Container shipping network climate adaptability recovery method fusing toughness theory

Abstract

The invention is suitable for the technical field of marine transportation, and provides a container marine transportation network climate adaptability recovery method fusing a toughness theory, and the method comprises the steps: obtaining liner plan data, ship dynamic data, route adjustment data, port geographic coordinate data and multi-scale geofence data, introducing time dimension parameters, and obtaining a time dimension parameter; a space-time weighted container shipping dynamic network is constructed; the cascading failure strength of the space-time weighted container shipping dynamic network is quantified, and then the comprehensive efficiency index of the space-time weighted container shipping dynamic network is calculated; quantifying a toughness index of the space-time weighted container shipping dynamic network under an extreme weather event; and the cost effectiveness of the climate suitability improvement strategy of the space-time weighted container shipping dynamic network is evaluated. According to the method, the influence mechanism of the extreme weather event on the network efficiency can be quantitatively analyzed, and the recovery capability and adaptability of the network under the extreme weather event can be comprehensively evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of maritime transportation, and specifically relates to a method for restoring the climate adaptability of a container maritime transportation network integrating resilience theory. Background Art

[0002] With the intensification of global climate change, the impact of extreme weather events (such as hurricanes, storm surges, floods, etc.) on container maritime transportation networks has become increasingly significant. The existing technologies mainly focus on the following aspects: 1. The impact of extreme weather events on ports and waterways: Existing research mainly focuses on the direct impact of extreme weather events on individual ports or waterways, such as the damage of port facilities and the blockage of waterways. 2. Vulnerability analysis of container maritime transportation networks: Some research has analyzed the vulnerability of container maritime transportation networks through complex network theory, pointing out that the robustness of container maritime transportation networks is weak, and small-scale attacks or natural disasters may lead to large-scale failures of the network. 3. Application of resilience theory: The application of resilience theory in the field of transportation has gradually increased, especially in urban traffic networks and highway networks. However, the research on the resilience of container maritime transportation networks is still in its infancy, and most existing research focuses on the theoretical level, lacking specific quantitative assessments and recovery strategies.

[0003] Existing research has shown that container ports are important infrastructure in China and important hubs of the comprehensive transportation system. Conducting research on the climate adaptability recovery strategy of container maritime transportation networks integrating resilience theory in China's coastal container ports is of great significance for enhancing the resilience of port infrastructure and implementing the requirements of green development.

[0004] Currently, (1) there is a lack of quantitative analysis of the impact mechanism of extreme weather events: Most existing research stays at the qualitative analysis level, lacking quantitative analysis of how extreme weather events affect the efficiency of container maritime transportation networks, especially the lack of research on network cascading effects. (2) The maritime transportation network resilience assessment system is imperfect: Existing research on the resilience assessment of container maritime transportation networks lacks systematicness and multi-dimensionality, and fails to fully consider the recovery ability and adaptability of the network under extreme weather events. (3) The implementation of recovery strategies is poor: Most of the recovery strategies proposed in existing research stay at the theoretical level, lacking practical operability and economic feasibility, and it is difficult to connect with the existing port and waterway plans. Therefore, it is necessary to provide a method for restoring the climate adaptability of a container maritime transportation network integrating resilience theory to solve the above problems. Summary of the Invention

[0005] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a method for restoring the climate adaptability of a container maritime transportation network integrating resilience theory to solve the problems in the above background art.

[0006] The present invention is implemented as follows. A method for restoring the climate adaptability of a container shipping network integrating resilience theory, the method comprising the following steps:

[0007] Obtain liner schedule data, ship dynamic data, route adjustment data, port geographical coordinate data, and multi-scale geographical fence data, and introduce a time dimension parameter to construct a spatio-temporal weighted container shipping dynamic network;

[0008] Quantify the strength of cascading failures of the spatio-temporal weighted container shipping dynamic network based on the cascading failure propagation model, and then calculate the comprehensive efficiency index of the spatio-temporal weighted container shipping dynamic network based on transportation timeliness, operation economy, and network robustness;

[0009] Quantify the resilience index of the spatio-temporal weighted container shipping dynamic network under extreme weather events based on the resilience triangle theory;

[0010] Evaluate the cost-benefit of the climate suitability improvement strategy of the spatio-temporal weighted container shipping dynamic network.

