Multi-attributes Graph Algorithm for Association Rules Mining Over Energy Internet
In recent years, with the development of the energy internet. Developing energy internet system is a necessary requirement for building resource-saving and environment-friendly society. Due to the consumption of the load is affected by many factors, each factor is an attribute. Our main contribution is that as the property changes in the weight of all influencing factors in the different time intervals, and calculates the global attribute nodes based on the graph updating. Furthermore, for analysis and predicts the trend of user side power consumption. By this way, our objective is through the definition of various attributes, discovery groups of potential distribution formed by dense power graphs that are homogeneous with respect to the attribute correlation of users. To this aim, we present a new kind of pattern algorithm called Mapm algorithm. It’s a multi-attributes correlated pattern mining algorithm, based on the correlation operation of multiple attributes, through the results of mining to find similar users, so as to achieve the forecast purpose of real-time power consumption.
KeywordsEnergy internet Frequent attribute pattern Power attribute correlation
This work was supported by the National Natural Science Foundation of China (No. 61701104), by SRF for ROCS, SEM and by the Science Research of Education Department of Jilin Province (No. 201698).
- 6.Boustani, A., Maiti, A., Jazi, S.Y., Jadliwala, M., Namboodiri, V.: Seer grid: privacy and utility implications of two-level load prediction in smart grids. IEEE Trans. Parallel Distrib. Syst. 28(2), 546–557 (2017)Google Scholar
- 14.Karunaratne, T.M.: Learning predictive models from graph data using pattern mining. Doctoral dissertation, Department of Computer and Systems Sciences, Stockholm University (2014)Google Scholar
- 15.Hong, T.P., Wu, J.M.T., Li, Y.K., Chen, C.H.: Generalizing concept-drift patterns for fuzzy association rules. J. Netw. Intell. 3(2), 126–137 (2018)Google Scholar
- 16.Philippe, F.V., Jerry, C.W.L., Rage, U.K., Yun, S.K., Rincy, T.: A survey of sequential pattern mining. Data Sci. Pattern Recognit. 1(1), 54–77 (2017)Google Scholar
- 18.Singh, V.K., Shah, V., Jain, Y.K., Shukla, A., Thoke, A.S., Singh, V.K., Parganiha, V.: Proposing an efficient method for frequent pattern mining. World Acad. Sci., Eng. Technol. 61(48), 384–390 (2017)Google Scholar