Research On Investment Forecast Of Power Grid Technology Reform Based On Parameter Optimization Grey Model

With the rapid development of the economy,the scale of the existing power grid is difficult to meet the electricity demand of the whole society.The scale of power grid construction will increase,but at the same time it faces the problems of outdated grid equipment and line damage.Therefore,the technical transformation of the power grid is reasonable.To ensure the reliable operation of the grid system is critical to the sustainable development of the grid enterprise.However,in the investment decision-making of power grid technology reform,the professional technicians of power grid companies mainly rely on past historical experience to select several indicators related to the theoretical investment in power grid technology reform,and obtain the predicted value of technological innovation investment through simple regression analysis.Such a decisionmaking method is difficult to meet the actual needs.Therefore,an in-depth analysis of the main influencing factors of investment capacity and the adoption of an accurate and reasonable investment forecasting model are the key to the current grid investment forecast.Thus,the main research work of this paper is as follows:Aiming at the selection of correlation degree algorithm for the existing technical upgrading investment index of power grid,which adopts the method of piecewise calculation to find the average,sometimes results in conclusions contrary to the practical significance and can not reflect the negative correlation characteristics,a new Angle slope correlation degree is improved in this paper.In this paper,the improved Angle slope correlation degree takes the existing gray slope correlation degree as the basic model,synthesizes the idea of cosine distance,and optimizes the correlation degree algorithm from the overall level.Finally,through the comparison of the traditional slope correlation degree,the grid technology investment forecasting experiment is used for comparison experiments.The index extracted by the improved algorithm is used for investment forecasting.The prediction error is 3.16% smaller than the index extracted by the traditional slope correlation degree.The superior performance of the improved angle slope correlation algorithm.In view of the shortcomings of existing gray GM(1,N)in model parameter selection,an improved algorithm is more suitable for the investment prediction of power grid technological transformation.Commonly used investment prediction algorithm is analyzed,and the combination with the characteristics of power grid data sample quantity less choose to use the gray GM(1,N)model as an investment to measure the basic prediction model,aiming at the defect of gray model,optimize the model parameters,and consider the grid data has certain volatility,and markov models can to a certain extent,to improve data volatility,the markov model and grey model of organic combination of parameters optimization.Compared with the traditional grey GM(1,N)prediction model,the prediction accuracy of the proposed method is improved by 5.21%,with obvious improvement.And the multiple linear regression prediction method is compared with the method described in this paper.The prediction error of the prediction model described in this paper is only 43.67% of that of the regression prediction method,which is far better than the multiple regression prediction,thus confirming the applicability of the parameter optimization grey model used in this paper.