TRAFFIC DENSITY PREDICTION MODEL AT LOADING TERMINAL USING DISCRETE SIMULATION METHOD QUANTITATIVE APPROACH

Traffic density at the port loading terminal is a critical factor affecting the port's operational efficiency and overall performance. To overcome the challenges of the complexity of the traffic system at the port terminal, a discrete simulation approach is adopted in this study. A quantitative approach is used to collect data and accurately model traffic processes. This study aims to develop a predictive model of traffic density at Tanjung Emas port loading terminals using a discrete simulation methods quantitative approach . The results showed that the resulting traffic density prediction model has high accuracy and can be used as a predictive tool to assist decision-making in optimizing port loading terminal operations.


INTRODUCTION
Ports are important infrastructure in the global transportation and trade system.The port serves as the main gateway in connecting various types of cargo and cargo with sea transportation routes.Operational efficiency and port performance are crucial to ensure the smooth flow of goods and logistics services (Agustiningsih, 2023).
One of the key aspects in the operational efficiency of the port is traffic management at the manufacturing terminal (Indraprakoso, 2023).Traffic at ports is often complex because it involves different types of vehicles, containers, and cargo moving simultaneously.Traffic congestion at loading terminals can be a serious obstacle in carrying out smooth and timely operations, which can ultimately lead to delays in the loading and unloading process, increased operational costs, and decreased customer satisfaction.
To address these challenges, research and development of traffic density prediction models at port loading terminals is becoming increasingly important.Accurate predictive models can provide a clear view of the expected traffic situation in the future and enable port managers to take appropriate precautions and optimize traffic flow.
In recent years, discrete simulation methods have become one of the popular approaches to modeling and analyzing complex traffic systems.Discrete simulations allow researchers to model each entity in the system (such as vehicles, containers, and infrastructure) individually, and thus make it possible to evaluate various scenarios under realistic conditions.The quantitative approach in collecting data and analyzing simulation results also provides a high level of accuracy in predicting traffic density at ports (Tasikduatondok, 2020).
Amid the increasing complexity of transport and logistics systems, the need for more advanced technologies and methodologies in managing traffic at ports is increasingly urgent such as ship passenger service system with Boarding Pass (Hadiana & Hermanto, 2020).The use of information technology, such as discrete simulation, has proven effective in modeling and analyzing complex traffic systems, especially in constantly changing and unpredictable environments (Sopha & Sakti, 2021).Previous research has involved discrete simulations in the context of traffic management for a variety of applications, including highway, airport, and container terminal traffic.However, the use of discrete simulation methods to overcome the problem of traffic congestion at port loading terminals is still limited and has not been explored much.
In this context, this study aims to develop a predictive model of traffic density at Tanjung Emas port loading terminals using discrete simulation methods quantitative approach (Kurniati et al., 2022).The resulting model is expected to be an effective predictive tool in helping port managers to identify potential bottlenecks and take appropriate action to address the problem.Thus, this research contributes to improving the operational efficiency of port loading terminals and ultimately improving the overall performance of Tanjung Emas ports.
In addition, this research can also provide practical benefits by improving port operational efficiency and reducing excessive operational costs due to traffic congestion.The results of this study are expected to be widely applied in various ports and loading terminals, with certain adjustments depending on the characteristics and scale of operation of each port.Finally, the journal presents the results of experiments and validation of prediction models using actual data from Tanjung Emas port loading terminals.It is hoped that the results of this study will encourage the use of discrete simulation methods in further applications in the field of transportation and logistics, as well as inspire further research in optimizing operational efficiency in the port sector.Thus, this research has the potential to make a valuable contribution in facing challenges and opportunities in the ever-evolving world of transportation and commerce.
In this study, the actual data obtained from the Tanjung Emas port loading terminal will be used to test the validity and accuracy of the proposed prediction model.It is hoped that the results of this study will provide valuable insights for researchers and practitioners in the field of transportation and logistics, and can pave the way for further research in this field.Thus, this research has the potential to make a positive contribution in technology development and improvement of operational efficiency in the maritime and port industry (Malisan et al., 2021).

