Quality Assessment Of Power Grid Statistical Data Based On Cloud Model

With the rapid development of power industry, power grid statistical data plays a guiding role in the production, management and decision analysis of electric power company. But at the same time, the natural disasters, equipment failure, power cuts and other natural factors or human factors, and the vulnerability of power grid statistical data, both of them may affect the quality of statistical data in varying degrees and further disturb the characteristic analysis and prediction analysis of statistical indicators. What is more serious is that it may affect the com-pany’s management and decision analysis and cause the business error. Therefore, in order to respond to the strategic goals of "three sets of five" and "one strong three excellent", which were proposed by State Grid, and quickly improve statistical data’s supervision in corporate decision-making and management and coordinate to promote the sustainable development of company and society, it is urgent to construct a quality assessment model of power grid statis-tical data based on the new situation and new ideas.Aiming at the quality assessment problem of power grid statistical data, such as index system is not perfect, the evaluation results is not accurate classified, based on the deep research on how to construct the evaluation index system and ensure the accuracy of the evaluation results, this paper makes research on the quality assessment model of statistical data. The main research work of this paper are as follows:Firstly, based on the operation characteristics of power system and the basic characteris-tics of grid data, this paper puts forward a set of quality evaluation index system of power grid statistical data, and it makes an intensive study of assessment methods of each index, the calculation method of evaluation result and each index’s weight. Experiments show that the evaluation method of each index is feasible and practical in assessing the quality of power grid statistical data.Secondly, a quality assessment model of statistical data based on cloud model is proposed. In order to ensure the accuracy of the evaluation results and ascertain which evaluation grade the statistical data belongs to, this model turns the comments and the evaluation result into cloud model. Firstly, in order to obtain a plurality of trust grade cloud, soft classification is used to define the comment. Secondly, turn the evaluation result of each index into cloud model by backward cloud generator, and then construct a comprehensive trust evaluation cloud on this basis. Lastly, similarity algorithm is used to compute the similarity between the comprehensive trust evaluation cloud and each trust grade cloud, and then ascertain which evaluation grade the statistical data belongs to.Lastly, actual example is used to verify the feasibility and validity of this method. The results show that the method has stronger practicability in the quality assessment of power grid statistical data. And by using cloud model and law of large numbers, it can efficiently avoid the limitation of subjectivity when traditional method is used to make qualitative evalu-ating, and it also can ensure the accuracy and objectivity of the evaluation results in the greatest degree.