Port scheduling method and device, electronic equipment and readable storage medium

Abstract

The invention provides a port scheduling method and device, electronic equipment and a readable storage medium, and belongs to the field of marine traffic, and the method comprises the steps: obtaining historical port ship data and real-time port ship data, constructing a port route micro-network according to the historical port ship data, and transmitting the port route micro-network to a server; according to the historical port ship data and the port route micro network, performing node association degree analysis on the anchoring ground and the berths to obtain a node association degree set; and constructing a port scheduling optimization model according to the real-time port ship data, the port route micro-network and the node association degree set, and solving the port scheduling optimization model to obtain a port scheduling optimization strategy. According to the method, node correlation analysis is carried out on the anchoring ground and the berths through the port micro-network and historical port ship data, the correlation among the port channel, the anchoring ground and the berths can be effectively captured and used for port scheduling strategy optimization, and then the planning effect of port scheduling is improved.

Description

Technical Field

[0001] The present invention relates to the field of marine traffic technology, and in particular to a port scheduling method, device, electronic equipment and readable storage medium. Background Art

[0002] Channels, anchorages, berths and other facilities are key water resources supporting port operations. With the prosperity of port trade, the volume of ship traffic continues to rise, the traffic situation in port waters is complex, and the safety issues between ships and port water resources cannot be ignored. Fully and rationally utilizing port water resources is the basis for ensuring the safety of ships entering and leaving the port, berthing and unberthing operations, and improving port operation efficiency.

[0003] In traditional port scheduling, the berthing positions of ships entering the port are usually planned manually based on the current availability of berths, but the timeliness of manual planning is poor, and it is difficult to make the most reasonable plan for ships entering the port. For some intelligent ports, the route nodes are formed into a complex route network by points and lines, and each ship entering the port is planned through optimization algorithms. However, in actual port scheduling and planning operations, for example, when choosing a berth for a ship anchored at a certain anchorage, it is often more inclined to choose a certain berth or several berths according to the actual situation of the port. There is a correlation between anchorages and berths in actual scheduling. The existing optimization algorithms are only based on theory, and often do not consider the correlation between port channels, anchorages and berths in actual operations. Therefore, it is difficult for the existing optimization algorithms to obtain the optimal port scheduling strategy in practice, and they need to be improved.

[0004] Therefore, the existing technology does not consider the correlation between port channels, anchorages and berths in actual operations, making it difficult to obtain the optimal port scheduling strategy, which needs to be improved. Summary of the invention

[0005] In view of this, it is necessary to provide a port scheduling method, device, electronic device and readable storage medium to solve the technical problems existing in the prior art, that is, the correlation between port channels, anchorages and berths in actual operations is not considered, and it is difficult to obtain the actual optimal port scheduling strategy.

[0006] In order to solve the above technical problems, on the one hand, the present invention provides a port scheduling method, comprising: Obtain historical port ship data and real-time port ship data, build a port route micro-network based on the historical port ship data, and perform node correlation analysis on anchorages and berths based on the historical port ship data and the port route micro-network to obtain a node correlation set; A port scheduling optimization model is constructed based on real-time port ship data, port route micro-network and node association set, and the port scheduling optimization strategy is obtained by solving the port scheduling optimization model.

[0007] In a possible implementation, the historical port ship data includes ship berthing data, ship navigation data and navigation mark position information.

[0008] In one possible implementation, a port route micro-network is constructed based on historical port ship data, including: Determine the anchorage node based on the navigation mark position information; Perform trajectory clustering and boundary extraction on the ship trajectory data to obtain the berth geometric area of ​​each berth, and determine the berth node according to the berth geometric area; Construct a set of anchorage point position sequences based on the ship trajectory data, and determine the node connection edges of the port route micro-network based on the anchorage point position sequence set, anchorage nodes and berth nodes; A port route micro-network is constructed based on anchorage nodes, berth nodes and node connection edges.

