Introduction

In particular, by 2014, China’s expressway mileage had far exceeded that of the United States, with a gap of 92,000 km. By 2016, China’s traffic mileage had increased, and the national expressway network skeleton has been formed1. As an essential link connecting various regions, the traffic directly affects the development of the city. Moreover, with the improvement of people’s living standards and urban expansion, the city’s car ownership continues to rise, and the original road design is no longer applicable to the current situation. At the same time, the urban infrastructure has not been able to keep up with its pace in the process of urban development, the road planning is also relatively old, the traffic accident rate is increasing, and the traditional traffic management mode is no longer suitable for the current traffic situation.

With the continuous development of technology, information has become an essential factor in social development. As an essential technology for the in-depth development of information, the Internet of things is gradually valued and promoted by the state and various fields. In particular, active exploration has been made in smart city development, such as smart cities, smart transportation, smart furniture, and smart logistics. The Internet of things has also become a new growth point of economic development2. As the next generation mobile communication technology, 6G communication is expected to achieve higher data transmission rates, lower latency, and wider coverage. It will support more device connections and more complex application scenarios, providing a strong communication foundation for intelligent transportation systems3. In the intelligent highway transportation system, 6G communication will support high-speed, low latency communication between vehicles and infrastructure, achieving real-time data transmission and sharing. This will enable vehicles to quickly obtain road condition information, traffic signals, and emergency notifications, thereby making more accurate driving decisions. Meantime, 6G communication will also support the collaborative operation of large-scale vehicle formation driving and autonomous vehicle to improve the efficiency and safety of road traffic. Edge computing is a technology that pushes data processing and storage capabilities to the edge of the network, aiming to reduce data transmission delays and improve system response speed. By transferring data processing tasks from the cloud to edge devices, edge computing can process and analyze data more quickly to support real-time applications.

Intelligent transportation is mainly achieved depending on information technology, such as the Internet of Things and cloud computing. It has been listed as the top ten demonstration projects of the Internet of Things in China when it was proposed. The Ministry of Industry and Information Technology of the People’s Republic of China has promoted the construction of intelligent expressways. At the same time, it emphasizes that “wisdom” and “intelligence” are different, and there are essential differences: Intelligent transportation mainly refers to the use of modern science and technology, such as the Internet of Things information technology, high-end cloud computing, and other key technologies to build a smart transportation system, thereby coordinating people, vehicles, roads and the environment4. As a result, the construction and use of expressways, services, and other development forms with modern awareness can be achieved. What is more, energy can be better saved, and environmental pollution can be reduced to promote a new form of traffic development of China’s expressway intelligent transportation system.

To sum up, with the continuous increase in the number of vehicles, the traffic flow on highways continues to grow, bringing enormous pressure to road safety and traffic efficiency. By constructing an intelligent highway transportation system based on the Internet of Things, real-time monitoring and intelligent regulation of traffic flow can be achieved, effectively alleviating traffic congestion and improving road capacity. The Internet of things and the intellectual development of expressway are combined. With the data of Chinese expressway as the core, and with the help of cloud platform and Internet of things technology, it provides support for expressway traffic safety, provides safe and smooth traffic environment for people, promotes the development of intelligent transportation, and provides strong power for sustainable economic development. The main contribution of this work is to propose an innovative intelligent highway transportation system design scheme through in-depth analysis of the application potential of Internet of Things and cloud computing technology in highway traffic management. This scheme not only solves the shortcomings of traditional traffic management systems in real-time data and cross-regional collaborative management, but also significantly improves the safety, traffic efficiency, and operational management level of highways through intelligent means. The innovation lies in the use of cloud computing and big data technology to collect and analyze urban traffic data in real time, including road conditions, traffic flow, accident information, etc., providing travelers with real-time road condition information, best travel route recommendations, and other services.

The work is mainly divided into five sections. Section 1 introduces the research background of the Internet of Things and smart cities. Section 2 analyzes the recent research progress of expressways and intelligent transportation by referring to relevant documents of the intelligent transportation system. Section 3 builds the expressway service system architecture through the Internet of Things and data mining technology. Section 4 explains the system function management structure through system data analysis. Section 5 draws the research conclusion through the summary of the experimental results. Therefore, the key contribution of the implementation of the Internet of Things measurement is to design the overall expressway service system architecture and promote the digitalization and intelligence of the expressway management system.

