Wharf mobile charging pile allocation method based on dynamic voyage number scheduling

Abstract

The invention discloses a wharf mobile charging pile allocation method based on dynamic voyage number scheduling, and belongs to the technical field of port intelligent scheduling. The method comprises the steps that a dynamic voyage number arrival prediction model is constructed based on a prediction control algorithm, and the ship arrival time is predicted through rolling optimization in combination with the real-time state of a ship and external environment factors; constructing a charging pile real-time optimal allocation model, and generating a charging pile allocation scheme by adopting an optimization algorithm according to the predicted arrival time, the charging pile state and the ship charging demand; and real-time distribution and dynamic adjustment of the charging piles are realized. The method can effectively improve the utilization rate of the charging pile, shortens the ship charging waiting time, improves the overall operation efficiency of a wharf, and adapts to a complex and changeable port operation environment.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of port intelligent scheduling, and particularly relates to a wharf mobile charging pile deployment method based on dynamic voyage scheduling BACKGROUND With the increasing environmental protection requirements and the continuous development of new energy technology, many ships have begun to use electric drive, and the demand for charging at the wharf has increased significantly. During the operation of the wharf, the arrangement of ship voyages is dynamic and uncertain, and the arrival time, stay duration and charging demand of ships under different voyages are different. The traditional charging pile deployment method relies on experience or fixed plan, and cannot deploy the charging pile in real time and accurately according to the dynamic voyage information of the ship. This results in low utilization rate of charging piles, long waiting time for charging of some ships, and serious impact on the operation efficiency and service quality of the wharf. In addition, the existing voyage arrival prediction technology mostly uses simple statistical method or prediction model based on fixed rules. Various complex factors such as weather changes, channel congestion and ship failures are difficult to be accurately captured, so they cannot provide reliable basis for charging pile deployment. Therefore, it is necessary to design a wharf mobile charging pile deployment method based on dynamic voyage scheduling to solve the above problems. SUMMARY

[0002] The purpose of the present application is to provide a mobile charging pile allocation method based on dynamic voyage scheduling, which uses a predictive control algorithm to predict the arrival time of a dynamic voyage, in order to solve the problems of low utilization rate of charging piles, long waiting time of ships and inflexible scheduling in the prior art.

[0003] To achieve the above purpose, the technical solution adopted by the present application is as follows: A wharf mobile charging pile deployment method based on dynamic voyage scheduling, comprising the following steps: constructing a dynamic voyage arrival prediction model based on a predictive control algorithm to predict the arrival time of a ship; constructing a real-time optimal deployment model of charging piles to generate a charging pile allocation scheme according to the predicted arrival time, the state of the charging pile and the charging demand of the ship; realizing real-time allocation and dynamic adjustment of the charging pile.

[0004] Preferably, the dynamic voyage arrival prediction model is constructed based on a ship motion equation, combined with real-time state data of the ship and external environment data.

[0005] Preferably, the external environment data includes at least one of wind speed, wind direction, sea state and channel congestion degree.

[0006] Preferably, the predictive control algorithm uses a rolling optimization method to update the prediction model and recalculate the arrival time within a set time interval.

[0007] Preferably, the charging pile real-time optimal allocation model takes minimizing ship waiting time and maximizing charging pile utilization as the optimization objective.

[0008] Preferably, the allocation model adopts a genetic algorithm or a simulated annealing algorithm for solution.

[0009] Preferably, the charging pile state includes at least one of position, idle state, charging power, and remaining power.

[0010] Preferably, the ship charging demand includes at least one of ship type, battery capacity, current power, required charging power, and estimated charging duration.

[0011] Preferably, when the actual arrival time of the ship or the charging demand changes, the system recalculates and adjusts the charging pile allocation scheme.

[0012] Preferably, an electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the dynamic voyage scheduling-based wharf mobile charging pile allocation method when executing the computer program.

