Method and system for adaptive forecast of wind resources

摘要

A method and system are provided for determining at least one combined forecast value of non-conventional energy resources. An Input/output Interface receives an adaptively selected historical dataset and a current dataset from one or more predictive forecast models and/or measurements. An adaptive forecast module generates one or more variants of machine learning models to model the performance of the one or more predictive forecast models by training the one or more variants of machine learning models on the historical dataset. The adaptive forecast module correlates the current dataset with the historical dataset to adaptively obtain a filtered historical dataset. The adaptive forecast module evaluates the one or more variants of machine learning models on the filtered historical dataset. The adaptive forecast module derives a statistical model to determine the at least one combined forecast value by combining outputs obtained based on the evaluation.

主权项

1. A method for determining at least one combined forecast value of non-conventional energy resources for enabling adaptive forecasting of the non-conventional energy resources, the method comprising:
selecting a historical dataset comprising a first set of forecast values received from one or more predictive forecast models and a first set of actual values received from one or more measurements of the non-conventional energy resources; generating one or more variants of machine learning models to model performance of the one or more predictive forecast models by training the one or more variants of the machine learning models on the historical dataset; receiving a current dataset comprising a second set of forecast values derived from the one or more predictive forecast models and a second set of actual values derived from the one or more measurements of the non-conventional energy resources; correlating the current dataset with the historical dataset to adaptively obtain a filtered historical dataset; selecting the one or more variants of the machine learning models trained on the historical dataset and evaluating them on the filtered historical dataset to assign weights to each of the one or more variants of the machine learning models and their outputs; and deriving a statistical model in the form of an optimal combination function to determine at least one combined forecast value by combining weights assigned to the each of the one or more variants of the machine learning models trained based on the evaluating of the one or more variants of the machine learning models on the filtered historical dataset and the outputs of the each of the one or more variants of machine learning models trained on the historical dataset, wherein the selecting, the generating, the receiving, the correlating, the evaluating and the deriving are performed by a processor using computer-readable instructions stored in the memory.