METHOD
In this context, this study proposes a quantitative approach using discrete simulations to predict traffic density at Tanjung Emas port loading terminals.By combining quantitative aspects of data collection and analysis, this study aims to create an accurate and reliable model to predict traffic at loading terminals with various scenarios (Wibowo, 2022).
The advantage of this approach is its ability to integrate various variables that affect traffic at the port, including cargo volume, ship arrival time, loading and unloading schedules, and machine efficiency (Jinca, 2019).Thus, this predictive model is expected to provide a more holistic understanding of the traffic situation at port loading terminals and provide valuable insights for decision makers in creating optimal strategies to manage traffic more effectively.
The advantage of this approach is its ability to integrate various variables that affect traffic at the port, including cargo volume, ship arrival time, loading and unloading schedules, and machine efficiency (Jinca, 2019).Thus, this predictive model is expected to provide a more holistic understanding of the traffic situation at port loading terminals and provide valuable insights for decision makers in creating optimal strategies to manage traffic more effectively.
The data collected in this research includes historical traffic data gathered from the Tanjung Emas port loading terminal, by identifying relevant variables such as cargo volume per hour, ship loading and unloading times, the number of vehicles moving on specific routes, and traffic flow speed.Additionally, data on ship arrival and departure times, container handling, and other traffic data were also collected for further analysis.Subsequently, a descriptive statistical analysis was conducted, where the collected data was statistically analyzed to identify traffic patterns and trends within various time intervals.Descriptive statistical data such as mean, median, and standard deviation were used to provide an overview of traffic characteristics at the Tanjung Emas port loading terminal.
Next, a regression analysis was performed to determine the quantitative relationship between independent variables (e.g., cargo volume and loading/unloading time) and the dependent variable (traffic density).A regression model was built based on historical data, and the resulting regression coefficients provided information about the level of influence of each independent variable on traffic density.Following that, model validation and simulation development were carried out.A discrete-event simulation model was implemented to run simulations based on predefined data and parameters.The simulation generated predictions about traffic density at the Tanjung Emas port loading terminal under various operational scenarios.An analysis of sensitivity was conducted to assess the extent to which changes in key variables (such as cargo volume or loading/unloading time) could impact traffic density.The next step involved the application of the simulation prediction model as a decision-support tool at the Tanjung Emas port loading terminal.The final step was evaluation and improvement.The prediction model was periodically evaluated by comparing its predictions with actual data obtained from the Tanjung Emas port loading terminal.Based on feedback and evaluation results, the model could be enhanced to improve accuracy and relevance in predicting traffic density.

