EP-4742002-A1 - EFFICIENT POWER MANAGEMENT OF NETWORK DEVICES

EP4742002A1EP 4742002 A1EP4742002 A1EP 4742002A1EP-4742002-A1

Abstract

Techniques are disclosed for improved energy efficiency of network devices of a network system. For example, a computing system obtains time series data comprising information about computing devices of a computer network. The computing devices access other devices of the computer network via network devices that exchange network traffic of the computing devices. The computing system applies a machine learning system, trained with historical time series data, to the obtained time series data to predict a requirement of one or more of the network devices for exchanging network traffic of the computing devices for a next time interval. The computing system adjusts, based at least in part on the predicted requirement for the next time interval, operation of the one or more of the network devices.

Inventors

KOMMULA, RAJA
SUNKADA, Ganesh Byagoti Matad
SRIDHAR, THAYUMANAVAN
YAVATKAR, RAJ
KANNIAPPAN, Murugan

Assignees

Juniper Networks, Inc.

Dates

Publication Date: 20260513
Application Date: 20251107

Claims (15)

A computing system comprising: storage media; and processing circuitry in communication with the storage media, the processing circuitry configured to: obtain time series data comprising information about computing devices of a computer network, wherein the computing devices access other devices of the computer network via network devices that exchange network traffic of the computing devices; apply a machine learning system, trained with historical time series data, to the obtained time series data to predict a requirement of one or more of the network devices for exchanging network traffic of the computing devices for a next time interval; and adjust, based at least in part on the predicted requirement for the next time interval, operation of the one or more of the network devices.
The computing system of claim 1, wherein the computing devices comprise servers hosting one or more application workloads, wherein the information about the computing devices indicates a power throttling state of each of the servers, and wherein the historical time series data indicates historical power throttling states of the servers and historical network bandwidth usage of the network devices corresponding in time to the power throttling states of the servers.
The computing system of any of claims 1-2, wherein the computing devices comprise servers hosting application workloads, wherein the information about the computing devices indicates a central processing unit, CPU, usage or a graphic processing unit, GPU, usage of each of the servers, and wherein the historical time series data indicates historical CPU usage or GPU usage of the servers and historical network bandwidth usage of the network devices corresponding in time to the CPU usage or GPU usage of the servers.
The computing system of any of claims 1-3, wherein the computing devices comprise servers hosting application workloads, wherein the information about the computing devices indicates a resource utilization of each of the servers, and wherein the historical time series data indicates historical resource utilization of the servers and historical network bandwidth usage of the network devices corresponding in time to the resource utilization of the servers.
The computing system of any of claims 1-4, wherein the computing devices comprise servers hosting application workloads, and wherein the information about the computing devices indicates a network traffic intensity of each of the application workloads, and wherein the historical time series data indicates historical network traffic intensities of the application workloads hosted by the servers and historical network bandwidth usage of the network devices corresponding in time to the network traffic intensities of the application workloads.
The computing system of any of claims 1-5s, wherein the computing devices comprise user equipment, UE, devices, and wherein the network devices comprise wireless Access Points, APs, wherein the information about the computing devices indicates an operating channel frequency of each of the UE devices, and wherein the historical time series data indicates operating channel frequencies of the UE devices and network usage patterns of the wireless APs corresponding in time to the operating channel frequencies of the UE devices.
The computing system of any of claims 1-6, wherein the network device is configured to use one or more of a first operating channel operating at a first frequency comprising about a 2.5 GHz band and a second operating channel operating at a second frequency comprising about a 5 GHz band, and wherein to adjust the operation of the network device, the processing circuitry is configured to: enable the first operating channel and disable the second operating channel; or enable both of the first operating channel and the second operating channel.
The computing system of any of claims 1-7, wherein, to adjust the operation of the one or more of the network devices, the processing circuitry is configured to adjust one or more operational parameters affecting energy consumption of the network device.
The computing system of any of claims 1-8, wherein, to adjust the operation of the network device, the processing circuitry is configured to adjust at least one of: an operational state of a packet processing unit of the network device; a power budget for one or more packet processing units of the network device; a clock frequency of a central processing unit, CPU, of the network device; or a power level of an antennae or radio of the network device.
The computing system of any of claims 1-9, wherein the requirement comprises a network performance requirement, and wherein the processing circuitry is configured to adjust the operation of the one or more network devices by adjusting one or more operational parameters that increase a network bandwidth throughput of the one or more network devices based on a prediction by the machine learning system of an increase in the network performance requirement for the next time interval as compared to a past network performance requirement for a previous time interval.
The computing system of any of claims 1-9, wherein the requirement comprises a network performance requirement, and wherein the processing circuitry is configured to adjust the operation of the one or more network devices by adjusting one or more operational parameters that decrease a network bandwidth throughput of the one or more network devices based on a prediction by the machine learning system of a decrease in the network performance requirement for the next time interval as compared to a past network performance requirement for a previous time interval.
The computing system of any of claims 1-11, wherein the machine learning system is trained with historical time series data of the computing devices and the network devices.
A method comprising: obtaining, by processing circuitry of a computing system, time series data comprising information about computing devices of a computer network, wherein the computing devices access other devices of the computer network via network devices that exchange network traffic of the computing devices; applying, by the processing circuitry, a machine learning system, trained with historical time series data, to the obtained time series data to predict a requirement of one or more of the network devices for exchanging network traffic of the computing devices for a next time interval; and adjusting, by the processing circuitry and based at least in part on the predicted requirement for the next time interval, operation of the one or more of the network devices.
The method of claim 13, further comprising steps corresponding to the functionality recited in any of claims 2-12.
Computer-readable media comprising instructions that, when executed by one or more programmable processors, cause the one or more programmable processors to become configured to carry out the method of any of claims 13-14.

