Electric buses (EBs) have attracted more and more attention in recent years because of their energy-saving and pollution-free characteristics. However, very few studies have considered the impact of stochastic traffic conditions on their operations. This paper focuses on the departure interval optimisation of EBs which is a critical problem in the operations. We consider the stochastic traffic conditions in the operations and establish a departure interval optimisation model. The objective function aims at minimising passenger travel costs and enterprise operation costs, including waiting time costs, congestion costs, energy consumption costs and operational fixed costs. To solve this problem, a genetic algorithm (GA) based on fitness adjustment crossover and mutation rate is proposed. Based on the Harbin bus dataset, we find that improved GA performance is 4.481% higher, and it can solve the models more accurately and efficiently. Compared with the current situation, the optimisation model reduces passenger travel costs by 20.2% and helps improve passenger travel quality. Under stochastic traffic conditions, total cost change is small, but passenger travel costs increase significantly. This indicates the high impact degree of random traffic conditions on passenger travel. In addition, a sensitivity analysis is conducted to provide suggestions for improving the EBs operation and management.
{"title":"Optimising Electric Bus Departure Interval Considering Stochastic Traffic Conditions","authors":"Zhenyang Qiu, Xiaowei Hu, Shuai Song, Yu Wang","doi":"10.7307/ptt.v35i5.219","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.219","url":null,"abstract":"Electric buses (EBs) have attracted more and more attention in recent years because of their energy-saving and pollution-free characteristics. However, very few studies have considered the impact of stochastic traffic conditions on their operations. This paper focuses on the departure interval optimisation of EBs which is a critical problem in the operations. We consider the stochastic traffic conditions in the operations and establish a departure interval optimisation model. The objective function aims at minimising passenger travel costs and enterprise operation costs, including waiting time costs, congestion costs, energy consumption costs and operational fixed costs. To solve this problem, a genetic algorithm (GA) based on fitness adjustment crossover and mutation rate is proposed. Based on the Harbin bus dataset, we find that improved GA performance is 4.481% higher, and it can solve the models more accurately and efficiently. Compared with the current situation, the optimisation model reduces passenger travel costs by 20.2% and helps improve passenger travel quality. Under stochastic traffic conditions, total cost change is small, but passenger travel costs increase significantly. This indicates the high impact degree of random traffic conditions on passenger travel. In addition, a sensitivity analysis is conducted to provide suggestions for improving the EBs operation and management.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136102521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A macroscopic fundamental diagram (MFD) is an important basis for road network research. It describes the functional relationship between the average flow and average density of the road network. We proposed an MFD estimation method based on the traffic flow condition. Firstly, according to statistical theories, the road network data are divided into three traffic flow conditions (free flow, chaotic and congested) bounded by a 95% confidence interval of the maximum traffic capacity of each intersection in the road network. Then, in each condition, we combined principal component analysis and the Jolliffe B4 method to reduce dimension for extracting critical intersections. Finally, the full-scale dataset of the road network was reconstructed to estimate the road network MFD. Through numerical simulation and empirical research, it is found that the root mean square error and absolute percentage error between estimated MFD and true MFD considering the traffic flow condition are smaller than those without considering the traffic flow condition. The MFD estimation and the division of the traffic states of the road network were completed at the same time. The proposed method effectively saves the time cost of road network research and is highly accurate.
