Central Economics and Mathematics Institute of Russian Academy of Sciences, National Research University Higher School of Economics, Moscow 101000, Russian
Prof. Dr. Andranik S. Akopov
Central Economics and Mathematics Institute of Russian Academy of Sciences, National Research University Higher School of Economics, Moscow 101000, Russian
There are many reasons for traffic congestions such as the "stop-and-go wave effect", periodic increase in intensity of vehicle and pedestrian traffic ("rush hours"), frequent maneuvering, uncontrolled pedestrians’ movement on road crossings and other factors. This paper considers the problem of biobjective optimization and rebalancing of vehicles’ and pedestrians’ flows with the use of Manhattan road networks (MRNs) with smart traffic lights (STLs) as the case study of intelligent transportation system (ITS). For this purpose, we have studied the possibilities of applying STLs to control of traffic in large-scale road networks providing a speed harmonization and traffic prioritization between vehicles and pedestrians. The considered multiagent system (MAS) includes agent vehicles, agent pedestrians and agent lights that interact with each other according with given rules (e.g., V2V, V2P, V2I). Such STLs use information on the traffic structure and its density to switch signals at each moment in time. In the non-stationary mode with a periodic traffic intensity to provide the analysis of traffic flows done by STLs it has been suggested to use the fuzzy clustering algorithm aggregated with the density-based spatial clustering algorithm (FCA-DBSCAN). At the uniform motion fixed durations of phases set up for STLs that computed individually with use of the suggested parallel hybrid biobjective real-coded genetic algorithm (BORCGA-BOPSO). The approach allows to improve significantly the time-efficiency of seeking optimal individualised STLs’ characteristics while keeping up their quality. Moreover, the ITS based on STLs with parameters optimized with the BORCGA-BOPSO provides significant traffic improvement in MRNs in contrast to the case of uncontrolled pedestrian crossings and using usual (i.e., non-smart) traffic lights.
6 October 2021 in IEEE Transactions on Intelligent Transportation Systems
Over the past two decades, several simulation-based approaches have been developed to seek optimal solutions in complex multiagent systems (MASs). One example of these complex systems is the proposed multiagent fuzzy transportation system (FTS), in which agents, such as manned ground vehicles (MGVs) and unmanned ground vehicles (UGVs), use fuzzy logic for maneuvering while interacting with each other. The complexity of an FTS as an optimization problem is caused by two major factors, viz., inability to apply gradient-based optimization methods and uncertainty present in the FTS model. In these MASs, the objective functions are computed as an outcome of multiple agent-to-agent interactions. For the proposed FTS, two interconnected objectives are of prime importance while modeling the system: the number of potential traffic accidents, which should be minimized, and the output traffic that needs to be maximized. The resulting model is a simulation-based biobjective optimization problem. In an attempt to improve the maneuverability at various road network configurations (RNCs), in this work, a new parallel real-coded genetic algorithm based on fuzzy clustering (FCGA) is proposed that considers the specific requirements of the FTS model. Use of the FCGA aggregated with the FTS overcomes the difficulties associated with the optimization model and the limitations caused by simulation-based optimization (the large dimensionality of decision space, uncertainty present in the MAS environment, etc.). After showing superior performance in approximating the Pareto-optimal solutions for known test instances, the proposed FCGA is applied to the proposed multiagent FTS to approximate the optimal parameters. Because of the optimization of FTS parameters with the FCGA and the use of the proposed fuzzy clustering algorithm (FCA) for the traffic density estimate, the suggested approach substantially improves the maneuverability of UGVs and MGVs to change lanes while considering turning based on fuzzy rules and overtaking.
Modern requirements for urban traffic management and control call for the design of High-Capacity Reconfigurable Multilayer Road Networks (RMRNs). This paper discusses the proposed evolutionary synthesis approach, a promising method for finding the best configurations of RMRNs, aiming to create road networks with optimized layouts that maximize vehicle outflow. As the complexity of RMRNs increases, due to the addition of overpasses and tunnels, the expenses for building these road networks also rise significantly. Therefore, it is essential to find a balance when choosing the optimal topological solution for an RMRN. These solutions need to maximize traffic flow while minimizing the complexity of the RMRN. To achieve this goal, a new multiagent hybrid clustering-assisted genetic algorithm (MA-HCAGA). The proposed algorithm combines the use of binary-coded crossovers and mutations as genetic operators, and Biobjective Discrete Particle Swarm Optimization (BODPSO) techniques to improve the evolutionary search process. In addition, the algorithm combines the use of finite-state machines (FSMs) to control the transitions between the states of agent-processes and the fuzzy clustering technique (FCA) to estimate the swarm and select clusters for interaction among the groups of agent-processes and particle swarms. The superior performance of the MA-HCAGA algorithm in evolutionary synthesis of RMRNs has been demonstrated through comparisons with other well-known multiobjective optimization methods. MA-HCAGA has been successfully applied in the evolutionary synthesis of RMRNs, allowing a decision maker to select the optimal RMRN topologies along the approximate Pareto front by selecting specific solutions. A traffic flow simulation model, aggregated with the MA-HCAGA algorithm, has been developed to simulate vehicle flow at various configurations of RMRNs. The results of this study show the effectiveness of the proposed method for configuring RMRNs in order to optimize vehicle outflow and reduce the complexity of RMRNs.
The article discusses the development and study of a new matrix-based hybrid genetic algorithm (MBHGA) for solving an agent-based model of firms’ behavior with controlled trade interactions. The proposed model employs symmetric strategies optimized using the MBHGA algorithm. This algorithm combines evolutionary search with real-coded crossover and matrix binary-coded crossover as genetic operators, creating a hybrid approach. The aim of the designed system is to assist decision-makers in selecting optimal strategies for their firms in situations where some companies impose restrictions on interactions. As demonstrated by the results of optimization experiments, the MBHGA algorithm significantly outperformed other methods, such as RCGA, PSO, GWO, SPEA2, and NSGA-II, in terms of both accuracy (measured by deviations from reference values) and the quality of the Pareto front approximation (measured by LHV, IGD, and CPF) when solving an agent-based model of firms’ behavior. As demonstrated in this study, the performance of MBHGA significantly depends on the size of the model (i.e., the number of agents), and it can be enhanced by parallelizing the evolutionary search process, including matrix crossover operations for decision variables. Optimization experiments using a genetic algorithm were conducted to maximize utility functions for agent companies under trade restrictions. The results showed that trade restrictions have a negative impact on the utility function values in both single- and multi-objective optimization, for selected countries and for all countries’ firms. However, an optimization-based approach using the MBHGA algorithm can help minimize the negative consequences of trade restrictions by providing the ability to find nondominated solutions and the best possible trade-offs.