Abstract
With the improvement of operation monitoring and data acquisition levels of smart meters, mining data associated with smart meters becomes possible. Besides, precisely assessing the operation quality of smart meters plays an important role in purchasing metering equipment and improving the economic benefits of power utilities. First, seven indexes for assessing operation quality of smart meters are defined based on the metering data and the Gaussian mixture model (GMM) clustering algorithm is applied to extract the typical index data from the massive data of smart meters. Then, the combination optimization model of index’s weight is presented with the subject experience of experts and object difference of data considered; and the comprehensive assessment algorithm based on the revised technique for order preference by similarity to an ideal solution (TOPSIS) is proposed to evaluate the operation quality of smart meters. Finally, the proposed data-driven assessment algorithm is illustrated by the actual metering data from Zhejiang Ningbo power supply company of China and practical application is briefly introduced. The results show that the proposed algorithm is effective for assessing the operation quality of smart meters and could be helpful for energy measurement and asset management.
Highlights
With the increase of customers’ requirements on power quality, power marketing has received more and more attention from power companies [1,2]
In order to fully consider the subjective scoring based on expert experience and modify the weights according to the characteristics of the data themselves, a combined optimization model of index weight of operation quality for smart meters based on the weight membership degree is presented as max f (x) =
In order to demonstrate the effectiveness of the proposed GCT-based algorithm, the results of the equipment operation quality assessment based on simple additive weighting (SAW), analytic hierarchy process (AHP) and the proposed GCT-based algorithm are shown in Table 6, respectively
Summary
With the increase of customers’ requirements on power quality, power marketing has received more and more attention from power companies [1,2]. The quality assessment indexes of terminal meters for pre-operation quality, operation quality and maintenance are proposed and the quality assessment model for whole-life-cycle is presented based on entropy weight method and improved AHP in Reference [11]. The Gaussian mixture model (GMM) [20,21] clustering algorithm is applied to discover the internal correlation among the fault alarm data and to extract the typical indexes that characterize the operation quality of the smart meters, thereby to reduce the storage scale and calculation complexity of the comprehensive assessment model of smart meters. There are massive data to be processed, it is necessary to utilize suitable clustering method (i.e., GMM clustering method in this work) to reduce the scale of data for further assessment Given this background, a GMM, combination weight model and revised TOPSIS (GCT)-based algorithm is proposed in this paper. The application of the proposed algorithm in the actual system of Zhejiang Province is introduced briefly
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