{"title":"Macroscopic Fundamental Diagram Estimation Considering Traffic Flow Condition of Road Network","authors":"Xiaoli Deng, Yao Hu","doi":"10.7307/ptt.v35i5.107","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.107","url":null,"abstract":"A macroscopic fundamental diagram (MFD) is an important basis for road network research. It describes the functional relationship between the average flow and average density of the road network. We proposed an MFD estimation method based on the traffic flow condition. Firstly, according to statistical theories, the road network data are divided into three traffic flow conditions (free flow, chaotic and congested) bounded by a 95% confidence interval of the maximum traffic capacity of each intersection in the road network. Then, in each condition, we combined principal component analysis and the Jolliffe B4 method to reduce dimension for extracting critical intersections. Finally, the full-scale dataset of the road network was reconstructed to estimate the road network MFD. Through numerical simulation and empirical research, it is found that the root mean square error and absolute percentage error between estimated MFD and true MFD considering the traffic flow condition are smaller than those without considering the traffic flow condition. The MFD estimation and the division of the traffic states of the road network were completed at the same time. The proposed method effectively saves the time cost of road network research and is highly accurate.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136022494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the future, mixed traffic flow will consist of human-driven vehicles (HDVs) and connected autonomous vehicles (CAVs). Effective traffic management is a global challenge, especially in urban areas with many intersections. Much research has focused on solving this problem to increase intersection network performance. Reinforcement learning (RL) is a new approach to optimising traffic signal lights that overcomes the disadvantages of traditional methods. In this paper, we propose an integrated approach that combines the multi-agent advantage actor-critic (MA-A2C) and smart navigation (SN) to solve the congestion problem in a road network under mixed traffic conditions. The A2C algorithm combines the advantages of value-based and policy-based methods to stabilise the training by reducing the variance. It also overcomes the limitations of centralised and independent MARL. In addition, the SN technique reroutes traffic load to alternate paths to avoid congestion at intersections. To evaluate the robustness of our approach, we compare our model against independent-A2C (I-A2C) and max pressure (MP). These results show that our proposed approach performs more efficiently than others regarding average waiting time, speed and queue length. In addition, the simulation results also suggest that the model is effective as the CAV penetration rate is greater than 20%.
{"title":"Improving Traffic Efficiency in a Road Network by Adopting Decentralised Multi-Agent Reinforcement Learning and Smart Navigation","authors":"Hung Tuan Trinh, Sang-Hoon Bae, Quang Duy Tran","doi":"10.7307/ptt.v35i5.246","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.246","url":null,"abstract":"In the future, mixed traffic flow will consist of human-driven vehicles (HDVs) and connected autonomous vehicles (CAVs). Effective traffic management is a global challenge, especially in urban areas with many intersections. Much research has focused on solving this problem to increase intersection network performance. Reinforcement learning (RL) is a new approach to optimising traffic signal lights that overcomes the disadvantages of traditional methods. In this paper, we propose an integrated approach that combines the multi-agent advantage actor-critic (MA-A2C) and smart navigation (SN) to solve the congestion problem in a road network under mixed traffic conditions. The A2C algorithm combines the advantages of value-based and policy-based methods to stabilise the training by reducing the variance. It also overcomes the limitations of centralised and independent MARL. In addition, the SN technique reroutes traffic load to alternate paths to avoid congestion at intersections. To evaluate the robustness of our approach, we compare our model against independent-A2C (I-A2C) and max pressure (MP). These results show that our proposed approach performs more efficiently than others regarding average waiting time, speed and queue length. In addition, the simulation results also suggest that the model is effective as the CAV penetration rate is greater than 20%.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136105705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mladenka Blagojević, Dragana Šarac, Katarina Mostarac
Postal service providers can reorganize the last-mile delivery process within the scope of universal service and apply some of the flexible models for the organization of the delivery process. In this paper, the question of the selection of Flexible Last-Mile Delivery Models (FLMDM) is treated using multicriteria decision-making. We have identified four different sustainable models of last-mile delivery with an emphasis on the number of delivery workers. One postal service provider from Europe was selected, where proposed FLMDM are tested. The proposed last-mile delivery models are ranked using Multiple Criteria Decision Analysis (MCDA) technique. In this context, MCDA techniques are used to make a comparative assessment of alternatives. This paper aims to find the optimal delivery costs in each variant of the delivery model - an optimal number of workers for the last-mile delivery. The obtained results suggest the AB delivery model as the optimal choice for the last-mile delivery. Also, results ensure the complete allocation of the required number of technological workers in the delivery (the number of delivery workers), by applying the originally proposed, flexible solution (models) for the organization of last-mile delivery.
