Power cell tracking and optimization system
A computing system can receive and compile power cell data, and in certain examples, the power cell data can be distributed to a distributed ledger. The computing system can further determine approximate battery end of life (ABEL) for each power cell based on a compiled historical record of power cell data. Based on the determined ABEL, the computing system can generate ABEL reports for users, determine optimal settings for a power cell or battery-powered device, and/or transmit notifications to users, to facilitate power cell usage optimization, and/or optimal repurposing or recycling timing.
1 . A computing system comprising:
a network communication interface communicating, over one or more networks, with multiple power cell sources that include a plurality of power cells of different types;
one or more processors; and
one or more memory resources storing instructions that, when executed by the one or more processors, cause the computing system to perform operations comprising:
receiving, over the one or more networks, from the multiple power cell sources, power cell data specific to each of the different types of power cells;
receiving context data for each of the different types of power cells, wherein for each of the different types of power cells, the context data indicates at least one condition under which one or more power cell sources of that type operate;
recording the received power cell data in one or more data logs;
executing one or more machine learning models to generate based, at least in part, on the power cell data specific to each of the different types of power cells of the multiple power cell sources, an approximate battery end of life (ABEL) determination for each of the multiple power cell sources; and
receiving newly recorded power cell data as learning input for the one or more machine learning models, to improve an accuracy of the ABEL determination for at least one of the different types of power cells;
based at least in part on the newly recorded power cell data, executing the one or more machine learning models to update the ABEL determination for each of the multiple power cell sources; and
for each of the multiple power cell sources, determining an optimal setting or operating condition for improving the ABEL determination, based on the context data received for the respective type of power cell.
2 . The computing system of claim 1 , wherein the operations further comprise:
confirming or adjusting one or more metrics used by the one or more machine learning models based on the newly recorded power cell data.
3 . The computing system of claim 1 , wherein the operations further comprise:
organizing the one or more data logs based on an identifier of each power cell of the plurality of power cells, and a timestamp indicating when power cell data for each power cell was received.
4 . The computing system of claim 1 , wherein the operations include:
receiving, via an interface, a data request that identifies a power cell of the plurality of power cells; and
wherein the generated ABEL determination for the identified power cell uses power cell data recorded with the one or more data logs.
5 . The computing system of claim 4 , wherein the interface is provided via a website or as an application program interface.
6 . The computing system of claim 1 , wherein the multiple power cell sources include electric or hybrid vehicle batteries and battery-based home energy storage systems.
7 . The computing system of claim 1 , wherein the received power cell data is recorded on an immutable ledger.
8 . The computing system of claim 1 , wherein the operations include executing multiple machine learning models for different types of power cells.
9 . The computing system of claim 8 , wherein the operations include executing the one or more machine learning models for power cells that are second life power cells.
10 . The computing system of claim 1 , wherein the operations include determining, based on the ABEL determination, when a power cell of the plurality of power cells is at end of life, and transmitting, to a user, a recommendation for use of the power cell at end of life.
11 . The computing system of claim 10 , wherein the recommendation includes repurposing the power cell as a second life battery.
12 . A non-transitory computer-readable medium that stores instructions, which when executed by one or more processors of a computing system, cause the computing system to perform operations that include:
receiving, over one or more networks, from multiple power cell sources of different types, power cell data specific to each of the different types of power cells;
receiving context data for each of the different types of power cells, wherein for each of the different types of power cells, the context data indicates at least one condition under which one or more power cell sources of that type operate;
recording the received power cell data in one or more data logs;
executing one or more machine learning models to generate based, at least in part, on the power cell data specific to each of the different types of power cells of the multiple power cell sources, an approximate battery end of life (ABEL) determination for each of the multiple power cell sources;
receiving newly recorded power cell data as learning input for the one or more machine learning models, to improve an accuracy of the ABEL determination for at least one of the different types of power cells;
based at least in part on the newly recorded power cell data, executing the one or more machine learning models to update the ABEL determination for each of the multiple power cell sources; and
for each of the multiple power cell sources, determining an optimal setting or operating condition for improving the ABEL determination, based on the context data received for the respective type of power cell.
13 . The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise:
confirming or adjusting one or more metrics used by the one or more machine learning models based on the newly recorded power cell data.
14 . The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise:
organizing the one or more data logs based on an identifier of each power cell of the multiple power cell sources, and a timestamp indicating when power cell data for each power cell was received.
15 . The non-transitory computer-readable medium of claim 12 , wherein the operations include:
receiving, via an interface, a data request that identifies a power cell of the multiple power cell sources; and
wherein the generated ABEL determination for the identified power cell uses power cell data recorded with the one or more data logs.
16 . The non-transitory computer-readable medium of claim 15 , wherein the interface is provided via a website or as an application program interface.
17 . The non-transitory computer-readable medium of claim 12 , wherein the multiple of power cell sources include electric or hybrid vehicle batteries and battery-based home energy storage systems.
18 . The non-transitory computer-readable medium of claim 12 , wherein the received power cell data is recorded on an immutable ledger.
19 . The non-transitory computer-readable medium of claim 12 , wherein the operations include executing multiple machine learning models for the different types of power cells.
20 . A computer-implemented method comprising:
receiving, over one or more networks, from multiple power cell sources of different types, power cell data specific to each of the different types of power cells;
receiving context data for each of the different types of power cells, wherein for each of the different types of power cells, the context data indicates at least one condition under which one or more power cell sources of that type operate;
recording the received power cell data in one or more data logs;
executing one or more machine learning models to generate based, at least in part, on the power cell data specific to each of the different types of power cells of the multiple power cell sources, an approximate battery end of life (ABEL) determination for each of the multiple power cell sources;
receiving newly recorded power cell data as learning input for the one or more machine learning models, to improve an accuracy of the ABEL determination for at least one of the different types of power cells;
based at least in part on the newly recorded power cell data, executing the one or more machine learning models to update the ABEL determination for each of the multiple power cell sources; and
for each of the multiple power cell sources, determining an optimal setting or operating condition for improving the ABEL determination, based on the context data received for the respective type of power cell.