A provincial and municipal access data center optimization method for a power customer service center to predict the number of potential users based on a logistic model

Abstract

The invention relates to a provincial and municipal access data center optimization method for a power customer service center to predict the number of potential users based on a logistic model. The specific technical scheme is as follows of according to existing access user samples and common user samples, collecting and judging the elements influencing the access of a user to a data center; according to the influence factors in the step 1, adopting a logistic regression method to train samples to obtain a regression model used for calculating the potential user probability of each province and city; estimating the potential user number of each province and city according to the access probability in the step 2; and establishing an optimization model of the provincial and municipal user access data center and obtaining an optimization scheme of the provincial and municipal user access data center. According to the present invention, the number of potential users of each province and city is estimated through the logistic logistic regression model, the maximum load capacity and the resource utilization rate of each data center are considered, and the province and city access data center problem is converted into an optimization model which considers the load balance and the time delay in a tradeoff mode by adjusting the size of a harmonic coefficient.

Description

Technical field: [0001] The invention relates to the technical field of intelligent customer service, in particular to a provincial and municipal access data center optimization method for predicting the number of potential users by a power customer service center based on a logistic model. Background technique: [0002] State Grid Power Supply Customer Service Center (code 95598) is a professional support department of State Grid marketing management, an important window for external service of service brands, and a frontier for disseminating corporate culture and social responsibility. It provides 95598 services with unified national standards for electricity customers and a population of 1.1 billion. In this process, for the requirements of high concurrent access, massive data processing, emergency response and rapid disaster recovery, it is a necessary development trend for traditional large-scale data centers to realize multiple activities in the same city or in differe...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides an optimization algorithm for provincial and municipal access data centers based on the logistic model, which is used to solve the defects in the prior art that the number of potential users in the area and the maximum user load of each center are not effectively considered.

Images