Fan rotating speed determination model training method, network device energy saving method and device

Abstract

This application provides a fan speed determination model training method, a network device energy-saving method, and a device, belonging to the field of network device energy-saving optimization technology. The method involves environmental modeling: defining a state space based on the current temperature of the network device, the current fan speed of the network device, the current load flow of the network device, and the average load flow over a predetermined future step; determining the action space, using fan speed as the control variable; a state update mechanism: simulating the thermal behavior of real network devices, calculating the temperature of the network device at the next moment based on the current state, current action, and ambient temperature, and then updating the state; constructing a reward function: building a reward function based on temperature control accuracy, fan energy consumption, and control smoothness; and training a fan speed determination model based on this environmental modeling, which can determine the optimal fan speed command based on predicted load flow, further improving the fan energy-saving effect of network devices.

Images