[0011] As a further solution of the present invention: The liner schedule data includes route codes, origin and destination ports, and shipping company names, and the ship dynamic data includes latitude and longitude coordinates, speed, heading, current status, and next port of call.

[0012] As a further solution of the present invention: In constructing the spatio-temporal weighted container shipping dynamic network, it further includes:

[0013] (1) First, perform traditional topology definition:

[0014] Node set: , where is the th ;

[0015] Edge set: , where is the starting point of , is the ending point of ;

[0016] Static weight: ;

[0017] (2) Secondly, perform time dimension expansion:

[0018] In the first step, discretize the time layer, and divide the continuous time axis into equally spaced time periods:

[0019]

[0020] where is the number of days;

[0021] Step 2: Construct a three-dimensional spatio-temporal network , where each spatio-temporal node is ;

[0022] Step 3: Define the spatio-temporal edge weight as a multi-dimensional vector :

[0023]

[0024] Where ; is during the time period actual sailing time; is during the time period liner frequency; is during the time period available shipping capacity;

[0025] (3) Thirdly, perform dynamic parameter quantization:

[0026] Step 1: Calculate the during the time period actual sailing time :

[0027]

[0028] Where is the distance, is the no-interference sailing speed; is wind and wave level coefficient during the time period; is actual route cost index during the time period; , are calibration parameters, is maximum route cost index during the time period;

[0029] Step 2: Calculate the during the time period liner frequency :

[0030]

[0031] Where is annual benchmark shift; is the seasonal fluctuation amplitude; is during the time period Temporary increase or decrease in shifts;

[0032] In the third step, calculate during the time period available shipping capacity :

[0033]

[0034] Among them, is the number of ships deployed within the time period; is the ship actual utilization rate in this voyage; is the ship rated container capacity; is the schedule reliability coefficient during the time period;

[0035] Based on the above steps, construct the described spatio-temporal weighted container shipping dynamic network, where the spatio-temporal weighted container shipping dynamic network is a physical layer network.

[0036] As a further solution of the present invention: In quantifying the strength of cascading failures of the spatio-temporal weighted container shipping dynamic network based on the cascading failure propagation model, it further includes:

[0037] (1) First, after the spatio-temporal weighted container shipping dynamic network is constructed, further construct a logical layer network , where the logical node is a set of cargo flow paths, representing the transportation path of goods from the starting point to the ending point; the logical edge is a set of shipping capacity scheduling relationships, representing the shipping capacity allocation or scheduling relationship between paths;

[0038] (2) Secondly, define the two-way influence factor between nodes:

[0039]

[0040] When the physical node fails, the load of the logical node will be interrupted in proportion to ;

[0041] (3) Thirdly, construct a cascading failure propagation model:

[0042] First, define the initial load: The load of the physical node is the weekly throughput of the port , and the load of the logical node is the shipping capacity demand of the path ;

[0043] When the node When it fails, its load is distributed according to the capacity ratio of adjacent nodes:

[0044]

[0045] Among them, is the newly added load of node ; is the distribution preference coefficient. When σ > 1, it is the node with a high preference degree; when σ < 1, it is the node with a low preference degree; is the transport capacity transfer efficiency, indicating the proportion of the load of the failed node transferred to adjacent nodes; is the original load of the failed node ; is the power of the degree of node , indicating the influence of node ; is the sum of the powers of the degrees of all adjacent nodes ;

[0046] Among them, in constructing the cascading failure propagation model, it also includes:

[0047] Constructing a propagation dynamics equation:

[0048]

[0049] Among them, is the physical facility elasticity coefficient; is the failure state of physical node p at time; is the load of logical node at time ; is the load of logical node at time ; is the load of logical node at time ; is the load of physical node at time ; is the load of physical node at time ;

[0050] Finally, based on the cascading failure propagation model, quantify the strength of cascading failure of the spatio-temporal weighted container sea movement dynamic network, and reveal the cascading effect of the spatio-temporal weighted container sea movement dynamic network.