Description

This application claims the benefit U.S. Utility Patent Application 19/352,233, which was filed on October 7, 2025, which claims the benefit of India Provisional Patent Application No. 202441085871, which was filed on November 8, 2024, the entire content of each of which are incorporated herein by reference. TECHNICAL FIELD This disclosure relates to computer networks and, more specifically, to improving energy efficiency in computer networks. BACKGROUND A computer network is a collection of interconnected network devices that can exchange data and share resources. In a packet-based network, such as an Ethernet network, the network devices communicate data by dividing the data into variable-length blocks called packets, which are individually routed across the network from a source device to a destination device. The destination device extracts the data from the packets and assembles the data into its original form. Certain network devices or nodes, such as routers, maintain routing information that describes routes through the network. Routers often have many central processing unit (CPU) cores and require a significant amount of memory and energy usage to support various tasks, such as management of the control plane and routing packets. In some cases, a router may have more than one hundred CPU cores, and many hundreds of gigabytes of random access memory. As enterprise networks, service provider networks, other types of networks, and data centers become larger, their overall energy usage increases. Some large data centers require a significant amount of power-enough to power many homes simultaneously. Data centers may also run application workloads that are compute- and data-intensive, such as cryptocurrency mining and machine learning applications, and consume a significant amount of energy. To be more energy efficient, some networks may source energy from renewable energy sources. However, the configuration of networks, data centers, and/or the applications that run on such networks are constantly changing and networks are often unable to dynamically increase their energy efficiency. SUMMARY Particular aspects are set out in the appended independent claims. Various optional embodiments are set out in the dependent claims. This disclosure describes techniques for improving and/or reducing power requirements and energy consumption by network devices that exchange network traffic of computing devices of a computing network. As an example, this may be useful in a data center network, so that the data center consumes less energy, while devices of the network maintain expected performance levels. In an example of the techniques of the disclosure, a power management controller of a computing system obtains time series data. The time series data comprises information about the computing devices of the computer network. In some examples, the information indicates, e.g., a power throttling state of the computing devices, a resource utilization, such as a central processing unit (CPU) usage or a graphic processing unit (GPU) usage, a network traffic intensity of one or more applications executed by the computing devices, an operating channel frequency on which the computing devices operate, or network usage patterns of the computing devices. The power management controller collects such metrics for each computing device of the computing devices and for each time interval of a plurality of time intervals. The power management controller applies a machine learning system, trained with historical time series data for the computing devices and the network devices, to the obtained time series data to predict a requirement for exchanging network traffic of each of the computing devices for a next time interval. Based at least in part on the predicted requirement for the next time interval, the power management controller adjusts operation of one or more network devices of the network devices. For example, based on a prediction that the computing devices may generate less network traffic over the next time interval as compared to a previous time interval, the power management controller described herein may adjust operation of one or more network devices of the network devices so as to decrease performance, such as by reducing a network throughput, deactivating one or more radios, or reducing an energy consumption of the one or more network devices, etc. In a similar fashion, based on a prediction that the computing devices may generate more network traffic over the next time interval as compared to a previous time interval, the power management controller may adjust operation of one or more network devices of the network devices so as to increase performance, such as by increasing a network throughput, activating one or more radios, or increasing an energy consumption of the one or more network devices. The techniques of the disclosure may provide specific improvements to the computer-related field of computer network