Rooftop PV Data Interpolation Using WGAN and Whale Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing PV data interpolation technologies suffer from high calculation complexity, low interpolation accuracy, and limited universality, particularly in handling missing data due to equipment failure and climate interference, which affects PV forecasting and grid connection.
Innovation Solution
A building photovoltaic data interpolation method using Wasserstein Generative Adversarial Networks (WGAN) and Whale optimization algorithm, involving data preprocessing, feature learning with CNN, and optimization through Whale optimization to reconstruct missing data samples.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional PV data interpolation technology is used, then the calculation complexity is high, but the interpolation accuracy is low
Solution Approach 1:
The patent transforms the interpolation problem into a parameter optimization problem by using WGAN to learn the underlying data distribution parameters. The whale optimization algorithm then optimizes these parameters to generate accurate interpolated values, changing the approach from direct complex calculation to parameter-based generation.
Solution Approach 2:
The patent introduces WGAN as an intermediary model that learns the data distribution and generates interpolated values, rather than directly computing them through complex conventional algorithms. The whale optimization algorithm serves as another intermediary to optimize the WGAN training process, simplifying the overall computational path.
2Adaptability or versatility
If conventional PV data interpolation technology is used, then the calculation complexity is high, but the applicability to PV data universality is low
Solution Approach 1:
The WGAN model is designed to learn the universal data distribution characteristics of PV data across different scenarios. Once trained, it can generate interpolated values for various PV data types and missing patterns, making the solution universally applicable rather than requiring separate complex algorithms for each case.
Solution Approach 2:
By transforming the interpolation task into learning data distribution parameters through WGAN, the system achieves universality across different PV data scenarios. The whale optimization algorithm further enhances this by efficiently optimizing the training process, making the universal solution computationally feasible.
3Measurement precision
If WGAN and whale optimization algorithm are used, then the interpolation accuracy is improved, but the training complexity increases
Solution Approach 1:
The patent implements feedback mechanisms where the whale optimization algorithm monitors and adjusts the WGAN training process based on interpolation performance. This feedback loop ensures that the increased training complexity leads to proportionally higher interpolation accuracy by continuously optimizing the model parameters.
Solution Approach 2:
The training process is made dynamic through the whale optimization algorithm, which adaptively adjusts training parameters and hyperparameters during the training phase. This dynamic approach manages training complexity by focusing computational resources on the most impactful parameters, achieving high accuracy without uniformly increasing complexity across all aspects.
Data Source
AI summary
A building photovoltaic data interpolation method based on WGAN and whale optimization algorithm is provided, which includes: obtaining historical building roof photovoltaic output data, perform preprocessing on the historical building roof photovoltaic output data, and uses CNN to build a GAN; describing missing value position of preprocessed data by using a binary mask matrix, and setting Wasserstein distance to define a loss function of a GAN generator and a discriminator; taking the loss function as a fitness function, optimizing an input to the GAN generator through a whale optimization algorithm and obtaining optimized candidate samples; fusing the optimized candidate samples and a photovoltaic data processed by the binary mask matrix to obtain completed reconstructed samples, so as to improve the complementary accuracy, optimize the random noise, remove the unfavorable influencing components, and provide services for building rooftop PV data interpolation more accurately.