Wind Power Output Forecasting with Smoothed Weather Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing penetration of wind power stations into power systems poses challenges for safe, stable, economic, and reliable operation due to the unpredictability of wind power output, necessitating accurate and timely predictions to manage the integration of wind energy effectively.
Innovation Solution
A method for predicting wind power output involves acquiring initial meteorological data, identifying and smoothing abnormal data, determining instantaneous wind energy density, performing rolling averaging, and inputting these data into a predictive model to forecast wind power output, utilizing a combination of boosting and time series models for enhanced accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If wind power station capacity and scale continue to expand, then the proportion of wind power in total generation increases, but the safety and stability of the power system deteriorates
Solution Approach 1:
The patent applies preliminary action by performing wind power output prediction before the actual wind power generation occurs. The system periodically acquires meteorological data, processes it through abnormal value identification and smoothing, calculates wind energy density, and inputs these features into a predictive model to forecast wind power output in advance. This allows power system operators to prepare appropriate scheduling and control strategies beforehand, managing the integration of wind energy while maintaining system stability.
2Measurement precision
If initial meteorological data contains abnormal sub-data, then prediction accuracy deteriorates, but data processing complexity increases
Solution Approach 1:
The patent applies preliminary action by identifying and smoothing abnormal meteorological data before it is used for wind power prediction. The system periodically acquires initial meteorological data sets, identifies abnormal sub-data through comparison with historical data and statistical analysis, and smooths these abnormal values using neighboring data points. This preprocessing ensures that only clean, reliable data is input into the prediction model, maintaining high prediction accuracy without requiring overly complex processing algorithms.
Solution Approach 2:
The patent applies self-service by implementing automated abnormal data detection and smoothing mechanisms that operate without manual intervention. The system automatically identifies abnormal sub-data by comparing current meteorological data with historical patterns, calculates statistical deviations, and applies smoothing algorithms using surrounding data points. This self-service approach maintains data quality and prediction accuracy while avoiding the need for complex manual data processing or external intervention.
3Reliability
If rolling averaging calculation is performed on instantaneous wind energy density, then prediction reliability improves, but calculation time increases
Solution Approach 1:
The patent applies partial action by performing rolling averaging calculation on wind energy density using a selectively chosen time window that balances reliability improvement with calculation efficiency. The system calculates instantaneous wind energy density from smoothed meteorological data, then applies rolling averaging over a predetermined time period to obtain more reliable average wind energy density values. This partial averaging approach improves prediction reliability by reducing the impact of instantaneous fluctuations while avoiding the excessive calculation time that would result from using larger time windows or more complex averaging methods.
Data Source
AI summary
The present disclosure provides a prediction method of wind power output, an electronic device, a storage medium and a system, and relates to the technical field of wind power. The method includes: periodically acquiring an initial meteorological data set corresponding to each received time node, wherein the initial meteorological data set includes initial meteorological sub-data of at least one dimension of at least one meteorological element; after acquiring the latest initial meteorological data set, identifying and smoothing the abnormal sub-data to obtain a smoothed meteorological data set; determining an average wind energy density in a target time period; taking the smooth meteorological data set and the average wind energy density in the target time period as the input features of the model, and obtaining a wind power output predictive value via the model.