Journal of Systems Science and Complexity

, Volume 28, Issue 5, pp 1080–1101 | Cite as

A novel hybrid FA-Based LSSVR learning paradigm for hydropower consumption forecasting

  • Ling Tang
  • Zishu Wang
  • Xinxie Li
  • Lean YuEmail author
  • Guoxing Zhang


Due to the nonlinearity and nonstationary of hydropower market data, a novel hybrid learning paradigm is proposed to predict hydropower consumption, by incorporating firefly algorithm (FA) into least square support vector regression (LSSVR), i.e., FA-based LSSVR model. In the novel model, the powerful and effective artificial intelligence (AI) technique, i.e., LSSVR, is employed to forecast hydropower consumption. Furthermore, a promising AI optimization tool, i.e., FA, is especially introduced to address the crucial but difficult task of parameters determination in LSSVR (e.g., hyper and kernel function parameters). With the Chinese hydropower consumption as sample data, the empirical study has statistically confirmed the superiority of the novel FA-based LSSVR model to other benchmark models (including existing popular traditional econometric models, AI models and similar hybrid LSSVRs with other popular parameter searching tools), in terms of level and directional accuracy. The empirical results also imply that the hybrid FA-based LSSVR learning paradigm with powerful forecasting tool and parameters optimization method can be employed as an effective forecasting tool for not only hydropower consumption but also other complex data.


