Dynamic frequency scaling of multi-core processor in wireless communication networks
The disclosure describes a method and system for dynamic frequency scaling of multi-core processor in wireless communication networks. The method comprising: transmitting, by a network node (NN), core-load data and a plurality of key indicators of each core group of a plurality of core groups in the multi-core processor to a central management entity (CME); receiving, by the NN, a core-load prediction model associated for each core group from the CME; determining, by the NN, an estimated core-load data for each core group using the associated core-load prediction model and determining, by the NN, a maximum estimated core-load data among the estimated core-load data of each core group; and determining, by the NN, an optimum multi-core processor frequency for the network node based on the maximum estimated core-load data.
1. A method for dynamic frequency scaling of a multi-core processor in a wireless communication network, the method comprising:
transmitting, by a network node, core-load data and a plurality of key indicators of each core group of a plurality of core groups in the multi-core processor to a central management entity (CME);
receiving, by the network node, a core-load prediction model associated for the each core group from the CME in response to the transmission, the core-load prediction model being determined based on the core-load data and the plurality of key indicators of the each core group;
determining, by the network node, an estimated core-load data for the each core group based on the plurality of key indicators of each core group using the associated core-load prediction model;
determining, by the network node, a maximum estimated core-load data among the estimated core-load data of each core group; and
determining, by the network node, a multi-core processor frequency for the network node based on the maximum estimated core-load data.
2. The method as claimed in claim 1 , wherein associated one or more key indicators from the plurality of key indicators of the each core group is determined for predicting future core-load data in the multi-core processor using a feature selection technique in machine learning,
wherein a relationship between the future core-load data for the each core group and the associated one or more key indicators is learned to build the core-load prediction model associated for each core group using a machine learning technique.
3. The method as claimed in claim 1 , wherein prior to determining the estimated core-load data for each core group based on the plurality of key indicators of each core group using the associated core-load prediction model, the method further comprising:
training a core-load and frequency relationship model to be utilized to increase a current processor frequency to an optimum frequency for which the estimated core-load data becomes less than an upper threshold limit, based on the estimated core-load data being above the upper threshold limit and to decrease the current processor frequency to the optimum frequency for which the estimated core-load data remains less than the upper threshold limit, based on the estimated core-load data being below a lower threshold limit.
4. The method as claimed in claim 1 , wherein the each core group of the plurality of core groups in the multi-core processor comprises of one or more processor cores used by an application.
5. The method as claimed in claim 1 , wherein the plurality of key indicators comprise at least one of average core-load data, individual core-load data, a downlink throughput data, an uplink throughput data, an average downlink throughput data, and an average uplink throughput data.
6. The method as claimed in claim 1 , further comprising:
scaling a current multi-core processor frequency of the multi-core processor to the determined multi-core processor frequency.
7. The method as claimed in claim 6 , wherein the scaling the current multi-core processor frequency comprises changing the current multi-core processor frequency in steps of one frequency level each time or by changing the current multi-core processor frequency in steps of multiple frequency levels each time.
8. The method as claimed in claim 1 , further comprising:
detecting an unexpected core-load in at least one of the core group of the plurality of core groups based on at least one of current core-load data, memory buffer data, and network traffic data; and
scaling a current multi-core processor frequency of the multi-core processor to a maximum multi-core processor frequency based on detecting the unexpected core-load.
9. The method as claimed in claim 8 , wherein the unexpected core-load is detected based on at least one of the current core-load data, the memory buffer data, and the network traffic data increasing from a previous value being above an associated specified threshold value.
10. A network node for dynamic frequency scaling of a multi-core processor in a wireless communication network, comprising:
at least one processor comprising processing circuitry; and
a memory communicatively coupled to at least one processor, wherein the memory stores processor-executable instructions, and at least one processor, individually and/or collectively, is configured to:
transmit core-load data and a plurality of key indicators of each core group of a plurality of core groups in the multi-core processor to a central management entity (CME);
receive a core-load prediction model associated for the each core group from the CME in response to the transmission, the core-load prediction model being determined based on the core-load data and the plurality of key indicators of the each core group;
determine an estimated core-load data for the each core group based on the plurality of key indicators of each core group using the associated core-load prediction model;
determine a maximum estimated core-load data among the estimated core-load data of each core group; and
determine a multi-core processor frequency for the network node based on the maximum estimated core-load data.
11. The network node as claimed in claim 10 , wherein:
associated one or more key indicators from the plurality of key indicators of the each core group is determined for predicting future core-load data in the multi-core processor using a feature selection technique in machine learning,
wherein a relationship between the future core-load data for the each core group and the associated one or more key indicators is learned to build the core-load prediction model associated for each core group using a machine learning technique.
12. The network node as claimed in claim 10 , wherein prior to determining the estimated core-load data for each core group based on the plurality of key indicators of each core group using the associated core-load prediction model, the network node is configured to:
train a core-load and frequency relationship model to be utilized to increase a current processor frequency to an optimum processor frequency for which the maximum estimated core-load data becomes less than an upper threshold limit, based on the estimated core-load data being above the upper threshold limit and to decrease the current core group frequency to the optimum core group frequency for which the maximum estimated core-load data remains less than the upper threshold limit, based on the estimated core-load data being below a lower threshold limit.
13. The network node as claimed in claim 10 , wherein the each core group of the plurality of core groups in the multi-core processor comprises of one or more processor cores used by an application.
14. The network node as claimed in claim 10 , wherein the plurality of key indicators comprise at least one of average core-load data, individual core-load data, a downlink throughput data, an uplink throughput data, an average downlink throughput data, and an average uplink throughput data.
15. The network node as claimed in claim 10 , wherein the at least one processor is configured to:
scale a current multi-core processor frequency of the multi-core processor to the determined multi-core processor frequency.
16. The network node as claimed in claim 15 , wherein the scaling the current multi-core processor frequency comprises changing the current multi-core processor frequency in steps of one frequency level each time or by changing the current multi-core processor frequency in steps of multiple frequency levels each time.
17. The network node as claimed in claim 10 , wherein the at least one processor is configured to:
detect an unexpected core-load in at least one of the core group of the plurality of core groups based on at least one of current core-load data, memory buffer data, and network traffic data; and
scale a current multi-core processor frequency of the multi-core processor to a maximum multi-core processor frequency based on detecting the unexpected core-load.
18. The network node as claimed in claim 17 , wherein the unexpected core-load is detected based on at least one of the current core-load data, the memory buffer data, and the network traffic data increasing from a previous value being above an associated specified threshold value.
19. The network node as claimed in claim 17 , wherein the current core-load data of a highest loaded core in the core-group among the plurality of cores in core group is used to decide the multi-core processor frequency.
20. One or more non-transitory computer-readable storage media storing computer-executable instructions that, when executed by at least one processor of a network node, cause the network node to perform operations, the operations comprising:
transmitting core-load data and a plurality of key indicators of each core group of a plurality of core groups in the multi-core processor to a central management entity (CME);
receive a core-load prediction model associated for the each core group from the CME in response to the transmission, the core-load prediction model being determined based on the core-load data and the plurality of key indicators of the each core group;
determining an estimated core-load data for the each core group based on the plurality of key indicators of each core group using the associated core-load prediction model;
determine a maximum estimated core-load data among the estimated core-load data of each core group; and
determining a multi-core processor frequency for the network node based on the maximum estimated core-load data.