OD-matrix Estimation Model And Algorithm Based On Immune Genetic Algorithm

Nowadays, during the science and the technology progressing, the rapid development of urban population, traffic problem has become one of the most vexing social problems. Growing in a traffic jam, traffic accidents around the world all losses of the city. In order to solve these problems existing in traffic, we must prepare the urban road traffic planning, strengthen urban traffic regulation. The situation analysis of road traffic OD matrix is the important prerequisite of this.OD matrix can reflect the user to traffic network basic needs, and to direct the flow of network reflected in the spatial distribution of state, it is also on the urban road traffic planning and management, and the important basis for road network traffic flow prediction. The original way to obtain road traffic OD matrix is through investigation, although this trip method with high precision, but takes a lot of human, material and financial resources, especially for developing countries and the city, spend so great cost but the life cycle of the data is short, it is lack of efficiency. Then academic put it forward through road traffic flow. In the unstructured methods of OD-matrix estimation,almost every models take once observed sample of traffic flow as the true value to project OD-matrix,resulting in the deviation of the projection results. In this paper, the introduction of the true value of traffic flow parameters anmend the model based on the entropy maximization model. Meanwhile, this paper presents an OD-matrix estimation model based on Immune Genetic Algorithm, using the well global search capability of the Immune Genetic Algorithm.Examples show that the immune genetic algorithm can efficiently search out the optimal OD-matrix during estimating OD-matrices.This paper,In Chapter 1, OD matrix's prediction research background and the domestic and foreign research progress are introduced. In Chapter 2, introduces some popular OD matrix prediction research methods, emphatically introduces the Growth model, the gravity model, the Opportunity model, and the minimum information model. The third chapter describes the theoretical basis and the research methods of OD matrix, and compares the maximum likelihood method, the minimum worse method and the entropy maximization model. In Chapter 4, we describe the genetic algorithm and the immune genetic algorithm, and introduce the immune genetic algorithm into entropy maximization model and fix the model. In Chapter 5, OD matrix model is applied to the actual cases, we compare the entropy maximization models that fixed before and after, and also compare the fixed entropy maximization models that using the genetic algorithm and the immune genetic algorithm.