[0009] In a possible implementation, node association analysis is performed on anchorages and berths based on historical port ship data and port route micro-network to obtain a node association set, including: Determine the number of ship trajectories from each anchorage to each berth based on ship navigation data and port route micro-network, and determine the support and support ranking set between nodes of each anchorage and berth based on the number of ship trajectories; Determine the berthing ratio from each anchorage to each berth according to the ship navigation data and the port route micro-network, and determine the confidence and confidence ranking set between nodes of each anchorage and berth according to the berthing ratio; The associated node set of each berth is determined according to the support sorting set and the confidence sorting set.

[0010] In one possible implementation, a port scheduling optimization model is constructed based on real-time port ship data, port route micro-network and node association set, including: Determine decision variables and scheduling optimization objectives based on real-time port vessel data and port route micro-network; Determine the decision variable constraints based on the node association degree set; Determine the objective function constraints based on real-time port ship data and port route micro-network; A port scheduling optimization model is constructed based on decision variables, scheduling optimization objectives, decision variable constraints and objective function constraints.

[0011] In a possible implementation, the decision variable constraint condition is determined according to the node association degree set, including: Determine anchorage selection constraints based on node association degree sets; The speed constraint is determined according to a preset ship upstream speed and a preset ship downstream speed.

[0012] In a possible implementation, the port scheduling optimization model is solved to obtain the port scheduling optimization strategy, including: Construct the initial scheduling decision and candidate decision solution set according to the port scheduling optimization model; The initial scheduling decision is used as the initial population of the genetic algorithm, and the set of decision solutions to be selected is used as the candidate population. The initial population is iteratively optimized based on the genetic algorithm to obtain the port scheduling optimization strategy.

[0013] On the other hand, the present invention also provides a port dispatching device, comprising: A micro-network construction unit is used to obtain historical port ship data and real-time port ship data, construct a port route micro-network based on the historical port ship data, and perform node correlation analysis on anchorages and berths based on the historical port ship data and the port route micro-network to obtain a node correlation set; The scheduling optimization unit is used to construct a port scheduling optimization model based on real-time port ship data, port route micro-network and node association set, and solve the port scheduling optimization model to obtain the port scheduling optimization strategy.

[0014] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein: Memory for storing computer programs; The processor is coupled to the memory and is used to execute the computer program to implement the steps in the above-mentioned port scheduling method.

[0015] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned port scheduling method are implemented.

[0016] The beneficial effects of the present invention are as follows: the port scheduling method provided by the embodiment of the present invention first obtains historical port ship data and real-time port ship data, constructs a port route micro-network based on the historical port ship data, performs node correlation analysis on anchorages and berths based on the historical port ship data and the port route micro-network to obtain a set of associated nodes; then, a port scheduling optimization model is constructed based on the real-time port ship data, the port route micro-network and the set of associated nodes, and the port scheduling optimization model is solved to obtain a port scheduling optimization strategy. The present invention performs node correlation analysis on anchorages and berths through port micro-networks and historical port ship data, which can effectively capture the correlation between port channels, anchorages and berths, and use it in the optimization of port scheduling strategies, thereby improving the planning effect of port scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of a flow chart of an embodiment of a port scheduling method provided by the present invention; Figure 2 A schematic diagram of the process of constructing a port route micro-network according to an embodiment of the present invention; Figure 3 A schematic diagram of a process of node relevance analysis according to an embodiment of the present invention; Figure 4 A schematic diagram of a process for constructing a port scheduling optimization model according to an embodiment of the present invention; Figure 5 A schematic diagram of a process for determining a decision variable constraint condition according to an embodiment of the present invention; Figure 6 A schematic diagram of a process for solving a port scheduling optimization model according to an embodiment of the present invention; Figure 7 A schematic structural diagram of an embodiment of a port dispatching device provided by the present invention; Figure 8 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0021] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0022] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] Before presenting the embodiments, the following names are explained.

[0024] Port micro-network: refers to the information aggregation based on the historical port ship data of the port, abstracting the berths and anchorages in the port as nodes, and abstracting the port routes as edges, and constructing a simplified representation of the port channel-berth-anchorage micro-topological network.

