Zhen Shen

Agent-based traffic simulation and traffic signal timing optimization with GPU

With the advantage of simulating the details of a transportation system, the “microsimulation” of a traffic system has long been a hot topic in the Intelligent Transportation Systems (ITS) research. The Cellular Automata (CA) and the Multi-Agent System (MAS) modeling are two typical methods for the traffic microsimulation. However, the computing burden for the microsimulation and the optimization based on it is usually very heavy. In recent years the Graphics Processing Units (GPUs) have been applied successfully in many areas for parallel computing. Compared with the traditional CPU cluster, GPU has an obvious advantage of low cost of hardware and electricity consumption. In this paper we build an MAS model for a road network of four signalized intersections and we use a Genetic Algorithm (GA) to optimize the traffic signal timing with the objective of maximizing the number of the vehicles leaving the network in a given period of time. Both the simulation and the optimization are accelerated by GPU and a speedup by a factor of 195 is obtained. In the future we will extend the work to large scale road networks.

A GPU-Based Parallel Genetic Algorithm for Generating Daily Activity Plans

As computing technologies develop, there is a trend in traffic simulation research in which the focus is moving from macro- and meso-simulation to micro-simulation since microsimulation can provide more detailed quantitative results. Moreover, the success of the Artificial societies-Computational experiments-Parallel execution (ACP) approach indicates that integrating other metropolitan systems such as logistic, infrastructure, legal and regulatory, and weather and environmental systems to build an Artificial Transportation System (ATS) can be helpful in solving Intelligent Transportation Systems (ITS) problems. However, the computational burden is very heavy as there are many agents interacting in parallel in the ATS. Therefore, a parallel computing tool is desirable. We think that we can employ a Graphics Processing Unit (GPU), which has been applied in many areas. In this paper, we use a GPU-adapted Parallel Genetic Algorithm (PGA) to solve the problem of generating daily activity plans for individual and household agents in the ATS, which is important as the activity plans determine the traffic demand in the ATS. Previous research has shown that GA is effective but that the computational burden is heavy. We extend the work to GPU and test our method on an NVIDIA Tesla C2050 GPU for two scenarios of generating plans for 1000 individual agents and 1000 three-person household agents. Speedup factors of 23 and 32 are obtained compared with implementations on a mainstream CPU.

Artificial Societies and GPU-Based Cloud Computing for Intelligent Transportation Management

The article focuses on the C part of the ACP approach. The ACP approach comprises of artificial societies, computational experiments, and parallel execution of real and artificial systems. It explains the advantages of cloud computing and GPUs and presents the architectures of GPU-based cloud computing for transportation systems.

A GPU based trafficparallel simulation module of artificial transportation systems

Traffic micro-simulation is an important tool in the Intelligent Transportation Systems (ITS) research. In the microsimulation, a bottom up system can be built up by the interactions of vehicle agents, road agents, traffic lights agents, etc. The Artificial societies, Computational experiments, and Parallel execution (ACP) approach suggests integrating other metropolitan systems such as logistic, infrastructure, legal and regulatory, weather and environmental systems to build an Artificial Transportation System (ATS) to help solve ITS problems. This is reasonable as the transportation system is complex that is affected by many systems interacting with each other. However, there is a challenge that the computing burden can be very heavy as there can be many agents of different kinds interacting in parallel in ATS. In recent years, the Graphics Processing Units (GPUs) have been applied successfully in many areas for parallel computing. Compared with the traditional CPU cluster, GPU has an obvious advantage of low cost of hardware and electricity consumption. In this paper, we build a parallel traffic simulation module of ATS with GPU. The simulation results are reasonable and a maximum speedup factor of 105 is obtained compared with the CPU implementations.

A weighted pattern recognition algorithm for short-term traffic flow forecasting

Hysteretic optimization (HO) is a recently proposed heuristic physical optimization algorithm based on the well-known demagnetization process of magnetic materials in magnetism. The Capacitated Vehicle Routing Problem (CVRP) is an important variant of the vehicle routing problem which is one of the most important and intensively studied combinatorial optimization problems. In this study, we apply HO to the Capacitated Vehicle Routing Problem (CVRP), by generalizing the external field and endowing the configuration space with a proper distance. The experimental results with benchmark problems show the proposed method is competitive with other popular algorithms, such as particle swarm optimization, genetic algorithms.The k-nearest neighbor (k-NN) nonparametric regression is a classic model for single point short-term traffic flow forecasting. The traffic flows of the same clock time of the days are viewed as neighbors to each other, and the neighbors with the most similar values are regarded as nearest neighbors and are used for the prediction. In this method, only the information of the neighbors is considered. However, it is observed that the “trends” in the traffic flows are useful for the prediction. Taking a sequence of consecutive time periods and viewing the a sequence of “increasing”, “equal” or “decreasing” of the traffic flows of two consecutive periods as a pattern, it is observed that the patterns can be used for prediction, despite the patterns are not from the same clock time period of the days. Based on this observation, a pattern recognition algorithm is proposed. Moreover, empirically, we find that the patterns from different clock time of the days can have different contributions to the prediction. For example, if both to predict the traffic flow in the morning, the pattern from the morning can lead to better prediction than same patterns from afternoon or evening. In one sentence, we argue that both the pattern and the clock time of the pattern contain useful information for the prediction and we propose the weighted pattern recognition algorithm (WPRA). We give different weights to the same patterns of different clock time for the prediction. In this way, we take both virtues of the k-NN method and the PRA method. We use the root mean square error (RMSE) between the actual traffic flows and the predicted traffic flows as the measurement. By applying the results to actual data and the simulated data, about 20% improvement compare with the PRA is obtained.

