Tuesday , October 23 2018

A Two-step Forecasting Solution and Upscaling
Technique for Small Size Wind Farms Located in
Hilly Areas of Romania

Ion LUNGU1, George CARUTASU2, Alexandru PIRJAN2,
Simona-Vasilica OPREA1, Adela BARA1
1 The Bucharest University of Economic Studies,

6 Romană Square, Bucharest, 010374, Romania
ion.lungu@ie.ase.ro; simona.oprea@csie.ase.ro; bara.adela@ie.ase.ro
2 Romanian-American University,
1B Expozitiei Blvd., Bucharest, 012101, Romania
carutasu.george@profesor.rau.ro; pirjan.alexandru@profesor.rau.ro

Abstract: Taking into account the well-known benefits of using renewable energy as an important energy source, some practical aspects regarding operation must be underlined. In the specific case of wind power plants (WPP) forecasting the generated wind power is the most important issue for assuring stability of Romania’s National Power System (NPS) and economic efficiency of wind power plant operation. The wind power plant operator should report daily to National Dispatching Centre, the hourly energy production for the next day. In case of inaccurate energy production prediction, the National System Operator must take additional measures in order to maintain the stability of NPS. The purpose of our research is to develop a solution, based on Artificial Neural Networks, for forecasting the wind energy production of small output power wind farms located in hilly areas of Romania, thus improving the accuracy of the hourly prediction. The case study is based on two-year historical data for a wind power plant comprising two power production groups situated in Tulcea County, in southeastern Romania. By using this approach, we have also explored the possibility of algorithm generalization, starting from the detailed model of the first production group and generalize it to the second one.

Keywords: renewable energy, wind power forecasting, upscaling technique, artificial neural network.

>>Full text<<
CITE THIS PAPER AS
: Ion LUNGU, George CARUTASU, Alexandru PIRJAN, Simona-Vasilica OPREA, Adela BARA, A Two-step Forecasting Solution and Upscaling Technique for Small Size Wind Farms Located in Hilly Areas of Romania, Studies in Informatics and Control, ISSN 1220-1766, vol. 25(1), pp. 77-86, 2016.

  1. Introduction

1.1 Wind energy resources

In the last years, due to the European legislation facilities for Renewable Energy Source (RES), the wind energy capacity in EU- 28 has been increasing, up to 128.8 GW [1]. In 2014, 11791 MW were installed, with an estimated value between €13 bn and €18 bn. The wind energy share in total energy production is estimated to 285 TWh, which represents approximatively 8% of the total EU energy consumption. Regarding Romania, the same source reveals, at the end of 2014, an installed capacity of 2953.6 MW, having risen with 354 MW, when compared to 2013. Concerning the installation rate, the value is nearly half of the previous year, a fact that could be explained by the reduction of energy consumption and green certificates’ value. As a whole, the National System Operator (NSO), reported for 1st of July, 2014 an installed capacity of 24582 MW with with the next composition as energy source: Hydro 28.8%, Coal 26.66%, Hydrocarbon 22.57%, Wind 12.10%, Nuclear 5.74%, Solar 5.15 and Biomass 0.41%. The distribution of energy sources may vary depending upon both on the season and availability. Anyway, the most important annual growth was registered in China [2], 43%, with a total wind power capacity of 369,597 MW.

1.2 The mechanism of the system

The National Power System should balance in any moment the energy consumption to production. Because of the hazardous nature of wind, it is difficult to estimate in terms of hours (as a time scale), the wind energy production. The wind power plant operator has to notify the NSO for the next day hourly production. The wind power plant operator receives a subsidy from national government, known as “green certificates”.

The value of green certificates and the market mechanism are regulated by EU and national laws [3, 4]. The actual estimation indicates an accuracy of 70% for wind power prediction. According to the Commercial Code, if the production is lower than the notification, the wind power plant operator has to pay for the unbalance. The National Dispatching Centre must compensate the unbalance by activating Fast Tertiary Reserves. The higher the prediction error is, the higher the costs incurred. The wind power plant operators may use various commercial tools (PredictWind, WPPT, Wind Speed Predictor, WINDcast etc.) developed by independent commercial providers or resulting from international research projects [5]. Our obtained results are part of an integrated system in development [6] as a result of a scientific research project (Intelligent system for predicting, analysing and monitoring performance indicators and business processes in the field of renewable energies – SIPAMER). Due to the field relevance in Romania, the same goal of developing an integrated system for renewable energy sources management is approached by other research projects in progress [7].

The majority of wind farms in Romania have a small output power and are situated on hilly terrain [8]. Therefore, in this paper, we are developing a solution for forecasting the wind energy production and the consumed energy for these types of wind power plants.

We aim to improve the forecast accuracy of the existing forecasting software, used by a small wind park located in Baia, in Tulcea County, in South East Romania, by developing a two-step forecasting technique that is best suited for hilly terrain that causes a change of the wind direction from one turbine to another when situated at different altitudes. We also develop an upscaling technique by starting from one turbine and forecasting the energy production for six turbines grouped into two production groups, located on hilly terrain, in close proximity.

We focus on obtaining a forecasting solution with an improved accuracy prediction for small wind farms located on hilly terrain and also a solution that can be useful for potential investors that want to build these types of wind farms.

