基于灰色遗传支持向量机的短时交通流预测

Short-Term Traffic Flow Prediction Based on Grey Genetic Support Vector Machine

为了进一步提高短时交通流预测的精确度,通过分析灰色模型、遗传算法和支持向量机模型的特点,提出一种组合的短时交通流预测模型.模型运用灰色模型对原始交通流数据序列进行累加,弱化其随机性,再通过遗传优化支持向量机模型进行预测,利用灰色模型将预测结果进行累减,得到最终的预测值表.以长春市某主干路交通流数据为基础,验证了该模型的有效性和可行性.

In order to further improve the accuracy of the short-term traffic flow prediction,a combination of short-term traffic flow prediction models has been proposed by analyzing the characteristics of grey model,genetic algorithm and support vector machine（SVM）model.First,the paper uses the grey model to accumulate the original traffic flow data and weaken the randomness of the traffic flow data sequence,then forecast through support vector machine（SVM）model based on genetic algorithm.Finally,using the regressive features of grey model to reduction of the forecast results,the final predicted value table is gotten.The model was verified based on the traffic flow data of the major road in Changchun and the experimental result shows that the proposed model is effective and feasible.