Bi-level Expansion Planning of Data Centers With Electricity-heat-computation Coupling System Based on Data-driven Scenario Generation

YANG Lingfang; LIN Yujie; ZHANG Ziquan; YANG Qiang

doi:10.13334/j.0258-8013.pcsee.252049

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Bi-level Expansion Planning of Data Centers With Electricity-heat-computation Coupling System Based on Data-driven Scenario Generation

更新时间：2026-10-10

- Bi-level Expansion Planning of Data Centers With Electricity-heat-computation Coupling System Based on Data-driven Scenario Generation
- Vol. 46, Issue 15, Pages: 6148-6160(2026)
- 作者机构：
  
  1. 1 浙江大学电气工程学院,浙江省,杭州市,310027
  2. 2 中国南方电力调度控制中心,广东省,广州市,510663
- 作者简介：
- 基金信息：
- DOI：10.13334/j.0258-8013.pcsee.252049
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
YANG Lingfang, LIN Yujie, ZHANG Ziquan, et al. Bi-level Expansion Planning of Data Centers With Electricity-heat-computation Coupling System Based on Data-driven Scenario Generation[J]. 2026, 46(15): 6148-6160.
DOI：

YANG Lingfang, LIN Yujie, ZHANG Ziquan, et al. Bi-level Expansion Planning of Data Centers With Electricity-heat-computation Coupling System Based on Data-driven Scenario Generation[J]. 2026, 46(15): 6148-6160. DOI： 10.13334/j.0258-8013.pcsee.252049.

摘要

为应对数据中心绿色转型过程中面临的不确定性规划挑战，该文提出一种数据驱动的扩展规划方法。首先，构建基于多通道一维U-net的扩散模型，生成源荷多元时间序列场景，以刻画不确定性；其次，建立电-热-算耦合系统扩展规划模型，以总经济成本最小为目标，并考虑各服务器的独立运行状态与CPU温度约束；再次，针对服务器能耗模型的非线性特性，设计一种启发式双层求解策略，上层通过启发式算法优化服务器配置数量，并将其作为固定参数传递至下层，从而使原问题线性化，下层调用求解器直接求解模型，得到总成本并反馈至上层，反复迭代以确定服务器、冷却系统和能源设备的最佳容量；最后，基于改进的18节点热力系统和IEEE-14节点电力系统的仿真结果表明，所提方法能有效表征源荷不确定性，在提升数据中心能效的同时显著降低经济成本。

Abstract

This work proposes a data-driven expansion planning solution

aiming at environmentally friendly upgrading and uncertainty modelling of data centers (DCs). Firstly

a multi-channel one-dimensional U-net based diffusion model is designed to generate scenarios of source-load multivariate time series

thus coping with the uncertainties. Then

an electricity-heat-computation coupling system expansion model is established

which considers CPU temperature constraints and individual status of servers with the objective of minimizing performance cost. To deal with the non-linearity of server model

a heuristic bi-level solving scheme is presented. At the upper level

the configured number of servers is determined by heuristic algorithm and transferred to the lower lever as a constant

thus making the planning model linear. At the lower level

the planning model is directly solved by commercial solver

and the performance cost is submitted back to the upper level

thereby iteratively obtaining the optimal capacities of servers

cooling systems and energy equipment. Based on a modified 18-node district heating system and an IEEE-14 bus power system

the numerical results confirm that the proposed solution can effectively characterize the source-load uncertainties

improve the energy efficiency and reduce economic cost of DCs.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Data-driven Modeling of Organic Rankine Cycle Based on Long Short-term Memory Networks

A Review on Global Multiphysics Numerical Simulation Techniques and Applications of DC Arc Plasma Torch

A Review of Power System Planning Method and Impact Assessment of “Source-grid-load” Integrating Electric Meteorology

Research Progress on the Kinetic Reaction Mechanism of Hydrogen-enriched Methane Combustion

The impact of green transformational leadership on radical green innovation

Related Author

No data

Related Institution

No data

AI问答

⁰