{"title":"Selecting the Flexible Last-Mile Delivery Models Using Multicriteria Decision-Making","authors":"Mladenka Blagojević, Dragana Šarac, Katarina Mostarac","doi":"10.7307/ptt.v35i5.292","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.292","url":null,"abstract":"Postal service providers can reorganize the last-mile delivery process within the scope of universal service and apply some of the flexible models for the organization of the delivery process. In this paper, the question of the selection of Flexible Last-Mile Delivery Models (FLMDM) is treated using multicriteria decision-making. We have identified four different sustainable models of last-mile delivery with an emphasis on the number of delivery workers. One postal service provider from Europe was selected, where proposed FLMDM are tested. The proposed last-mile delivery models are ranked using Multiple Criteria Decision Analysis (MCDA) technique. In this context, MCDA techniques are used to make a comparative assessment of alternatives. This paper aims to find the optimal delivery costs in each variant of the delivery model - an optimal number of workers for the last-mile delivery. The obtained results suggest the AB delivery model as the optimal choice for the last-mile delivery. Also, results ensure the complete allocation of the required number of technological workers in the delivery (the number of delivery workers), by applying the originally proposed, flexible solution (models) for the organization of last-mile delivery.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136018833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Urban rail transit plays a very important role in cities’ social and economic development. To ensure the safe and stable operation of urban rail transit operation equipment and facilities, it is necessary to monitor a large number of safety hazard statuses and data and improve the over-centralisation of traditional monitoring. This paper designs a scheme for storing, validating and monitoring the safety hazard status of urban rail transit operation equipment and facilities based on blockchain technology. The safety hazards of equipment and facilities during the operation stage of urban rail transit are listed using the literature analysis method and the case study method. The European RAMS (reliability, availability, maintainability and safety) standard method is used to determine the safety hazard status of equipment and facilities by availability index. Based on the features of the consensus mechanism, smart contract and other features of blockchain technology, this paper designs an overall scheme for storing, verifying and monitoring the safety hazard status of equipment and facilities. This scheme provides a practical operation method for evaluating the safety hazard status of rail transit equipment and facilities, which is conducive to the safety rectification of the entire urban rail transit.
{"title":"Monitoring Scheme for Safety Hazard Status of Urban Rail Transit Operation Equipment and Facilities Based on Blockchain Technology","authors":"Meng Li, Qi Lin","doi":"10.7307/ptt.v35i5.187","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.187","url":null,"abstract":"Urban rail transit plays a very important role in cities’ social and economic development. To ensure the safe and stable operation of urban rail transit operation equipment and facilities, it is necessary to monitor a large number of safety hazard statuses and data and improve the over-centralisation of traditional monitoring. This paper designs a scheme for storing, validating and monitoring the safety hazard status of urban rail transit operation equipment and facilities based on blockchain technology. The safety hazards of equipment and facilities during the operation stage of urban rail transit are listed using the literature analysis method and the case study method. The European RAMS (reliability, availability, maintainability and safety) standard method is used to determine the safety hazard status of equipment and facilities by availability index. Based on the features of the consensus mechanism, smart contract and other features of blockchain technology, this paper designs an overall scheme for storing, verifying and monitoring the safety hazard status of equipment and facilities. This scheme provides a practical operation method for evaluating the safety hazard status of rail transit equipment and facilities, which is conducive to the safety rectification of the entire urban rail transit.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136103016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yi Zhu, Shuyan Chen, Ying Wu, Fengxiang Qiao, Yongfeng Ma
The shared parking mode represents a feasible solution to the persistent problem of parking scarcity in urban areas. This paper aims to examine the shared parking choice behaviours using a combination of structural equation modelling (SEM) and neural network, taking into account both the parking location characteristics and the travellers’ characteristics. Data were collected from a commercial district in Nanjing, China, through an online questionnaire survey covering 11 factors affecting shared parking choice. The method involved two steps: firstly, SEM was applied to examine the influence of these factors on shared parking choice. Following this, the seven factors with the strongest correlation to shared parking choice were used to train a neural network model for shared parking prediction. This SEM-informed model was found to outperform a neural network model trained on all eleven factors across precision, recall, accuracy, F1 and AUC metrics. The research concluded that the selected factors significantly influence shared parking choice, reinforcing the hypothesis regarding the importance of parking location and traveller characteristics. These findings provide valuable insights to support the effective implementation and promotion of shared parking.
