e-Science are examples of applications that handle large data sets nowadays, putting in evidence the importance of communications to improve performance and support quality of service offering in distributed systems.
? The DAG scheduling algorithms for multiprocessors have been adapted for scheduling in distributed systems, incorporating intrinsic characteristics of such systems for an enhanced performance.
? Regarding the scheduling itself, the classification includes system architecture, decision making, planning scheme, strategies, and performance estimation.
? Research assuming that the scheduler has information about resources bandwidth, memory, and processors quantity and performance, as well as jobs computation and communication costs, is very common.
|