Demand side management is one of the key topics of smart grids. This study integrates the service computing paradigm in smart grid domain and proposes a demand side personalised recommendation system (PRS). The proposed PRS employs service recommendation techniques to infer residential users’ potential interests and needs on energy saving appliances, and then it recommends energy saving appliances to users, therefore potentially creating opportunities to save energy for the grid. The proposed approach starts by applying a non-intrusive appliance load monitoring (NILM) method based on generalised particle filtering to disaggregate the end users’ household appliance utilisation profiles from the smart meter data. Based on the NILM results, several inference rules are applied to infer the preferences and energy consumption patterns, and to form the user profile. In parallel, information retrieval techniques are applied to extract keywords from the textual appliance advertisements (Ads), and to define the appliance profile. Finally, the similarity measurement method is applied to compare the user profile and appliance profile, to rank the appliance Ad, and to make the recommendations. Experiments are conducted to validate the proposed system.

References

1. 1)
  - 9. Wang, H., Meng, K., Dong, Z.Y., et al: ‘Efficient real-time residential energy management through MILP based rolling horizon optimization’. Proc. IEEE PES General Meeting, 2015.
2. 2)
  - 15. Pazzani, M., Billsus, D.: ‘Learning and revising user profiles: the identification of interesting Web sites’, Mach. Learn., 1997.
3. 3)
  - 14. Mooney, R., Bennett, P., Roy, L.: ‘Book recommending using text categorization with extracted information’. Proc. Recommender Systems Papers from 1998 Workshop, Technical Report WS-98–08, 1998.
4. 4)
  - 25. Basu, K., Debusschere, V., Bacha, S., et al: ‘Non-intrusive load monitoring: a temporal multi-label classification approach’, IEEE Trans. Ind. Inf., 2015, 11, (1), pp. 262–270.
5. 5)
  - 17. Wang, X., Luo, F., Qian, Y., et al: ‘A personalized electronic movie recommendation system based on support vector machine and improved particle swarm optimization’, Plost One, 2016, 11, (11).
6. 6)
  - 3. Giri, J., Sun, D., Avila-Rosales, R.: ‘A more intelligent grid’, IEEE Power Energy Mag., 2009, 7, (2), pp. 34–40.
7. 7)
  - 5. Chen, Z., Wu, L., Fu, Y.: ‘Real-time price-based demand response management for residential appliances via stochastic optimization and robust optimization’, IEEE Trans. Smart Grid, 2012, 3, (4), pp. 1822–1831.
8. 8)
  - 8. Wang, H., Meng, K., Luo, F., et al: ‘Demand response through smart home energy management using thermal inertia’. Proc. Australasian Universities Power Engineering Conf., 2013.
9. 9)
  - 11. Rastergar, M., Fotuhi-Firuzabad, M., Aminifar, F.: ‘Load commitment in a smart home’, Appl. Energy, 2012, 96, pp. 45–54.
10. 10)
  - 16. Wang, X., Wen, J., Luo, F.: ‘Personalized recommendation system based on support vector machine and particle swarm optimization’. Proc. 8th Int. Conf. on Knowledge Science, Engineering and Management, 2015.
11. 11)
  - 24. Kolter, J., Batra, S., Ng, A.: ‘Energy disaggregation via discriminative sparse coding’. Proc. 24th Annual Conf. on Neural Information Processing Systems, 2010.
12. 12)
  - 12. Piette, M., Watson, D., Motegi, N., et al: ‘Automated demand response strategies and commissioning commercial building controls’. Proc. 14th National Conf. Building Commissioning, San Francisco, CA, April 2006.
13. 13)
  - 28. Amazon. Available at www.amazon.com.
14. 14)
  - 23. Hsueh-Hsien, C., Ching-Luang, L., Hong-Tzer, Y.: ‘load recognition for different loads with the same load-monitoring system’. Proc. 12th Int. Conf. on Computer Supported Cooperative Work in Design, 2008.