[0025] The present invention provides a port scheduling method, device, electronic equipment and storage medium, which are respectively described below.

[0026] Figure 1 A flow chart of an embodiment of the port dispatching method provided by the present invention is as follows: Figure 1 As shown, the port scheduling method includes: S101, obtaining historical port ship data and real-time port ship data, constructing a port route micro-network based on the historical port ship data, and performing node correlation analysis on anchorages and berths based on the historical port ship data and the port route micro-network to obtain a set of correlated nodes; S102. Construct a port scheduling optimization model based on real-time port ship data, port route micro-network and associated node set, and solve the port scheduling optimization model to obtain a port scheduling optimization strategy.

[0027] Compared with the prior art, the port scheduling method provided by the embodiment of the present invention first obtains historical port ship data and real-time port ship data, constructs a port route micro-network based on the historical port ship data, performs node correlation analysis on anchorages and berths based on the historical port ship data and the port route micro-network to obtain a set of associated nodes; then, a port scheduling optimization model is constructed based on the real-time port ship data, the port route micro-network and the set of associated nodes, and the port scheduling optimization model is solved to obtain a port scheduling optimization strategy. The present invention performs node correlation analysis on anchorages and berths through port micro-networks and historical port ship data, which can effectively capture the correlation between port channels, anchorages and berths, and use it in the optimization of port scheduling strategies, thereby improving the planning effect of port scheduling.

[0028] In some embodiments of the present invention, the historical port ship data includes ship berthing data, ship navigation data and navigation mark position information.

[0029] Specifically, in order to construct a port route micro-network that can accurately describe the conditions of port channels, anchorages, and berths, it is necessary to obtain the historical port ship data of the port, including ship berthing data, ship navigation data, and navigation mark position information. The ship berthing data includes the position coordinates of each ship when it is berthed at the port, the ship navigation data includes the position coordinates of each ship in the process of sailing to the berth in the port area and the time label corresponding to each position coordinate, and the navigation mark position information includes the position coordinates of the navigation mark used to identify the anchorage water area in the port area.

[0030] In some embodiments of the present invention, Figure 2 FIG. 1 is a flow chart of constructing a port route micro-network according to an embodiment of the present invention. Figure 2 As shown in the figure, a port route micro-network is constructed based on historical port ship data, including: S201, determining the anchorage node according to the navigation mark position information; S202, performing trajectory clustering processing and boundary extraction on the ship trajectory data to obtain the berth geometric area of ​​each berth, and determining the berth node according to the berth geometric area; S203, constructing a set of anchorage point position sequences according to the ship trajectory data, and determining the node connection edges of the port route micro-network according to the anchorage point position sequence set, the anchorage node and the berth node; S204: construct a port route micro network based on anchorage nodes, berth nodes and node connection edges.

[0031] Specifically, the nodes of the port route micronetwork By anchor node and berth nodes Composition, edge Represented by the adjacency relationship of routes between berths and anchorages, the network construction process includes the determination of anchorage nodes, berth nodes and route edges.

[0032] In the embodiment, for an anchorage node, the range of the anchorage waters is usually identified by a dedicated navigation mark, so a set of anchorage waters ranges can be obtained according to the navigation mark position information. For any anchorage, its geometric center point is determined as an anchorage node.

[0033] For berth nodes, firstly, based on the ship trajectory data, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm is used to cluster the trajectories and obtain the trajectories of moored ships in the port waters. Then, the K-means (k-means clustering algorithm) clustering algorithm is used to cluster each segment of the moored ship trajectory, and the cluster center point is used as the berthing position point for each berthing of the ship. Then, the berthing position points located in the anchorage waters are eliminated, and the DBSCAN algorithm is further used to cluster the remaining berthing position point data to obtain a cluster cluster set. The last embodiment extracts the boundary of each cluster cluster set based on the convex hull algorithm to obtain the spatial geometric area range of the cluster, and obtains the geometric area belonging to the berth waters through area range matching and identification, and the center points of these geometric areas are determined as berth nodes.

