Two-Stage Clustering Approach for the Household Electricity Load Profiles by Fuzzy Logic and Neural Network Techniques

Abstract

In this paper, household electricity load profile (LP) clustering problem is addressed. LP clustering analysis has been utilized as predicted end-user LPs for demand or supply management strategies to maintain the stability of the power systems. The consumption dynamics of the LPs are formed by the combinations of technical and social factors. Hence, discovering the dynamic patterns of the LPs has been a challenging problem. For this problem, we have offered successive applications of Sugeno fuzzy-logic (SFL) and self-organizing map neural network (SOMNN) techniques. Firstly, the data sets of the LPs are clustered by fuzzy logic approach by the reference models which are generated with the common family-types per persons. Then, considering the extra input of the weighted occupancy profiles, SOMNN is performed to improve the clustering result according to the dataset. The proposed strategy has been simulated by MATLAB® and the related results are presented.

Keywords

• Clustering
• Sugeno Fuzzy Logic
• Self-Organizing Map Neural Network
• Household Load Profiles

Evsel Elektriksel Yük Profilleri için Bulanık Mantık ve Yapay Sinir Ağları Teknikleri ile İki-Kademeli Kümeleme Yaklaşımı

Abstract

Bu çalışmada, evsel elektriksel yük profili (YP) kümeleme problemi ele alınmıştır. YP kümeleme analizleri ile güç sistemlerinin kararlılığını sağlamada yararlanılan talep veya arz yönetimi stratejilerinin icrasında gerekli olan tahmini son kullanıcı YP tiplerinin elde edilmesi sağlanabilmektedir. YP tüketim dinamikleri hem teknik hem de sosyal unsurların etkileri ile şekillenmektedir. Bu bakımdan, YP dinamik davranışını anlamlandırmak zor bir problemdir. Bu çalışmada, bahsedilen bu problemin çözümü için iki ayrı aşamada sırasıyla Sugeno bulanık- mantık (SBM) ve öz-düzenleyici haritalı yapay sinir ağları (ÖDHYSA) tekniklerinin uygulandığı çözüm önerilmiştir. İlk olarak, YP veri seti ev halkı sayısı temelli aile tipleri üzerinden modellenen referans yük tipleri dikkate alınarak SBM tekniği ile sınıflandırılmıştır. Daha sonra, evde hâlihazırda bulunan hane halkının zaman bazlı ağırlıklandırılmış şekliyle de belirleyici bir giriş verisi olduğu düşünülerek ÖDHYSA tekniği uygulanıp kümeleme sonuçları iyileştirilmiştir. Önerilen stratejinin benzetim çalışması MATLAB® ortamında
gerçekleştirilip ilgili sonuçlar sunulmuştur.

Keywords

• Kümeleme
• Sugeno Bulanık Mantık
• Öz-düzenleyici Haritalı Yapay Sinir Ağları
• Evsel Yük Profilleri
• Clustering
• Clustering
• Sugeno Fuzzy Logic
• Sugeno Fuzzy Logic
• Self-Organizing Map Neural Network
• Self-Organizing Map Neural Network
• Household Load Profiles
• Household Load Profiles

References

1. [1] A. Jain, "Data clustering: 50 years beyond K-means," Pattern Recognition Letters, vol. 31, no.8, pp. 651-666, 2010.
2. [2] Z. Wang and T. Hong, "Generating realistic building electrical load profiles through the Generative Adversarial Network (GAN)," Energy and Buildings, vol. 224, no. 110299, pp. 1-15, 2020.
3. [3] F. McLoughlin, D. Aidan and M. Conlon,"A clustering approach to domestic electricity load profile characterisation using smart metering data" Applied Energy, vol. 141, pp.190-199, 2015.
4. [4] J. Aghaei and M. I. Alizadehand, "Demand response in smart electricity grids equipped with renewable energy sources: A review," Renewable and Sustainable Energy Reviews, vol. 18, pp. 64-72, 2013.
5. [5] Z. Zakaria and K. L. Lo, "Two-stage fuzzy clustering approach for load profiling," presented at the 44th IEEE UPEC, Glasgow, UK, 2009.
6. [6] L. Sun, K. Zhou and S. Yang, "An ensemble clustering based framework for household load profiling and driven factors identification," Sustainable Cities and Society, vol. 53, no. 101958, pp. 1- 11, 2020.
7. [7] M. Espinoza, C. Joye, R. Belmans, and B. D. Moor, "Short-term load forecasting, profile identification, and customer segmentation: a methodology based on periodic time series," IEEE Transactions on Power Systems, vol. 20, no. 3, pp. 1622-1630, 2015.
8. [8] D. Colley, N. Mahmoudi, D. Eghbal, and T.K. Saha, "Queensland load profiling by using clustering techniques," IEEE AUPEC, Perth, Australia, 2014.

9. [9] K. A. Choksi, J. Sonal and N. M. Pindoriya, "Feature based clustering technique for investigation of domestic load profiles and probabilistic variation assessment: Smart meter dataset," Sustainable Energy, Grids and Networks, vol. 22, no. 100346, pp. 1-11, 2020.
10. [10] J. N. Fidalgo, M. A. Matos and L. Ribeiro, "A new clustering algorithm for load profiling based on billing data," Electric Power Systems Research, vol. 82, no. 1, pp. 27-33, 2012.
11. [11] Z. Ma, R. Yan and N. Nord. "A variation focused cluster analysis strategy to identify typical daily heating load profiles of higher education buildings," Energy, vol. 134, no. 1, pp. 90-102, 2017.
12. [12] C.M.R. do Carmo and T. H. Christensen. "Cluster analysis of residential heat load profiles and the role of technical and household characteristics," Energy and Buildings, vol. 125, no. 1, pp. 171- 180, 2016.
13. [13] M. Piao, H. S. Shon, J. Y. Lee and K. H. Ryu "Subspace projection method based clustering analysis in load profiling," IEEE Transactions on Power Systems, vol. 29, no. 6, pp. 2628-2635, 2014.
14. [14] D. Vercamer, B. Steurtewagen, D. V. Poel, and F. Vermeulen,"Predicting consumer load profiles using commercial and open data," IEEE Transactions on Power Systems, vol. 3, no. 1.5, pp. 3693-3701, 2015.
15. [15] I. Richardson, M. Thomson, D. Infield and C. Clifford, “Domestic electricity use: A high- resolution energy demand model,” Energy and Buildings, vol. 42, no. 10, pp. 1878-1887, 2010.
16. [16] R. Granell, C. J. Axon and D. C. H. Wallom, "Impacts of Raw Data Temporal Resolution Using Selected Clustering Methods on Residential Electricity Load Profiles’,’IEEE Transactions on Power Systems, vol. 30, no. 6, pp. 3217-3224, 2015.
17. [17] L. A. Zadeh.‘’Fuzzy sets’’,Information and Control, vol. 8, pp. 338-353, 1965.
18. [18] R. Xu and D.C. Wunsch, ’’Clustering,’’ Wiley-IEEE, 2009.
19. [20] T. Kohonen. "Self-organized formation of topologically correct feature maps," Biological cybernetics, vol. 43, no. 1, pp. 59-69, 1982.