[0013] The beneficial effects of the present application are: 1. By adopting a real-time optimal allocation strategy based on dynamic voyage arrival prediction, charging station resources can be reasonably allocated according to the actual needs of ships and their arrival times. This can avoid the situation of idle charging stations and resource waste, thereby significantly improving the utilization rate of charging stations.

[0014] 2. By combining accurate voyage arrival prediction and timely allocation of charging stations, ships can start charging faster once they arrive at the port, thereby reducing charging waiting time. This helps to improve the operational efficiency of ships and reduce operating costs.

[0015] 3. The efficient charging station allocation strategy helps to optimize the resource allocation of the port. The time of ships staying in the port will be shortened, and the throughput of the port will be increased. Once the competitiveness of the port is improved, it can provide strong support for its sustainable development.

[0016] 4. The invention adopts a predictive control algorithm and a dynamic allocation strategy. Various complex factors such as weather changes and shipping route congestion will be fully considered to assess their impact on voyage and charging demand. It has strong adaptability and stability and can still maintain good performance in complex and variable port operating environments. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The allocation technology flowchart of the present application. DETAILED DESCRIPTION

[0018] Example One: As Figure 1 shown, a method for deploying mobile charging piles at a port based on dynamic voyage scheduling, comprising the following steps: A dynamic voyage arrival prediction model is constructed based on a predictive control algorithm to predict the arrival time of a ship; An optimal real-time deployment model for charging piles is constructed to generate a charging pile allocation scheme based on the predicted arrival time, charging pile status, and ship charging demand; Real-time allocation and dynamic adjustment of charging piles are achieved.

[0019] Preferably, the dynamic voyage arrival prediction model is constructed based on a ship motion equation, combined with real-time state data of the ship and external environmental data.

[0020] Preferably, the external environmental data includes at least one of wind speed, wind direction, sea state, and channel congestion level.

[0021] Preferably, the predictive control algorithm uses a rolling optimization method to update the prediction model and recalculate the arrival time within a set time interval.

[0022] Preferably, the optimal real-time deployment model for charging piles aims to minimize ship waiting time and maximize charging pile utilization.

[0023] Preferably, the deployment model uses a genetic algorithm or simulated annealing algorithm for solution.

[0024] Preferably, the charging pile status includes at least one of position, idle state, charging power, and remaining capacity.

[0025] Preferably, the ship charging demand includes at least one of ship type, battery capacity, current capacity, required charging capacity, and estimated charging duration.

[0026] Preferably, when the actual arrival time of the ship or the charging demand changes, the system recalculates and adjusts the charging pile allocation scheme.

[0027] Preferably, an electronic device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the method for deploying mobile charging piles at a port based on dynamic voyage scheduling.

[0028] Embodiment two: Further, the dynamic voyage arrival prediction based on the predictive control algorithm is as follows: In terms of data collection and preprocessing: Relevant data on past ship voyages is collected, including departure point, destination, estimated voyage time, actual voyage time, ports of call, and dwell time. Simultaneously, real-time information on the ship's current position, as well as real-time data such as speed, wind direction, wind speed, sea state, and channel congestion, are collected. The collected data is cleaned and preprocessed, removing outliers and missing values, and standardizing and unifying data from different formats for use in subsequent predictive models. In the model building phase: A dynamic navigation arrival prediction model is constructed using predictive control algorithms. Predictive control algorithms are a control strategy based on model prediction and rolling optimization, fully considering the dynamic characteristics of the system and future constraints.

[0029] In this embodiment, the ship's equation of motion is used as the basic model, and a predictive model is constructed by combining the ship's real-time state and external environmental factors. For example, based on information such as the ship's speed, heading, wind direction, wind speed, and water current speed, the ship's position and travel time in the next time period can be predicted. Simultaneously, past navigation data is used to train the model and optimize parameters to improve the model's predictive accuracy.