[0034] For route edges, the example first initializes an empty Matrix as adjacency matrix ,in is the total number of nodes in the network. Then, the berthing positions of each ship are sorted in time series, and the corresponding node numbers are assigned to them based on the spatial analysis method to obtain the berthing position sequence set. According to the actual route conditions, the connection relationship between the berthing points and the route is determined through analysis. The connection relationship is mapped to the connection relationship between nodes and recorded in the adjacency matrix. Then, the berthing position sequence is iteratively analyzed to gradually improve the adjacency matrix. , to realize the extraction and storage of topological connection relations between nodes in the port route micro-network.

[0035] Finally, according to the constructed adjacency matrix, for any node in the adjacency matrix and nodes , if the node and nodes There is a connection relationship between the two nodes, indicating that there is an edge connecting the two nodes. The entire adjacency matrix is ​​traversed and all connected nodes are connected through topological edges to obtain the route micro-network represented by the topology.

[0036] In addition, for each edge, the direction and weight of the edge are analyzed in the route micro-network in the embodiment. The direction of the edge represents the direction of the ship from one node to another node, which is represented by an arrow in the route micro-network. The weight of the edge Expressed by the ship trajectory frequency, the formula is:

[0037] in, is the number of trajectories stored at the corresponding position in the adjacency matrix, indicating the node and nodes The number of ship tracks between For the node The total number of ship voyages to other nodes in the network.

[0038] In some embodiments of the present invention, Figure 3 FIG. 1 is a flow chart of node association analysis according to an embodiment of the present invention. Figure 3 As shown in the figure, based on the historical port ship data and the port route micro-network, the node correlation analysis of anchorages and berths is performed to obtain the associated node set, including: S301, determining the number of ship trajectories from each anchorage to each berth according to the ship navigation data and the port route micro-network, and determining the support degree and support degree ranking set between nodes of each anchorage and each berth according to the number of ship trajectories; S302, determining the berthing ratio from each anchorage to each berth according to the ship navigation data and the port route micro-network, and determining the confidence and confidence ranking set between the nodes of each anchorage and each berth according to the berthing ratio; S303: Determine the associated node set of each berth according to the support sorting set and the confidence sorting set.

[0039] Specifically, in general, the ship has determined the berth location to be berthed before arriving at the port. When the ship arrives at the port and the pre-berth berth is not vacant, the ship usually anchors in the anchorage and waits. The anchorage is selected by the driver based on experience and usually shows a certain tendency. This tendency reflects the potential association between different anchorages and the berth to be berthed, as well as the potential association between the port channel connecting the anchorage and the berth. For the route micro-network, the embodiment calculates the support between the network anchorage node and the berth node and confidence , which can measure the correlation between anchorage nodes and berth nodes, explore the correlation between different anchorages and planned berths, and provide support for port scheduling.

[0040] For any anchor node and berth nodes , the support between two nodes represents the anchorage Anchored berth Number of ships at anchor The ratio of the total number of ships berthing at the berths in the port micro-network after anchoring, where the number of ships can be obtained from the number of ship trajectories between nodes. The support calculation formula between nodes is expressed as:

[0041] in, Indicates anchor node With Berth Node The number of ship trajectories between is the number of trajectories stored in the corresponding position in the network adjacency matrix. Indicates anchor node The number of ship trajectories between all berth nodes that have a connection relationship, Indicates the anchor node in the network The number of berth nodes that have a connection relationship.

[0042] The higher the support between nodes, the more likely it is to be anchored at the anchorage. Ships are more likely to berth at berths . At the berth where the vessel intends to berth If the anchorage nodes are determined, the support ranking set of anchorage nodes associated with the berth and ranked according to the support calculation results is obtained through support calculation. , Used to indicate the berth in the network according to the support calculation results The number of associated anchorages.

