CN-121996048-A - Machine learning of relationships between ambient air temperature and power consumption

Abstract

Embodiments of the present disclosure relate to machine learning of a relationship between ambient air temperature and power consumption. Example devices and techniques are described. An example device includes one or more processors and one or more memories storing instructions. The instructions, when executed, cause the one or more processors to determine a respective configuration environment temperature for each of the plurality of network devices. The instructions cause the one or more processors to determine a respective current traffic load on each of the plurality of network devices. The instructions cause the one or more processors to determine, for each of the plurality of network devices and based on the respective configuration ambient temperature and the respective current traffic load, a respective estimated power usage value. The instructions cause the one or more processors to sum the respective estimated power usage values to generate a total estimated power usage value and output a representation of the total estimated power usage value.

Inventors

• R. Komura
• G. B.M. Songkada
• SRIDHAR T
• YAVATKAR RAJENDRA S.

Assignees

• 瞻博网络公司

Dates

Publication Date

20260508

Application Date

20251105

Priority Date

20241108

Claims (20)

1. 1. A computing device, comprising: one or more processors, and One or more memories storing instructions that, when executed by the one or more processors, cause the one or more processors to: determining a respective configuration ambient temperature for each of a plurality of network devices; Determining a respective current traffic load on each of the plurality of network devices; determining, for each of the plurality of network devices and based on the respective configured ambient temperature and the respective current traffic load, a respective estimated power usage value; Generating a total estimated power usage value based at least in part on the respective estimated power usage values, and Outputting a representation of the total estimated power usage value.
2. 2. The computing device of claim 1, wherein the configured ambient temperature of a first network device of the plurality of network devices comprises a configured maximum operating temperature of the first network device.
3. 3. The computing device of claim 1, wherein to determine the respective estimated power usage values, the instructions cause the computing device to provide the respective configured ambient temperatures and the respective current traffic loads to one or more machine learning models to obtain the respective estimated power usage values.
4. 4. The computing device of claim 3, wherein the one or more machine learning models are trained using historical ambient temperature data, historical traffic load data, and historical power usage data.
5. 5. The computing device of any of claims 1-4, wherein the instructions further cause the computing device to: Determining an estimated ambient temperature for a first network device of the plurality of network devices based on the air temperature, the estimated ambient temperature including a programmable maximum operating temperature for the first network device, and Outputting a representation of the estimated ambient temperature of the first network device.
6. 6. The computing device of claim 5, wherein the air temperature comprises at least one of an inlet air temperature measured by a first temperature sensor located on or within the first network device, an average of a plurality of air temperatures measured by a plurality of temperature sensors located within the first network device, an inlet air temperature measured by a second temperature sensor located within a facility in which the first network device is located, or an outside temperature measured by a third temperature sensor located outside of the facility in which the first network device is located.
7. 7. The computing device of claim 5, wherein the estimated ambient temperature of the network device comprises a recommended maximum operating temperature of the network device.
8. 8. The computing device of claim 5, wherein to determine the estimated ambient temperature of the network device, the instructions cause the computing device to provide at least one of the air temperature or a fan speed of the first network device to one or more machine learning models to obtain the estimated ambient temperature of the network device.
9. 9. The computing device of claim 8, wherein the one or more machine learning models are trained based on at least two of historical air temperature data, historical fan speed data, or configured ambient temperatures for the plurality of network devices.
10. 10. The computing device of claim 5, wherein the representation of the estimated ambient temperature of the first network device comprises at least one of a visual representation of a recommended maximum operating temperature displayed via a user interface, or a command sent to the first network device to change a configuration ambient temperature of the first network device to the estimated ambient temperature of the network device.
11. 11. A computing method, comprising: Determining, by the one or more processors, a respective configuration ambient temperature for each of the plurality of network devices; Determining, by the one or more processors, a respective current traffic load on each of the plurality of network devices; Determining, by the one or more processors, for each of the plurality of network devices and based on the respective configuration environment temperature and the respective current traffic load, a respective estimated power usage value; generating, by the one or more processors, a total estimated power usage value based at least in part on the respective estimated power usage values, and Outputting, by the one or more processors, a representation of the total estimated power usage value to an output device.
12. 12. The computing method of claim 11, wherein the configured ambient temperature of a first network device of the plurality of network devices comprises a configured maximum operating temperature of the first network device.
13. 13. The computing method of claim 11, wherein determining the respective estimated power usage values comprises providing the respective configured ambient temperatures and the respective current traffic loads to one or more machine learning models to obtain the respective estimated power usage values.
14. 14. The computing method of claim 13, wherein the one or more machine learning models are trained using historical ambient temperature data, historical traffic load data, and historical power usage data.
15. 15. The computing method of any of claims 11 to 14, further comprising: Determining an estimated ambient temperature for a first network device of the plurality of network devices based on the air temperature, the estimated ambient temperature including a programmable maximum operating temperature for the first network device, and Outputting a representation of the estimated ambient temperature of the first network device.
16. 16. The computing method of claim 15, wherein the air temperature comprises at least one of an inlet air temperature measured by a first temperature sensor located on or within the first network device, an average of a plurality of air temperatures measured by a plurality of temperature sensors located within the first network device, an inlet air temperature measured by a second temperature sensor located within a facility in which the first network device is located, or an outside temperature measured by a third temperature sensor located outside of the facility in which the first network device is located.
17. 17. The computing method of claim 15, wherein determining the estimated ambient temperature of the network device comprises providing at least one of the air temperature or a fan speed of the first network device to one or more machine learning models to obtain the estimated ambient temperature of the network device.
18. 18. The computing method of claim 17, wherein the one or more machine learning models are trained based on at least two of historical air temperature data, historical fan speed data, or configured ambient temperatures for the plurality of network devices.
19. 19. The computing method of claim 15, wherein the representation of the estimated ambient temperature of the first network device comprises at least one of a visual representation of a recommended maximum operating temperature displayed via a user interface, or a command sent to the first network device to change a configuration ambient temperature of the first network device to the estimated ambient temperature of the network device.
20. 20. A computer readable storage medium encoded with instructions for causing one or more programmable processors to perform the method of any of claims 11-19.