The contributions of this work are listed as follows:

  • Innovation in intelligent highway transportation system design: A design scheme for an intelligent highway transportation system based on the Internet of Things is proposed. Through cloud computing and big data technology, real-time collection and analysis of urban traffic data are achieved, significantly improving the safety and traffic efficiency of highways.

  • System architecture and functional implementation: A cloud platform architecture that includes IaaS, PaaS, and SaaS layers is built, realizing the digitization and intelligence of the highway traffic management system, and providing real-time traffic information and the optimal travel route recommendation services.

  • Experimental verification and performance improvement: The effectiveness of the proposed system design scheme is verified through experiments, and the results show that the system has significant effects in reducing traffic congestion, improving traffic flow prediction accuracy, and reducing the incidence of traffic accidents.

  • Smart city construction and policy recommendations: The research results provide theoretical support and practical guidance for the construction of transportation systems in smart cities, which will help the government and relevant departments formulate more effective transportation policies and management measures.

Literature review

Computer network technology, multimedia and communication technology, and the Internet of Things has been widely accepted in various fields with the rapid development and broad application of computer technology. Furthermore, various intelligent expressway transportation systems have been built and perfected continually, all of which depend on the development of the Internet of Things and high-tech information technologies such as cloud computing5. Numerous scholars have conducted relevant research. For instance, Li et al. (2022) optimized privacy protection and reliable offloading in vehicle edge computing and networks systems. Although their approach helped improve user data privacy, there might be a trade-off between performance and privacy protection in practical applications6. Li et al. (2022) discussed the use of network slicing technology to enhance the reliability analysis of Internet of Vehicles clusters. Although an innovative integrated analysis framework was proposed, its complexity might have new challenges in management and maintenance during implementation7. Liu & Ke (2023) proposed a cloud-assisted Internet of Things intelligent transportation system and analyzed the potential advantages of traffic control in smart cities. However, the method relied on high-performance cloud computing resources and ignored the processing capabilities of edge devices and their impact on real-time performance8. Shen et al. (2022) designed a data integrity verification scheme for Internet of Things-assisted transportation systems, which was innovative in terms of data exchange security, but did not fully consider the limited resources of Internet of Things devices and the computational cost of the verification process9. Atiq et al. (2023) explored the reliable resource allocation and management of fog computing in Internet of Things transportation, emphasizing the advantages of distributed computing. However, they did not delve into the handling of resource competition and system complexity, which might affect practicality10. Miri et al. (2023) proposed a novel method for improving resource utilization in Internet of Things transportation systems based on Markov transition and TDMA protocols. However, its practical performance evaluation in large-scale vehicle networks was insufficient, which affected its widespread application11. Khattak & Khan (2024) analyzed the evaluation and challenges of Internet of Things simulators in intelligent transportation, pointing out the limitations of current simulators in complex traffic scenarios. However, no specific solutions were proposed, and practical guidance was weak12.

Additionally, some scholars have also conducted relevant research on the application of edge computing and blockchain technology in intelligent transportation systems. As proposed by Li et al. (2022), the BDRA scheme improved the registration and authentication security of VANETs through blockchain and decentralized identity recognition. However, the complexity of its implementation might increase system overhead and affect scalability in large-scale scenarios13. Li et al. (2024) proposed a two-stage unloading model for the optimization of distributed on-board edge computing. Although the algorithm had effectively improved the computing efficiency, its adaptability in dynamic environments and extensive verification of multiple scenarios still needed to be strengthened14. Chen et al. (2023) combined blockchain, smart contract and edge computing for distributed logistics resource allocation. This method improved data transparency and system security, but ignored the limited computing power of edge devices and potential latency issues, and the scalability of application scenarios still needed further verification15. Das et al. (2023) reviewed the application of blockchain in intelligent transportation systems and analyzed its potential in improving data privacy and transparency. However, in the challenge analysis, the performance bottleneck of edge computing and the real-time problems of on chain operations had not been fully solved, which limited the feasibility of actual deployment16. Moura et al. (2024) proposed a framework combining edge computing and distributed ledger technology to improve the safety and efficiency of the transportation system. Its architecture design was reasonable, but its performance in dealing with large-scale data transmission and high-frequency vehicle interaction lacked empirical support, and further verification of operability was needed17.

