A Quality of Service Based Energy Efficiency Evaluation Method for Data Centers

Abstract

The invention proposes a data center energy efficiency evaluation method based on service quality, constructs a data center service quality evaluation index system including a target layer, a decision layer and an influencing factor layer; constructs a judgment matrix, and calculates the weight vector of each decision layer and each decision layer. The weight vector of the influencing factor layer in the index; divide the service quality of the data center into G grades, and combine the relevant information of the data center service quality influencing factor layer to obtain the service quality evaluation level of each influencing factor; calculate the service quality of each decision-making level indicator Evaluation matrix; the service quality value of the data center is obtained through the fuzzy comprehensive evaluation method. The invention constructs a more systematic and comprehensive evaluation index system, and solves the problem of objective weight distribution in decision-making with multiple influencing factors through the analytic hierarchy process, and at the same time uses the fuzzy comprehensive evaluation method to quantify the service quality; Propose improvement measures to avoid single and one-sided evaluation of service quality.

Description

technical field [0001] The invention belongs to the field of cloud computing, and in particular relates to a data center energy efficiency evaluation method based on service quality. Background technique [0002] Cloud computing is an Internet-based model for the addition, use, and delivery of related services, often involving the provision of dynamically scalable and often virtualized resources over the Internet. The virtualization of software and hardware resources by cloud services increases the power of a single server. Large-scale cloud computing data centers consume a lot of energy, which is several times or even dozens of times that of traditional data centers. With the development of cloud computing technology, data center technology has become one of the most concerned issues in the field of cloud computing. [0003] The advent of the cloud era has made the problem of high energy consumption in data centers more and more serious. High performance, low energy consum...

AI Technical Summary

Problems solved by technology

[0004] The existing data center energy efficiency evaluation methods mostly subjectively select the evaluation indicators of different aspects of the existing data center, and assign corresponding weights through expert knowledge, so as to obtain an evaluation level of data center energy efficiency, which is applied to various data center energy efficiency The comparison among them gives a rough sorting result; most of the studies on data center service quality use the user evaluation matrix to obtain the overall evaluation value based on the user’s rating of the recent service, but the specific user evaluation is not given. For which aspects, the correspondence between these aspects and data center data

The existing evaluation model can only obtain the energy efficiency level of the data center, not the specific value, and cannot reflect the improvement of the energy efficiency of a single data center before and after; at the same time, the existing evaluation model simply uses the evaluation value of service quality and the energy consumption of the data center The ratio of the data center represents the energy efficiency of the data center, and there is a certain degree of subjectivity in the selection of service quality parameters. The user evaluation matrix introduced can only reflect the user's feelings and cannot be combined with the real situation of the data center; for the service quality parameter weight The assigned value lacks objectivity; at the same time, these evaluation models can only obtain an overall evaluation value, but cannot obtain specific deficiencies in the service quality of the data center, resulting in the inability to obtain targeted improvement plans

Images