[0051] As a further solution of the present invention: after constructing the spatio-temporal weighted container sea movement dynamic network, it also includes:

[0052] Construct a linear programming model;

[0053] Clean the data and align the entities of the spatio-temporal weighted container sea movement dynamic network through the linear programming model;

[0054] Among them, in the construction of the linear programming model, it also includes:

[0055] Define decision variables:

[0056] Objective function:

[0057] Constraint conditions:

[0058] Among them, is the set of shipping lines; is set; is the rated container capacity of the ship ; is the total transport capacity demand of the shipping line ; is the single-ship loading and unloading time, , is the quay crane efficiency, is the number of quay cranes; is the maximum available total loading and unloading time of the ship , is the maximum available number of sailings of the ship .

[0059] As a further solution of the present invention: in calculating the comprehensive efficiency index of the spatio-temporal weighted container sea movement dynamic network based on transport timeliness, operational economy, and network robustness, it also includes:

[0060] First step, determine the boundary of the spatio-temporal weighted container sea movement dynamic network, and determine the nodes, the number of shipping lines, and the direction of the cargo flow covered in the evaluation area;

[0061] Second step, establish a three-layer index system including transport timeliness, operational economy, and network robustness; among them,

[0062] (1) The transport timeliness index includes the average speed ratio and the on-time arrival rate two sub-indices:

[0063] The calculation formula of the average speed ratio is:

[0064]

[0065] Among them, is the designed speed of the shipping route ; is the actual average speed of the shipping route ; is any ship on the shipping route ; is the set of ships on the shipping route ; is the total number of ships in the set of ships ; ;

[0066] The formula for calculating the on-time arrival rate is as follows:

[0067]

[0068] wherein, is the planned arrival time of the ship ; is the actual arrival time of the ship ; is the set of ships; is the allowable time deviation threshold; is the indicator function, taking 1 when the condition is met, otherwise 0;

[0069] (2) The operation economy indicators include the cost per TEU and the capacity utilization rate of two sub-indicators:

[0070] The formula for calculating the cost per TEU is as follows:

[0071]

[0072] wherein, is the fuel cost, is the total voyage of the ship ; is the average speed of the ship ; is the main engine fuel consumption rate, is the unit price of fuel;

[0073] wherein, is the port cost, , is the basic berthing cost of the port ; is the total number of containers at the port ; is the handling cost per TEU of the port ; is the set of ports;

[0074] Among them, is the canal passage fee, is the total length of the ship, is the ship width, is the deadweight tonnage;

[0075] Among them, is other costs;

[0076] Utilization rate of transport capacity The calculation formula is:

[0077]

[0078] Among them, is the actual number of loaded containers of the ship and, is the maximum number of loaded containers of the ship ; is the ship set;

[0079] (3) The network robustness indicators include node betweenness centrality and edge redundancy index two sub-indicators:

[0080] Node betweenness centrality The calculation formula is:

[0081]

[0082] Among them, is the total number of the shortest paths from node s to node t; is the number of the shortest paths passing through node v; among them, the summation range is for all node pairs to sum;

[0083] Normalize the node betweenness centrality :

[0084] Among them, V is the total number of nodes of the spatio-temporal weighted container sea movement dynamic network; is the normalized node betweenness centrality, and the range is between [0, 1];

[0085] Edge redundancy index The calculation formula is:

[0086]

[0087] Among them, is the number of paths with alternative paths in the path set ; is the total number of edges in the spatio-temporal weighted container sea movement dynamic network; For an edge , the path ratio with alternative paths;

