降低数据中心能耗的一个关键问题是降低空调系统的能耗。通过分析流场以及各个机柜负载对温度场的影响,阐明了各机恒负载对全场温升的影响。提出了温升影响矩阵的概念,并以此概念为基础,建立了负载分配优化算法。通过此算法优化分配负载后,全场最高温度能够尽可能降低。经过算例的计算与比较,验证了算法的可行性。 A key issue in reducing data center energy consumption is reducing the energy consumption of air conditioning systems. By analyzing the influence of the flow field and the load of each cabinet on the temperature field, the influence of constant load of each machine on the temperature rise of the entire field is clarified. The concept of temperature rise influence matrix is ​​put forward. Based on this concept, a load distribution optimization algorithm is established. Optimized through this algorithm to allocate load, the audience can minimize the maximum temperature. After the calculation and comparison of examples, the feasibility of the algorithm is verified.