DOI QR코드

DOI QR Code

Spatio-temporal Load Forecasting Considering Aggregation Features of Electricity Cells and Uncertainties in Input Variables

  • Zhao, Teng (Dept. of Electrical Engineering, Shanghai Jiao Tong University) ;
  • Zhang, Yan (Dept. of Electrical Engineering, Shanghai Jiao Tong University) ;
  • Chen, Haibo (State Grid Shanghai Municipal Power Company)
  • Received : 2016.10.01
  • Accepted : 2017.08.09
  • Published : 2018.01.01

Abstract

Spatio-temporal load forecasting (STLF) is a foundation for building the prediction-based power map, which could be a useful tool for the visualization and tendency assessment of urban energy application. Constructing one point-forecasting model for each electricity cell in the geographic space is possible; however, it is unadvisable and insufficient, considering the aggregation features of electricity cells and uncertainties in input variables. This paper presents a new STLF method, with a data-driven framework consisting of 3 subroutines: multi-level clustering of cells considering their aggregation features, load regression for each category of cells based on SLS-SVRNs (sparse least squares support vector regression networks), and interval forecasting of spatio-temporal load with sampled blind number. Take some area in Pudong, Shanghai as the region of study. Results of multi-level clustering show that electricity cells in the same category are clustered in geographic space to some extent, which reveals the spatial aggregation feature of cells. For cellular load regression, a comparison has been made with 3 other forecasting methods, indicating the higher accuracy of the proposed method in point-forecasting of spatio-temporal load. Furthermore, results of interval load forecasting demonstrate that the proposed prediction-interval construction method can effectively convey the uncertainties in input variables.

E1EEFQ_2018_v13n1_38_f0001.png 이미지

Fig. 1. Procedure of proposed STLF method

E1EEFQ_2018_v13n1_38_f0002.png 이미지

Fig. 2. Flowchart of cellular load regression

E1EEFQ_2018_v13n1_38_f0003.png 이미지

Fig. 3. Structural diagram of SLS-SVRNs algorithm

E1EEFQ_2018_v13n1_38_f0004.png 이미지

Fig. 4. Schematic diagram for confidence interval evaluation

E1EEFQ_2018_v13n1_38_f0005.png 이미지

Fig. 5. Map of the service area after cellular division

E1EEFQ_2018_v13n1_38_f0006.png 이미지

Fig. 6. Evolution of cellular peak load in terms of land-usetype and distance to main roads

E1EEFQ_2018_v13n1_38_f0007.png 이미지

Fig. 7. Results of multi-level cell clustering

E1EEFQ_2018_v13n1_38_f0008.png 이미지

Fig. 8. Number of samples for each forecasting model

E1EEFQ_2018_v13n1_38_f0009.png 이미지

Fig. 9. Spatio-temporal load forecasting results andforecasting error of the service area in 2013, 2014and 2015

E1EEFQ_2018_v13n1_38_f0010.png 이미지

Fig. 10. MAPE (cell-fixed) of STLF results using differentmethods

Table 1. Simulation data sets of the test case.

E1EEFQ_2018_v13n1_38_t0001.png 이미지

Table 2. MAPE (year-fixed) of STLF results using different methods

E1EEFQ_2018_v13n1_38_t0002.png 이미지

Table 3. Interval forecasts of input variables (external properties)

E1EEFQ_2018_v13n1_38_t0003.png 이미지

Table 4. Sampled blind number of input variables (external properties)

E1EEFQ_2018_v13n1_38_t0004.png 이미지

Table 5. Evaluation of interval load forecasting.