[0088] Among them, the definition of an alternative path: First, for each edge (u→v), find all the path sets that use this edge ; for each path , then check whether there is an alternative path p' that satisfies: p' does not pass through edge e, and the weight of p' ≤ 1.2 × the weight of the original path; finally, count the path ratio with alternative paths;

[0089] In the third step, calculate the comprehensive efficiency index of the spatio-temporal weighted container sea dynamic network according to the three-layer index system; among them, the comprehensive efficiency index of the spatio-temporal weighted container sea dynamic network

[0090]

[0091] Among them, are weights respectively.

[0092] As a further solution of the present invention: In quantifying the resilience index of the spatio-temporal weighted container sea dynamic network under extreme weather events based on the resilience triangle theory, it further includes:

[0093] The calculation formula of the resilience index Re of the spatio-temporal weighted container sea dynamic network under extreme weather events is as follows:

[0094]

[0095] In the formula, is between 0 and 1; represents the starting moment when the spatio-temporal weighted container sea dynamic network is affected by extreme weather events, represents the moment when the spatio-temporal weighted container sea dynamic network returns to its original state, represents the moment of the global network efficiency; represents the initial network efficiency;

[0096] Among them, if , it means that the spatio-temporal weighted container sea dynamic network is not affected by extreme weather events, and the performance of the spatio-temporal weighted container sea dynamic network remains in its original state;

[0097] Among them, if , it means that extreme weather events have a negative impact on the spatio-temporal weighted container sea dynamic network, and recovery strategies need to be taken to restore the performance of the spatio-temporal weighted container sea dynamic network;

[0098] Among them, if , it means that the spatio-temporal weighted container sea transportation dynamic network is severely damaged by a destructive event and takes a long time to recover.

[0099] As a further solution of the present invention: in the cost-benefit evaluation of the climate suitability improvement strategy of the spatio-temporal weighted container sea transportation dynamic network, it further includes:

[0100] Construct an improved greedy algorithm based on a multi-constraint marginal cost optimization model;

[0101] Evaluate the cost-benefit of different climate suitability improvement strategies of the spatio-temporal weighted container sea transportation dynamic network based on the improved greedy algorithm to determine the climate suitability improvement strategy with the optimal cost-benefit;

[0102] Formulate a climate adaptation recovery strategy for the spatio-temporal weighted container sea transportation dynamic network based on the dynamic adaptive policy path enhancement framework to ensure the rapid recovery of the spatio-temporal weighted container sea transportation dynamic network under extreme weather events.

[0103] As a further solution of the present invention: in the construction of the improved greedy algorithm based on the multi-constraint marginal cost optimization model, it further includes:

[0104] First, define a four-dimensional cost vector: C = [economic cost, carbon emissions, recovery time, climate vulnerability];

[0105] Secondly, construct the multi-constraint marginal cost optimization model :

[0106]

[0107] Among them, is the implementation intensity of the th climate suitability improvement strategy; is the climate vulnerability index of port ; is the climate risk sensitivity coefficient; is the economic cost of implementing the climate suitability improvement strategy; is the carbon emissions caused by the implementation of the climate suitability improvement strategy; is the recovery time of the port or shipping route after a climate disaster; is the climate vulnerability threshold; , , are weight coefficients; is to take the partial derivative with respect to the strategy implementation intensity ;

[0108] The multi-constraint marginal cost optimization model is dynamically updated using the NSGA-II multi-objective optimization framework of the weight coefficients 、 、 。

[0109] As a further solution of the present invention: the dynamic adaptive policy path enhancement framework specifically includes:

[0110] (1)Construct a system failure signal quantification system:

[0111] ATP calculation model:

[0112]

[0113] wherein, is the real-time wind speed of the port ; is the historical maximum wind speed of the port ; is the cumulative rainfall of the port ; the historical maximum cumulative rainfall of the port ; is the hinterland economic equivalent of the port ; is the sum of the hinterland economic equivalents of all ports; is the total number of ports;

