Electric vehicle charging stations emplacement using genetic algorithms and agent-based simulation

A data-driven approach of layout evaluation for electric vehicle charging infrastructure using agent-based simulation and GIS

“…However, the ABS model can capture the behaviors of agents in an environment through the use of decision rules, which govern the interactions between agents in the simulation. The commonly used ABS platforms and frameworks are SimFleet, 9,42 MATSim, 14,43 EnerPol, 24 Repast Symphony, [44][45][46][47] and AnyLogic. 7 Jordan et al 9 proposed a simulation-optimization approach for layout designs of ET CS.…”

“…12 The EV types studied in the literature include electric buses, 13 taxies, 7 private cars, 14 and trucks, 15 while most research focuses on the planning of public fast CSs in urban environments. From the perspective of operation research, the EVCI location problem can be regarded as selecting the appropriate points in the candidate set to optimize certain objectives, which usually include one or more of the following goals: (a) reducing the overall cost (e.g., constructure cost, operation cost, electricity cost, and environmental cost), 2,16 (b) increasing EV user satisfaction (service range and distance, search time, and queuing time), 4,6,9 (c) improving EVCI utilization, 17,18 and (d) optimizing power grid performance (e.g., peak-load shifting and reduction in power losses). 19,20 With the rapid development of mobile Internet, Internet of Things and Intelligent Transportation Systems, EV trajectory, traffic, and geographic information system (GIS) data have been increasingly used in the application of mathematical optimization methodologies to EVCI location problems.…”

“…23 The effectiveness of these approaches should be verified in environments close to reality (e.g., through simulation in large-scale vehicle movement scenarios). 9 Under such motivation, several agent-based simulation (ABS) models have been developed to evaluate and optimize the EVCI layout. 9,[24][25][26] In these ABS models, potential EV purchasers, existing EV users, passengers, and fleet managers are modeled as different types of agents with a certain level of intelligence.…”

Multiobjective Optimization of Chemically Assisted Magnetic Abrasive Finishing (MAF) on Inconel 625 Tubes Using Genetic Algorithm: Modeling and Microstructural Analysis

“…In present study, a total of five input parameters and three output parameters were considered for the design of the experiment. Previous studies have proved that soft computing techniques provide more reliable optimum results in the case of multiobjective optimization [ 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 ]. GA is an inbuilt tool in MATLAB, which make it friendlier for users.…”

“…As per the SCOPUS database, more than sixty-four thousand articles have been published to date. Researchers have successfully implemented GA in various disciplines, such as machining [ 35 ], drug repurposing [ 36 ], automobiles [ 37 ], earth work activities [ 38 ], transportation [ 39 ], antenna [ 40 ], energy planning [ 41 ], electric vehicle [ 42 ], structural design [ 43 ], etc. Figure 8 represents the genetic algorithm flow chart.…”