System for configuring demand response for energy grid assets

A non-transitory computer readable medium comprising software code for controlling a frequency control response of a plurality of assets connected to an electricity distribution grid, the plurality of assets arranged to supply electrical energy to and/or consume electrical energy from the grid, and configurable to adjust energy flow to or from the grid in response to changes in operating conditions of the grid, wherein the grid is arranged to operate at a predetermined grid frequency, the software code adapted, when executed on one or more data processing devices, to perform operations including:

• for each of a plurality of assets, the plurality of assets being arranged to supply electrical energy to and/or consume electrical energy from the grid, and configurable to adjust energy flow to or from the grid in response to changes in operating conditions of the grid, wherein the grid is arranged to operate at a predetermined grid frequency, and wherein at least one of the plurality of assets has a non-linear asset demand response configuration specifying a demand response of the asset to variations in frequency of the grid detected at the asset, measuring a local grid frequency measurement via a sensor;
• for each of the plurality of assets, accessing a mapping, the mapping arranged to:
• receive an asset demand response configuration as input;
• and
• output one or more performance indicators relating to the operation of the asset in relation to a required demand response service when operated using the asset configuration;
• determining, by an optimization function, an optimization metric comprising a measure of the effectiveness of the plurality of assets at implementing a desired demand response, the optimization function taking inputs based on the performance indicators output by the mappings;
• performing a search process to determine an altered optimization metric by varying an asset demand response configuration for one or more of the plurality of assets, wherein the search process is continued until a termination criterion is met of the altered optimization metric;
• determining updated asset demand response configurations for the plurality of assets based on the altered optimization metric;
• transmitting the updated asset demand response configurations to one or more asset control devices associated with the plurality of assets;
• and
• performing frequency control response by controlling in real-time, by the control devices, energy flow between the plurality of assets and the grid in accordance with the updated asset configurations and in response to measured changes in frequency of the grid corresponding to the measured local grid frequencies;
• wherein controlling the energy flow between the plurality of assets and the grid comprises, via the control devices, adjusting power set points for the assets based on the updated asset configurations.

A computer system comprising one or more processors with associated memory configured to:

• for each of a plurality of assets, the plurality of assets being arranged to supply electrical energy to and/or consume electrical energy from the grid, and configurable to adjust energy flow to or from the grid in response to changes in operating conditions of the grid, wherein the grid is arranged to operate at a predetermined grid frequency, and wherein at least one of the plurality of assets has a non-linear asset demand response configuration specifying a demand response of the asset to variations in frequency of the grid detected at the asset, measure a local grid frequency measurement via a sensor;
• access, for each of the plurality of assets, a trained neural network model, the neural network model trained using historical grid frequency data arranged to:
• receive an asset demand response configuration as input;
• and
• output one or more performance indicators relating to the operation of the asset in relation to a required demand response service when operated using the asset configuration;
• wherein the plurality of assets are connected to an electricity distribution grid that provides a demand response service, and wherein the assets are arranged to supply electrical energy to and/or consume electrical energy from the grid, and are configurable to adjust energy flow to or from the grid in response to changes in operating conditions of the grid;
• determine, by an optimization function, an optimization metric comprising a measure of the effectiveness of the plurality of assets at implementing a desired demand response, the optimization function taking inputs based on the performance indicators output by the neural network models;
• perform a search process to determine an altered optimization metric by varying an asset demand response configuration for one or more of the plurality of assets, wherein the search process is continued until a termination criterion of the altered optimization metric is met;
• determine updated asset demand response configurations for the plurality of assets based on the altered optimization metric;
• transmit the updated asset demand response configurations to one or more asset control devices associated with the assets determining updated asset demand response configurations for the plurality of assets based on the altered optimization metric;
• and
• control in real-time, by the control devices, energy flow between the plurality of assets and the grid in accordance with the updated asset configurations and in response to measured changes in frequency of the grid in order to perform frequency control response corresponding to the measured local grid frequencies;
• wherein controlling the energy flow between the plurality of assets and the grid comprises, via the control devices, adjusting power set points for the assets based on the updated asset configurations.