Ordinal Optimization and Quantification of Heuristic Designs

This paper focuses on the performance evaluation of complex man-made systems, such as assembly lines, electric power grid, traffic systems, and various paper processing bureaucracies, etc. For such problems, applying the traditional optimization tool of mathematical programming and gradient descent procedures of continuous variables optimization are often inappropriate or infeasible, as the design variables are usually discrete and the accurate evaluation of the system performance via a simulation model can take too much calculation. General search type and heuristic methods are the only two methods to tackle the problems. However, the “goodness” of heuristic methods is generally difficult to quantify while search methods often involve extensive evaluation of systems at many design choices in a large search space using a simulation model resulting in an infeasible computation burden. The purpose of this paper is to address these difficulties simultaneously by extending the recently developed methodology of Ordinal Optimization (OO). Uniform samples are taken out from the whole search space and evaluated with a crude but computationally easy model when applying OO. And, we argue, after ordering via the crude performance estimates, that the lined-up uniform samples can be seen as an approximate ruler. By comparing the heuristic design with such a ruler, we can quantify the heuristic design, just as we measure the length of an object with a ruler. In a previous paper we showed how to quantify a heuristic design for a special case but we did not have the OO ruler idea at that time. In this paper we propose the OO ruler idea and extend the quantifying method to the general case and the multiple independent results case. Experimental results of applying the ruler are also given to illustrate the utility of this approach.

Quantifying Heuristics in the Ordinal Optimization Framework

Finding the optimal design for a discrete event dynamic system (DEDS) is in general difficult due to the large search space and the simulation-based performance evaluation. Various heuristics have been developed to find good designs. An important question is how to quantify the goodness of the heuristic designs. Inspired by the Ordinal Optimization, which has become an important tool for optimizing DEDS, we provide a method which can quantify the goodness of the design. By comparing with a set of designs that are uniformly sampled, we measure the ordinal performances of heuristic designs, i.e., we quantify the ranks of all (or some of) the heuristic designs among all the designs in the entire search space. The mathematical tool we use is the Hypothesis Testing, and the probability of making Type II error in the quantification is controlled to be under a very low level. The method can be used both when the performances of the designs can be accurately evaluated and when such performances are estimated by a crude but computationally easy model. The method can quantify both heuristics that output a single design and that output a set of designs. The method is demonstrated through numerical examples.

A fuzzy model on how the management affects a worker's state

A workers energy level, mood, skill level can affect her/his working performance. These factors can be regarded as the “state” of the worker and they affect the production. Also, these factors are affected by the management. In this way, the management affects the production. One important task of managing a factory is keeping the production in a high level and in a safe condition via improving the management. However, in the literature usually this is done in an exogenous way, that is, a survey is given and based on the survey result the management is improved. This paper provides a first step for “optimizing” the management in an endogenous and analytical way. We propose a framework based on which we can analyze how the management affects the state of the worker and then affects the production. The basic idea is that we regard the management as a control policy to control the state of a worker to make the worker-position fitness as good as possible. We admit that it is difficult to evaluate how the management affects the workers state as this problem is closely related to the uncertainty rooted in the human-being. To attack this difficulty, we introduce the fuzzy method to model how the management affects a workers state. By the method in this paper, reasonable results can be obtained, based on which the management can be improved. In the future, it may be possible to collect real data to improve the method in this paper.

Two intersections traffic signal control method based on ADHDP

With the rapid development of Chinese economy and automotive industry, urban traffic congestion has become increasingly serious. Therefore, how to effectively alleviate the traffic congestion and improve the efficiency of vehicles has become the main concern. Traffic signal control is one of the effective ways to solve urban traffic congestion. In this paper, a traffic signal control method based on Action-Dependent Heuristic Dynamic Programming (ADHDP) is investigated. The control algorithm is simulated on two intersections, both of which have two phases with four entrance approaches. The computer simulation results show that the control method has the better ability of on-line learning compared with traditional Fix-Time Control, and can effectively improve the average speed of vehicles, and reduce travel time and alleviate the traffic pressure.

Application of vector ordinal optimization to the transportation systems with agent based modelling

As the computing technology develops, micro-simulation becomes more and more important in the Intelligent Transportation Systems (ITS) research, because it can provide detailed descriptions of the system. However, for a multi-agent systems (MAS) modelling of an ITS, the computation burden is large, as it involves the computation of the state changing of all the agents. Further, if we consider simulation based optimization, which can be simply understood as an intelligent way of running a number of micro-simulations, the computation burden is huge. Moreover, there are multiple objective optimization problems in the ITS. The Vector Ordinal Optimization (VOO) method is a powerful tool for multi-objective optimization. In this paper, we apply VOO to the problem of optimizing the stop times and delay time of an ITS. We test the method on a 4 intersection lattice road network, and on the 18 intersection road network of the Zhongguancun area of Beijing. Compared with the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) method, the VOO method can achieve a speedup of factor of more than 150, with only a little sacrifice of performance.