Overall, existing research mainly focuses on the application of Internet of Things technology in intelligent transportation systems, such as vehicle communication, data processing, and information security. However, these studies often overlook the deep integration and practical application potential of Internet of Things technology in intelligent transportation systems on highways, especially the real-time data processing and analysis capabilities assisted by cloud computing and big data technology. In addition, existing literature lacks in-depth exploration in the experimental verification and performance improvement of intelligent transportation systems. In response to this gap, the advantage and innovation of this work lies in proposing a design scheme for an intelligent highway transportation system based on the Internet of Things. This scheme achieves real-time collection and analysis of urban transportation data through cloud computing and big data technology, and introduces a cloud platform system architecture including IaaS, PaaS, and SaaS layers to provide real-time traffic information and best travel route recommendation services. This work thus provides reference for improving the safety, traffic efficiency, and operational management level of highways through intelligent means.

Method

Internet of things

The Internet of things is the “Internet-connected with everything,” a vast network formed by the combination of various information sensing devices and the Internet, which can realize the interconnection of people, machines, and things anytime and anywhere18,19. The realization of the Internet of things mainly depends on specific communication protocols, which can unify various information formats. At this time, there is a need for various data collectors and sensor equipment to support the development and application of the Internet of Things. The Internet of Things architecture mainly includes the perception layer, network transmission layer, information processing layer, and application layer. Figure 1 shows the architecture.

Fig. 1
figure 1

Internet of things architecture.

Full size image

In Fig. 1, the perception layer mainly collects relevant data for the Internet of things system, including various data acquisition technologies and sensing technologies, and can realize the dynamic connection and information collection. The network layer is mainly a variety of communication systems, which is the critical part of the Internet of things, providing a more efficient communication protocol to realize the Internet of things. The application layer is mainly the interface part of the Internet of things and users. It can obtain the corresponding data according to different industries, process, classify, screen, process the data according to the industry’s needs, and finally present the results to the users. The implementation of this part mainly depends on various databases and professional software20,21.

Data mining technology

Data mining technology mainly relies on four fundamental technologies: database, artificial intelligence, mathematical statistics, and visualization. Data mining technology’s algorithm input is the database, algorithm output is knowledge or pattern extraction and discovery, and algorithm processing is the specific design of search methods22. The description or illustration of algorithm design is mainly divided into three parts: input, output, and processing. The data mining algorithm mainly involves three aspects: mining objects, mining tasks, and mining methods.

The process of data mining is also called KDD (Knowledge Discovery in Database). Data mining refers to the extraordinary process of automatically extracting useful information hidden in data sets. Data mining technology in the mining methods is divided into four categories: statistical methods, machine learning methods, neural network methods, and database methods23. Statistical methods can be subdivided into regression analysis and discriminant analysis. Data mining technology comprises many mining objects such as relational databases, spatial databases, and text databases. Neural network methods can be subdivided into a forward neural network and a self-organizing neural network. Machine learning in data mining technology mainly means the genetic algorithm. Data mining technology is mainly based on multi-dimensional data analysis. Data mining is a long process and a specific step, which is mainly produced in KDD. Its main feature is that it can extract, transform, analyze, and model big data and extract critical data.

In order to meet the needs of information fusion, it is necessary to standardize it. Various signal indices are standardized by constructing transformation functions. Interval standardization functions can be expressed as:

$${a_i}={u_{{d_i}}}({x_i})\left\{ \begin{gathered} 1 - \frac{{\hbox{min} (m_{1}^{i} - {x_i},{x_i} - m_{2}^{i})}}{{\hbox{max} (m_{1}^{i} - {x_i},{M_i} - m_{2}^{i})}}\mathop {}\nolimits^{{}} {x_i} \notin [m_{1}^{i},m_{2}^{i}] \hfill \\ 1\mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} \mathop {}\nolimits^{{}} {x_i} \in [m_{1}^{i},m_{2}^{i}] \hfill \\ \end{gathered} \right.$$
(1)

In (1), \({d_i}=[m_{i}^{{}},{M_i}]\) indicates the threshold of \(i\), \({x_i}\) is the actual measured value of the target, and \(\operatorname{m}\) is a fixed value.

System requirements analysis

In the system’s design, it is necessary to consider the system requirements, which is also the key to determining the system’s success or failure. Insufficient analysis of system requirements may lead to impaired function and system design capability, and excessive analysis may lead to waste. Therefore, considering the feasibility of an expressway intelligent transportation system based on the Internet of things, the discussion is carried out from user demand and technology.