{"title":"Use of Structural Equation Modelling and Neural Network to Analyse Shared Parking Choice Behaviour","authors":"Yi Zhu, Shuyan Chen, Ying Wu, Fengxiang Qiao, Yongfeng Ma","doi":"10.7307/ptt.v35i5.209","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.209","url":null,"abstract":"The shared parking mode represents a feasible solution to the persistent problem of parking scarcity in urban areas. This paper aims to examine the shared parking choice behaviours using a combination of structural equation modelling (SEM) and neural network, taking into account both the parking location characteristics and the travellers’ characteristics. Data were collected from a commercial district in Nanjing, China, through an online questionnaire survey covering 11 factors affecting shared parking choice. The method involved two steps: firstly, SEM was applied to examine the influence of these factors on shared parking choice. Following this, the seven factors with the strongest correlation to shared parking choice were used to train a neural network model for shared parking prediction. This SEM-informed model was found to outperform a neural network model trained on all eleven factors across precision, recall, accuracy, F1 and AUC metrics. The research concluded that the selected factors significantly influence shared parking choice, reinforcing the hypothesis regarding the importance of parking location and traveller characteristics. These findings provide valuable insights to support the effective implementation and promotion of shared parking.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136019082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bin He, Yaping Liu, Xiaocheng Gao, Fei An, Xikui Lv
In order to avoid the congestion in front of the entrance gate units, it is necessary to analyse and optimise the queuing situation at the planning and design stage. The security inspection area and the ticket-checking area were jointly considered, and a queuing congestion analysis method was proposed. Firstly, the research problem was stated. Then, the problem of calculating the number of passengers in each subarea at any time was transformed into the problem of calculating the transit time of each passenger in each subarea. The transit time was divided into basic transit time and additional transit time. Based on the velocity-density relationship, a quantisation method for basic transit time was proposed related to passenger arrival time. The additional transit time was determined by the moment when the passengers left the subarea according to the sequence of arrival of passengers, the number of queuing passengers in the subarea and the congestion of the subarea to be entered. Finally, the queuing situation of passengers in each subarea at any moment was obtained through passenger flow recursion. Examples showed that the proposed method can deal with multiple working conditions and avoid the tedious and time-consuming scene construction process of the microsimulation software.
{"title":"Passenger Queuing Analysis Method of Security Inspection and Ticket-Checking Area without Archway Metal Detector in Metro Stations","authors":"Bin He, Yaping Liu, Xiaocheng Gao, Fei An, Xikui Lv","doi":"10.7307/ptt.v35i5.266","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.266","url":null,"abstract":"In order to avoid the congestion in front of the entrance gate units, it is necessary to analyse and optimise the queuing situation at the planning and design stage. The security inspection area and the ticket-checking area were jointly considered, and a queuing congestion analysis method was proposed. Firstly, the research problem was stated. Then, the problem of calculating the number of passengers in each subarea at any time was transformed into the problem of calculating the transit time of each passenger in each subarea. The transit time was divided into basic transit time and additional transit time. Based on the velocity-density relationship, a quantisation method for basic transit time was proposed related to passenger arrival time. The additional transit time was determined by the moment when the passengers left the subarea according to the sequence of arrival of passengers, the number of queuing passengers in the subarea and the congestion of the subarea to be entered. Finally, the queuing situation of passengers in each subarea at any moment was obtained through passenger flow recursion. Examples showed that the proposed method can deal with multiple working conditions and avoid the tedious and time-consuming scene construction process of the microsimulation software.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136018961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, the author investigated the stated preference survey in transport modelling. The research was conducted to ensure that the best fractional orthogonal design of stated preference paired comparison survey would not increase the error or uncertainty in transport-related decision modelling. The research was conducted based on artificial Monte Carlo simulated respondents, and the results were assessed with standard mathematical-statistical tools. Although the assessment should have resulted in 0% errors, according to our 2,000 sample, a minor 5% of errors occurred. The problem to be investigated in this paper is that the best-designed survey could have some errors.
{"title":"Evaluation of Stated Preference Surveys with Statistical Methods","authors":"Tibor Sipos","doi":"10.7307/ptt.v35i5.259","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.259","url":null,"abstract":"In this paper, the author investigated the stated preference survey in transport modelling. The research was conducted to ensure that the best fractional orthogonal design of stated preference paired comparison survey would not increase the error or uncertainty in transport-related decision modelling. The research was conducted based on artificial Monte Carlo simulated respondents, and the results were assessed with standard mathematical-statistical tools. Although the assessment should have resulted in 0% errors, according to our 2,000 sample, a minor 5% of errors occurred. The problem to be investigated in this paper is that the best-designed survey could have some errors.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136103459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Transportation, which is a significant facilitator of global trade and development, faces a serious problem with respect to sustainability. Firstly, there is the need to minimise greenhouse gas emissions while maintaining profitability and social responsibility. Transportation will be totally decarbonised by consistently moving towards a more sustainable, diverse and resilient range of transportation modes with advanced vehicle technologies. However, what impact this will have on the economic performance of transport service providers remains a big question. The aim of this study is to examine the short-run relationship between environmental sustainability in road freight transportation and the economic performance of the road freight transport sector in the European Union using an autoregressive conditional heteroscedasticity (ARCH) model. The analysis was conducted using annual data spanning from 2008 to 2021. The results indicate that energy taxes on transport and storage, biodiesel consumption and vehicle capacity utilisation have a positive and significant impact on freight transport performance (FTP). The findings suggest that policymakers could use energy taxes and incentives to promote the use of biodiesel in the transportation sector to increase FTP. Additionally, efforts to improve vehicle capacity utilisation could significantly increase FTP and have positive environmental implications such as reducing traffic congestion and emissions.