Description

Machine learning of relationships between ambient air temperature and power consumption Cross Reference to Related Applications The present application claims united states patent application 19/341,916, entitled "MACHINE LEARNING OF RELATIONSHIP BETWEEN AMBIENT AIR TEMPERATURE AND POWER CONSUMPTION", filed 26 at 9, 2025, which claims united states provisional patent application 202441085971, entitled "MACHINE LEARNING OF RELATIONSHIP BETWEEN AMBIENT AIR TEMPERATURE AND POWER CONSUMPTION", filed 8 at 11, 2024, each of which is incorporated herein by reference in its entirety. Technical Field The present disclosure relates to computer network facilities using electricity. Background In a typical cloud data center environment, there is a large collection of interconnected servers that provide computing and/or storage capacity to run various applications. For example, a data center may include facilities that host applications and services for subscribers (e.g., customers of the data center). The data center may, for example, host all infrastructure equipment such as networking and storage systems, redundant power supplies, and environmental controls. In a typical data center, clusters of storage servers and application servers (compute nodes) are interconnected by a high-speed switching fabric provided by one or more layers of physical network switches and routers. More complex data centers provide user support equipment located in various physical host facilities for infrastructure throughout the world. As data centers become larger, the energy usage of the data centers increases. Some large data centers require large power (e.g., about 100 megawatts), which is sufficient to power a large number of households (e.g., about 80000). Data centers may also run compute and data-intensive application workloads, such as cryptographic mining and machine learning applications, that consume large amounts of energy. As energy usage increases, data center customers and data center suppliers themselves have become more concerned about efficient use of power. Disclosure of Invention In general, techniques for power management of network devices are described. In particular, techniques are described for determining a recommended chassis ambient temperature (e.g., recommended maximum operating temperature) for a network device and for using machine learning based power estimation of the ambient temperature. Network devices typically have a maximum operating temperature that can be set by a network administrator, which may sometimes be referred to as an ambient temperature. The maximum fan speed may be determined by the configuration ambient temperature. As the fan speed increases, the power consumption of the device also increases. When the temperature is higher, the device typically consumes more power because the fan must run at a higher speed to keep the chassis temperature within set limits (e.g., below the maximum operating temperature). Traditionally, an administrator may monitor outside weather temperatures and adjust the ambient temperature of the network device accordingly. Conventional networks may waste power if an administrator forgets or ignores configuring the ambient temperature based on external conditions. This is particularly noticeable when the external temperature is significantly lower than the ambient temperature of the current configuration. Moreover, because the power consumption of the network device and the entire network is affected by the ambient temperature, network administrators often struggle to allocate an appropriate amount of power without knowing the power requirements associated with the different environmental settings. Traditionally, network administrators may typically rely on external weather conditions to determine the appropriate ambient temperature for each network device in a network configuration. However, once a network administrator establishes such an ambient temperature value, the network administrator may still be uncertain as to how the configuration will affect power consumption. Such uncertainty may lead to oversubscription or undersubscription of power at the grid, resulting in wasted energy and increased costs, or conversely, power shortages in conventional networks. The techniques of this disclosure may determine a recommended ambient temperature for the network device and/or may estimate a power demand associated with the current traffic load based on the ambient temperature(s). Accordingly, the techniques of this disclosure may provide particular improvements to the computer-related art of computer network and data center power management that may have one or more practical applications. For example, when the cool air supplied to a data center or other network facility has a lower temperature, such a technique may result in a power savings over the electrical facility of a conventional data center by reducing the ambient temperature and thereby reducing the fan speed