User demand analysis

The system will involve many subjects, such as relevant administrative departments, expressway operators, equipment suppliers, and related derivative service providers, so it is necessary to conduct a more comprehensive analysis when considering the needs of users. First of all, the administrative department demands to tell the traffic management department that it needs to know the real-time traffic flow and understand the traffic flow of each traffic entrance and exit and the overall traffic situation of critical areas through visualization technology. Also, traffic flow modeling and grooming model are needed to analyze and predict the data flow to complete the natural dredging work24. When there is abnormal traffic flow, it is also necessary to build an abnormal traffic accident model to monitor the abnormal flow. When some traffic sections have bottlenecks due to the influence of climate, facilities, and other factors, or when there are violations and accidents, they can be recorded, reported, and stored.

It is necessary for expressway operators to effectively manage the relevant facilities and equipment on the expressway to ensure the timely acquisition of traffic flow, the regular operation of traffic facilities and equipment, the push of traffic information, and the collection of various information of toll station information.

The demand for expressway service demanders represents the future development trend of intelligent transportation. The automated driving technology, expressway traffic flow, and road environment information acquisition provide the basis for coordinating travel plans, driving routes, and route arrangements. Simultaneously, the weather conditions, the distribution of service areas, and the traffic information in front of the owners need to be informed the first time so that all parties can make a timely response.

Expressway derivative service providers, namely navigation, ETC, financial services, and vehicle rental enterprises, provide more convenient expressway services for car owners.

Technical requirement analysis

The realization of intelligent transportation of expressway needs to consider the characteristics of openness, compatibility, dynamic, global, and intelligent to realize the intelligent system. The first is openness, which needs to open the national information system to meet customers’ needs. Compatibility mainly refers to that in the intelligent transportation system, data acquisition, processing, mining, interaction, and other technologies need a lot of equipment support, so the system needs absolute compatibility. Dynamic is that the vehicles in high-speed traffic are dynamic, so nodes and systems must collect relevant information and signals in real-time to further identify the traffic operation status25,26.

Global mainly considers the economic problem of deploying sensor nodes on the expressway. Different application fields and application scenarios are completed on the information processing platform to ensure the equipment operation, information recording, storage, global system, and local system analysis.

Intelligence mainly refers to collaborative processing and pattern recognition. Many heterogeneous nodes are deployed to complete the information collection so that the intelligent transportation system can automatically judge, control, and manage the traffic information to realize the overall intelligent development.

Model and experimental design

Design of civil and industrial wireless communication technology modules such as GPRS/CDMA/3G/4G

Expressway intelligent transportation system can be roughly divided into three categories: network application subsystem, information service center, and command and control center. The three levels are different, and they also correspond to three modules and three different functions. For example, the information service center and command and control center’s role is specific, and their functions are relatively straightforward. However, the application subsystem, mainly a variety of subsets, contains all the application systems except the information service center and command and control center explicitly, as shown in Fig. 2.

Fig. 2
figure 2

Intelligent transportation system hierarchy.

Full size image

Design of WI-FI wireless local area communication, ray, microwave, and infrared communication technology

Perception is the basis of intelligent system construction, that is, real-time acquisition of dynamic information through various optical, electrical, acoustic, and wave sensors. The expressway system is a vast system with many elements and intricate layers, including many system state information. The sensitivity and accuracy of the perception system will determine an intelligent transportation system’s overall practical performance. The perception layer mainly collects necessary information through various object-to-object connection terminal devices (M2M devices). These devices are distributed in all aspects of traffic. They continuously collect fresh video, images, text, data, and other information. Then, they are connected through wireless sensor networks to form a whole part. Integration technology of multi-sensor depth fusion based on RFID technology, wireless communication technology, and inductance sensing technology is the foundation of intelligent transportation. Information fusion technology achieves a more objective and in-depth understanding of the same goal through information processing, collaborative use, and complementary complementarity27. The expressway intelligent transportation system’s perceptual information covers a wide range and has different signal and information modes.

