Electrical equipment energy efficiency chaos analysis method based on massive measurement data
A technology of metering data and electrical equipment, applied in the field of chaotic analysis of energy efficiency of electrical equipment based on massive metering data, can solve problems such as power supply shortage, power load analysis and prediction, power grid planning difficulties, waste, etc.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2016-06-22
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the technical field of electrical engineering, and in particular relates to a chaos analysis method for energy efficiency of electrical equipment based on massive metering data. Background technique
[0002] At present, the characteristics of my country's electric energy structure are as follows: the proportion of high energy consumption industries is relatively high, and the industrial economy is extremely dependent on electricity, coal and other energy sources. Judging from the current situation at home and abroad, energy has become a key factor affecting the development and scale expansion of enterprises. However, with the rapid development of enterprises and the continuous expansion of scale, while the demand for energy continues to increase, the phenomenon of waste is also very serious. At the same time, the highest power load in my country generally continues to grow rapidly, the peak-to-valley difference increases, and ...
Examples
Embodiment Construction
[0059] As shown in the figure, the present invention comprises the following steps:
[0060] 1) Use fuzzy C-means clustering (FCM) to determine the extent to which the comprehensive load characteristics of users belong to a certain cluster with the degree of membership, and put n industry users x i (i=1,2,,,n) is divided into c fuzzy classes, and the cluster center of each class is calculated to minimize the weighted error square sum function within the class; FCM uses fuzzy division, so that each given data Points use the degree of membership between (0, 1) to determine the degree to which they belong to each group; adapting to the introduction of fuzzy division, the membership matrix U allows elements with values between 0 and 1; normalization stipulates that a The sum of the degrees of membership of a dataset is equal to 1:
[0061] J ( U , c 1 , ...