[0114] (2)Construct a policy tree based on deep reinforcement learning:

[0115] State space: ATP level, network connectivity, ship occupancy rate;

[0116] Action space: {reroute, temporarily call at, activate alternate port, initiate land transport connection};

[0117] Reward function: ;

[0118] wherein, and are weight coefficients; is the cost change after the implementation of the climate adaptation recovery strategy; is the time change after the implementation of the climate adaptation recovery strategy; is the reward coefficient; is the recovery benefit after the implementation of the climate adaptation recovery strategy.

[0119] Compared with the prior art, the beneficial effects of the present invention are:

[0120] (1)Quantitatively analyze the impact mechanism of extreme weather events: By constructing a topological structure and efficiency evaluation method for the container shipping network, the impact mechanism of extreme weather events on network efficiency is quantitatively analyzed, especially the research on network cascade effects;

[0121] (2)Multi-dimensional evaluation system: A multi-dimensional resilience evaluation system for the container shipping network is proposed, which can comprehensively evaluate the recovery ability and adaptability of the network under extreme weather events;

[0122] (3)Economically feasible recovery strategies: Based on the greedy strategy of minimizing marginal cost and the dynamic adaptive policy path, economically feasible recovery strategies for the container shipping network are proposed, which can effectively improve the risk resistance ability and recovery speed of the network. Brief Description of the Drawings

[0123] Figure 1 It is a flowchart of a climate adaptation recovery method for a container shipping network integrating resilience theory provided by the present invention.

[0124] Figure 2 It is a schematic structural diagram of a dynamic adaptive policy path enhancement framework provided by the present invention. Detailed Embodiments

[0125] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0126] The following describes the specific implementation of the present invention in detail with reference to specific embodiments.

[0127] As Figure 1 shown, an embodiment of the present invention provides a climate adaptation recovery method for a container shipping network integrating resilience theory, and the method includes the following steps:

[0128] Step S1: Obtain liner schedule data, ship dynamic data, route adjustment data, port geographical coordinate data and multi-scale geographical fence data, and introduce a time dimension parameter to construct a spatio-temporal weighted container sea movement dynamic network;

[0129] In an embodiment of the present invention, the liner schedule data includes route code, origin and destination ports, and shipping company name, and the ship dynamic data includes longitude and latitude coordinates, speed, heading, current status (underway / anchored / berthed), and next port of call.

[0130] It should be noted that: (1) The liner schedule data and vessel movement data are structured data. The present invention retrieves the liner schedule data and vessel movement data of shipping databases such as Alphaliner in real time through an API interface; (2) The route adjustment data is unstructured data. The present invention uses natural language processing (NLP) technology to parse the route adjustment text information in port announcements and shipping company notices. The sources of unstructured data include port official website announcements, shipping company emails, social media notifications, etc.; The above unstructured data is cleaned based on Python; (3) The port geographical coordinate data and multi-scale geographical fence data are spatial data. The present invention can integrate the port geographical coordinates and multi-scale geographical fence data through a GIS platform (ArcGIS / QGIS).

[0131] Based on the above structured data, unstructured data, and spatial data, a spatio-temporal weighted container sea movement dynamic network is modeled. That is, on the basis of the traditional static topology, time dimension parameters (such as vessel scheduling intervals and seasonal capacity fluctuations) are introduced to construct a spatio-temporal weighted container sea movement dynamic network (Space-Time Network), and the edge weights include sailing time, liner frequency, and dynamic capacity change factors.

