A Multi-step ahead photovoltaic power forecasting model based on TimeGAN, Soft DTW-based K-medoids clustering, and a CNN-GRU hybrid neural network

Li, Qing; Zhang, Xinyan; Ma, Tianjiao; Liu, Dagui; Wang, Heng; Hu, Wei

doi:10.1016/j.egyr.2022.08.180

Cited by 47 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It introduces the concept of supervised loss and an embedding network to reduce the adversarial learning space's dimensionality. It is able to generate training to handle a mixed-data setting, where both static (attributes) and sequential data (features) are able to be generated at the same time [16]. TimeGAN is a framework to synthesize sequential data composed of four networks: generator, discriminator, recovery, and embedder.…”

Section: Time Ganmentioning

confidence: 99%

Generation and Evaluation of Tabular Data in Different Domains Using Gans

Marecha,

2023

AJRCoS

View full text Add to dashboard Cite

Deep learning techniques like Generative Adversarial Networks (GANs) provide solutions in many domains where real data needs to be kept private. Synthesizing tabular data is difficult because of its high complexity. Tabular data usually contains a mixture of discrete and continuous data, which is not an easy model to build. The contributions made in this paper include training and generating data with the original Vanilla Gan, then CGan and WGan-Gp and WCGan-Gp which performs better than the former. The Adult Income Census dataset mainly focuses on predicting whether income exceeds 50,000 per year based on census data, then comparing the accuracy of machine learning models and calculating the F1 scores. Then the use of TimeGan on the stock dataset, comparing synthetic data vs real data. This paper will explore the use of GANs for generating and evaluating tabular data in different domains.

show abstract

Section: Time Ganmentioning

confidence: 99%

Generation and Evaluation of Tabular Data in Different Domains Using Gans

Marecha,

2023

AJRCoS

View full text Add to dashboard Cite

show abstract

“…DTW [23] distance is a typical technique in the addressing time-series related problems [24], and also practical and suitable for the building energy field [25]. In this study, it is used to measure the distance between multi-dimension data for k-medoids clustering, and it is calculated following the Equations ( 5)-( 7) [26].…”

Section: Distance Measurementioning

confidence: 99%

Energy Schedule Setting Based on Clustering Algorithm and Pattern Recognition for Non-Residential Buildings Electricity Energy Consumption

et al. 2023

View full text Add to dashboard Cite

Building energy modelling (BEM) is crucial for achieving energy conservation in buildings, but occupant energy-related behaviour is often oversimplified in traditional engineering simulation methods and thus causes a significant deviation between energy prediction and actual consumption. Moreover, the conventional fixed schedule-setting method is not applicable to the recently developed data-driven BEM which requires a more flexible and data-related multi-timescales schedule-setting method to boost its performance. In this paper, a data-based schedule setting method is developed by applying K-medoid clustering with Principal Component Analysis (PCA) dimensional reduction and Dynamic Time Warping (DTW) distance measurement to a comprehensive building energy historical dataset, partitioning the data into three different time scales to explore energy usage profile patterns. The Year–Month data were partitioned into two clusters; the Week–Day data were partitioned into three clusters; the Day–Hour data were partitioned into two clusters, and the schedule-setting matrix was developed based on the clustering result. We have compared the performance of the proposed data-driven schedule-setting matrix with default settings and calendar data using a single-layer neural network (NN) model. The findings show that for the data-driven predictive BEM, the clustering results-based data-driven schedule setting performs significantly better than the conventional fixed schedule setting (with a 25.7% improvement) and is more advantageous than the calendar data (with a 9.2% improvement). In conclusion, this study demonstrates that a data-related multi-timescales schedule matrix setting method based on cluster results of building energy profiles can be more suitable for data-driven BEM establishment and can improve the data-driven BEMs performance.

show abstract

“…Such performance is not attainable with shallow learning models. Deep learning models, including stacked autoencoder (SAE) [27,28], deep belief network (DBN) [29,30], recurrent neural network (RNN) [31], and enhanced variants of long short-term memory (LSTM) [32,33] and gated recurrent unit (GRU) [34], offer enhanced accuracy and stability in prediction. In References [1,35], CNN was employed for data filtering and denoising, while the pooling layer reduced data dimensionality and memory requirements and improved processing speed.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Power-Generation Prediction of High Humidity Island Photovoltaic Power Station Based on a Deep Hybrid Model

Wang,

Jia,

et al. 2024

Sustainability

View full text Add to dashboard Cite

Precise prediction of the power generation of photovoltaic (PV) stations on the island contributes to efficiently utilizing and developing abundant solar energy resources along the coast. In this work, a hybrid short-term prediction model (ICMIC-POA-CNN-BIGRU) was proposed to study the output of a fishing–solar complementary PV station with high humidity on the island. ICMIC chaotic mapping was used to optimize the initial position of the pelican optimization algorithm (POA) population, enhancing the global search ability. Then, ICMIC-POA performed hyperparameter debugging and L2-regularization coefficient optimization on CNN-BIGRU (convolutional neural network and bidirectional gated recurrent unit). The L2-regularization technique optimized the loss curve and over-fitting problem in the CNN-BIGRU training process. To compare the prediction effect with the other five models, three typical days (sunny, cloudy, and rainy) were selected to establish the model, and six evaluation indexes were used to evaluate the prediction performance. The results show that the model proposed in this work shows stronger robustness and generalization ability. K-fold cross-validation verified the prediction effects of three models established by different datasets for three consecutive days and five consecutive days. Compared with the CNN-BIGRU model, the RMSE values of the newly proposed model were reduced by 64.08%, 46.14%, 57.59%, 60.61%, and 34.04%, respectively, in sunny, cloudy, rainy, continuous prediction 3 days, and 5 days. The average value of the determination coefficient R2 of the 20 experiments was 0.98372 on sunny days, 0.97589 on cloudy days, and 0.98735 on rainy days.

show abstract

A Multi-step ahead photovoltaic power forecasting model based on TimeGAN, Soft DTW-based K-medoids clustering, and a CNN-GRU hybrid neural network

Cited by 47 publications

References 43 publications

Generation and Evaluation of Tabular Data in Different Domains Using Gans

Generation and Evaluation of Tabular Data in Different Domains Using Gans

Energy Schedule Setting Based on Clustering Algorithm and Pattern Recognition for Non-Residential Buildings Electricity Energy Consumption

Short-Term Power-Generation Prediction of High Humidity Island Photovoltaic Power Station Based on a Deep Hybrid Model

Contact Info

Product

Resources

About