E1EEFQ_2018_v13n1_38_t0005.png 이미지

References

  1. A. N. Sekhar, K. S. Rajan and A. Jain, "Spatial informatics and geographical information systems: tools to transform electric power and energy systems," in TENCON 2008-2008 IEEE Region 10 Conference, pp. 1-5, 2008.
  2. P. B. T. Inc., "Interactive city map of electricity, "http://www.powermap.com.cn/, 2016-08-26
  3. X. Bai, Z. Chao and M. U. Gang, "Review and prospect of the spatial load forecasting methods," Proceedings of the CSEE, vol. 33, no. 25, pp. 78-92, 2013.
  4. X. Bai, G. Peng-wei, M. Gang, Y. Gan-gui, L. Ping, C. Hong-wei, L. Jie-fu, and B. Yang, "A spatial load forecasting method based on the theory of clustering analysis," Physics Procedia, vol. 24, Part A, pp. 176- 183, 2012. https://doi.org/10.1016/j.phpro.2012.02.027
  5. J. D. Melo, E. M. Carreno and A. Padilha-Feltrin, "Multi-agent simulation of urban social dynamics for spatial load forecasting," IEEE Transactions on Power Systems, vol. 27, no. 4, pp. 1870-1878, 2012. https://doi.org/10.1109/TPWRS.2012.2190109
  6. J. D. Melo, E. M. Carreno, A. Padilha Feltrin, and C. R. Minussi, "Grid‐based simulation method for spatial electric load forecasting using power‐law distribution with fractal exponent," International Transactions on Electrical Energy Systems, 2015.
  7. Monika, D. Srinivasan and T. Reindl, "Real-time display of data from a smart-grid on geographical map using a GIS tool and its role in optimization of game theory," in Smart Grid Technologies - Asia,, pp. 1-6, 2015.
  8. X. He, Q. Ai, R. C. Qiu, J. Ni, L. Piao, Y. Xu, and X. Xu, "3D Power-map for smart grids - An integration of high-dimensional analysis and visualization," Statistics, 2015.
  9. E. M. Carreno, R. M. Rocha and A. Padilha-Feltrin, "A cellular automaton approach to spatial electric load forecasting," Power Systems, IEEE Transactions on, vol. 26, no. 2, pp. 532-540, 2011.
  10. J. Yu, F. Yan, W. Yang, and X. Gao, "Spatial load forecasting of distribution network based on fuzzy multi-objective multi-person decision making," Power System Technology, vol. 30, no. 7, pp. 69-76, 2006.
  11. S. Lei, C. Sun, Q. Zhou, and X. Zhang, "Application of fuzzy rough set theory in spatial load forecasting," Power System Technology, vol. 29, no. 9, pp. 26-30, 2005.
  12. X. Yang, J. Yuan, T. Zhang, and H. Mao, "Application of uncertainty reasoning based on cloud theory in spatial load forecasting," in World Congress on Intelligent Control and Automation, pp. 7567 - 7571, 2006.
  13. W. B. Tao, L. Z. Zhang, P. Hong, L. I. Zhen-Yuan, and Z. Hua, "Spatial electric load forecasting based on double-level bayesian classification," Proceedings of the CSEE, 2007.
  14. Z. Quan, S. Wei, H. Ren, Z. Yun, C. Sun, G. Xie, and J. Deng, "Spatial load forecasting of distribution network based on least squares support vector machine and load density index system," Power System Technology, vol. 35, no. 1, pp. 66-71, 2011.
  15. L. J. Liu, Y. Fu, S. W. Ma, and R. Hu, "Spatial load forecasting of distribution network based on intuitionistic fuzzy entropy and fuzzy clustering," Advanced Materials Research, vol. 516-517, no. 100, pp. 1433-1436, 2012. https://doi.org/10.4028/www.scientific.net/AMR.516-517.1433
  16. Z. Sun, X. Wang, Z. Shouxiang, W. Lei, and S. Guo, "New load density forecasting method for objective network planning," in International Conference on MEMS NANO, and Smart Systems, pp. 114-117, 2009.
  17. M. Ghofrani, M. Ghayekhloo, A. Arabali, and A. Ghayekhloo, "A hybrid short-term load forecasting with a new input selection framework," Energy, vol. 81, pp. 777-786, 2015. https://doi.org/10.1016/j.energy.2015.01.028
  18. S. Li, P. Wang and L. Goel, "Short-term load forecasting by wavelet transform and evolutionary extreme learning machine," Electric Power Systems Research, vol. 122, pp. 96-103, 2015. https://doi.org/10.1016/j.epsr.2015.01.002
  19. C. H. Jin, G. Pok, Y. Lee, H. Park, K. D. Kim, U. Yun, and K. H. Ryu, "A SOM clustering pattern sequence-based next symbol prediction method for day-ahead direct electricity load and price forecasting," Energy Conversion and Management, vol. 90, pp. 84-92, 2015. https://doi.org/10.1016/j.enconman.2014.11.010