[0030] Rolling optimization and predictive update section: The predictive control algorithm employs a rolling optimization method, as follows: At specific time intervals, the prediction model is updated based on the latest collected data, and the arrival times of ships in the next time period are recalculated. Each update considers not only the current state and environmental information but also various uncertainties that may arise in the future, such as weather changes and temporary restrictions on shipping routes. By reasonably estimating these factors, the prediction results are continuously adjusted to ensure the accuracy and real-time nature of the forecast.

[0031] 2. Set up a real-time optimal allocation strategy for charging stations based on dynamic voyage arrival predictions: Regarding charging pile status monitoring and data collection: Real-time monitoring of the status of all mobile charging piles at the dock is required, including information such as the location of the charging pile, whether it is idle, its charging power, and the remaining battery level. Furthermore, information related to ship charging needs must be collected, such as the ship's type, battery capacity, current battery level, required charging amount, and estimated charging time.

[0032] The deployment model construction link is as follows: to shorten the ship waiting time for charging as much as possible and maximize the utilization rate of charging piles, a real-time optimal deployment model of charging piles is constructed. This model takes into account factors such as dynamic voyage arrival time of ships, charging pile status, and ship charging demand. For example, when new ship voyage information is updated, based on the predicted arrival time and the ship's charging demand, combined with the current charging pile idle condition and other ship charging plans, optimization algorithms such as genetic algorithm and simulated annealing algorithm are used to calculate the optimal charging pile deployment scheme, and each ship is assigned to a charging pile and the charging start and end time.

[0033] The real-time allocation and dynamic adjustment workflow is as follows: according to the pre-set allocation model, real-time allocation and adjustment of charging piles are carried out. When a ship arrives at the port or new voyage information changes, the system will immediately recalculate the allocation scheme and adjust the allocation of charging piles according to the new scheme. For example, if a ship arrives at the port ahead of schedule, the system will refer to the current use of charging piles and prioritize the allocation of idle charging piles for charging; if the charging demand of a ship changes, the system will re-evaluate the allocation scheme and adjust the charging plans of other ships to ensure the overall optimal state. At the same time, the system will promptly inform the port management personnel and crew of the allocation results so that they can promptly understand the charging arrangement.

[0034] Embodiment three: This embodiment provides a dynamic voyage arrival prediction implementation process based on a predictive control algorithm, and the specific process is as follows: 1. Data collection: In a certain port, real-time information of past ships can be obtained through an automatic identification system AIS, such as their position, speed, and heading. At the same time, past voyage data of ships departing from the port is retrieved from the port management system, including the departure port, destination port, planned voyage time, and actual voyage time, etc. Take a container ship departing from Shanghai Port to Ningbo Port as an example. The voyage data shows that the planned voyage time is 12 hours, and the historical average voyage time is between 11.5 and 12.5 hours. During the voyage, real-time collected data shows that the wind speed is 5 to 8 meters per second, the wind direction is southeast, and the sea condition is good.

[0035] 2. Model construction and training phase: Using a predictive control algorithm, and based on the ship motion equations, the real-time collected data is combined with historical sailing data to build a prediction model. By training with a large amount of historical sailing data, the parameters in the model can be determined, such as the speed correction coefficient of the ship under different wind speed, wind direction and sea conditions. For example, after training, it is found that under the current wind speed and wind direction conditions, the speed of this container ship will be 3% higher than the standard speed.

[0036] 3. Rolling optimization and predictive update part: The prediction model is updated every 15 minutes based on the latest collected data. Once the wind direction suddenly changes to south and the wind speed increases to 10 meters per second during the ship's voyage, the system immediately updates the data and recalculates the ship's estimated arrival time at Ningbo Port. After rolling optimization and prediction, it is found that the container ship will arrive at Ningbo Port 30 minutes later than originally planned.