[0043] For any anchor node and berth nodes , the confidence between two nodes represents the berth The ships berthing at the anchorage Number of anchorings, berth occupancy The ratio of the number of times all scheduled ships at berth dropped anchor. The number of times ships dropped anchor can also be obtained from the number of ship trajectories between nodes. The confidence calculation formula between nodes is expressed as follows:

[0044] in, Indicates berth node With anchorage node The number of ship tracks between Represents all anchor nodes to berth nodes in the network The number of ship tracks.

[0045] The higher the confidence between nodes, the closer the berth is. Ships have a greater tendency to choose anchorage Drop anchor. At the berth where the ship intends to berth In the case of confirmation, the confidence ranking set of anchorage nodes associated with the berth and ranked according to the confidence calculation results is obtained through confidence calculation , Indicates the berths in the network that are consistent with the proposed berths according to the confidence calculation results The number of associated anchorages.

[0046] Then , for any berth node in the route micro-network , we can get the anchor node set that is associated with it and sorted by the degree of association , the corresponding anchorage number is .

[0047] In some embodiments of the present invention, Figure 4 FIG. 1 is a flow chart of constructing a port scheduling optimization model according to an embodiment of the present invention. Figure 4 As shown in the figure, a port scheduling optimization model is constructed based on real-time port ship data, port route micro-network and node association set, including: S401, determining decision variables and scheduling optimization objectives based on real-time port ship data and port route micro-network; S402, determining decision variable constraints according to the node association degree set; S403, determining objective function constraints according to real-time port ship data and port route micro-network; S404: Construct a port scheduling optimization model according to decision variables, scheduling optimization objectives, decision variable constraints and objective function constraints.

[0048] In some embodiments of the present invention, Figure 5 FIG. 1 is a flow chart of determining the constraint conditions of decision variables according to an embodiment of the present invention. Figure 5 As shown, the decision variable constraints are determined according to the node association set, including: S501, determining anchorage selection constraints according to a node association degree set; S502: Determine a speed constraint according to a preset ship upstream speed and a preset ship downstream speed.

[0049] Specifically, in the process of port scheduling optimization, for a set of scheduled ships in the port , the set of berths that are considered reliable for each dispatched ship in the port is , the embodiment constructs and solves the port scheduling optimization model to optimize each ship to be scheduled in the set The scheduled scheduling plan.

[0050] In the process of constructing the port scheduling optimization model, the embodiment first needs to determine the decision variables and scheduling optimization objectives, where the decision variables include each ship to be scheduled Anchorage decision variables during in-port scheduling and the speed variables of the ship during navigation in the port The speed variable According to whether the ship needs to choose an anchorage to wait for berthing, it can be divided into the speed variable of the ship sailing from the port entry point to the anchorage or berth and the speed variable of the ship sailing from the anchorage to the berth .

[0051] According to the previous steps, the available anchorages in the port are , the corresponding anchorage number set is . Anchorage decision variables Expressed as ,in Indicates Ships to be dispatched The selected anchorage number set, and , the speed variable of the ship sailing from the port to the anchorage or berth Expressed as ; The speed variable of the ship sailing from the anchorage to the berth Expressed as .

[0052] Then the port scheduling optimization model takes the total sailing distance, total sailing time and total berthing time of the scheduled ships as the minimum scheduling optimization target, and the model is as follows:

[0053]

[0054]

[0055] in, Indicates the distance from the port entry point to the berth of the dispatched ship; Indicates from the port entry point to the berth Sailing time; Indicates the distance from the port of entry to the anchorage distance; Indicates the distance from the port of entry to the anchorage Sailing time; Indicates the sailing time from the anchorage to the berth; Indicates ship At anchor The duration of the mooring; Represents an indicator function used to check the status of the ship's assigned anchorage.