  20. F. L. Quilumba, W. Lee, H. Huang, D. Y. Wang, and R. L. Szabados, "Using smart meter data to improve the accuracy of intraday load forecasting considering customer behavior similarities," IEEE Transactions on Smart Grid, vol. 6, no. 2, pp. 911-918, 2015. https://doi.org/10.1109/TSG.2014.2364233
  21. C. Wang, G. Grozev and S. Seo, "Decomposition and statistical analysis for regional electricity demand forecasting," Energy, vol. 41, no. 1, pp. 313-325, 2012. https://doi.org/10.1016/j.energy.2012.03.011
  22. A. S. Khwaja, M. Naeem, A. Anpalagan, A. Venetsanopoulos, and B. Venkatesh, "Improved short-term load forecasting using bagged neural networks," Electric Power Systems Research, vol. 125, pp. 109-115, 2015. https://doi.org/10.1016/j.epsr.2015.03.027
  23. S. Bandyopadhyay, T. Ganu, H. Khadilkar, and V. Arya, "Individual and aggregate electrical load forecasting: one for all and all for one," in ACM Sixth International Conference, pp. 1653-1654, 2015.
  24. X. M. Yang, J. S. Yuan, J. F. Wang, and X. Gao, "A new spatial forecasting method for distribution network based on cloud theory," Proceedings of the CSEE, vol. 26, no. 6, pp. 30-36, 2006.
  25. M. Batty, Cities and complexity: understanding cities with cellular automata, agent-based models, and fractals: The MIT press, pp. 1-565, 2007.
  26. J. D. Melo, E. M. Carreno, A. Calvino, and A. Padilha-Feltrin, "Determining spatial resolution in spatial load forecasting using a grid-based model," Electric Power Systems Research, vol. 111, pp. 177- 184, 2014. https://doi.org/10.1016/j.epsr.2014.02.019
  27. B. Xiao, P. Nie, G. Mu, J. Wang, and L. Tian, "A spatial load forecasting method based on multilevel clustering analysis and support vector machine," Automation of Electric Power Systems, vol. 39, no. 12, pp. 56-61, 2015.
  28. R. Lleti, M. C. Ortiz, L. A. Sarabia, and M. S. Sanchez, "Selecting variables for k-means cluster analysis by using a genetic algorithm that optimises the silhouettes," Analytica Chimica Acta, vol. 515, no. 1, pp. 87-100, 2004. https://doi.org/10.1016/j.aca.2003.12.020
  29. A. Rajaraman, J. Leskovec and J. D. Ullman, Mining of massive datasets, 1 ed. Cambridge, United Kingdom: Cambridge University Press, pp. 253-254, 2011.
  30. A. Khosravi, S. Nahavandi and D. Creighton, "Load forecasting and neural networks: A prediction interval-based perspective," in Computational intelligence in power engineering: Springer, pp. 131-150, 2010.
  31. J. W. Taylor and R. Buizza, "Neural network load forecasting with weather ensemble predictions," IEEE Transactions on Power Systems, vol. 17, no. 3, pp. 626-632, 2002. https://doi.org/10.1109/TPWRS.2002.800906
  32. A. Khosravi, S. Nahavandi and D. Creighton, "Construction of optimal prediction intervals for load forecasting problems," IEEE Transactions on Power Systems, vol. 25, no. 3, pp. 1496-1503, 2010. https://doi.org/10.1109/TPWRS.2010.2042309
  33. A. Khosravi, S. Nahavandi and D. Creighton, "Prediction interval construction and optimization for adaptive neurofuzzy inference systems," IEEE Transactions on Fuzzy Systems, vol. 19, no. 5, pp. 983-988, 2011. https://doi.org/10.1109/TFUZZ.2011.2130529
  34. N. A. A. Jalil, M. H. Ahmad and N. Mohamed, "Electricity load demand forecasting using exponential smoothing methods," World Applied Sciences Journal, vol. 22, no. 11, pp. 1540-1543, 2013.
  35. A. W. L. Yao, S. C. Chi and J. H. Chen, "An improved Grey-based approach for electricity demand forecasting," Electric Power Systems Research, vol. 67, no. 3, pp. 217-224, 2003. https://doi.org/10.1016/S0378-7796(03)00112-3
  36. G. I. Treyz, Regional economic modeling: A systematic approach to economic forecasting and policy analysis. Berlin, Germany: Springer Science & Business Media, pp. 258-262, 2013.
  37. D. B. Stephenson, C. Coelho, F. J. DOBLAS REYES, and M. Balmaseda, "Forecast assimilation: a unified framework for the combination of multi - model weather and climate predictions," Tellus A, vol. 57, no. 3, pp. 253-264, 2005. https://doi.org/10.3402/tellusa.v57i3.14664
  38. A. J. Coale, P. Demeny and B. Vaughan, Regional Model Life Tables and Stable Populations: Studies in Population, 2 ed. New York, USA: ACADEMIC PRESS, pp. 25-36, 2013.