Result
The results of this study produced a traffic density prediction model at the Tanjung Emas Port Loading Terminal based on a discrete simulation method with a quantitative approach.This model can project the level of traffic density at the terminal based on certain relevant variables, such as cargo volume, ship loading and unloading time, the number of vehicles moving in a particular lane, and other influential variables (Prabowo et al., 2020).The use of discrete simulation methods in this study allows the model to describe the traffic system at the Tanjung Emas port loading terminal as a series of entities that interact with each other in discrete time.Thus, the model can reflect the complex and dynamic traffic situation at the port terminal more realistically.
The resulting prediction model has been tested and validated using actual data or historical data from the Tanjung Emas port loading terminal (Fahrianto, n.d.).This helps measure the level of accuracy and validity of the model in predicting traffic density.If the model shows consistent results close to the actual data, it indicates that the model has a high level of accuracy and can be relied upon as a predictive tool to anticipate traffic congestion levels at the terminal.In addition, the results of this study also highlight the factors that affect traffic density at Tanjung Emas port loading terminals.The variables that have a significant influence on traffic density are identified through regression analysis and discrete simulations (Pratama, 2019).For example, it can be identified that an increase in cargo volume has an impact on increasing traffic density, or that inefficient scheduling in loading and unloading ships can lead to higher density.
The results of this study provide valuable insights for Tanjung Emas port loading terminal managers in operational decision making.By utilizing this predictive model, they can plan and allocate resources more efficiently to optimize traffic flow at terminals.This can help reduce waiting time, prevent congestion, and improve the overall efficiency of loading terminal operations.In addition, the results of this study also make an important contribution in the field of transportation and logistics research.Traffic density prediction models developed using discrete simulation methods, quantitative approaches can be a reference for further research in the development of technologies and methodologies to optimize traffic systems at ports and other transportation infrastructure.This research can be the foundation for future research that is more sophisticated and more precise in understanding and addressing traffic problems in various transportation facilities.
The results of the sensitivity analysis will provide valuable information for terminal managers in making decisions related to operational arrangements.They can identify those areas that are most vulnerable to traffic congestion and focus on efforts to manage and reduce congestion levels in those areas.For example, if the enhancement n cargo volume has a significant impact on density, so terminal managers can anticipate increased volume by increasing loading and unloading capacity and implementing more efficient traffic management strategies (Mahyuddin et al., 2021).In addition, the results of this study can also provide suggestions and recommendations for improvement and optimization of traffic density prediction models.Although this model has produced satisfactory results, there is always room for improvement and improvement.Researchers can analyze model performance in various operational scenarios and evaluate whether the model is suitable for application in more complex situations or with different parameters.
The discussion of this research will discuss the implications of the findings on the operational management of Tanjung Emas port loading terminals.This section will discuss how these predictive models can be used to inform day-to-day decisions in managing traffic at terminals.In addition, researchers will also discuss the limitations of the model that has been developed and how it can affect the level of accuracy and validity of predictions.In a broader context, the discussion of this research will also place this predictive model in the perspective of the port and transportation industry as a whole.In the face of rapid economic and trade growth, port loading terminal managers need to face the challenge of improving operational efficiency and ensuring the smooth flow of goods and cargo.This predictive model can be an important tool in achieving these goals and increasing the competitiveness of Tanjung Emas port loading terminals at the global level.
Finally, the discussion section will also highlight the contribution of this research to the field of transportation and logistics science.By developing predictive models using discrete simulation methods of quantitative approaches, this research provides a foundation for further research in optimizing traffic systems in various transportation and logistics facilities.This research can inspire the development of new technologies and methodologies to address the complex challenges of managing traffic across a variety of operational environments.
Practical Implications: The results of this study have significant practical implications for Tanjung Emas port loading terminal managers.With an accurate traffic density prediction model, managers can use this tool as a guide to make strategic decisions in operational planning.Some of the practical implications of the study include: 1.More Efficient Loading and Unloading Schedule Planning: Predictive models can assist terminal managers in determining more efficient ship and truck loading and unloading schedules.By projecting traffic density at any given time, managers can avoid overlapping operations and ensure a smooth loading and unloading process.
2. Optimal Resource Allocation: Based on traffic density predictions, terminal managers can allocate resources such as personnel, heavy equipment, and facilities more effectively.This will help in avoiding the occurrence of lack or excess of resources that can affect operational productivity.3. Prevention of Congestion and Time Deviations: Predictive models can help identify potential traffic jams in a particular area and anticipate them by taking appropriate preventive measures.In addition, the model can also help reduce time deviations in the loading and unloading process, thereby improving the overall efficiency of the terminal.4. Improved Customer Service: By using predictive models, terminal managers can improve customer service by providing more accurate information about waiting times and loading and unloading.This will help customers better plan their logistics activities and reduce uncertainty.
Prediction Model Implementation: To implement this prediction model in the operational environment of Tanjung Emas port loading terminal, several steps can be followed: 1.Data Integration: Collection of relevant and quality data is key to implementing predictive models successfully.Operational data from terminals, historical traffic data, and real-time data must be well integrated in order for the model to have a solid foundation in projections.2. Use of Technology: Predictive models can be implemented using computer technology and appropriate simulation software.The use of advanced technology will facilitate data management and processing and run simulations efficiently.

Training and Deployment:
The terminal management team needs to be trained in correctly using predictive models and understanding the results generated.This model should be integrated into the terminal's decision-making process and routine operational planning.4. Evaluation and Update: Predictive models should be evaluated periodically to ensure their accuracy and relevance remain up-to-date.Changes in operational conditions or the external environment can affect model performance, so updates and upgrades are needed as needed.

