A New and Efficient K-Medoid Algorithm for Spatial Clustering

Zhang, Qiaoping; Couloigner, Isabelle

doi:10.1007/11424857_20

Cited by 78 publications

(38 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, we perform further analysis on the conditions under which a TFDI can be detected or cannot be detected by the EDSE detector. From the traversal attack simulation on an IEEE 39-bus system, we find that attacks on the transmission lines connected to bus 6 , bus 16 and bus 26 are more likely to trigger the detector, even with very low IDL. From the perspective of graph theory, these buses have high degree (the number of neighboring edges of the node).…”

Section: Discussion Of Undetected Tfdi Attacksmentioning

confidence: 99%

“…Therefore, the absolute value of line reactance |X| is chosen to be the weight of edge. The large graph is divided into several subgraphs using clustering algorithms, such as the L-bounded Graph Partition Method (LGPM) [25], the K-Medoid [26], and Chameleon [27], etc. In this paper, the LGPM method is applied to graph decomposition, since it is relatively stable and not affected by the choice of initial clustering centers.…”

Section: Power System Decompositionmentioning

confidence: 99%

See 1 more Smart Citation

Extended Distributed State Estimation: A Detection Method against Tolerable False Data Injection Attacks in Smart Grids

et al. 2014

View full text Add to dashboard Cite

False data injection (FDI) is considered to be one of the most dangerous cyber-attacks in smart grids, as it may lead to energy theft from end users, false dispatch in the distribution process, and device breakdown during power generation. In this paper, a novel kind of FDI attack, named tolerable false data injection (TFDI), is constructed. Such attacks exploit the traditional detector's tolerance of observation errors to bypass the traditional bad data detection. Then, a method based on extended distributed state estimation (EDSE) is proposed to detect TFDI in smart grids. The smart grid is decomposed into several subsystems, exploiting graph partition algorithms. Each subsystem is extended outward to include the adjacent buses and tie lines, and generate the extended subsystem. The Chi-squares test is applied to detect the false data in each extended subsystem. Through decomposition, the false data stands out distinctively from normal observation errors and the detection sensitivity is increased. Extensive TFDI attack cases are simulated in the Institute of Electrical and Electronics Engineers (IEEE) 14-, 39-, 118-and 300-bus systems. Simulation results show that the detection precision of the EDSE-based method is much higher than that of the traditional method, while the proposed method significantly reduces the associated computational costs.

show abstract

Section: Discussion Of Undetected Tfdi Attacksmentioning

confidence: 99%

Section: Power System Decompositionmentioning

confidence: 99%

Extended Distributed State Estimation: A Detection Method against Tolerable False Data Injection Attacks in Smart Grids

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Calculating the similarity matrix for K-medoids using DTW, has a time complexity of O(N 2 S 2 ), thus quadratic in the number of time series. For our experiment we used the PAM algorithm described by [21] in combination with the standard DTW algorithm using the Euclidean norm as distance. A big disadvantage of this method is that the number of clusters needs to be specified a priori, which is hard, especially in our case where we do not know exactly how many clusters are desirable for getting an insight in the households.…”

Section: Clustering Approachesmentioning

confidence: 99%

Energy consumption profiling using Gaussian processes

Leysen

Verbeke

Dagnely

et al. 2016

2016 IEEE 8th International Conference on Intelligent Systems (IS)

View full text Add to dashboard Cite

Abstract-We present a novel clustering approach for time series based on Gaussian process regression in order to discover insights in the spending habits of households. The advantage of the proposed method is that it avoids the pairwise comparison of time series, employed by many existing methods. To this end, it learns a generalized model on several time series at once, based on their likelihood. We have validated our method using a real-world energy consumption dataset of 71 households and compared it with K-medoids and agglomerative clustering, using dynamic time warping. We not only show that our method is superior in terms of scalability but also that the produced results are useful in the decision making process of a company.

show abstract

“…The similarity among objects can be defined by applying the Euclidean distance, Manhattan distance and so on [9,10]. In this paper, the Euclidean distance is applied and it is assumed that all the data is in a twodimensional space.…”

Section: The Rank-based K-medoids Algorithmmentioning

confidence: 99%

A Rank-Based K-medoids Clustering Algorithm by a Specific P System

Liu¹,

Li²

2015

Proceedings of the 5th International Conference on Computer Engineering and Networks — PoS(CENet2015)

View full text Add to dashboard Cite

In this paper, a rank-based K-medoids algorithm by a specific P system is proposed, which exhibits novel aspect of applying membrane computing in clustering. The traditional K-medoids clustering result suffers sensitivity to initial medoids selected randomly. To conquer the defect, we introduce the rank based on similarity between pairs of objects for the initialization. As a biological computing model, P system imitates the structure and function of living cells, and the reactions in it process in a maximal parallel and distributed manner. P system is adequate to solve clustering problem for its high parallelism and lower computational time complexity. A specific P system with a sequence of rule is constructed to realize the rank-based K-medoids algorithm. Through test verification, it can improve the clustering quality.

show abstract

A New and Efficient K-Medoid Algorithm for Spatial Clustering

Cited by 78 publications

References 8 publications

Extended Distributed State Estimation: A Detection Method against Tolerable False Data Injection Attacks in Smart Grids

Extended Distributed State Estimation: A Detection Method against Tolerable False Data Injection Attacks in Smart Grids

Energy consumption profiling using Gaussian processes

A Rank-Based K-medoids Clustering Algorithm by a Specific P System

Contact Info

Product

Resources

About