Photovoltaic Power Interval Prediction via NSGA-II-DLSSVM
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting photovoltaic power output are inaccurate and unreliable, especially in bad weather conditions, as they ignore uncertainty and often assume normal distribution, leading to local extreme values and reduced reliability.
Innovation Solution
A short-term interval prediction method using an NSGA-II-based double least squares support vector machine (NSGA-II-DLSSVM) that considers numerical and pattern similarity through fuzzy C-means clustering and Fre'chet distance, optimizing model parameters to provide a more reliable interval prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If data point prediction methods are used for photovoltaic power output, then the prediction process is simple, but the prediction accuracy is reduced sharply in bad weather conditions and reliability cannot be described
Solution Approach 1:
The prediction method is segmented into two distinct models: a point prediction model for deterministic output and an interval prediction model for uncertainty quantification. This segmentation allows each model to specialize in its strength while collectively providing both simplicity and reliability in photovoltaic power output prediction
Solution Approach 2:
The patent creates a composite prediction framework by combining multiple prediction approaches (point prediction and interval prediction) into a unified system. This composite structure integrates the simplicity of point prediction with the reliability of interval prediction, achieving both goals simultaneously
2Reliability
If traditional neural network models are used for interval prediction, then the model can be constructed, but it is easy to fall into local extreme values and difficult to avoid defects
Solution Approach 1:
The patent replaces the traditional neural network optimization mechanism with a multi-objective optimization algorithm. This substitution eliminates the mechanical defect of local extreme values by using a different optimization approach that simultaneously considers multiple objectives (coverage probability and interval width), achieving both reliability and precision
3Device complexity
If assumption of normal distribution is made for photovoltaic power output, then the prediction model is simple to construct, but distribution errors are ignored and prediction accuracy is reduced
Solution Approach 1:
The patent changes the fundamental parameter assumption from normal distribution to a data-driven distribution obtained through clustering analysis. This parameter change allows the model to adapt to actual photovoltaic power output patterns without requiring complex theoretical distributions, maintaining simplicity while improving accuracy by reflecting real-world distribution characteristics
Data Source
AI summary
The present disclosure belongs to the technical field of information, provides a short-term interval prediction method for photovoltaic power output, and is a short-term interval prediction method for photovoltaic power output based on a combination of a multi-objective optimization algorithm and a least square support vector machine. The present disclosure firstly proposes a similar day classification method considering both numerical value and pattern similarity to enhance the regularity of samples, then constructs an adaptive proportional interval estimation model based on dual-LSSVM model, and optimizes model parameters by using NSGA-II algorithms to realize the interval prediction of photovoltaic power output. Results obtained by the method have high accuracy, and computation efficiency meets actual application requirements. The method can also be popularized and applied in the fields of grid connection and scheduling of renewable energy sources.