Design of saas layer

The intelligent transportation cloud platform for highways should be divided into three layers: IaaS layer (Infrastructure as a Service), PaaS layer (Platform as a Service), and SaaS layer (Software as a Service). On this basis, edge computing is introduced and a “hybrid cloud edge architecture” is built. The IaaS layer is located at the bottom of the cloud platform, providing necessary computing and storage capabilities, directly facing specific physical and hardware resources. The PaaS layer provides core services of cloud computing, provides software developers with an internet-based application development and running environment, and presents software application programming interfaces and operating platforms. The SaaS layer provides users with services (including highway managers, travelers and associated highway units), enabling users to access the required services anytime and anywhere through the Internet. The data processing and analysis at the edge computing layer can instantly process a large amount of information at the location where the data is generated, realize rapid response to emergencies, reduce the delay of data transmission to the cloud, and improve the real-time and reliability of the system. This hybrid architecture not only enhances the monitoring and intelligent adjustment capabilities of highway traffic flow, but also provides users with a safer and more efficient driving environment.

Traditional expressway intelligent transportation systems were mostly installed in local servers and accessed through client/server mode. They were mostly limited by scope and were unable to provide services to users anytime and anywhere. Most databases adopt master-slave architecture, which makes it challenging to expand dynamically according to load changes.

However, the SaaS layer of the expressway intelligent transportation platform is user-oriented and directly provides services for users. By connecting to the Internet, the users can obtain the required services without limitations to time and place and obtain the required services on demand through traditional PC clients, notebooks, mobile phones, PDA, and other intelligent terminals. SaaS layer adopts the form of multi-tenant to provide users with data access services of various expressway traffic systems and realize the related queries of different system data. It also provides a data isolation mechanism to ensure the security of data when users share data. The SaaS layer integrates intelligent management and intelligent service using the expressway’s intelligent traffic cloud platform, specializes the expressway management and convenient service, and effectively improves the management and service level of the expressway. Its application diagram is shown in Fig. 3.

Fig. 3
figure 3

Cloud platform SaaS application.

Full size image

On the basis of cloud platform architecture, edge computing is further introduced to handle tasks close to data sources, thus quickly responding to emergencies and reducing the need for data transmission to the cloud. By deploying real-time data processing and analysis capabilities at edge nodes, the system is able to process large amounts of sensor data in real-time, providing low latency decision support while reducing the computational burden on the cloud. This hybrid architecture not only improves the response speed of the system, but also enhances the flexibility and reliability of data processing. The integration of edge computing enables the system to achieve real-time monitoring and dynamic adjustment of traffic flow while maintaining the scalability and data analysis capability of cloud computing, thus playing a greater role in intelligent transportation management. Moreover, by analyzing the technical rationality of the work through the model structure, the performance structure of the intelligent transportation system proposed is compared with the existing model performance. The comparison results reveal that the intelligent services of the expressway intelligent transportation system include intelligent operation, value-added services, and information management services. Therefore, the intelligent transportation system can improve the intelligent degree of the expressway, and the overall technology is superior to other existing models.

An intelligent management application consists of intelligent construction, intelligent operation, and intelligent maintenance application, forming an integrated mechanism of expressway construction, operation, and maintenance. The intelligent service application is composed of basic information management service, travel service, and value-added service. It provides services for expressway managers, travelers, and expressway related units.

System function management

The basic information management service of the expressway intelligent transportation platform is to collect and share the data by expressway infrastructure, mainly including road condition information, toll station, and surrounding information, service area information, GIS geographic information, electromechanical equipment operation information, geological disaster early warning information and other infrastructure information, and ultimately make the information automatically form the expressway foundation. Figure 4 shows the system simulation interface. The primary information database provides relevant necessary information for expressway managers, which significantly improves expressway management efficiency. By collecting real-time traffic information, analyzing and processing it in time, it can provide comprehensive real-time traffic information for travelers, meet their travel information needs, and plan their travel routes in time.

Fig. 4
figure 4

The system simulation interface.

Full size image

Figure 4 shows the system simulation interface, which includes multiple functional modules for implementing key operations and monitoring of the intelligent highway transportation system. For example, the energy consumption estimation module can collect real-time energy consumption data from various sections of highways, estimate the energy consumption of different time periods and road sections through algorithm analysis, and visually display energy consumption trends in the form of charts, helping managers optimize energy use and reduce operating costs. The trend view module utilizes historical and real-time data to analyze the changing trends of key indicators such as traffic flow and accident rate through data mining techniques, predict possible future traffic conditions, and provide decision support for traffic planning and management. In addition, the simulation system may also include modules such as fault warning and maintenance scheduling, which can predict potential fault risks through real-time monitoring of equipment status and automatically generate scheduling plans for maintenance and repair work, ensuring the stable operation of highway infrastructure. These functional modules together form a comprehensive and efficient intelligent transportation management platform, improving the operational efficiency and service quality of highways.

