Multi-step prediction method of parking based on optimized wavelet neural network

Abstract

The invention discloses a multi-step prediction method of parking based on an optimized wavelet neural network. The method comprises a step of processing actually measured effective parking data intoan effective parking time series with a time interval of 5 minutes, and performing multiple-scale decomposition and reconstruction by using a wavelet function 'db32' to, and taking the function as a hidden layer function of the wavelet neural network, a step of adjusting a weight by using a particle swarm algorithm and carrying out gradual iterative update to obtain an optimal value, and a step ofreducing a prediction time of EPWNN by using an ELM algorithm and obtaining a prediction result according to a multi-step prediction strategy. Compared with genetic algorithm optimization neural network, genetic algorithm optimization wavelet neural network, extreme learning machine optimization wavelet transform, extreme learning machine optimization wavelet neural network, particle swarm optimization neural network algorithm, particle swarm optimization wavelet neural network and other algorithms, the prediction error of an EPWNN algorithm is reduced by 89.17%, and the time needed by prediction is reduced by an average of 50.83%.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a multi-step prediction method for parking spaces based on an optimized wavelet neural network. Background technique [0002] The convenience and speed of the car make it an indispensable part of life, and with the rapid growth of the number of private cars, the originally limited space in the city has become more crowded, and the parking space for each car has gradually become larger. Getting smaller and smaller. The parking problem in the city is becoming more and more serious, and the demand for parking is increasing day by day. The parking problem in the city has seriously hindered the development of the economy. Therefore, the prediction of parking spaces is of great significance to the improvement of traffic problems. [0003] At present, the relevant prediction methods mainly include: BP neural network, fuzzy neural network, gray theory, Markov, wavelet function,...

AI Technical Summary

Problems solved by technology

Support vector machine (Support Vector Machine, SVM) method uses the principle of structural risk minimization, and has good generalization ability in the case of few training samples. Unique advantages, SVM learning problems are convex optimization problems, known effective algorithms can be used to find the global minimum of the objective function, it controls the ability of the model by maximizing the edge of the decision boundary, but the user must provide other parameters, such as using Kernel function types and the introduction of slack variables, etc., are very difficult, so it is difficult to realize the prediction of effective parking spaces [6-7]

Particle swarm optimization does not have the "Crossover" and "Mutation" operations of the genetic algorithm, and does not need to adjust many parameters. Starting from a random solution, iteratively finds the global optimum from the local optimum, which is relatively better than Neural network and genetic algorithm are not easy to fall into the global optimum, but because the quality of the solution is evaluated through repeated iterative updates of the fitness function, the speed is relatively slow [8]

Images