Artificial intelligence firefly algorithm hybrid model hydropower consumption least squares support vector regression time series forecasting 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Comsan M N H, Nuclear electricity for sustainable development: Egypt a case study, Energy Conversion and Management, 2010, 51(9): 1813–1817.CrossRefGoogle Scholar
  2. [2]
    Batista N C, Melício R, Matias J C O, and Catalão J P S, Photovoltaic and wind energy systems monitoring and building/home energy management using ZigBee devices within a smart grid, Energy, 2013, 49: 306–315.CrossRefGoogle Scholar
  3. [3]
    Tang L, Yu L, and He K J, A novel data-characteristic-driven modeling methodology for nuclear energy consumption forecasting, Applied Energy, 2014, 128: 1–14.CrossRefGoogle Scholar
  4. [4]
    Lean H H and Smyth R, Will initiatives to promote hydroelectricity consumption be effective? Evidence from univariate and panel LM unit root tests with structural breaks, Energy Policy, 2014, 68: 102–115.CrossRefGoogle Scholar
  5. [5]
    Chang X L, Liu X H, and Zhou W, Hydropower in China at present and its further development, Energy, 2010, 35(11): 4400–4406.CrossRefGoogle Scholar
  6. [6]
    Wang S, Yu L, Tang L and Wang S Y, A novel seasonal decomposition based least squares support vector regression ensemble learning approach for hydropower consumption forecasting in China, Energy, 2011, 36(11): 6542–6554.CrossRefGoogle Scholar
  7. [7]
    Zeng M, Xue S, Ma M J, and Zhu X L, New energy bases and sustainable development in China: A review, Renewable and Sustainable Energy Reviews, 2013, 20: 169–185.CrossRefGoogle Scholar
  8. [8]
    Houri A, Prospects and challenges of using hydropower for electricity generation in Lebanon, Renewable Energy, 2006, 31(11): 1686–1697.CrossRefGoogle Scholar
  9. [9]
    Vicuna S, Leonardson R, Hanemann M W, Dale L L, and Dracup J A, Climate change impacts on high elevation hydropower generation in California’s Sierra Nevada: A case study in the Upper American River, Climatic Change, 2008, 87(1): 123–137.CrossRefGoogle Scholar
  10. [10]
    Bianco V, Manca O, and Nardini S, Electricity consumption forecasting in Italy using linear regression models, Energy, 2009, 34(9): 1413–1421.CrossRefGoogle Scholar
  11. [11]
    Huang M, He Y, and Cen H, Predictive analysis on electric-power supply and demand in China, Renewable Energy, 2007, 32(7): 1165–1174.CrossRefGoogle Scholar
  12. [12]
    Yao M and Wang X, Electricity consumption forecasting based on a class of new GM(1,1) model, Mechatronics and Automatic Control Systems, 2014, 237: 947–953.CrossRefGoogle Scholar
  13. [13]
    Guo W Y, Shen X L, Ma X K, Ma L, and Cao T, Comparative study of grey forecasting model and ARMA model on Beijing electricity consumption forecasting, Mechatronics and Automatic Control Systems, 2004, 237: 501–508.CrossRefGoogle Scholar
  14. [14]
    Erdogdu E, Electricity demand analysis using cointegration and ARIMA modelling: A case study of Turkey, Energy Policy, 2007, 35(2): 1129–1146.CrossRefzbMATHGoogle Scholar
  15. [15]
    Ahmad A S, Hassan M Y, Abdullah M P, Rahman H A, Hussina F, Abdullaha H, and Saidurb R, A review on applications of ANN and SVM for building electrical energy consumption forecasting, Renewable and Sustainable Energy Reviews, 2014, 33: 102–109.CrossRefGoogle Scholar
  16. [16]
    Ardakani F J and Ardehali M M, Long-term electrical energy consumption forecasting for developing and developed economies based on different optimized models and historical data types, Energy, 2014, 65: 452–461.CrossRefGoogle Scholar
  17. [17]
    Kavaklioglu K, Modeling and prediction of Turkey’s electricity consumption using support vector regression, Applied Energy, 2011, 88(1): 368–375.CrossRefGoogle Scholar
  18. [18]
    Jain R K, Smith K M, Culligan P J, and Taylor J E, Forecasting energy consumption of multifamily residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy, Applied Energy, 2014, 123: 168–178.CrossRefGoogle Scholar
  19. [19]
    Tang L, Yu L, Wang S, Li J P, and Wang S Y, A novel hybrid ensemble learning paradigm for nuclear energy consumption forecasting, Applied Energy, 2012, 93: 432–443.CrossRefGoogle Scholar
  20. [20]
    Tang L, Wang S, He K J, and Wang S Y, A novel mode-characteristic-based decomposition ensemble model for nuclear energy consumption forecasting, Annals of Operations Research, 2014, 1–22, DOI  10.1007/s10479-014-1595-5.Google Scholar
  21. [21]
    Yang F M, Li M, Huang A Q, and Li J, Forecasting time series with genetic programming based on least square method, Journal of Systems Science and Complexity, 2014, 27(1): 117–129.MathSciNetCrossRefzbMATHGoogle Scholar
  22. [22]
    Hassani H, Abdollahzadeh M, Iranmanesh H, and Miranian A, A self-similar local neuro-fuzzy model for short-term demand forecasting, Journal of Systems Science and Complexity, 2014, 27(1): 3–20.MathSciNetCrossRefzbMATHGoogle Scholar