Discussion
In the discussion of this study, the focus will be on the implications and evaluation of the prediction results generated by the traffic density prediction model at the Tanjung Emas port loading terminal (Ghani, 2022).Researchers will conduct an in-depth analysis of the model's performance to assess the extent to which it is reliable and relevant in predicting traffic density.First of all, the researcher will collect predictive data from the model for various time periods and operational situations at the terminal.The data from this prediction will be compared with the actual data that has been collected from the Tanjung Emas port loading terminal.Thus, researchers can measure the extent to which the model's predicted results approach or match the reality of traffic at the terminal.
Analysis of the accuracy and validity of the model will be performed using various evaluation metrics.One commonly used metric is the Mean Absolute Percentage Error (MAPE), which calculates the percentage difference between a prediction result and the actual data (Anam & Jakaria, 2023).In addition, the coefficient of determination (R-squared) can also be used to measure how well variations in data can actually be explained by predictive models.If the evaluation results show that the model has a high level of accuracy and can produce predictions close to the actual data, this will provide strong evidence of the reliability of the prediction model.The model is likely to be relied upon as a tool for Tanjung Emas port loading terminal managers in making more effective operational decisions and planning.
However, researchers will also acknowledge the limitations and assumptions used in model development.No prediction model is perfect, and there is always uncertainty associated with future predictions based on historical data.Therefore, in the discussion, the researcher will note areas where the model may have difficulties or need improvement.In addition, changes in operational and environmental conditions can also affect model performance.Therefore, the discussion will also discuss the importance of updating and improving the model regularly to maintain its accuracy and relevance.The discussion may also include comparisons with previous research that has been done in the field of traffic density prediction.By comparing the results of this study with similar studies, researchers can demonstrate the unique contribution of this study and the advantages of the methods used.
Overall, the discussion will provide a comprehensive overview of the reliability of the prediction model and the implications of its results in the context of managing Tanjung Emas port loading terminals.This research will make a valuable contribution to the improvement of terminal operational efficiency and performance, as well as serve as a foundation for further research in the development of more sophisticated and appropriate predictive models.
The discussion of this study will cover other important aspects that will be discussed by researchers related to prediction results and their application in the context of Tanjung Emas port loading terminals.

1.
Error Rate and Uncertainty: In addition to measuring model accuracy with metrics such as MAPE and R-squared, the discussion will also delve deeper into error rates and uncertainty in prediction results.Researchers will find out if there are specific patterns in model prediction errors and how certain factors can contribute to prediction uncertainty.Being aware of this level of uncertainty will help terminal managers deal with risks and plan more adaptive strategies.2.
Evaluation of Alternative Scenarios: In the discussion, the researcher can also propose and evaluate several alternative scenarios in the operation of the terminal.For example, they can compare traffic density predictions in scenarios with additional capacity, or changes in loading and unloading schedules.This will help the terminal manager in making the right decision and identifying the most optimal solution.3.
Relevance to Long-Term Planning: The discussion will also discuss how the results of these predictions can contribute to the long-term planning of Tanjung Emas port loading terminals.By having reliable predictive models, terminal managers can integrate these prediction results into their strategic planning, such as the development of additional infrastructure or investment in more advanced technology.4.
Implementation and Integration in Terminal Management Systems: In addition to discussing model performance, researchers will also discuss challenges and opportunities in implementing this predictive model in the Tanjung Emas port loading terminal management system.The integration of the model in existing management systems and terminal software can be a key factor in generating tangible benefits from this model.

5.
Validity for Different Time Scales: The discussion may also involve an evaluation of the extent to which this model is valid for different time scales.For example, whether the model is suitable for predicting traffic density on a daily, weekly, or monthly scale.The model's ability to provide traffic projections across multiple timescales adds flexibility and utility to predictive models.6.
Economic and Environmental Benefits: In addition to discussing operational benefits, discussions can also evaluate the economic and environmental implications of appropriate prediction results.
Reduced lead times and optimal density levels can contribute to cost efficiency and reduce negative environmental impacts, such as greenhouse gas emissions.
In conclusion, the discussion of this study will describe comprehensively about the value and benefits of traffic density prediction models at Tanjung Emas port loading terminals.The implications of reliable and relevant predictive results in operational decision making and long-term planning will contribute significantly to terminal efficiency and performance.The results could also encourage further research in the field of traffic prediction and inspire the development of more innovative and effective solutions in managing traffic at other transportation facilities and ports.1.
Validation with Future Data: In the discussion, researchers can also discuss how this predictive model can be tested and validated with future data that has never been used in model development.
By testing the model with future data, it will be able to gauge how well it is able to deal with unprecedented situations.Validation with future data can also provide more information about the robustness of the model and how relevant the predicted results are for long-term use.