Two service systems realize travel service: travel guidance service and third-party information service, as shown in Fig. 5.

Fig. 5
figure 5

Schematic diagram for travel service.

Full size image

Figure 5 reveals that in the intelligent transportation system, the vehicle terminal and mobile service system can be connected with each other by using the Internet of Things and cloud computing technology, which can improve the traffic efficiency of the expressway and further promote tourism consumption. Meanwhile, the research has an important contribution to solving the problem of road congestion and improving road traffic safety.

Implementation of application

To verify the effectiveness of the proposed intelligent highway transportation system, this work conducts a series of simulation experiments to simulate real-world traffic scenarios and evaluate the system’s performance. When the system is used, the computer and mobile terminals need to log in. After inputting the account name and pass word, the user can realize the connection with the national intelligent transportation system and learn the system’s relevant information and other car owners through information query. The expressway traffic management departments and service derivatives can obtain the information about road and expressway equipment using the video technology, save it in the background, and number the video monitoring log according to time and content, thereby providing technical support for the retrieval and processing of relevant information.

According to the relational model of the E-R entity diagram transformation of expressway video surveillance’s push application service database, the data table comprises five parts: expressway user table, expressway user privilege table, video surveillance equipment table, section information table, and video surveillance equipment’s log table. The expressway user table is shown in Table 1, and the expressway user privilege table is shown in Table 2. The frequency monitoring equipment table is shown in Table 3.

Table 1 Expressway user.
Full size table
Table 2 Expressway user rights.
Full size table
Table 3 Video surveillance equipment.
Full size table

In the simulation experiment, this work simulates the data processing tasks under different traffic flows, and compares the proposed algorithm with the intelligent transportation system that only uses edge computing technology (Only EC), the intelligent transportation system that only uses cloud computing technology (Only CC), and the model algorithms proposed by Khattak & Khan (2024) from the aspects of processing efficiency, system performance, cost-effectiveness, and accident response time. In terms of traffic flow management, simulation environments are created to represent typical peak hours of busy highways. The system can effectively distribute traffic data to the control center, which in turn provides dynamic route recommendations for drivers. Regarding event response, the system’s event detection and response mechanism is tested by introducing simulated accidents and lane congestion. For real-time information provision, the accuracy and timeliness of the information system provided to drivers are evaluated.

This work further conducts case studies. The Guangzhou-Foshan Expressway section is known for its high traffic volume and frequent congestion. Taking a section of the Guangzhou Foshan Expressway as an example, the proposed algorithm is deployed for a period of three months, during which its performance is monitored and compared with the same period the previous year.

Results and discussion

Performance analysis of systems under different models

First, compare the proposed algorithm with the intelligent transportation system using only edge computing technology (Only EC), the intelligent transportation system using only cloud computing technology (Only CC), and the algorithm proposed by Khattak & Khan (2024) in terms of processing efficiency, system performance, cost-effectiveness, accident response time and other indicators, as shown in Figs. 6 and 7.

Fig. 6
figure 6

Comparison results of event response and processing efficiency of various model algorithms.

Full size image

As shown in Fig. 6, when comparing and analyzing the event time response and processing efficiency of different intelligent transportation system models, the proposed algorithm has significant advantages in accident processing time, only requiring 120 milliseconds, which is much lower than that of other models. Its accident response time is also excellent, only 12 s, which may be attributed to its optimized data processing flow and efficient algorithm design. However, Only EC has 201 ms of incident processing time and 35 s of response time, which shows that both processing efficiency and response speed are delayed. Only CC performs the worst, with a processing time of 443 milliseconds and a response time of up to 65 s, which may be due to delays caused by data processing on remote servers. The model proposed by Khattak & Khan (2024) falls between the two, with a processing time of 163 milliseconds and a response time of 22 s. Although not as good as the proposed algorithm, it still demonstrates good performance. Overall, the proposed algorithm has demonstrated strong capabilities in quickly and accurately handling and responding to traffic accidents, highlighting its potential for application in intelligent transportation systems.