[0056] In the port scheduling optimization model, the ship's sailing time can be quantified by the ratio of distance to sailing speed, and the ship's berthing time can be quantified by the difference between the ship's anchoring end time and the ship's anchoring start time. The formula is expressed as:

[0057]

[0058] in, Indicates ship The average speed from the port to the anchorage or berth, It indicates the average sailing speed from anchorage to berth; Indicates the time to start anchoring; Indicates the moment of ending anchoring; Indicates ship Expected time of arrival at port; Indicate berth The estimated idle time is acceptable for vessel berthing operations.

[0059] After determining the decision variables and the scheduling optimization target, the embodiment also needs to determine the constraint conditions, wherein the decision conditions are divided into decision variable constraint conditions and other objective function constraint conditions.

[0060] Among them, the decision variable constraints include anchorage selection constraints and speed constraints. The anchorage selection constraint formula is expressed as:

[0061] The anchorage selection constraint indicates that for any ship to be dispatched, its anchorage selection should be obtained from the node association set in the previous step, and the solution of the anchorage decision variable is the number corresponding to the selected anchorage.

[0062] The speed constraint formula is expressed as:

[0063]

[0064] The speed constraint is used to define the upper and lower limits of the ship's speed. and Indicates the upper and lower speed constraints of upstream ships in the port, and Indicates the upper and lower speed constraints for downstream ships in the port. Indicates ship speed; Indicates ship i Entering the port location point, when Ship Go up to the port, Ship Go down to the port.

[0065] Other objective function constraints include anchorage type constraint, anchorage water depth constraint, ship berthing time constraint, berth status constraint and conflict constraint.

[0066] Among them, the anchorage type constraint formula is expressed as:

[0067] This constraint means that the ship should anchor in the corresponding type of anchorage. Indicates any ship to be dispatched Type, where ships are divided into two types: dangerous goods ships (which are marked as 1) and other types of ships (which are marked as 0); Indicates any anchorage Here, the anchorage is divided into two types: dangerous goods anchorage (which is marked as 1) and other types of anchorage (which is marked as 0).

[0068] The anchorage water depth constraint formula is expressed as:

[0069] This constraint means that the draft of the anchored ship should meet the requirements of the anchorage water depth. Indicates anchorage j Depth of water; Indicates ships to be dispatched draught; The surplus water depth is 0.5 m in the embodiment with reference to relevant specifications.

[0070] The ship berthing time constraint formula is expressed as:

[0071] This constraint means that a ship is considered to be anchored only when the time it stays in the anchorage is greater than the preset time threshold. Indicates the preset time threshold for a vessel to remain anchored at an anchorage.

[0072] The berth status constraint formula is expressed as:

[0073] This constraint means that the length of the berth where the ship intends to berth should meet the actual berthing needs. Indicates the proposed berth The idle length of Indicates the proposed berth Ships Length; Indicates the length of the berth where the ship intends to berth; Indicates the occupied length of the berth. It is 0 when there is no ship berthing at the berth.

[0074] The conflict constraint means that the distance between ships is not allowed to be too close. When three or more ships are too close in space at the same time during the navigation process, it is considered that there is a ship conflict. The embodiment regards the position of the ship at each time as a discrete point, and uses the DBSCAN clustering algorithm to detect whether there is a ship conflict in the channel at each time. That is, if three or more ships are too close in space at a certain time, it is considered that a conflict exists. In the application of the DBSCAN clustering algorithm, the minimum field radius is set , and set the minimum number of points MinPts within the area radius to 3.

[0075] In some embodiments of the present invention, Figure 6 FIG. 1 is a flow chart of solving the port scheduling optimization model according to an embodiment of the present invention, as shown in FIG. Figure 6 As shown in the figure, the port scheduling optimization model is solved to obtain the port scheduling optimization strategy, including: S601, constructing an initial scheduling decision and a candidate decision solution set according to the port scheduling optimization model; S602: Using the initial scheduling decision as the initial population of the genetic algorithm and the set of decision solutions to be selected as the candidate population, the initial population is iteratively optimized based on the genetic algorithm to obtain a port scheduling optimization strategy.