[0037] Example Four: This embodiment provides a method for real-time optimal deployment of charging piles based on dynamic voyage arrival prediction. The specific process is as follows: 1. Charging pile and ship information collection: The port is equipped with 10 mobile charging stations. The status of each charging station must be monitored in real time, such as whether it is idle, whether it is charging, or the charging power, etc. In addition, the charging demand information of the ships arriving at the port should also be collected. For example, a bulk carrier has a battery capacity of 5000 degrees, and its current charging level is 2000 degrees. Therefore, it needs to be charged for 3000 degrees, and the estimated charging time is 6 hours.

[0038] 2. Deployment model construction and operation: When constructing the real-time optimal deployment model of charging piles, two goals are pursued: one is to minimize the waiting time for charging, and the other is to maximize the utilization rate of charging piles. When there are multiple ships approaching the port, the predicted arrival time and charging demand of each ship can be used, combined with the current charging pile status, to calculate the optimal deployment scheme using a genetic algorithm. For example, there are two ships approaching the port, one is the bulk carrier mentioned earlier, which is expected to arrive in 3 hours; the other is an oil tanker, which is expected to arrive in 4 hours, with a battery capacity of 8000 degrees, a current power of 3000 degrees, and a need for charging of 5000 degrees, with an estimated charging time of 8 hours. After the deployment model calculation, an idle charging pile will be reserved for the bulk carrier 1 hour before its arrival, and an idle charging pile will be reserved for the oil tanker 2 hours before its arrival.

[0039] 3. Real-time deployment and dynamic adjustment: If the actual arrival time of a ship is different from the predicted time, the system recalculates the schedule immediately. For example, if a bulk carrier arrives 30 minutes earlier than predicted, the system finds that a charging station is available at the time of the bulk carrier's arrival, and the system adjusts the schedule to have the bulk carrier use the charging station. The system also reevaluates the schedule for the oil tanker to ensure that the entire schedule is optimal.

Claims

1. A method for allocating mobile charging piles at docks based on dynamic voyage scheduling, characterized in that, Includes the following steps: A dynamic voyage arrival prediction model is constructed based on predictive control algorithms to predict the arrival time of ships. Construct a real-time optimal allocation model for charging piles, and generate a charging pile allocation plan based on the predicted arrival time, charging pile status and ship charging demand. Real-time allocation and dynamic adjustment of charging piles.

2. The method for allocating mobile charging piles at docks based on dynamic voyage scheduling according to claim 1, characterized in that, The dynamic voyage arrival prediction model is constructed based on the ship's motion equations, combined with real-time ship status data and external environment data.

3. The method for allocating mobile charging piles at docks based on dynamic voyage scheduling according to claim 2, characterized in that, The external environmental data includes at least one of wind speed, wind direction, sea state, and channel congestion.

4. The method for allocating mobile charging piles at docks based on dynamic voyage scheduling according to claim 1, characterized in that, The predictive control algorithm employs a rolling optimization method, updating the predictive model and recalculating the arrival time within a set time interval.

5. The method for allocating mobile charging piles at docks based on dynamic voyage scheduling according to claim 1, characterized in that, The real-time optimal allocation model for charging piles aims to minimize ship waiting time and maximize charging pile utilization.

6. A method for allocating mobile charging piles at docks based on dynamic voyage scheduling according to claim 5, characterized in that, The matching model is solved using a genetic algorithm or a simulated annealing algorithm.

7. The method for allocating mobile charging piles at docks based on dynamic voyage scheduling according to claim 1, characterized in that, The status of the charging pile includes at least one of location, idle status, charging power, and remaining power.

8. A method for allocating mobile charging piles at docks based on dynamic voyage scheduling according to claim 1, characterized in that, The ship charging requirements include at least one of the following: ship type, battery capacity, current battery level, required charging amount, and estimated charging time.

9. A method for allocating mobile charging piles at docks based on dynamic voyage scheduling according to claim 1, characterized in that, When the actual arrival time of a ship or its charging needs change, the system recalculates and adjusts the charging pile allocation scheme.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements a method for allocating mobile charging piles at a dock based on dynamic voyage scheduling as described in any one of claims 1 to 9.

Images