15. 15)
  - 1. Luo, F., Zhao, J., Dong, Z.Y., et al: ‘Cloud-based information infrastructure for next-generation power grid: conception, architecture, and applications’, IEEE Trans. Smart Grid, 2015, 4, (7), pp. 1896–1912.
16. 16)
  - 21. Hart, G.: ‘Nonintrusive appliance load monitoring’, Proc. IEEE, 1992.
17. 17)
  - 4. Chen, C., Wang, J., Kishore, S.: ‘A distributed direct load control approach for large-scale residential demand response’, IEEE Trans. Power Syst., 2014, 29, (5), pp. 2219–2228.
18. 18)
  - 22. Berges, M., Goldman, E., Matthews, H., et al: ‘Enhancing electricity audits in residential buildings with non-intrusive load monitoring’, J. Ind. Ecol., 2007, 14, (5), pp. 844–858.
19. 19)
  - 7. Luo, F., Dong, Z.Y., Meng, K., et al: ‘An operational planning framework for large scale thermostatically controlled load dispatch’, IEEE Trans. Ind. Inf., 2016, 13, (1), pp. 217–227.
20. 20)
  - 6. Luo, F., Zhao, J., Dong, Z.Y., et al: ‘Optimal dispatch of air conditioner loads in southern China region by direct load control’, IEEE Trans. Smart Grid, 2015, 7, (1), pp. 439–450.
21. 21)
  - 30. Kong, W., Dong, Z.Y., Hill, D., et al: ‘Improving non-intrusive load monitoring efficiency via a hybrid-programming method’, IEEE Trans. Ind. Inf., doi: 10.1109/TII.2016.2590359.
22. 22)
  - 13. Adomavicius, G., Tuzhilin, A.: ‘Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions’, IEEE Trans. Knowl. Data Eng., 2005, 17, (6), pp. 734–749.
23. 23)
  - 20. Plotwatt Home. Available at https://plotwatt.com/.
24. 24)
  - 10. Pedrasa, M.A., Spooner, T., MacGill, I.: ‘Coordinated scheduling of residential distributed energy resources to optimize smart home energy services’, IEEE Trans. Smart Grid, 2010, 1, (2), pp. 134–143.
25. 25)
  - 29. Ebay. Available at www.ebay.com.
26. 26)
  - 32. Salton, G.: ‘Automatic text processing’ (Addison-Wesley, 1989).
27. 27)
  - 27. Breese, J., Heckerman, D., Kadie, C.: ‘Empirical analysis of predictive algorithms for collaborative filtering’. Proc. 14th Conf. Uncertainty in Artificial Intelligence, 1998.
28. 28)
  - 33. Rocchio, J.: ‘Relevance feedback in information retrieval’, in ‘SMART retrieval system – experiments in automatic document processing’ (Prentice Hall, Upper Saddle River, NJ, USA, 1971).
29. 29)
  - 31. Egarter, D., Phuvana, V., Elmenreich, W.: ‘PALDi: Online load disaggregation via particle filtering’, IEEE Trans. Instrum. Meas., 2015, 64, (2), pp. 467–477.
30. 30)
  - 34. Kolter, Z., Johnson, M.: ‘REDD: A public data set for energy disaggregation research’. Proc. Workshop on Data Mining Applications in Sustainability, 2011.
31. 31)
  - 35. Kong, W., Dong, Z.Y., Jia, Y., et al: ‘A rule based domestic load profile for future smart grid’. Proc. Australia Universities Power Engineering Conf., 2014.
32. 32)
  - 18. Luo, F., Ranzi, G., Wang, X., et al: ‘Service recommendation in smart grid: vision, technologies, and applications’. Proc. Int. Conf. on Service Science, China, 2016, in press.
33. 33)
  - 19. Energy Start Appliances Recommended by Alabama Power. Available at http://www.alabamapower.com/residential/save-money-energy/energy-star/appliances.asp.
34. 34)
  - 36. Stop Hand Washing: Newest dishwashers save more water than you can. Available at http://lifehacker.com/stop-hand-washing-newer-dishwashers-save-more-water-th-1704681500.
35. 35)
  - 2. Luo, F., Dong, Z.Y., Meng, K., et al: ‘Enabling the big data analysis in the smart grid’. Proc. IEEE PES General Meeting, 2015.
36. 36)
  - 26. Kim, H., Marwah, M., Arlitt, M., et al: ‘Unsupervised disaggregation of low frequency power measurements’. Proc. SIAM Int. Conf. on Data Mining, 2011.

Non-intrusive energy saving appliance recommender system for smart grid residential users

References

Related content