Fig. 7
figure 7

Comparison results of cost benefit and resource utilization of various model algorithms.

Full size image

The cost-effectiveness and CPU utilization of various intelligent transportation system models are compared and analyzed. As shown in Fig. 7, the proposed algorithm demonstrates good cost-effectiveness and resource utilization efficiency with a monthly cost of 7004 yuan and a CPU utilization rate of 53%. Although the CPU utilization rate of Only EC is slightly higher, which is 60%, the cost also increases to 8543 yuan/month. It is worth noting that Only CC has the lowest CPU utilization rate at 51%, but the highest cost at 11,674 yuan/month. This may be due to the fact that cloud computing models require more server resources to process data, and to ensure the reliability of data processing and system stability, resource redundancy strategies may be adopted,. This results in some resources remaining idle even during off peak hours, thereby reducing overall CPU utilization. The model proposed by Khattak & Khan (2024) achieves a relative balance between cost and resource utilization efficiency with a cost of 7561 yuan/month and a CPU utilization rate of 57%. Overall, the proposed algorithm has demonstrated strong competitiveness in cost control and resource utilization.

This work further compares the accident occurrence of each algorithm model, as shown in Table 4.

Table 4 Comparison results of Accident occurrences for various Algorithm models.
Full size table

Table 4 shows that the proposed algorithm demonstrates significant advantages in key indicators when comprehensively evaluating the performance of intelligent transportation systems. Specifically, compared with the existing system, this algorithm reduces the average traffic congestion time by 25%, which is far more than 15% of Only EC, 10% of Only CC, and 20% of the model proposed by Khattak & Khan (2024). In terms of reducing the incidence of traffic accidents, the proposed algorithm leads with a decrease of 18%. In comparison, the Only EC and Only CC models only have a decrease of 10% and 5%, respectively, while the model proposed by Khattak & Khan (2024) has a decrease of 12%. In addition, the proposed algorithm reduces the accident rate to 27%, which is not only 10% lower than existing systems, but also better than the 30%, 32%, and 31% of Only EC, Only CC, and Khattak & Khan (2024)’s model. These results fully demonstrate the outstanding performance of the proposed algorithm in improving traffic efficiency and safety, highlighting its potential and practical benefits in the field of intelligent transportation systems.

Actual case analysis

In case studies, the accident response and handling efficiency of the Guangzhou-Foshan Expressway section where the proposed algorithm is deployed is compared with the same period of the previous year, shown in Fig. 8.

Fig. 8
figure 8

Comparison results of event response and handling efficiency of the Guangzhou-Foshan Expressway section before and after deploying the proposed algorithm (a. Accident response time; b. Accident handling time).

Full size image

As shown in Fig. 8, in the case study of deploying the proposed algorithm on the Guangzhou-Foshan Expressway section, compared with the original situation, this algorithm shows significant improvements in both accident handling time and accident response time. Specifically, the accident handling time has been reduced from an average of 150.54 milliseconds to 120.53 milliseconds, and the accident response time has also been reduced from 22.38 s to 12.43 s. This improvement remained consistent during the 91-day observation period, demonstrating the effectiveness of the proposed algorithm in practical applications. Especially on the 11th, 21st, and 61st days, the algorithm shows better processing and response capabilities, which may be due to the optimization of the model for specific situations at these time points. Overall, the proposed algorithm improves the efficiency of accident management by reducing accident handling and response time, helping to alleviate traffic congestion, enhance road safety, and provide drivers with a safer and more efficient driving environment.

Further demonstrate the plan and results of real-world testing of the system, as shown in Table 5.

Table 5 System testing results in the real world.
Full size table

As shown in Table 5, through these on-site tests, the performance of the system under real-world conditions can be comprehensively evaluated, including the robustness and applicability of the system under complex challenges such as variable weather, equipment failures, and human factors. These testing results will provide valuable data to further optimize and adjust the system, ensuring its effectiveness and reliability in practical applications.