[0132] Preferably, in the constructed spatio-temporal weighted container sea movement dynamic network, it further includes:

[0133] (1) First, the traditional topology is defined:

[0134] Node set: , where is the th ;

[0135] Edge set: , where is the starting point of , is the end point of ;

[0136] Static weight: ;

[0137] (2) Secondly, the time dimension is extended:

[0138] In the first step, the discretization of the time layer is performed, and the continuous time axis is divided into equally spaced time periods (such as divided by week):

[0139]

[0140] where is the number of days;

[0141] In the second step, a three-dimensional spatio-temporal network is constructed , where each spatio-temporal node is ;

[0142] Step 3: Set the dynamic edge weight function:

[0143] Define the spatio-temporal edge weight as a multi-dimensional vector :

[0144]

[0145] where ; is during the actual sailing time (including weather influence); is during the liner frequency (trips / week); is during the available shipping capacity (TEUs / week);

[0146] (3) Again, perform dynamic parameter quantization:

[0147] Step 1: Calculate the actual sailing time during the :

[0148]

[0149] where is the distance, is the non-interference sailing speed (knots); is wind and wave level coefficient during the is actual route cost index during the and are calibration parameters (recommended , ), is maximum route cost index during the

[0150] Step 2: Considering the seasonal adjustment and emergency scheduling of liner frequency, calculate the liner frequency during the :

[0151]

[0152] where is The annual benchmark shift; is the seasonal fluctuation range (usually taking values from 0.2 to 0.5); is within the time period the temporary increase or decrease in shifts (such as suspension during the freezing period);

[0153] In the third step, calculate the available transport capacity within the time period :

[0154]

[0155] Among them, is the number of ships deployed within the time period; is the ship actual utilization rate in this voyage; is the ship rated container capacity; is the schedule reliability coefficient within the time period (taking values from 0 to 1);

[0156] Based on the above steps, the spatio-temporal weighted container sea transportation dynamic network is constructed, where the spatio-temporal weighted container sea transportation dynamic network is a physical layer network.

[0157] Existing research is mostly based on static topology analysis. The present invention realizes network dynamic evolution modeling through the Time Slicing technology, and can capture the instantaneous impact of events such as temporary suspension of navigation and seasonal adjustment on the network. The spatio-temporal weighted container sea transportation dynamic network of the present invention greatly reduces the robustness test error and is closer to the actual operation scenario than the traditional static model.

[0158] Specifically, after constructing the spatio-temporal weighted container sea transportation dynamic network, it further includes:

[0159] Construct a Port Knowledge Graph (PortKG), embed multi-language aliases, historical names and geographical coordinate features of ports, and solve naming conflict problems such as "Shenzhen Port / Shenzhen Port / Shekou Port". And design a linear programming model to verify the throughput-capacity relationship, with the objective function being the weekly throughput of the port ≥ ∑(weekly shifts of the route × single-ship capacity), and the constraint conditions including the terminal operation time window and the loading and unloading efficiency threshold. Specifically:

[0160] Construct a linear programming model;

[0161] Perform data cleaning and entity alignment on the spatio-temporal weighted container sea transportation dynamic network through the linear programming model;

[0162] Among them, in the construction of the linear programming model, it further includes:

[0163] Define decision variables:

[0164] Objective function: (Maximize the total transport capacity)

[0165] Constraint conditions:

[0166] Among them, is the set of shipping lines; is set; is the rated container capacity of the ship, that is, the number of standard containers that the ship is designed to load; is the total transport capacity demand of the shipping line is the shipping line ; is the loading and unloading time of a single ship, , is the quay crane efficiency. For example, is the number of quay cranes; is the ship maximum available total loading and unloading time, is the ship maximum available number of sailings.

[0167] Step S2: Quantify the strength of cascading failures of the spatio-temporal weighted container shipping dynamic network based on the cascading failure propagation model, and then calculate the comprehensive efficiency index of the spatio-temporal weighted container shipping dynamic network based on transport timeliness, operational economy, and network robustness;

[0168] Preferably, in the quantification of the strength of cascading failures of the spatio-temporal weighted container shipping dynamic network based on the cascading failure propagation model, it further includes:

[0169] (1) First, after the spatio-temporal weighted container shipping dynamic network is constructed, further construct a logical layer network , where the logical node is the set of cargo flow paths, representing the transport path of goods from the starting point to the ending point; the logical edge is the set of transport capacity scheduling relationships, representing the transport capacity allocation or scheduling relationships between paths;

[0170] (2) Second, define the two-way influence factor between nodes:

[0171]

[0172] When the physical node fails, the logical node The load of will be interrupted in proportion; for example, if the total cargo volume of a certain path is 1000 TEU and the port has processed 300 TEU, then ( path) = 30%. If the port fails, the load of this path will be reduced by 30% (i.e., 300 TEU).

