Energy resource management within a 5G radio access network
A method includes receiving, at one or more processing devices from application programming interfaces associated with one or more utility services providers, energy consumption data for each of a plurality of cell sites of a radio access network, accessing a machine learning model trained to determine, based on the energy consumption data, one or more operating parameters of the cell sites, the one or more operating parameters being indicative of corresponding usage levels of each of the plurality of cell sites, determining, based on an output of the machine learning model, a power resource configuration for the plurality of cell sites, specifying, for each of the plurality of cell sites, whether the corresponding cell site can be powered by a renewable energy source during a period of time in the future, and transmitting, via at least a subset of the APIs, a signal that identifies the power resource configuration.
1 . A method comprising:
receiving, from application programming interfaces (APIs) associated with one or more utility services providers, energy consumption data for each of a plurality of cell sites of a radio access network (RAN);
accessing a machine learning model trained to determine, based on the energy consumption data, one or more operating parameters of the cell sites, the one or more operating parameters being indicative of corresponding usage levels of each of the plurality of cell sites;
determining, based on an output of the machine learning model, a power resource configuration for the plurality of cell sites, the power resource configuration specifying, for each of the plurality of cell sites, whether the corresponding cell site can be powered by a renewable energy source during a period of time; and
transmitting, via at least a subset of the APIs, a signal that identifies the power resource configuration, the signal including a recommendation to switch at least one of the plurality of cell sites from a non-renewable energy source to the renewable energy source.
2 . The method of claim 1 , wherein receiving from APIs associated with one or more utility services providers, energy consumption data for each of a plurality of cell sites of a RAN comprises, receiving data on a periodic basis, that indicates energy usage and site load information.
3 . The method of claim 1 , wherein receiving from APIs associated with one or more utility services providers, energy consumption data for each of a plurality of cell sites of a RAN comprises, receiving data that indicates whether energy consumed is non-renewable energy or renewable energy.
4 . The method of claim 1 , wherein at least a first subset of the APIs associated with one or more utility service providers are configured to communicate with a control center associated with a utility service provider.
5 . The method of claim 1 , wherein at least a second subset of the APIs associated with one or more utility service providers are configured to communicate directly with one or more smart meters located at one or more cell sites of the RAN.
6 . The method of claim 1 , wherein determining, based on an output of the machine learning model, a power resource configuration for the plurality of cell sites comprises determining a power resource configuration that would reduce a load on a particular grid within the RAN, wherein the particular grid includes a subset of the plurality of cell sites.
7 . The method of claim 1 , further comprising analyzing the energy consumption data for each of the plurality of cell sites of the RAN to identify power consumption trends, trends in bands deployed by a RAN solution engine associated with the plurality of cell sites, and cell site traffic trends.
8 . The method of claim 1 , comprising:
transmitting a control signal to a particular cell site, wherein the control signal is configured to implement a band configuration at the particular cell site.
9 . The method of claim 1 , wherein the one or more operating parameters being indicative of corresponding usage levels of each of the plurality of cell sites comprises renewable energy usage, non-renewable energy usage, total daily energy consumption, site load information, daily cell site traffic trends, and daily band deployment trends.
10 . A system comprising:
one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
receiving, from application programming interfaces (APIs) associated with one or more utility services providers, energy consumption data for each of a plurality of cell sites of a radio access network (RAN);
accessing a machine learning model trained to determine, based on the energy consumption data, one or more operating parameters of the cell sites, the one or more operating parameters being indicative of corresponding usage levels of each of the plurality of cell sites;
determining, based on an output of the machine learning model, a power resource configuration for the plurality of cell sites, the power resource configuration specifying, for each of the plurality of cell sites, whether the corresponding cell site can be powered by a renewable energy source during a period of time; and
transmitting, via at least a subset of the APIs, a signal that identifies the power resource configuration, the signal including a recommendation to switch at least one of the plurality of cell sites from a non-renewable energy source to the renewable energy source.
11 . The system of claim 10 , wherein receiving from APIs associated with one or more utility services providers, energy consumption data for each of a plurality of cell sites of a RAN comprises, receiving data on a periodic basis, that indicates energy usage and site load information.
12 . The system of claim 10 , wherein receiving from APIs associated with one or more utility services providers, energy consumption data for each of a plurality of cell sites of a RAN comprises, receiving data that indicates whether energy consumed is non-renewable energy or renewable energy.
13 . The system of claim 10 , wherein at least a first subset of the APIs associated with one or more utility service providers are configured to communicate with a control center associated with a utility service provider.
14 . The system of claim 10 , wherein at least a second subset of the APIs associated with one or more utility service providers are configured to communicate directly with one or more smart meters located at one or more cell sites of the RAN.
15 . The system of claim 10 , wherein determining, based on an output of the machine learning model, a power resource configuration for the plurality of cell sites comprises determining a power resource configuration that would reduce a load on a particular grid within the RAN, wherein the particular grid includes a subset of the plurality of cell sites.
16 . The system of claim 10 , wherein the operations comprise analyzing the energy consumption data for each of the plurality of cell sites of the RAN to identify power consumption trends, trends in bands deployed by a RAN solution engine associated with the plurality of cell sites, and cell site traffic trends.
17 . The system of claim 10 , wherein the operations comprise:
transmitting a control signal to a particular cell site, wherein the control signal is configured to implement a band configuration at the particular cell site.
18 . The system of claim 10 , wherein the one or more operating parameters being indicative of corresponding usage levels of each of the plurality of cell sites comprises renewable energy usage, non-renewable energy usage, total daily energy consumption, site load information, daily cell site traffic trends, and daily band deployment trends.
19 . One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
receiving, from application programming interfaces (APIs) associated with one or more utility services providers, energy consumption data for each of a plurality of cell sites of a radio access network (RAN);
accessing a machine learning model trained to determine, based on the energy consumption data, one or more operating parameters of the cell sites, the one or more operating parameters being indicative of corresponding usage levels of each of the plurality of cell sites;
determining, based on an output of the machine learning model, a power resource configuration for the plurality of cell sites, the power resource configuration specifying, for each of the plurality of cell sites, whether the corresponding cell site can be powered by a renewable energy source during a period of time; and
transmitting, via at least a subset of the APIs, a signal that identifies the power resource configuration, the signal including a recommendation to switch at least one of the plurality of cell sites from a non-renewable energy source to the renewable energy source.
20 . The one or more non-transitory computer storage media of claim 19 , wherein receiving from APIs associated with one or more utility services providers, energy consumption data for each of a plurality of cell sites of a RAN comprises, receiving data on a periodic basis, that indicates energy usage and site load information.