Energy efficiency optimization method, system and joint modeling method for multi-tenant data center

Abstract

The invention relates to a multi-tenant data center energy efficiency optimization method, system and joint modeling method, including: based on the law of diminishing marginal returns, establishing a benefit function between the tenant's income and the number of servers currently used by the tenant; Server requirements, calculate the shared market unit price of servers; tenants determine the actual number of shared servers based on the market unit price, and managers use tenants' shared servers to build a public resource pool to migrate and integrate tenant loads. Therefore, the present invention can use the idle servers of the multi-tenant data center to implement migration and integration of tenant loads without relying on cloud providers, so as to reduce energy consumption. The invention also jointly models the server sharing incentive mechanism and the original energy-saving mechanism of the multi-tenant data center, and proposes a new approximation algorithm to ensure the authenticity and feasibility of the joint optimization model, and realize greater energy-saving cost optimization.

Description

technical field [0001] The present invention relates to the field of cloud computing and distributed systems, in particular to a multi-tenant data center energy efficiency optimization method, system and joint modeling method. Background technique [0002] With the rapid development of Internet technology, people's demand for large-scale computing and storage is increasing day by day, so data centers, as the core facilities of Internet technology, have developed rapidly. In recent years, with the rapid growth of the number and scale of data centers, huge energy consumption has become the main factor restricting its development. At the same time, due to the high energy consumption characteristics of the data center, the data center can play an increasingly important role in the emergency demand response project of the power grid, especially for the emergency demand response of the power grid, and the data center can be reduced through appropriate load scheduling. Power deman...

AI Technical Summary

Problems solved by technology

Compared with the previous method, this method further considers motivating tenants to optimize global energy efficiency, but this method still has two shortcomings: 1) If only the backup server and the cloud server in the current data center are considered to constitute public resources, in the implementation of the mechanism, there are There may be insufficient public resources, which will lead to a decrease in the implementation efficiency of the mechanism and affect energy efficiency optimization; 2) When renting cloud provider servers to supplement public resources, the cost depends on the cloud provider's pricing. If the price is too high, it will not be conducive to reducing energy efficiency Optimized total cost

Images