REFERENCES

  1. THE EUROPEAN WIND ENERGY ASSOCIATION Wind in power 2014 European Statistics, 2015 (http://www.ewea.org/fileadmin/files/library/publications/statistics/EWEA-Annual-Statistics-2014.pdf).
  2. GLOBAL ENERGY COUNCIL, Wind in Number, 2015 (http://www.gwec.net/wp-content/uploads/2015/03/GWEC_Global_Wind_2014_Report_LR.pdf).
  3. COMMISSION DECISION C (2011) 4938/2011 Green Certificates Promotion Scheme of Energy Produced from Renewable Energy Sources, European Commission.
  4. LAW 220/2008, Law for Establishing the System for Promoting Energy from Renewable Sources, Romanian Parliament.
  5. GIEBEL, G., R. BROWNSWORD, G. KARINIOTAKIS, M. DENHARD, C. DRAXL, The State-of-the-art in Short-Term Prediction of Wind Power: A Literature Overview, ANEMOS plus, 2010 (http://www.anemos-plus.eu/images/pubs/deliverables/aplus.deliverable_d1.2.stp_sota_v1.1.pdf).
  6. BARA, A., I. LUNGU, S. V. OPREA, G. CARUTASU, C. P. BOTEZATU, C. BOTEZATU, Design Workflow for Cloud Service Information System for Integration and Knowledge Management Based in Renewable Energy, Journal of Information Systems & Operations Management, Volume 8, No.2/2014, pp. 230-237.
  7. STANESCU, I. A., STEFAN, G. NEAGU, C. E. CIRNU, Renewable Energy Decision Support Systems: The Challenge of Data Integration, Studies in Informatics and Control, Vol. 24 (2), 2015, pp. 191-200.
  8. http://www.transelectrica.ro/documents/10179/32316/7productie19.pdf/3fd49432-1dd5-46ea-bbd1-02964fe0b6c4, official website, accessed on 21.11.2015.
  9. D’AMICO, G., F., PETRONI, F., PRATTICO, Wind Speed and Energy Forecasting at Different Time Scales: A Nonparametric Approach, Physica A: Statistical Mechanics and its Applications, Volume 406, 2014, pp. 59-66.
  10. SHI, J., J. GUO, S., ZHENG, Evaluation of Hybrid Forecasting Approaches for Wind Speed and Power Generation Time Series, Renewable and Sustainable Energy Reviews, vol. 16(5), 2012, pp. 3471-3480.
  11. LEI, M., L. SHIYAN, J. CHUANWEN, L., HONGLING, Z. YAN, A Review on the Forecasting of Wind Speed and Generated Power, Renewable and Sustainable Energy Reviews, Volume 13, Issue 4, 2009, pp. 915-920.
  12. MAATALLAH, O. A., A. ACHUTHAN, K. JANOYAN, P. MARZOCCA, Recursive Wind Speed Forecasting Based on Hammerstein Auto-Regressive Model, Energy, vol. 145, 2015, pp. 191-197.
  13. COSTA, A., A., CRESPO, J. NAVARRO, G. LIZCANO, H. MADSEN, E. FEITOSA, A Review on the Young History of The Wind Power Short-Term Prediction, Renewable and Sustainable Energy Reviews, vol. 12(6), 2008, pp. 1725-1744.
  14. CHEN, K., J. YU, Short-Term Wind Speed Prediction Using an Unscented Kalman Filter Based State-Space Support Vector Regression Approach, Energy, vol. 113, 2014, pp. 690-705.
  15. LIU, H., H. Q., TIAN, Y. F. LI, H. L. ZHANG, Comparison of Four Adaboost Algorithm Based Artificial Neural Networks in Wind Speed Predictions, Energy Conversion and Management, Volume 92, 2015, pp. 67-81.
  16. CHITSAZ, H., N. AMJADY, H. ZAREIPOUR, Wind Power Forecast Using Wavelet Neural Network Trained by Improved Clonal Selection Algorithm, Energy Conversion and Management, Volume 89, 2015, pp. 588-598.
  17. BLONBOU, R., Very Short-Term Wind Power Forecasting with Neural Networks and Adaptive Bayesian Learning, Renewable Energy, Volume 36, Issue 3, 2011, pp. 1118-1124.
  18. LI, G., SHI, J., On Comparing Three Artificial Neural Networks for Wind Speed Forecasting, Applied Energy, Volume 87, Issue 7, 2010, pp. 2313-2320.
  19. OLAOFE, Z. O., A 5-Day Wind Speed &Amp; Power Forecasts Using a Layer Recurrent Neural Network (LRNN), Sustainable Energy Technologies and Assessments, Vol. 6, 2014, pp. 1-24.
  20. REN, C., N. AN, J. WANG, L. LI, B. HU, D. SHANG, Optimal Parameters Selection for BP Neural Network Based on Particle Swarm Optimization: A Case Study of Wind Speed Forecasting, Knowledge-Based Systems, Volume 56, 2014, pp. 226-239.
  21. YEH, W. C., Y. M. YEH, P. C. CHANG, Y. C. KE, V. CHUNG, Forecasting Wind Power in the Mai Liao Wind Farm Based on the Multi-Layer Perceptron Artificial Neural Network Model with Improved Simplified Swarm Optimization, J. of El. Power & En. Sys., vol. 55, 2014, pp 741-748.
  22. FOLEY, A. M., P. G. LEAHY, A. MARVUGLIA, E. J. MCKEOGH, Current Methods and Advances in Forecasting of Wind Power Generation, Renewable Energy, Volume 37, no. 1, 2012, pp. 1-8.
  23. KARINIOTAKIS, G., I. MARTÍ, D. CASAS, et al., What Performance Can Be Expected by Short-Term Wind Power Prediction Models Depending on Site Characteristics, In Proc. of the European Wind Energy Conference EWEC 2004.
  24. Wind Power Energy, official website, www.wpe.ro, accessed on 13.11.2015.
  25. MONTEIRO, C., R. BESSA, V. MIRANDA, A., BOTTERUD, A. J. WANG, G. CONZELMANN, Wind Power Forecasting: State-of-the-art 2009., No. ANL/DIS-10-1. Argonne National Laboratory. (ANL), 2009.

https://doi.org/10.24846/v25i1y201609