Systems and methods for accelerated computations in data-driven energy management systems

A method comprising:

• at one or more electronic devices each having one or more processors and memory:
• storing, in a database, data associated with a computer-based energy asset management system, wherein the energy asset management system is adapted for providing control in relation to a plurality controllable assets, wherein the controllable assets include electric vehicles (EVs);
• performing data summarization on an original dataset comprising data from the database to generate a summarized dataset, wherein the size of the summarized dataset is smaller than the size of the original dataset, wherein each of at least some records in the summarized dataset represents a plurality of records in the original dataset;
• training a computation model using data from the summarized dataset, wherein the computation model comprises an optimizer, wherein the training involves training the optimizer using data from the summarized dataset;
• and
• providing control in relation to the plurality of controllable assets using the trained computation model, wherein the providing control involves using the trained optimizer, and wherein the providing control using the trained optimizer involves scheduling of charging interactions for EVs.

A system, comprising:

• one or more processors;
• and
• memory storing instructions for execution by the one or more processors, the instructions for operations comprising:
• storing, in a database, data associated with a computer-based energy asset management system, wherein the energy asset management system is adapted for providing control in relation to a plurality controllable assets, wherein the controllable assets include electric vehicles (EVs);
• performing data summarization on an original dataset comprising data from the database to generate a summarized dataset, wherein the size of the summarized dataset is smaller than the size of the original dataset, wherein each of at least some records in the summarized dataset represents a plurality of records in the original dataset;
• training a computation model using data from the summarized dataset, wherein the computation model comprises a predictor, wherein the training involves training the predictor using data from the summarized dataset;
• generating predictions relating to charging interactions of EVs;
• and
• providing control in relation to the plurality of controllable assets using the trained computation model, wherein the providing control involves using predictions generated by the trained predictor, and wherein the providing control is based on the predictions relating to charging interactions of EVs.

A system, comprising:

• one or more processors;
• and
• memory storing instructions for execution by the one or more processors, the instructions for operations comprising:
• storing, in a database, data associated with a computer-based energy asset management system, wherein the energy asset management system is adapted for providing control in relation to a plurality controllable assets, wherein the controllable assets include electric vehicles (EVs);
• performing data summarization on an original dataset comprising data from the database to generate a summarized dataset, wherein the size of the summarized dataset is smaller than the size of the original dataset, wherein each of at least some records in the summarized dataset represents a plurality of records in the original dataset;
• training a computation model using data from the summarized dataset, wherein the computation model comprises an optimizer, wherein the training involves training the optimizer using data from the summarized dataset;
• and
• providing control in relation to the plurality of controllable assets using the trained computation model, wherein the providing control involves using the trained optimizer, and wherein the providing control using the trained optimizer involves scheduling of charging interactions for EVs.

A non-transitory computer-readable medium having computer-readable instructions stored thereon, the computer-readable instructions executable by at least one processor to cause the performance of operations comprising:

• storing, in a database, data associated with a computer-based energy asset management system, wherein the energy asset management system is adapted for providing control in relation to a plurality controllable assets, wherein the controllable assets include electric vehicles (EVs);
• performing data summarization on an original dataset comprising data from the database to generate a summarized dataset, wherein the size of the summarized dataset is smaller than the size of the original dataset, wherein each of at least some records in the summarized dataset represents a plurality of records in the original dataset;
• training a computation model using data from the summarized dataset, wherein the computation model comprises a predictor, wherein the training involves training the predictor using data from the summarized dataset;
• generating predictions relating to charging interactions of EVs;
• and
• providing control in relation to the plurality of controllable assets using the trained computation model, wherein the providing control involves using predictions generated by the trained predictor, and wherein the providing control is based on the predictions relating to charging interactions of EVs.

A non-transitory computer-readable medium having computer-readable instructions stored thereon, the computer-readable instructions executable by at least one processor to cause the performance of operations comprising:

• storing, in a database, data associated with a computer-based energy asset management system, wherein the energy asset management system is adapted for providing control in relation to a plurality controllable assets, wherein the controllable assets include electric vehicles (EVs);
• performing data summarization on an original dataset comprising data from the database to generate a summarized dataset, wherein the size of the summarized dataset is smaller than the size of the original dataset, wherein each of at least some records in the summarized dataset represents a plurality of records in the original dataset;
• training a computation model using data from the summarized dataset, wherein the computation model comprises an optimizer, wherein the training involves training the optimizer using data from the summarized dataset;
• and
• providing control in relation to the plurality of controllable assets using the trained computation model, wherein the providing control involves using the trained optimizer, and wherein the providing control using the trained optimizer involves scheduling of charging interactions for EVs.