Electric loadshape forecasting based on smart meter signals

1. A method for forecasting electricity demand for a utility system, comprising:

receiving a set of input signals containing electrical usage data from a set of smart meters, wherein each smart meter in the set gathers electrical usage data from a customer of the utility system;

using the set of input signals to train an inferential model, which learns correlations among the set of input signals;

using the inferential model to produce a set of inferential signals, wherein the inferential model produces an inferential signal for each input signal in the set of input signals;

using a Fourier-based decomposition-and-reconstruction technique, which decomposes each signal in the set of inferential signals into deterministic and stochastic components, and uses the deterministic and stochastic components to generate a set of synthesized signals, which are statistically indistinguishable from the inferential signals; and

projecting the set of synthesized signals into the future to produce a forecast for the electricity demand for the utility system; using the forecast for the electricity demand to control a supply of electricity provided by the utility system.

2. The method of claim 1 , wherein controlling the supply of electricity provided by the utility system comprises one or more of the following:

controlling an amount of electricity produced by one or more power plants in the utility system;

purchasing electricity for the utility system through a power grid;

selling electricity produced by the utility system through the power grid;

storing electricity for future use by the utility system; and

making plans to construct a new power plant for the utility system.

3. The method of claim 1 , wherein generating the set of synthesized signals comprises:

generating a set of un-normalized signals; and

performing an ambient-weather-normalization operation on the set of un-normalized signals to generate the set of synthesized signals, wherein the ambient-weather-normalization operation uses historical, current and predicted weather measurements and historical electrical usage data to adjust the set of un-normalized signals to account for effects of weather on the forecast for electricity demand.

4. The method of claim 1 , wherein receiving the set of input signals comprises receiving a set of advanced metering infrastructure (AMI) signals.

5. The method of claim 1 , wherein the inferential model is trained using a nonlinear, nonparametric (NLNP) regression technique.

6. The method of claim 5 , wherein the NLNP regression technique comprises a Multivariate State Estimation Technique (MSET).

7. The method of claim 1 , wherein using the Fourier-based decomposition-and-reconstruction technique to generate the set of synthesized signals comprises using a telemetry parameter synthesis (TPSS) technique, which creates a high-fidelity synthesis equation that is used to generate the set of synthesized signals.

8. The method of claim 1 , wherein the electrical usage data comprises kilowatt measurements and kilowatt-hour measurements.

9. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for forecasting electricity demand for a utility system, the method comprising:

receiving a set of input signals containing electrical usage data from a set of smart meters, wherein each smart meter in the set gathers electrical usage data from a customer of the utility system;

using the set of input signals to train an inferential model, which learns correlations among the set of input signals;

using the inferential model to produce a set of inferential signals, wherein the inferential model produces an inferential signal for each input signal in the set of input signals;

using a Fourier-based decomposition-and-reconstruction technique, which decomposes each signal in the set of inferential signals into deterministic and stochastic components, and uses the deterministic and stochastic components to generate a set of synthesized signals, which are statistically indistinguishable from the inferential signals; and

projecting the set of synthesized signals into the future to produce a forecast for the electricity demand for the utility system using the forecast for the electricity demand to control a supply of electricity provided by the utility system.

10. The non-transitory computer-readable storage medium of claim 9 , wherein controlling the supply of electricity provided by the utility system comprises one or more of the following:

controlling an amount of electricity produced by one or more power plants in the utility system;

purchasing electricity for the utility system through a power grid;

selling electricity produced by the utility system through the power grid;

storing electricity for future use by the utility system; and

making plans to construct a new power plant for the utility system.

11. The non-transitory computer-readable storage medium of claim 9 , wherein generating the set of synthesized signals comprises:

generating a set of un-normalized signals; and

performing an ambient-weather-normalization operation on the set of un-normalized signals to generate the set of synthesized signals, wherein the ambient-weather-normalization operation uses historical, current and predicted weather measurements and historical electrical usage data to adjust the set of un-normalized signals to account for effects of weather on the forecast for electricity demand.

12. The non-transitory computer-readable storage medium of claim 9 , wherein receiving the set of input signals comprises receiving a set of advanced metering infrastructure (AMI) signals.

13. The non-transitory computer-readable storage medium of claim 9 , wherein the inferential model is trained using a nonlinear, nonparametric (NLNP) regression technique.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the NLNP regression technique comprises a Multivariate State Estimation Technique (MSET).

15. The non-transitory computer-readable storage medium of claim 9 , wherein using the Fourier-based decomposition-and-reconstruction technique to generate the set of synthesized signals comprises using a telemetry parameter synthesis (TPSS) technique, which creates a high-fidelity synthesis equation that is used to generate the set of synthesized signals.

16. The non-transitory computer-readable storage medium of claim 9 , wherein the electrical usage data comprises kilowatt measurements and kilowatt-hour measurements.

17. A system that forecasts electricity demand for a utility system, comprising:

at least one processor and at least one associated memory; and

a forecasting mechanism that executes on the at least one processor, wherein during operation, the forecasting mechanism:

receives a set of input signals containing electrical usage data from a set of smart meters, wherein each smart meter in the set gathers electrical usage data from a customer of the utility system;

uses the set of input signals to train an inferential model, which learns correlations among the set of input signals;

uses the inferential model to produce a set of inferential signals, wherein the inferential model produces an inferential signal for each input signal in the set of input signals;

uses a Fourier-based decomposition-and-reconstruction technique, which decomposes each signal in the set of inferential signals into deterministic and stochastic components, and uses the deterministic and stochastic components to generate a set of synthesized signals, which are statistically indistinguishable from the inferential signals; and

projects the set of synthesized signals into the future to produce a forecast for the electricity demand for the utility system uses the forecast for the electricity demand to control a supply of electricity provided by the utility system.