Online adaptive lasso estimation in vector autoregressive models for high dimensional wind power forecasting

Messner, Jakob W.; Pinson, Pierre

doi:10.1016/j.ijforecast.2018.02.001

Cited by 101 publications

(53 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typical methods include time-series models (auto-regression, and variants to incorporate spatial dependence) as well as machine learning approaches such as SVM and neural networks. Recent research in this area has focused on scaling-up these methodologies to be able to incorporate many spatial locations (Cavalcante, Bessa, Reis, & Browell, 2016;Messner & Pinson, 2018), and conditioning statistical model on large scale weather regimes for wind energy applications (Browell, Drew, & Philippopoulos, 2018) or cloud regimes for solar (McCandless, Haupt, & Young, 2016). Augmenting power production data with remote sensing is a well-established strategy for improving solar power forecast performance via incorporation of satellite imagery (Blanc, Remund, & Vallance, 2017) for hours-ahead forecasting and sky cameras (Chow et al, 2011;Kazantzidis et al, 2017) for intrahour forecasting.…”

Section: Very Short-term Forecastingmentioning

confidence: 99%

The future of forecasting for renewable energy

Sweeney

Bessa

Browell

et al. 2019

WIREs Energy & Environment

Self Cite

150

View full text Add to dashboard Cite

Forecasting for wind and solar renewable energy is becoming more important as the amount of energy generated from these sources increases. Forecast skill is improving, but so too is the way forecasts are being used. In this paper, we present a brief overview of the state‐of‐the‐art of forecasting wind and solar energy. We describe approaches in statistical and physical modeling for time scales from minutes to days ahead, for both deterministic and probabilistic forecasting. Our focus changes then to consider the future of forecasting for renewable energy. We discuss recent advances which show potential for great improvement in forecast skill. Beyond the forecast itself, we consider new products which will be required to aid decision making subject to risk constraints. Future forecast products will need to include probabilistic information, but deliver it in a way tailored to the end user and their specific decision making problems. Businesses operating in this sector may see a change in business models as more people compete in this space, with different combinations of skills, data and modeling being required for different products. The transaction of data itself may change with the adoption of blockchain technology, which could allow providers and end users to interact in a trusted, yet decentralized way. Finally, we discuss new industry requirements and challenges for scenarios with high amounts of renewable energy. New forecasting products have the potential to model the impact of renewables on the power system, and aid dispatch tools in guaranteeing system security. This article is categorized under: Energy Infrastructure > Systems and Infrastructure Wind Power > Systems and Infrastructure Photovoltaics > Systems and Infrastructure

show abstract

Section: Very Short-term Forecastingmentioning

confidence: 99%

The future of forecasting for renewable energy

Sweeney

Bessa

Browell

et al. 2019

WIREs Energy & Environment

Self Cite

150

View full text Add to dashboard Cite

show abstract

“…Multivariate forecasts which encode information on the spatio-temporal dependency of neighbouring sites can be tackled via a vector autoregressive models (VAR) at these time horizons. With an increasing number of sites, making sparse estimates of the coefficient matrices becomes more important, as does estimating them via efficient numerical procedures [83][84][85].…”

Section: Statistical Time Series Modelsmentioning

confidence: 99%

Minute-Scale Forecasting of Wind Power—Results from the Collaborative Workshop of IEA Wind Task 32 and 36

et al. 2019

View full text Add to dashboard Cite

The demand for minute-scale forecasts of wind power is continuously increasing with the growing penetration of renewable energy into the power grid, as grid operators need to ensure grid stability in the presence of variable power generation. For this reason, IEA Wind Tasks 32 and 36 together organized a workshop on “Very Short-Term Forecasting of Wind Power” in 2018 to discuss different approaches for the implementation of minute-scale forecasts into the power industry. IEA Wind is an international platform for the research community and industry. Task 32 tries to identify and mitigate barriers to the use of lidars in wind energy applications, while IEA Wind Task 36 focuses on improving the value of wind energy forecasts to the wind energy industry. The workshop identified three applications that need minute-scale forecasts: (1) wind turbine and wind farm control, (2) power grid balancing, (3) energy trading and ancillary services. The forecasting horizons for these applications range from around 1 s for turbine control to 60 min for energy market and grid control applications. The methods that can be applied to generate minute-scale forecasts rely on upstream data from remote sensing devices such as scanning lidars or radars, or are based on point measurements from met masts, turbines or profiling remote sensing devices. Upstream data needs to be propagated with advection models and point measurements can either be used in statistical time series models or assimilated into physical models. All methods have advantages but also shortcomings. The workshop’s main conclusions were that there is a need for further investigations into the minute-scale forecasting methods for different use cases, and a cross-disciplinary exchange of different method experts should be established. Additionally, more efforts should be directed towards enhancing quality and reliability of the input measurement data.

show abstract

“…Wind power generation prediction is an effective measure to improve the acceptance capacity of wind power and ensure the stable operation of power grid. A high-precision wind power generation prediction model directly affects power quality, power grid stability and the balance between power grid processing load and power generation, which is of great practical significance for power grid security, stability and efficient operation [3]. Wind power generation is affected by wind speed fluctuation on three time scales: ultra-short-term fluctuation (a few minutes) influences the control of wind turbine to a certain extent, medium-term fluctuation (from a few hours to a few days) has a certain impact on wind power grid connection and power grid dispatch and long-term fluctuations (weeks or months) are related to maintenance plans for wind farms and power grids.…”

Section: Introductionmentioning

confidence: 99%

A Novel Deep Learning Approach for Wind Power Forecasting Based on WD-LSTM Model

Liu

Zhao

et al. 2020

Energies

View full text Add to dashboard Cite

Wind power generation is one of the renewable energy generation methods which maintains good momentum of development at present. However, its extremely intense intermittences and uncertainties bring great challenges to wind power integration and the stable operation of wind power grids. To achieve accurate prediction of wind power generation in China, a hybrid prediction model based on the combination of Wavelet Decomposition (WD) and Long Short-Term Memory neural network (LSTM) is constructed. Firstly, the nonstationary time series is decomposed into multidimensional components by WD, which can effectively reduce the volatility of the original time series and make them more stable and predictable. Then, the components of the original time series after WD are used as input variables of LSTM to predict the national wind power generation. Forty points were used, 80% as training samples and 20% as testing samples. The experimental results show that the MAPE of WD-LSTM is 5.831, performing better than other models in predicting wind power generation in China. In addition, the WD-LSTM model was used to predict the wind power generation in China under different development trends in the next two years.

show abstract

Online adaptive lasso estimation in vector autoregressive models for high dimensional wind power forecasting

Cited by 101 publications

References 23 publications

The future of forecasting for renewable energy

The future of forecasting for renewable energy

Minute-Scale Forecasting of Wind Power—Results from the Collaborative Workshop of IEA Wind Task 32 and 36

A Novel Deep Learning Approach for Wind Power Forecasting Based on WD-LSTM Model

Contact Info

Product

Resources

About