[0076] Specifically, after constructing the port dispatch optimization model, the embodiment uses a genetic algorithm to solve the optimization model. The decision variable solution set is expressed as , the optimized ship scheduling plan is expressed as .

[0077] In the genetic algorithm solution process, the embodiment constructs an initial scheduling decision and a candidate decision solution set according to the port scheduling optimization model, and then uses the initial scheduling decision as the initial population of the genetic algorithm, and uses the candidate decision solution set as the candidate population. The initial scheduling decision can be determined according to the node association set in the port scheduling optimization model, and the initial scheduling decision is constructed according to the anchorage with the highest association. In the iterative optimization process, the roulette method is used as the genetic algorithm selection strategy, the uniform crossover is used as the genetic algorithm crossover strategy, and the random reset mutation strategy is used as the genetic algorithm mutation strategy, and the initial population is iteratively optimized until the preset iteration round is reached or the result is no longer significantly optimized.

[0078] In summary, in order to capture and reasonably utilize the correlation between port channels, anchorages and berths in the process of port scheduling planning, the present invention constructs a route micro-network through historical port ship data, and analyzes the support and confidence between anchorages and nodes. The correlation between anchorages and berths and the correlation of the port channels connecting the two are determined according to the support and confidence between nodes, and the decision variable constraints are determined according to the obtained correlation. The port scheduling optimization strategy is solved under the constraint, which realizes the effective capture and utilization of the correlation between port channels, anchorages and berths, and effectively improves the planning effect of the scheduling strategy in port scheduling.

[0079] The present invention performs node correlation analysis on anchorages and berths through port micro-networks and historical port ship data, which can effectively capture the correlation between port channels, anchorages and berths and use it in the optimization of port scheduling strategies, thereby improving the planning effect of port scheduling.

[0080] In order to better implement the port dispatching method in the embodiment of the present invention, based on the port dispatching method, correspondingly, Figure 7 As shown, the present invention also provides a port dispatching device, the port dispatching device 700 includes: The micro-network construction unit 701 is used to obtain historical port ship data and real-time port ship data, construct a port route micro-network according to the historical port ship data, and perform node correlation analysis on anchorages and berths according to the historical port ship data and the port route micro-network to obtain a node correlation set; The scheduling optimization unit 702 is used to construct a port scheduling optimization model based on real-time port ship data, port route micro-network and node association set, and solve the port scheduling optimization model to obtain a port scheduling optimization strategy.

[0081] The port dispatching device 700 provided in the above embodiment can implement the technical solution described in the above port dispatching method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above port dispatching method embodiment, which will not be repeated here.

[0082] like Figure 8 As shown, the present invention also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802 and a display 803. Figure 8 Only some components of the electronic device 800 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0083] In some embodiments, the processor 801 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 802, such as the port scheduling method of the present invention.

[0084] In some embodiments, the processor 801 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 801 may be local or remote. In some embodiments, the processor 801 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0085] In some embodiments, the memory 802 may be an internal storage unit of the electronic device 800, such as a hard disk or memory of the electronic device 800. In other embodiments, the memory 802 may also be an external storage device of the electronic device 800, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 800.

[0086] Furthermore, the memory 802 may include both an internal storage unit of the electronic device 800 and an external storage device. The memory 802 is used to store application software installed in the electronic device 800 and various data.

[0087] In some embodiments, the display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 803 is used to display information of the electronic device 800 and to display a visual user interface. The components 801-803 of the electronic device 800 communicate with each other via a system bus.

[0088] In one embodiment, when the processor 801 executes the port scheduling program in the memory 802, the following steps may be implemented: Obtain historical port ship data and real-time port ship data, build a port route micro-network based on the historical port ship data, and perform node correlation analysis on anchorages and berths based on the historical port ship data and the port route micro-network to obtain a set of related nodes; A port scheduling optimization model is constructed based on real-time port ship data, port route micro-network and associated node sets, and the port scheduling optimization strategy is obtained by solving the port scheduling optimization model.

