Wind Power Uncertainties Forecasting based on Long Short Term Memory Model for Short-Term Power Market

Kedia, Akanksha; Sanyal, A.; Gogoi, Abinab; Kumar, Ambar; Goswani, Arup Kumar; Tiwari, Prashant; Choudhury, Nalin Behari Deb

doi:10.1109/stpec49749.2020.9297752

Cited by 5 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RESs power production fluctuates smoothly in the short-term period along with time series. Moreover, the ARMA can handle these short-term power forecasts [29]- [31]. The ARMA can be expressed as follows,…”

Section: A Arma-based Prediction Processmentioning

confidence: 99%

See 1 more Smart Citation

Multistage Model Predictive Control Co-Risk Dispatch for Coupled Electricity and Heat System

et al. 2021

View full text Add to dashboard Cite

The energy transition can facilitate the rapid development of the coupled electricity and heat system (CEHS), accommodating the higher share of renewable energy. However, uncertain renewable energy sources (RESs) and overlimit risk can bring significant challenges for the safe operation of the CEHS. Considering uncertain RESs integration and overlimit risk within the upper and lower bounds jointly with high probability, the multistage model predictive control (MPC) co-risk dispatch model for the CEHS can be proposed in this paper. The model can hedge against the operational risk for the multistage rolling dispatch. In the context of the multistage real-time risk dispatch, the MPC framework is presented, which contains three processes, autoregressive moving average (ARMA) model prediction process, risk-based optimization process, and penalty-based feedback correction process. In the prediction process, the ARMA method can be employed to accurately predict the RESs power, which is characterized as the merit of the short-term forecast. In the optimization process, the violation risk of overlimit chance constraints caused by the output power fluctuation can be mitigated using the distributionally robust chance-constrained (DRCC) under the Wasserstein ambiguity set. The tractable approximation reformulation can be obtained by adopting the Worst-Case Conditional Value-at-Risk (WC-CVaR) approximation method. In the feedback correction process, penalty-based load shedding and RESs spillage can lower the risk level by minimizing the risk penalty cost. In the numerical case, the risk performance analysis based on the modified Barry Island system is implemented. The analysis demonstrates that the daily average violation probability can be mainly affected by the Wasserstein radius while the total cost can be affected by the violation probability . The dispatch energy for the CEHS is obtained using the proposed approach, which outperforms the existing robust optimization (RO) approach.

show abstract

Section: A Arma-based Prediction Processmentioning

confidence: 99%

“…The flowchart of the iteration process can be described in Fig. 11 Solve the tractable conic program (31) Solve the tractable conic program (30) Obtain the solution set…”

Section: Appendixmentioning

confidence: 99%

Multistage Model Predictive Control Co-Risk Dispatch for Coupled Electricity and Heat System

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Intelligent learning methods based on artificial intelligence can identify complex relationships between input and output, making them another popular area of research. Machine learning models, including Artificial Neural Networks (ANN) [3][4][5], Machine Learning (ML) [6][7][8], Support Vector Regression (SVR) [9], Support Vector Machine (SVM) [10][11][12][13], and Long Short-term Memory Neural Networks (LSTM) [14][15][16][17][18], are among the methods currently being explored by researchers.…”

Section: Introductionmentioning

confidence: 99%

Application of a novel generative adversarial network to wind power forecasting

Liao,

Wu,

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

As the global economy rapidly develops, energy consumption and carbon dioxide emissions have increased annually, prompting countries to strive for carbon neutrality by 2050. Accurate wind power forecasting can aid power system dispatch departments to obtain wind farms’ output and improve the power system’s new energy absorption capacity by coordinating multiple power generation resources. To this end, this study proposes a novel method for wind power forecasting: the Generative Adversarial Network method-based Deep Q Neural Network (GDQN). Wind power is a nonlinear model with random characteristics like dynamics and uncertainty. The GDQN generates wind power data similar to historical wind power data, solving the problem of insufficient wind power data samples by developing adversarial networks. The deep Q-learning network is then utilized to predict future wind power data. The experimental results based on the actual test of the total power generated by all wind turbines in a complete wind farm indicate that the proposed GDQN method can significantly reduce the Mean Absolute Percentage Error (MAPE %) of wind power forecasting, as compared to other commonly used methods in wind power forecasting.

show abstract

Hybrid model for wind power estimation based on BIGRU network and error discrimination‐correction

Li,

Jin,

Dan

et al. 2024

IET Renewable Power Gen

View full text Add to dashboard Cite

Accurate estimation of wind power is essential for predicting and maintaining the power balance in the power system. This paper proposes a novel approach to enhance the accuracy of wind power estimation through a hybrid model integrating neural networks and error discrimination‐correction techniques. In order to improve the accuracy of estimation, a bidirectional gating recurrent unit is developed, forming an initial wind power estimation curve through training. Additionally, a sequential model‐based algorithmic configuration optimizes bidirectional gating recurrent unit's network hyperparameters. To tackle estimation errors, a multi‐layer perceptron combined with sequential model‐based algorithmic configuration is employed to create a classification model that automatically discerns the quality of estimates. Subsequently, an innovative correction model, based on grey relevancy degree and relevancy errors, is devised to rectify erroneous estimates. The final estimates result from a summation of the initial estimates and the values derived from error corrections. By analysing the real data from a wind farm in northwest China, a simulation test validates the proposed hybrid model. Experimental results demonstrate a substantial improvement in modelling accuracy when compared to the initial model.

show abstract

Wind Power Uncertainties Forecasting based on Long Short Term Memory Model for Short-Term Power Market

Cited by 5 publications

References 15 publications

Multistage Model Predictive Control Co-Risk Dispatch for Coupled Electricity and Heat System

Multistage Model Predictive Control Co-Risk Dispatch for Coupled Electricity and Heat System

Application of a novel generative adversarial network to wind power forecasting

Hybrid model for wind power estimation based on BIGRU network and error discrimination‐correction

Contact Info

Product

Resources

About