Abstract
The artificial intelligence calculation method can effectively solve various nonlinear mapping relationships. The strength of these nonlinear solvers is exploited for the evaluation of power grid investment risk using back propagation (BP) neural network optimized by genetic algorithm. The mathematical model of the problem is constructed by selecting the transfer function of the neural network and defining the fitness function of genetic algorithm. BP neural network has good ability of self-learning, self-adaptation and generalization, which can overcome the drawbacks of traditional evaluation methods relying on experts' experience. For the characteristics of genetic algorithm global optimization, the genetic algorithm is used to optimize the weight and threshold of BP neural network, and BP neural network is trained to obtain the optimal evaluation model. The model fully exploits the local search ability of BP neural network and the global search ability of genetic algorithm. It has obtained good evaluation accuracy for the processing of multi-dimensional influence factor problem. And the model can be adapted to different power grids by changing the training data. However, the method cannot describe the specific relationship between each impact factor and the investment risk of the grid. The case study shows that the method can accurately and effectively evaluate power grid investment risk and improve the fault tolerance of the power grid investment risk evaluation.
Highlights
The power industry is an important part of the national economy which is indispensable in many fields and is closely related to people’s life
Based on the characteristics of multi-dimensional, nonlinear and strong correlation of power grid investment risk, this paper proposes a power grid investment risk evaluation model based on GA-back propagation (BP) neural network
The analysis of the results shows that there are several serious errors in the results of the power grid investment risk evaluation model based on BP neural network
Summary
The power industry is an important part of the national economy which is indispensable in many fields and is closely related to people’s life. B. INNOVATION CONTRIBUTION The number of illustrative applications of these solvers based on back propagation (BP) neural networks and genetic algorithms is seen in the literature, such as nonlinear optics problems [14], nonlinear nanofluidic systems of Jeffery-Hamel flow [15], the dynamics of nonlinear singular heat conduction model of the human head [16], nonlinear Painlev’e II systems in applications of random matrix theory [17], hermal analysis of porous fin model [18], Nonlinear Singular Thomas-Fermi Systems [19], credit evaluation for listed companies [20], vibration dynamics of rotating electrical machines [21], environmental quality assessment [22], grid fault diagnosis [23], wind speed soft sensor [24], prediction of postgraduate entrance examination [25], fault section locating in distribution net-work with DG [26], crude oil production prediction [27], prediction of junction temperature for high power LED [28]. As long as the training data has changed, a power grid investment risk evaluation model, which is suitable for each power grid investment risk, can be obtained
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
