Context-aware parameter estimation for forecast models

摘要

Methods, systems, and computer-readable storage media for providing at least one parameter for use with a forecast model. Implementations include actions of receiving a first context vector, the first context vector including a plurality of context attributes that describe a first context, retrieving a first parameter vector from a repository based on the first context vector, the repository electronically storing a plurality of parameter vector, each parameter vector being associated with a respective context and including one or more parameters, parameterizing the forecast model based on parameters provided in the first parameter vector to provide a parameterized forecast model, optimizing the parameterized forecast model to provide an optimized forecast model, and forecasting one or more values using the optimized forecast model.

主权项

1. A computer-implemented method for providing at least one parameter for use with a forecast model, the method being executed using one or more processors and comprising:
receiving, by the one or more processors, a first context vector, the first context vector comprising a plurality of context attributes at a current time, that describe a first context of an energy time series; retrieving, by the one or more processors, a first parameter vector from a repository based on the first context vector, the repository electronically storing a plurality of parameter vectors that describe respective contexts, each of the respective contexts comprising a plurality of external factors defining one or more of a seasonal pattern, an event and an exception and each of the plurality of parameter vectors comprising one or more parameters; parameterizing, by the one or more processors, the forecast model based on the one or more parameters provided in the first parameter vector to provide a parameterized forecast model; optimizing, by the one or more processors, the parameterized forecast model using a local optimization that runs in parallel to a global optimization to provide an optimized forecast model based on the first context; forecasting, by the one or more processors, one or more values using the optimized forecast model; and adjusting, by the one or more processors, an energy supply based on the one or more values.