Power load prediction method of GWO optimized Elman based on DNA hairpin variation

Abstract

The invention discloses a power load prediction method for optimizing Elman through GWO based on DNA hairpin variation, an Elman power load prediction model is constructed, parameters of the Elman power load prediction model are optimized by using an improved grey wolf algorithm, and the improved grey wolf algorithm is that DNA hairpin variation is adopted to act on the grey wolf algorithm. The original grey wolf algorithm is improved, molecular biology and a GWO optimization algorithm are combined, a designed mutation operator enables the algorithm to have the capability of jumping out of local optimum, and the convergence speed and the convergence precision are improved; and compared with a static network, the Elman neural network has a relatively strong dynamic mapping characteristic through an internal feedback mechanism, so that the Elman neural network has a relatively strong capability of adapting to a time-varying characteristic, and the power load prediction speed is improved while the prediction precision is met.

Description

technical field [0001] The invention belongs to the field of intelligent optimization technology improvement, and in particular relates to a GWO optimization Elman's power load prediction method based on DNA hairpin variation. Background technique [0002] The power system is mainly composed of the power grid and power users. Its task is to provide users with standard and reliable power to meet various load needs and provide power for people's lives and social production. The demand for electricity of various users changes dynamically, and the particularity of electric energy makes it difficult to store it in large quantities, which requires the production of electricity and the system load to maintain a dynamic balance, so as to meet the needs of users and make the system run stably and efficiently. . Therefore, it is necessary to develop power load system forecasting technology, which is the basis for power distribution and dispatching, and is also an important basis for ...

AI Technical Summary

Problems solved by technology

From the optimization of complex problems to the late stage of optimization, the pack of wolves gradually tends to the location or surroundings of the head wolf, and it is very easy to fall into a local optimum, which makes the algorithm unable to jump out of the local extremum to obtain the global optimal solution

[0007] Genetic algorithm is an earlier intelligent optimization algorithm, which has a strong global search ability, but the algorithm is prone to fall into local optimum and premature

Images