A Two-Stage Stochastic Optimization Method and System for Data Centers Considering Wind and Solar Uncertainty

Abstract

This invention relates to the field of data center optimization technology, specifically disclosing a two-stage stochastic optimization method and system for data centers that considers the uncertainties of wind and solar power. The method includes: modeling the data center power supply system; generating wind and solar power output samples based on Monte Carlo simulations; using Koleski decomposition to ensure that the generated random samples satisfy the complementarity of wind and solar power output; introducing a first-order autoregressive model and combining it with a multivariate normal distribution to generate random scenarios, obtaining wind and solar power output curves for each scenario; constructing a two-stage stochastic optimization model that includes computing power scheduling and multi-energy coordination, with the objective of minimizing the expected operating cost of the system; solving the model; and determining the optimal time-series operation strategy for computing power tasks. This invention's two-stage stochastic optimization covers the adjustment costs caused by prediction errors with a lower risk premium, providing effective support for the reliable operation of data centers under conditions of fluctuating renewable energy output and time-series mismatch of computing power load.

Images