{"title":"Environmental Sustainability and Freight Transport Performance in the EU – An Autoregressive Conditional Heteroscedasticity (ARCH) Model Analysis","authors":"Sebastian Kot, Stephen Ojinji","doi":"10.7307/ptt.v35i5.293","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.293","url":null,"abstract":"Transportation, which is a significant facilitator of global trade and development, faces a serious problem with respect to sustainability. Firstly, there is the need to minimise greenhouse gas emissions while maintaining profitability and social responsibility. Transportation will be totally decarbonised by consistently moving towards a more sustainable, diverse and resilient range of transportation modes with advanced vehicle technologies. However, what impact this will have on the economic performance of transport service providers remains a big question. The aim of this study is to examine the short-run relationship between environmental sustainability in road freight transportation and the economic performance of the road freight transport sector in the European Union using an autoregressive conditional heteroscedasticity (ARCH) model. The analysis was conducted using annual data spanning from 2008 to 2021. The results indicate that energy taxes on transport and storage, biodiesel consumption and vehicle capacity utilisation have a positive and significant impact on freight transport performance (FTP). The findings suggest that policymakers could use energy taxes and incentives to promote the use of biodiesel in the transportation sector to increase FTP. Additionally, efforts to improve vehicle capacity utilisation could significantly increase FTP and have positive environmental implications such as reducing traffic congestion and emissions.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136019078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate energy consumption prediction is essential for improving the driving experience. In the urban road scenario, we discussed the influencing factors of energy consumption and divided the modes from various perspectives. The differences in energy consumption characteristics and distribution laws for electric vehicles using the IDM and CACC car-following models under different traffic flows are compared. An energy consumption prediction framework based on the LightGBM model is proposed. According to the study, driving range, acceleration, accelerating time, decelerating time and cruising time all significantly impact the overall energy consumption of electric vehicles. There are apparent differences in energy consumption characteristics and distribution laws under different traffic flows: average energy consumption is lower under low flow and increased under high flow. The CACC-electric vehicles consume more energy in low flow than IDM-electric vehicles. Under high flow, the opposite is true. The results show that the proposed framework has a high accuracy: the MAPE based on IDM datasets is 3.45% and the RMSE is 0.039 kWh; the MAPE based on CACC datasets is 5.57% and the RMSE is 0.042 kWh. The MAPE and RMSE are reduced by 33.7% and 50.6% (maximum extent) compared to the best comparison algorithm.
{"title":"Prediction of Electric Vehicle Energy Consumption in an Intelligent and Connected Environment","authors":"Qingchao Liu, Fenxia Gao, Jingya Zhao, Weiqi Zhou","doi":"10.7307/ptt.v35i5.202","DOIUrl":"https://doi.org/10.7307/ptt.v35i5.202","url":null,"abstract":"Accurate energy consumption prediction is essential for improving the driving experience. In the urban road scenario, we discussed the influencing factors of energy consumption and divided the modes from various perspectives. The differences in energy consumption characteristics and distribution laws for electric vehicles using the IDM and CACC car-following models under different traffic flows are compared. An energy consumption prediction framework based on the LightGBM model is proposed. According to the study, driving range, acceleration, accelerating time, decelerating time and cruising time all significantly impact the overall energy consumption of electric vehicles. There are apparent differences in energy consumption characteristics and distribution laws under different traffic flows: average energy consumption is lower under low flow and increased under high flow. The CACC-electric vehicles consume more energy in low flow than IDM-electric vehicles. Under high flow, the opposite is true. The results show that the proposed framework has a high accuracy: the MAPE based on IDM datasets is 3.45% and the RMSE is 0.039 kWh; the MAPE based on CACC datasets is 5.57% and the RMSE is 0.042 kWh. The MAPE and RMSE are reduced by 33.7% and 50.6% (maximum extent) compared to the best comparison algorithm.","PeriodicalId":54546,"journal":{"name":"Promet-Traffic & Transportation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136019609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}