Electric power data sequence array optimization method based on order dependence

Abstract

The invention relates to an electric power data sequence array optimization method based on sequence dependence, which comprises the following steps of 1) operating an algorithm BuildEC on each station Si to obtain a local equivalence class; 2) establishing a global equivalence class on the same attribute of each site by utilizing a DisBuild algorithm, and transmitting different values and occurrence times on each attribute of each site to a central site of the attribute; 3) combining the global equivalence classes on different attributes until no equivalence class is combined at all stations; and 4) after the step 3) is completed, determining a target value at the central station, then sending the target value to each station, and after the stations receive the data, finishing data repair in parallel to finish the data optimization. Compared with the prior art, the method has the advantages of improving the data quality, reducing the modification during the repair process, being beneficial to ensuring the data universality and the like.

Description

technical field [0001] The invention relates to the technical field of power data optimization, in particular to an order-dependent power data sequence array optimization method. Background technique [0002] With the wide application of digital technology in the power industry, in order to ensure the safe, reliable and efficient operation of the system, a large number of management information systems, geographic information systems, power market information systems and real-time information systems for power grid operation have been widely used in the power system. applications, which generate a large amount of data. The increase of these massive data, especially considering that these data describe the properties of the power system itself in various conditions and situations in detail and in depth from all aspects, levels and links, has created a need for the wide application of data mining. conditions of. [0003] Data quality is a multi-dimensional concept, each dime...

AI Technical Summary

Problems solved by technology

[0005] Multiple order dependencies may share their (partial) right-hand properties, in which case there may be multiple orders on the same right-hand property column that need to be satisfied, however these orders may themselves conflict and cannot be satisfied by one One is to deal with these orders, because fixing one order may lead to violating other orders, and easily needs to be modified. A better strategy is to combine these orders into a total order oφ. When oφ is satisfied, all orders oφ1,. .., oφm will also satisfy

Images