Discussion

This work explores the effectiveness and potential of intelligent transportation systems in practical applications by constructing an Internet of Things-based intelligent highway transportation system. The comparative experiments suggest that the proposed algorithm significantly outperforms existing systems in terms of average time for handling traffic accidents. The accident handling time is reduced from 150.54 milliseconds to 120.53 milliseconds, and the response time is also reduced from 22.38 s to 12.43 s. This improvement is not only reflected in numbers, but also demonstrates enormous application value in practical traffic management, which is consistent with the views of Arthur et al. (2021)28and Dhingra et al. (2021)29. In addition, the proposed algorithm achieves a 25% reduction in traffic congestion time, far exceeding other models, indicating the outstanding performance of the algorithm in improving traffic flow efficiency.

Meantime, the proposed algorithm has demonstrated strong competitiveness in terms of cost-effectiveness and resource utilization. Compared with the research of scholars in related fields, the proposed algorithm costs 7004 yuan per month and has a CPU utilization rate of 53%, while Khattak and Khan’s model costs 7561 yuan per month and has a CPU utilization rate of 57%. In addition, the proposed algorithm reduces the accident rate to 27%, which is 10% lower than existing systems. This result has breakthrough significance in the field of intelligent transportation systems, which is consistent with the viewpoint of Musa et al. (2023)30.

The stability of network connections is crucial for ensuring real-time data transmission between IoT devices and cloud platforms. Any network interruption or delay may cause a decrease in event response speed, affecting the overall performance of the system. In order to alleviate this problem, the following measures should be taken. First, carry out data processing near the data source by introducing edge computing, decreasing the dependence on the central cloud, thus reducing the delay and improving the response speed. Second, enhance the reliability of data transmission by implementing a network redundancy strategy to transmit critical data through multiple network paths. In addition, develop predictive maintenance algorithms to monitor network status in real-time, and predict and avoid potential network issues, thus reducing the risk of system performance degradation. Finally, enhance the fault tolerance of the system to ensure that it can maintain the normal operation of critical functions in the event of network interruptions or delays. Through these measures, the robustness of intelligent transportation systems in the face of network fluctuations can be improved, ensuring rapid response and handling of traffic incidents, thereby enhancing the reliability and efficiency of the entire system. Future research can further explore the specific impact of network stability on system performance and develop more technological means to improve system robustness.

In practical applications, taking the Guangzhou-Foshan Expressway section as an example, the system effectively alleviates traffic congestion and improves road capacity through real-time monitoring and intelligent adjustment of traffic flow. The accurate data analysis and timely information feedback significantly improve driving safety. This provides effective technical support and solutions for solving practical problems in urban traffic management, such as traffic congestion and driving safety. Moreover, the design and implementation of the system also provide practical guidance for the construction of smart cities and the formulation of transportation policies, which helps to promote the commercialization and large-scale application of intelligent transportation systems, and thus promote the sustainable development of the social economy. In theoretical terms, this work provides a new perspective and theoretical basis for the design and optimization of intelligent transportation systems by analyzing the potential applications of the Internet of Things and cloud computing technology in highway traffic management. Especially in terms of processing efficiency, system performance, cost-effectiveness, and accident response time, comparative analysis provides valuable references and comparison standards for subsequent research.

Conclusion

The Internet of things technology and cloud platform is used to design and study the expressway traffic command system, the overall architecture of intelligent transportation system is designed, and the IaaS layer, PaaS layer, and SaaS layer of the cloud platform are deployed. The system requirements are considered on this basis. The system is designed according to the user needs and technical requirements to embed the Internet of Things technology in intelligent transportation and realize the relevant functions. The key finding is that the intelligent transportation system of smart cities has an important impact on the informatization of urban expressways. Specifically, the system has reduced the average traffic congestion time by 25%, the accident rate by 18%, and the accident rate by 10% compared to the existing system. Through the adoption of the Internet of Things and management information system, the main contribution of the research is to optimize the smart city and tourism transportation services through the structural design of the intelligent transportation system. In the following research, intelligent transportation facilities will be deeply analyzed. Embedding the Internet of Things into the command traffic system can promote the development of the Internet of Things in transportation, provides ideas for the realization of intelligent transportation on expressways, and is of great significance to the intelligent construction of expressway transportation in the future.

Ensuring real-time data processing and system reliability is crucial in complex and ever-changing traffic environments. However, factors such as network latency and device failures may affect the real-time response capability of the system. Subsequently, high availability and fault tolerance design can be adopted to ensure that the system can continue to operate in the event of partial component failure and optimize network architecture and data transmission protocols to reduce network latency. At the same time, implement real-time monitoring and fault warning mechanisms to promptly detect and solve problems.