[0089] It should be understood that: when the processor 801 executes the port scheduling program in the memory 802, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0090] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 800 mentioned, and the electronic device 800 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 800 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0091] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions in the port scheduling method provided in the above-mentioned method embodiments can be implemented.

[0092] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0093] The port dispatching method, device, electronic device and storage medium provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A port dispatching method, characterized in that: include: Acquire historical port ship data and real-time port ship data, construct a port route micro-network according to the historical port ship data, and perform node correlation analysis on anchorages and berths according to the historical port ship data and the port route micro-network to obtain a node correlation set; A port scheduling optimization model is constructed according to the real-time port ship data, the port route micro-network and the node association degree set, and the port scheduling optimization model is solved to obtain a port scheduling optimization strategy.

2. The port dispatching method according to claim 1, characterized in that: The historical port ship data includes ship berthing data, ship navigation data and navigation mark position information.

3. The port dispatching method according to claim 2, characterized in that: The constructing of a port route micro-network according to the historical port ship data comprises: Determine the anchorage node according to the navigation mark position information; Performing trajectory clustering processing and boundary extraction on the ship trajectory data to obtain a berth geometric area of ​​each berth, and determining a berth node according to the berth geometric area; Constructing a set of anchorage point position sequences according to the ship trajectory data, and determining node connection edges of the port route micronetwork according to the anchorage point position sequence set, the anchorage node and the berth node; A port route micro network is constructed according to the anchorage nodes, the berth nodes and the node connection edges.

4. The port dispatching method according to claim 2, characterized in that: The node association degree set obtained by performing node association degree analysis on anchorages and berths according to the historical port ship data and the port route micro-network includes: Determine the number of ship trajectories from each anchorage to each berth according to the ship navigation data and the port route micro-network, and determine the support between nodes and the support ranking set of each anchorage and each berth according to the number of ship trajectories; Determine the berthing ratio of each anchorage to each berth according to the ship navigation data and the port route micro-network, and determine the confidence and confidence ranking set between nodes of each anchorage and each berth according to the berthing ratio; The associated node set of each berth is determined according to the support sorting set and the confidence sorting set.

5. The port dispatching method according to claim 1, characterized in that: The port scheduling optimization model is constructed according to the real-time port ship data, the port route micro-network and the node association set, including: Determine decision variables and scheduling optimization objectives according to the real-time port ship data and the port route micro-network; Determining decision variable constraints according to the node association degree set; Determining objective function constraints based on the real-time port ship data and the port route micro-network; A port scheduling optimization model is constructed according to the decision variables, the scheduling optimization objectives, the decision variable constraints and the objective function constraints.

6. The port dispatching method according to claim 5, characterized in that: The determining of the decision variable constraint conditions according to the node association degree set includes: Determining anchorage selection constraints according to the node association degree set; The speed constraint is determined according to a preset ship upstream speed and a preset ship downstream speed.

7. The port dispatching method according to claim 1, characterized in that: The port scheduling optimization model is solved to obtain the port scheduling optimization strategy, including: Constructing an initial scheduling decision and a candidate decision solution set according to the port scheduling optimization model; The initial scheduling decision is used as the initial population of the genetic algorithm, the decision solution set to be selected is used as the candidate population, and the initial population is iteratively optimized based on the genetic algorithm to obtain the port scheduling optimization strategy.

8. A port dispatching device, characterized in that: include: A micro-network construction unit is used to obtain historical port ship data and real-time port ship data, construct a port route micro-network according to the historical port ship data, and perform node correlation analysis on anchorages and berths according to the historical port ship data and the port route micro-network to obtain a node correlation set; The scheduling optimization unit is used to construct a port scheduling optimization model according to the real-time port ship data, the port route micro-network and the node association set, and solve the port scheduling optimization model to obtain a port scheduling optimization strategy.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store computer programs; The processor, coupled to the memory, is used to execute a computer program to implement the steps in the port scheduling method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the port scheduling method according to any one of claims 1 to 7 are implemented.

Images