  23. [23]
    Chen X J, Wang J Z, Sun D H, and Liang J Z, Time series forecasting based on novel support vector machine using artificial fish swarm algorithm, Proceedings of the 4th International Conference on Natural Computation (ICNC’08), Jinan, 2008.Google Scholar
  24. [24]
    Saini L M, Aggarwal S K, and Kumar A, Parameter optimisation using genetic algorithm for support vector machine-based price-forecasting model in national electricity market, Generation, Transmission & Distribution, 2010, 4(1): 36–49.CrossRefzbMATHGoogle Scholar
  25. [25]
    Pai P F and Hong W C, Support vector machines with simulated annealing algorithms in electricity load forecasting, Energy Conversion and Management, 2005, 46(17): 2669–2688.CrossRefGoogle Scholar
  26. [26]
    Chen Z Q, Yang S L, and Wang X J, PLS-SVR optimized by PSO algorithm for electricity consumption forecasting, Applied Mathematics & Information Sciences, 2013, 7: 331–338.CrossRefzbMATHGoogle Scholar
  27. [27]
    Yang X S, Nature-Inspired Metaheuristic Algorithms, Luniver Frome, 2008.Google Scholar
  28. [28]
    Fister I, Fister Jr I, Yang X S, and Brest J, A comprehensive review of firefly algorithms, Swarm and Evolutionary Computation, 2013, 13: 34–46.CrossRefGoogle Scholar
  29. [29]
    Baykasolu A and Ozsoydan F B, An improved firefly algorithm for solving dynamic multidimensional knapsack problems, Expert Systems with Applications, 2014, 41(8): 3712–3725.CrossRefGoogle Scholar
  30. [30]
    Kazema A, Sharifia E, Hussainb F K, Saberic M, and Hussaind O K, Support vector regression with chaos-based firefly algorithm for stock market price forecasting, Applied Soft Computing, 2013, 13(2): 947–958.CrossRefGoogle Scholar
  31. [31]
    Xiong T, Bao Y K, and Hu Z Y, Multiple-output support vector regression with a firefly algorithm for interval-valued stock price index forecasting, Knowledge-Based Systems, 2014, 55: 87–100.CrossRefGoogle Scholar
  32. [32]
    Ch S, Sohani S K, Kumar D, Malik A, Chahar B R, Nema A K, Panigrahi B K, and Dhimand R C, Support vector machine-firefly algorithm based forecasting model to determine malaria transmission, Neurocomputing, 2013, 129: 279–288.CrossRefGoogle Scholar
  33. [33]
    Yang X S, Firefly algorithms for multimodal optimization, Lecture Notes in Computer Science, 2009, 5792: 169–178.CrossRefGoogle Scholar
  34. [34]
    Vapnik V, The Nature of Statistical Learning Theory, Springer New York, 1995.CrossRefzbMATHGoogle Scholar
  35. [35]
    Suykens J A K and Vandewalle J, Least squares support vector machine classifiers, Neural Processing Letters, 1999, 9(3): 293–300.MathSciNetCrossRefGoogle Scholar
  36. [36]
    Yu L, Wang S Y, and Lai K K, A novel nonlinear ensemble forecasting model incorporating GLAR and ANN for foreign exchange rates, Computers & Operations Research, 2005, 32(10): 2523–2541.CrossRefzbMATHGoogle Scholar
  37. [37]
    Diebold F X and Mariano R S, Comparing predictive accuracy, Journal of Business & Economic Statistics, 2002, 20(1): 134–144.MathSciNetCrossRefGoogle Scholar
  38. [38]
    Box G E P, Jenkins G M, and Reinsel G C, Time Series Analysis: Forecasting and Control, John Wiley & Sons, New Jersey, 2013.Google Scholar
  39. [39]
    Deng J L, Control problems of grey systems, Systems & Control Letters, 1982, 1(5): 288–294.CrossRefzbMATHGoogle Scholar
  40. [40]
    Zhang G Q, Patuwo B E, and Hu M Y, Forecasting with artificial neural networks: The state of the art, International Journal of Forecasting, 1988, 14(1): 35–62.CrossRefGoogle Scholar
  41. [41]
    Li X L, A new intelligent optimization method-artificial fish school algorithm, Doctor’s Degree Thesis, Zhejiang University, 2003.Google Scholar
  42. [42]
    Ren Y and Bai G C, Determination of optimal SVM parameters by using GA/PSO, Journal of Computers, 2010, 5: 1160–1168.CrossRefGoogle Scholar
  43. [43]
    Christober Asir Rajan C and Mohan M R, An evolutionary programming based simulated annealing method for solving the unit commitment problem, International Journal of Electrical Power & Energy Systems, 2007, 29(7): 540–550.CrossRefGoogle Scholar
  44. [44]
    Kennedy J and Eberhart R, Particle swarm optimization, Proceedings of the 1995 IEEE International Conference on Neural Networks, University of Western Australia Press, Perth, Western Australia, 1995, 1942–1948.Google Scholar

Copyright information

© Institute of Systems Science, Academy of Mathematics and Systems Science, CAS and Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Ling Tang
    • 1
  • Zishu Wang
    • 1
  • Xinxie Li
    • 1
  • Lean Yu
    • 1
    Email author
  • Guoxing Zhang
    • 2
  1. 1.School of Economics and ManagementBeijing University of Chemical TechnologyBeijingChina
  2. 2.School of ManagementLanzhou UniversityLanzhouChina

Personalised recommendations