Wind power prediction in new stations based on knowledge of existing Stations: A cluster based multi source domain adaptation approach

Tasnim, Sumaira; Rahman, Ashfaqur; Oo, Amanullah Maung Than; Haque, M. E.

doi:10.1016/j.knosys.2017.12.036

Cited by 40 publications

(16 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a recurrent network and finetuning, the authors of [13] achieve good results for multi-step prediction for ultra-short-term forecast horizon of PV. Through a cluster-based domain adaption approach, substantial improvements for TL are achieved in wind power forecasts in [14]. By clustering similar wind parks through their distribution, an intelligent weighting scheme provides predictions for a new park.…”

Section: Transfer Learning For Renewable Power Forecastsmentioning

confidence: 99%

Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast

Schreiber

Vogt

Sick

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Task embeddings in multi-layer perceptrons for multi-task learning and inductive transfer learning in renewable power forecasts have recently been introduced. In many cases, this approach improves the forecast error and reduces the required training data. However, it does not take the seasonal influences in power forecasts within a day into account, i.e., the diurnal cycle. Therefore, we extended this idea to temporal convolutional networks to consider those seasonalities. We propose transforming the embedding space, which contains the latent similarities between tasks, through convolution and providing these results to the network's residual block. The proposed architecture significantly improves up to 25% for multi-task learning for power forecasts on the EuropeWindFarm and Ger-manSolarFarm dataset compared to the multi-layer perceptron approach. Based on the same data, we achieve a ten percent improvement for the wind datasets and more than 20% in most cases for the solar dataset for inductive transfer learning without catastrophic forgetting. Finally, we are the first proposing zero-shot learning for renewable power forecasts to provide predictions even if no training data is available.

show abstract

Section: Transfer Learning For Renewable Power Forecastsmentioning

confidence: 99%

Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast

Schreiber

Vogt

Sick

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…However, the intermittent, unstable, and uncontrollable characteristics of wind energy make the reliability of wind power generation systems low. [ 7–9 ] Accurate and stable wind speed prediction is helpful to the dispatching and control of the power system. It can not only help dispatchers find the best operation and planning solutions of power allocation but also ensure the security and economy of the power system.…”

Section: Introductionmentioning

confidence: 99%

Wind Speed Prediction in the Hexi Corridor Region of China Using an Enhanced Multiscale Nonlinear Ensemble Model

Wang

Cheng

2021

Energy Tech

View full text Add to dashboard Cite

Accurate wind speed prediction has become more and more popular. Herein, an enhanced multi‐scale nonlinear ensemble model is proposed to predict short‐term wind speed. First, advanced data preprocessing technology is used to extract these feature sequences. Second, each feature sequence is predicted by bidirectional long short‐term memory. In addition, the gated recurrent unit (GRU) realizes nonlinear ensemble and integrates the prediction information. Finally, GRU with white noise test is utilized to correct the residual to retain the possible effective information in the residual. The performance of the model is evaluated using the daily and hourly wind speeds of two wind farms in the Hexi Corridor region. The experimental results show that the proposed model has the best prediction accuracy among all relevant models. Taking Zhangye wind farm as an example, in the daily wind speed dataset, mean absolute percentage error, square sum error, theil inequality coefficient and the index of agreement of the model are 0.6416, 5.4234, 0.0151, and 0.9979, respectively. In the hourly dataset, they are 0.1037, 0.0042, 0.0003, and 1.0000, respectively. In the wind speed data of the Guazhou wind farm, the hybrid model proposed in this research also performs best.

show abstract

“…Furthermore, it is necessary to point out that it is not possible to find a standard set of data for all investigations, since each work conducts its research according to the requirements and characteristics of different wind power plants. Another aspect to highlight is the fact that the majority of these studies focus on short-term prediction, owing to the speed of response and the best percentages of accuracy, using different software for data analysis, among which MATLAB ® is the most common (Dong and Yang, 2018; Lu et al, 2017; Tasnim et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Wind power forecasting: A systematic literature review

2019

View full text Add to dashboard Cite

Accurate and reliable prediction of wind energy in the short term is of great importance for the efficient operation of wind farms. One of the procedures to search for, summarize, organize and synthesize existing information is a systematic literature review. In this article, we present a systematic literature review on the predictive models of wind energy, aiming to establish the baseline for the development of a short-term wind energy prediction model that employs artificial intelligence tools to be applied in the Villonaco Wind Power Plant. Following a systematic method of literature review, we have established 4 research questions and 37 scientific articles that answer the said questions. Consequently, we found that artificial neural networks are used more frequently for the prediction of wind energy, which highlights its use in the studies consulted for the results achieved compared with that of other methods.

show abstract

Wind power prediction in new stations based on knowledge of existing Stations: A cluster based multi source domain adaptation approach

Cited by 40 publications

References 18 publications

Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast

Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast

Wind Speed Prediction in the Hexi Corridor Region of China Using an Enhanced Multiscale Nonlinear Ensemble Model

Wind power forecasting: A systematic literature review

Contact Info

Product

Resources

About