2.
Effect of Operational Policy: The discussion will also explore the effect of operational policy on traffic density at the terminal.For example, how changes in the loading and unloading prioritization system can affect density levels.By understanding the effect of these policies, terminal managers can design policies that are more effective in managing traffic.

3.
Data and Model Limitations: The discussion will also discuss the limitations of the data used in this study and how these limitations can affect the results and conclusions of the study.In addition, researchers will also identify the limitations of the models used and provide suggestions for the development of more sophisticated and appropriate models in the future.Comparison with Other Methods: The discussion will also present a comparison between the discrete simulation method of quantitative approaches used in this study with other methods that may be used in traffic density prediction.For example, does this model provide better results than linear regression methods or other predictive models.5.
Use of Models in Strategic Decisions: In addition to operational applications, the discussion will also explore the use of these models in long-term strategic decision making.For example, how this model can be used to plan terminal infrastructure expansion or assess the impact of future trade growth.6.
Contribution to Knowledge: The discussion will highlight the contribution of this research to knowledge and scientific literature in the field of transportation and logistics.The prediction models developed and research methodologies used can be valuable contributions to the development of knowledge in traffic management and transport infrastructure.7.
Relevance in Other Industries: In addition to port loading terminals, the discussion may also discuss the relevance of this predictive model in other industries such as other ports, airports, or other transportation facilities facing similar traffic problems.8.
Research Replication: The discussion will also discuss the possible replication of this research at other port loading locations or terminals.The extent to which these predictive models can be adapted and applied in different operational environments will be an important consideration.
Overall, the discussion of this study will provide a deep understanding of the results and implications of traffic density prediction models at Tanjung Emas port loading terminals.By exploring various relevant aspects and contexts, the discussion will make a significant contribution in facing the challenges of traffic management in complex and dynamic operational environments (Marfai, 2019).

CONCLUSION
The conclusion of this study is that the traffic density prediction model at the Tanjung Emas Port Loading Terminal using discrete simulation method, quantitative approach has great potential to be an effective tool in optimizing terminal operational performance.The results showed that this model can provide traffic density projections that are close to or match the actual data, indicating a high degree of accuracy.The implications of these prediction results are very relevant and useful for terminal managers in planning and making operational decisions.This predictive model can be used to plan more efficient loading and unloading schedules, allocate resources more precisely, and avoid bottlenecks that can disrupt traffic flow at terminals.Thus, the use of this predictive model can increase efficiency, reduce operational costs, and improve customer service.
However, it is important to remember that these predictive models also have limitations.Uncertainties and errors in predictions remain, especially when faced with unprecedented situations or significant external changes.Therefore, terminal managers need to be aware of this level of uncertainty and plan adaptive strategies.For the future, this research makes an important contribution to the field of transportation and logistics.The discrete simulation method, the quantitative approach used in this study, can be the basis for the development of more sophisticated and more appropriate predictive models in managing traffic in various transportation facilities and ports.This research can also encourage further research to optimize traffic systems and improve the efficiency of transportation infrastructure.
In conclusion, the traffic density prediction model at the Tanjung Emas Port Loading Terminal using a discrete simulation method quantitative approach has the potential to be a useful tool for terminal managers in optimizing operational performance.Despite its limitations, this model makes an important contribution to the understanding and management of traffic in complex operational environments.By continuing research and development, these predictive models can become a valuable resource for the transportation and logistics industry as a whole.

Table 1 .
Daily Traffic Data:

Table 3 .
Monthly Traffic Data: