Simulation-driven port water area traffic flow prediction scheduling optimization method and system

Abstract

The invention belongs to the technical field of port water area traffic optimization, and particularly relates to a simulation-driven port water area traffic flow prediction scheduling optimization method and system, and the method comprises the steps: obtaining the flow data, environment data and equipment state data of a port water area; predicting based on the historical flow data and the historical environment data to obtain a long-term prediction result; predicting based on the flow data, the environment data and the equipment state data to obtain a short-term prediction result; and initializing a scene and a reference plan of a simulation model based on the long-term prediction result, and enabling the simulation model to dynamically adjust and optimize the ship based on the short-term prediction result and the reference plan in the operation process. According to the method, the traffic prediction level of the port water area can be driven through the simulation technology, and dynamic scheduling is carried out in combination with real-time data.

Description

Technical Field

[0001] This invention belongs to the field of port waterway traffic optimization technology, and in particular relates to a simulation-driven port waterway traffic flow prediction, scheduling and optimization method and system. Background Technology

[0002] With the continued growth of global trade and the expanding demand for container shipping, port waterway transportation is facing increasing pressure, especially small and medium-sized container terminals, which face greater challenges in traffic organization and relatively scarce berth and equipment resources, requiring them to face greater pressure in traffic forecasting and scheduling under dynamic conditions.

[0003] Traditional port scheduling methods often rely on manual experience or rule-based scheduling, which cannot adapt to the dynamic changes in the port environment in real time, leading to a series of problems such as ship congestion, low loading and unloading efficiency, and waste of equipment resources.

[0004] While some studies have used simulation technology to optimize container terminal yards and loading / unloading equipment, research on dynamic prediction and intelligent scheduling of port waterway traffic flow remains relatively limited. Existing technologies typically focus on optimizing individual aspects, such as yard layout or the scheduling of single equipment, lacking a comprehensive consideration of the overall port waterway traffic flow. This is particularly true for small and medium-sized container terminals, which, due to limited facilities and budgets, urgently require a method or system that can achieve global optimization and improve operational efficiency through simulation technology. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a simulation-driven method and system for predicting and optimizing traffic flow in port waterways. This method and system can drive the traffic prediction level of port waterways through simulation technology and perform dynamic scheduling in conjunction with real-time data.

[0006] The first aspect of this invention provides a simulation-driven method for predicting and optimizing traffic flow in port waterways, comprising: Acquire flow data, environmental data, and equipment status data of the port waters, wherein the flow data includes at least historical flow data and real-time flow data, and the environmental data includes at least historical environmental data and real-time environmental data; Long-term prediction results are obtained based on the historical traffic data and the historical environmental data. Short-term prediction results are obtained based on the real-time traffic data, the real-time environmental data, and the device status data. The simulation model is initialized with a scenario and baseline plan based on the long-term forecast results, and the simulation model is dynamically adjusted and optimized for the ship based on the short-term forecast results and the baseline plan during operation.

[0007] Optionally, in the traffic data, the historical traffic data includes at least ship arrival data within a preset historical time range; the real-time traffic data includes at least real-time ship arrival data occurring within a unit of time; and the ship arrival data includes at least container throughput and the number of ships arriving.

[0008] Optionally, the historical environmental data includes at least statistical meteorological and hydrological data within a preset historical time range; the real-time environmental data includes at least real-time flow meteorological and hydrological monitoring data and early warning signals occurring within a unit of time.

[0009] Optionally, the step of obtaining long-term prediction results based on the historical traffic data and the historical environmental data includes: A seasonal ARIMA model is established using historical traffic data. The seasonal ARIMA model is ARIMA(p,d,q)(P,D,Q)s, where p is the non-seasonal autoregressive order; d is the non-seasonal differencing order; q is the non-seasonal moving average order; P is the seasonal autoregressive order; D is the seasonal differencing order; Q is the seasonal moving average order; and s is the seasonal period. The model building process includes: Historical traffic data is converted into a raw time series Yt; the raw time series is then stabilized to obtain a stabilized series; the stabilization process includes at least d-order non-seasonal difference and D-order seasonal difference; Based on the stationary sequence, the model parameters p, q, P and Q are determined, and the model parameters are fitted by the maximum likelihood estimation method; based on the fitted seasonal ARIMA model, the container throughput and / or ship arrivals within the first preset time range are predicted. Output long-term prediction results.

[0010] Optionally, the step of stabilizing the original time series to obtain a stabilized series includes: First, perform D-order seasonal differencing: , where B is the shift operator; Then, perform d-th order non-seasonal differencing to obtain the stationary sequence Wt: .

[0011] Optionally, determining the model parameters includes: The autocorrelation function and partial autocorrelation function of the stationary sequence Wt are calculated respectively, and the parameters are determined by analyzing the characteristics of the function graphs, where: For non-seasonal parameters (p, q): By observing the characteristics of the PACF plot at non-seasonal lag orders (lag=1,2,3...), if the PACF is truncated after lag p, the non-seasonal autoregressive order is determined to be p. By observing the characteristics of the ACF plot at the non-seasonal lag order, if the ACF is truncated after a lag of q, the order of the non-seasonal moving average is determined to be q. For seasonal parameters (P, Q): By observing the characteristics of the PACF plot at seasonal lag orders (lag=s,2s,3s...), if the PACF is truncated after a seasonal lag of P×s, the seasonal autoregressive order is determined to be P. By observing the characteristics of the ACF plot at the seasonal lag order, if the ACF is truncated after a seasonal lag of Q×s, the seasonal moving average order is determined to be Q.

[0012] Optionally, the short-term prediction result is obtained based on the real-time traffic data, the real-time environmental data, and the equipment status data; the prediction result within each unit time period in the second preset time range is the container throughput and / or ship arrivals, including: The real-time traffic data, the real-time environmental data, and the device status data are preprocessed, including normalization and sliding window processing. The preprocessed data is input into a pre-trained LSTM neural network model; The LSTM neural network model outputs short-term traffic prediction results for a second preset time range in the future.

[0013] Optionally, the pre-trained LSTM neural network model includes: Environmental sensing gating unit and equipment status sensing unit; wherein: The environmental perception gating unit is implemented by introducing an environmental factor weight vector into the input gate calculation of the LSTM; The device state sensing unit is implemented by introducing a device state influence factor into the input gate calculation of the LSTM.

[0014] Optionally, during the simulation model's operation, the ship is dynamically adjusted and optimized based on the short-term forecast results and the baseline plan, including: Based on the container throughput forecast value output by the short-term forecast, a resource elastic allocation mechanism is established using predefined resource objects in Flexsim CT. When the projected container throughput exceeds the baseline plan, the Flexsim CT simulator automatically initiates and evaluates standby equipment scheduling schemes, reallocating port resources to ensure that operational capacity matches projected demand.

[0015] A second aspect of the present invention provides a simulation-driven port waterway traffic flow prediction, scheduling, and optimization system, comprising: The data acquisition module is used to acquire at least the flow data, environmental data, and equipment status data of the port waters, wherein the flow data includes at least historical flow data and real-time flow data, and the environmental data includes at least historical environmental data and real-time environmental data; The long-term prediction module is at least used to predict long-term prediction results based on the historical traffic data and the historical environmental data. The short-term prediction module is at least used to predict short-term prediction results based on the real-time traffic data, the real-time environmental data, and the device status data. The simulation scheduling module is used at least to initialize the scenario and baseline plan of the simulation model based on the long-term prediction results, and to enable the simulation model to dynamically adjust and optimize the ship based on the short-term prediction results and the baseline plan during operation. Attached Figure Description

[0016] Figure 1 A flowchart illustrating a simulation-driven port waterway traffic flow prediction and scheduling optimization method according to an embodiment of this application is shown.

[0017] Figure 2 The diagram illustrates a flowchart of a long-term prediction method in a simulation-driven port waterway traffic flow prediction and scheduling optimization method according to an embodiment of this application.

[0018] Figure 3 The diagram illustrates the process of generating a baseline plan in a simulation-driven port waterway traffic flow prediction and scheduling optimization method according to an embodiment of this application.

[0019] Figure 4 A block diagram of a simulation-driven port waterway traffic flow prediction, scheduling, and optimization system is shown in one embodiment of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] like Figure 1 As shown, the first aspect of the present invention provides a simulation-driven method for predicting and optimizing port waterway traffic flow, comprising the following steps.

[0022] Step S100: Obtain flow data, environmental data, and equipment status data of the port waters, wherein the flow data includes at least historical flow data and real-time flow data, and the environmental data includes at least historical environmental data and real-time environmental data.

[0023] Step S200: Based on the historical traffic data and the historical environmental data, a long-term prediction result is obtained.

[0024] Specifically, the long-term forecast results are obtained by predicting the container throughput and / or ship arrivals within a first preset time range using the historical traffic data and the historical environmental data.

[0025] Step S300: Based on the real-time traffic data, the real-time environmental data, and the device status data, a short-term prediction result is obtained.

[0026] Specifically, the short-term forecast results are the forecast results for each unit time period within the second preset time range, namely container throughput and / or ship arrivals.

[0027] Step S400: Initialize the scenario and baseline plan of the simulation model based on the long-term prediction results, and enable the simulation model to dynamically adjust and optimize the ship based on the short-term prediction results and the baseline plan during operation.

[0028] Here, the present invention obtains long-term and short-term forecast results based on historical and real-time data. The long-term forecast results are used as a benchmark plan for the overall strategic implementation, while the short-term forecast results are used to predict the current situation in real time, enabling timely prediction of dynamic adjustments and optimizations for ships. This approach can meet the real-time operational needs of ships and has higher operating efficiency in some small and medium-sized terminals, improving their intelligence level. Furthermore, through simulation models, it can intelligently allocate berthing positions and operating times for each ship, optimize the order of ship entry into port and operating time, and avoid berth conflicts and operational delays.

[0029] In one embodiment of the present invention, the historical traffic data includes at least ship arrival data within a preset historical time range. The real-time traffic data includes at least real-time ship arrival data occurring within a unit of time; the ship arrival data includes at least container throughput and the number of ships arriving.

[0030] Specifically, the preset historical time period can be, for example, 3 years of ship arrival data, and the real-time traffic data can be, for example, ship arrival data occurring within 12 hours or within 1 hour.

[0031] In one embodiment of the present invention, the historical environmental data includes at least statistical meteorological and hydrological data within a preset historical time range; the real-time environmental data includes at least real-time flow meteorological and hydrological monitoring data, early warning signals, and short-term forecast data occurring within a unit of time.

[0032] Specifically, the preset historical time period can be, for example, 3 years of statistical meteorological and hydrological data, which can be divided according to seasons to facilitate subsequent understanding of seasonal historical patterns; the real-time flow data can be, for example, real-time flow meteorological and hydrological monitoring data, early warning signals and short-term forecast data that occurred in the past 2 hours.

[0033] Specifically, the Autoregressive Integrated Moving Average (ARIMA) model is a model that excels at capturing trends in data. In the application scenario of this invention, port waterway traffic flow is affected by long-term trends, periodic fluctuations, and seasonal fluctuations, which can be effectively captured by the ARIMA model.

[0034] like Figure 2 As shown, in one embodiment of the present invention, the step of obtaining a long-term prediction result based on the historical traffic data and the historical environmental data includes: A seasonal ARIMA model is established using historical traffic data. The seasonal ARIMA model is ARIMA(p,d,q)(P,D,Q)s, where p is the non-seasonal autoregressive order; d is the non-seasonal differencing order; q is the non-seasonal moving average order; P is the seasonal autoregressive order; D is the seasonal differencing order; Q is the seasonal moving average order; and s is the seasonal cycle.

[0035] Specifically, the model building process includes: Historical traffic data is converted into a raw time series Yt; the raw time series is then stabilized to obtain a stabilized series; the stabilization process includes at least d-order non-seasonal difference and D-order seasonal difference; Based on the stationary sequence, the model parameters p, q, P and Q are determined, and the model parameters are fitted by the maximum likelihood estimation method; based on the fitted seasonal ARIMA model, the container throughput and / or ship arrivals within the first preset time range are predicted. Output long-term prediction results.

[0036] Specifically, the step of stabilizing the original time series to obtain a stabilized series includes: First, perform D-order seasonal differencing: , where B is the shift operator; Then, perform d-th order non-seasonal differencing to obtain the stationary sequence Wt: .

[0037] Specifically, this invention achieves series stationarity by performing seasonal and non-seasonal differencing on the original time series. It should be noted that the reason for performing seasonal differencing first, followed by non-seasonal differencing, is that seasonality is usually a significant factor affecting stationarity, and its fluctuations can largely mask subtle trend fluctuations. Therefore, seasonal differencing is performed first to smooth out the peaks and troughs of each year or season; thus, the value of s can be s=12 or s=3. Then, non-seasonal differencing, i.e., trend differencing, is performed to smooth out some long-term unidirectional trends, thereby obtaining a stationary series.

[0038] Specifically, the determination of the model parameters includes: The autocorrelation function and partial autocorrelation function of the stationary sequence Wt are calculated respectively, and the parameters are determined by analyzing the characteristics of the function graphs, where: For non-seasonal parameters (p, q): By observing the characteristics of the PACF plot at non-seasonal lag orders (lag=1,2,3...), if the PACF is truncated after lag p, the non-seasonal autoregressive order is determined to be p. By observing the characteristics of the ACF plot at the non-seasonal lag order, if the ACF is truncated after a lag of q, the order of the non-seasonal moving average is determined to be q. For seasonal parameters (P, Q): By observing the characteristics of the PACF plot at seasonal lag orders (lag=s, 2s, 3s...), if the PACF is truncated after a seasonal lag of P×s, the seasonal autoregressive order is determined to be P. By observing the characteristics of the ACF plot at the seasonal lag order, if the ACF is truncated after a seasonal lag of Q×s, the seasonal moving average order is determined to be Q.

[0039] This approach allows for the generation of long-term forecasts using ARIMA models that take into account seasonality, such as data from several future periods, like months, quarters, or years.

[0040] In one embodiment of the present invention, the short-term prediction result is obtained based on the real-time traffic data, the real-time environmental data, and the equipment status data; the prediction result within each unit time period of the second preset time range is the container throughput and / or ship arrivals, including: The real-time traffic data, the real-time environmental data, and the device status data are preprocessed, including normalization and sliding window processing. The preprocessed data is input into a pre-trained LSTM neural network model; The LSTM neural network model outputs short-term traffic prediction results for a second preset time range in the future.

[0041] In one embodiment of the present invention, the pre-trained LSTM neural network model includes: Environmental sensing gating unit and equipment status sensing unit; wherein: The environmental perception gating unit is implemented by introducing an environmental factor weight vector into the input gate calculation of the LSTM; The device state sensing unit is implemented by introducing a device state influence factor into the input gate calculation of the LSTM.

[0042] Specifically, based on actual conditions, this invention introduces an environmental factor weight vector into the input gate calculation of LSTM. The environmental factor weight vector is constructed with reference to real-time environmental data, such as wind speed and tides.

[0043] Specifically, based on actual conditions, this invention also considers introducing a device state influence factor in the forget gate calculation of LSTM. The device state influence factor is constructed with reference to the device state vector, such as considering the quay crane fault state and the operating load rate.

[0044] Those skilled in the art will know that introducing new vectors or factors into LSTM can more closely approximate the situation mentioned in this invention, which combines the current equipment status and environmental conditions to predict fluctuations in ship arrival data in the next few hours, thus helping port managers to adjust resource allocation in a timely manner and make up for the shortcomings of the original model.

[0045] like Figure 3 As shown, in one embodiment of the present invention, Flexsim CT is used as a simulation model, and the scenario of the simulation model is initialized based on the long-term prediction results to obtain a baseline plan.

[0046] Specifically, since the long-term forecast results include container throughput and / or ship arrivals over a certain period of time, the results can be divided into corresponding baseline plans, including berth allocation baselines, resource planning baselines, and yard planning baselines. The berth allocation baseline is obtained by laying out the predicted arrivals over time, the resource planning baseline is obtained by calculating the required resource and equipment quantities based on the total container throughput, and the yard calculation baseline is used to further estimate the required yard capacity based on the predicted container throughput.

[0047] In one embodiment of the present invention, the simulation model dynamically adjusts and optimizes the ship based on the short-term forecast results and the baseline plan during operation, including: Based on the container throughput forecast value output by the short-term forecast, a resource elastic allocation mechanism is established using predefined resource objects such as quay cranes, yard cranes and container trucks in Flexsim CT. When the projected container throughput exceeds the baseline plan, the Flexsim CT simulator automatically initiates and evaluates standby equipment scheduling schemes, reallocating port resources to ensure that operational capacity matches projected demand.

[0048] This approach allows for the dynamic adjustment of long-term and short-term forecasts through simulation models. The baseline plan obtained from long-term forecasts is simulated, and the short-term forecasts are incorporated into the simulation model for adjustment. This ensures the rationality of port resource allocation, ultimately achieving global optimization of port waterway traffic, improving traffic forecasting and scheduling capabilities, and enhancing terminal operation efficiency.

[0049] like Figure 4 As shown, a second aspect of the present invention provides a simulation-driven port waterway traffic flow prediction, scheduling, and optimization system, comprising: The data acquisition module is used to acquire at least the flow data, environmental data, and equipment status data of the port waters, wherein the flow data includes at least historical flow data and real-time flow data, and the environmental data includes at least historical environmental data and real-time environmental data; The long-term forecasting module is used at least to predict long-term forecast results based on the historical traffic data and the historical environmental data. The forecast results within the first preset time range are container throughput and / or ship arrivals. The short-term forecasting module is used at least to predict short-term forecast results based on the real-time traffic data, the real-time environmental data, and the equipment status data; the forecast results for each unit time within the second preset time range are container throughput and / or ship arrivals. The simulation scheduling module is used at least to initialize the simulation model scenario based on the long-term prediction results and obtain the baseline plan, and to enable the simulation model to dynamically adjust and optimize the ship based on the short-term prediction results and the baseline plan during operation.

[0050] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure. As used in this disclosure and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this disclosure and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0051] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0052] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0053] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A simulation-driven method for predicting and optimizing traffic flow in port waterways, characterized in that, include: Acquire flow data, environmental data, and equipment status data of the port waters, wherein the flow data includes at least historical flow data and real-time flow data, and the environmental data includes at least historical environmental data and real-time environmental data; Long-term prediction results are obtained based on the historical traffic data and the historical environmental data. Short-term prediction results are obtained based on the real-time traffic data, the real-time environmental data, and the device status data. The simulation model is initialized based on the long-term forecast results to obtain a baseline plan, and the simulation model is dynamically adjusted and optimized for the ship based on the short-term forecast results and the baseline plan during operation.

2. The simulation-driven port waterway traffic flow prediction and scheduling optimization method according to claim 1, characterized in that, The historical traffic data includes at least ship arrival data within a preset historical time range; the real-time traffic data includes at least real-time ship arrival data occurring within a unit of time; and the ship arrival data includes at least container throughput and the number of ships arriving.

3. The simulation-driven port waterway traffic flow prediction and scheduling optimization method according to claim 1, characterized in that, The environmental data includes, in part, historical environmental data, statistical meteorological and hydrological data within a preset historical time range; and real-time flow data, including, in part, real-time flow meteorological and hydrological monitoring data, early warning signals, and short-term forecast data occurring within a unit of time.

4. The simulation-driven port waterway traffic flow prediction and scheduling optimization method according to claim 1, characterized in that, The long-term prediction results obtained based on the historical traffic data and the historical environmental data include: A seasonal ARIMA model is established using historical traffic data. The seasonal ARIMA model is ARIMA(p,d,q)(P,D,Q)s, where p is the non-seasonal autoregressive order; d is the non-seasonal differencing order; q is the non-seasonal moving average order; P is the seasonal autoregressive order; D is the seasonal differencing order; Q is the seasonal moving average order; and s is the seasonal period. The model building process includes: Historical traffic data is converted into a raw time series Yt; the raw time series is then stabilized to obtain a stabilized series; the stabilization process includes at least d-order non-seasonal difference and D-order seasonal difference; Based on the stationary sequence, the model parameters p, q, P and Q are determined, and the model parameters are fitted by the maximum likelihood estimation method; based on the fitted seasonal ARIMA model, the container throughput and / or ship arrivals within the first preset time range are predicted. Output long-term prediction results.

5. The simulation-driven port waterway traffic flow prediction and scheduling optimization method according to claim 4, characterized in that, The step of stabilizing the original time series to obtain a stabilized series includes: First, perform D-order seasonal differencing: , where B is the shift operator; Then, perform d-th order non-seasonal differencing to obtain the stationary sequence Wt: .

6. The simulation-driven port waterway traffic flow prediction and scheduling optimization method according to claim 5, characterized in that, The determination of the model parameters includes: The autocorrelation function and partial autocorrelation function of the stationary sequence Wt are calculated respectively, and the parameters are determined by analyzing the characteristics of the function graphs, where: For non-seasonal parameters (p, q): By observing the characteristics of the PACF plot at the non-seasonal lag order, if the PACF is truncated after lag p, the non-seasonal autoregressive order is determined to be p. By observing the characteristics of the ACF plot at the non-seasonal lag order, if the ACF is truncated after a lag of q, the order of the non-seasonal moving average is determined to be q. For seasonal parameters (P, Q): By observing the characteristics of the PACF plot at the seasonal lag order, if the PACF is truncated after the seasonal lag order P×s, the seasonal autoregressive order is determined to be P. By observing the characteristics of the ACF plot at the seasonal lag order, if the ACF is truncated after a seasonal lag of Q×s, the seasonal moving average order is determined to be Q.

7. The simulation-driven port waterway traffic flow prediction and scheduling optimization method according to claim 1, characterized in that, The method of obtaining short-term prediction results based on the real-time traffic data, the real-time environmental data, and the device status data includes: The real-time traffic data, the real-time environmental data, and the device status data are preprocessed, including normalization and sliding window processing. The preprocessed data is input into a pre-trained LSTM neural network model; The LSTM neural network model outputs short-term traffic prediction results for a second preset time range in the future.

8. The simulation-driven port waterway traffic flow prediction and scheduling optimization method according to claim 7, characterized in that, The pre-trained LSTM neural network model includes: Environmental sensing gating unit and equipment status sensing unit; wherein: The environmental perception gating unit is implemented by introducing an environmental factor weight vector into the input gate calculation of the LSTM; The device state sensing unit is implemented by introducing a device state influence factor into the input gate calculation of the LSTM.

9. The simulation-driven port waterway traffic flow prediction and scheduling optimization method according to claim 1, characterized in that, During operation, the simulation model dynamically adjusts and optimizes the ship based on the short-term forecast results and the baseline plan, including: Based on the container throughput forecast output of the short-term forecast, a resource elastic allocation mechanism is established using predefined resource objects such as quay cranes, yard cranes and container trucks in Flexsim CT. When the projected container throughput exceeds the baseline plan, the Flexsim CT simulator automatically initiates and evaluates standby equipment scheduling schemes, reallocating port resources to ensure that operational capacity matches projected demand.

10. A simulation-driven port waterway traffic flow prediction, scheduling, and optimization system, characterized in that, include: The data acquisition unit is used to acquire at least the flow data, environmental data, and equipment status data of the port waters, wherein the flow data includes at least historical flow data and real-time flow data, and the environmental data includes at least historical environmental data and real-time environmental data; The long-term forecasting unit is used at least to predict long-term forecast results based on the historical flow data and the historical environmental data. The forecast results within the first preset time range are container throughput and / or ship arrivals. The short-term forecasting unit is used at least to predict short-term forecast results based on the real-time traffic data, the real-time environmental data, and the equipment status data; the forecast results for each unit time within a second preset time range are container throughput and / or ship arrivals. The simulation adjustment unit is used at least to initialize the simulation model scenario based on the long-term prediction results and obtain the baseline plan, and to enable the simulation model to dynamically adjust and optimize the ship based on the short-term prediction results and the baseline plan during operation.

Images