[0173] (3)Thirdly, construct a cascading failure propagation model:

[0174] First, define the initial load: the load of a physical node is the weekly throughput of the port , and the load of a logical node is the capacity demand of the path ;

[0175] When a node fails, its load is allocated according to the capacity ratio of adjacent nodes:

[0176]

[0177] where is the newly added load of node (unit: TEU / week); is the allocation preference coefficient (when taking 1, it is evenly allocated according to the degree). When σ > 1, it prefers nodes with a high degree; when σ < 1, it prefers nodes with a low degree; is the capacity transfer efficiency (generally taking a value of 0.6 - 0.8), indicating the proportion of the load of the failed node transferred to adjacent nodes; is the original load of the failed node (unit: TEU / week); is the degree (number of connections) of node th power, indicating the influence of node ; is the sum of the th powers of the degrees of all adjacent nodes;

[0178] is, node can be a physical node or a logical node, and it needs to be distinguished according to the failure reason:

[0179] (1)Physical node failure (such as port paralysis): The load is allocated to adjacent physical nodes or logical nodes.

[0180] (2)Logical node failure (such as path interruption): The load is allocated to alternative logical nodes.

[0181] Among them, in constructing the cascading failure propagation model, it also includes:

[0182] Construct the propagation dynamics equation:

[0183]

[0184] where is the elasticity coefficient of physical facilities; is the failure state of physical node p at time (0 indicates failure, or 1 indicates non - failure); is the load of logical node at time (unit: TEU / week); is the load of logical node at time (unit: TEU / week); is the load of logical node at time (unit: TEU / week); is the load of physical node at time (unit: TEU / week); is the load of physical node at time (unit: TEU / week);

[0185] (4) Finally, based on the cascading failure propagation model, quantify the strength of cascading failure of the spatio - temporal weighted container sea - motion dynamic network, and reveal the cascading effect of the spatio - temporal weighted container sea - motion dynamic network.

[0186] Preferably, in calculating the comprehensive efficiency index of the spatio - temporal weighted container sea - motion dynamic network based on transportation timeliness, operation economy, and network robustness, it further includes:

[0187] The first step is to determine the boundary of the spatio - temporal weighted container sea - motion dynamic network, and determine the number of nodes, shipping lines, and the direction of cargo flow covered in the evaluation area;

[0188] The second step is to establish a three - layer index system including transportation timeliness, operation economy, and network robustness; where

[0189] (1) The transportation timeliness index includes the average speed ratio and the on - time arrival rate two sub - indexes:

[0190] The calculation formula of the average speed ratio is:

[0191]

[0192] where is the designed speed (knots) of the shipping route; ; is the actual average speed of the shipping route (calculated from AIS data); ; is any ship on the shipping route; ; is the set of ships on the shipping route; ; is the total number of ships in the set of ships; ; ;

[0193] The formula for the on-time arrival rate is as follows:

[0194]

[0195] wherein, is the planned arrival time of the ship (UTC); ; is the actual arrival time of the ship (based on the moment when berthing is completed); ; is the set of ships; is the allowable time deviation threshold (usually taken as 6 hours); is the indicator function, taking 1 when the condition is met, otherwise 0;

[0196] (2) The operation economy indicators include the cost per TEU and the capacity utilization rate with two sub-indicators:

[0197] The formula for the cost per TEU is as follows:

[0198]

[0199] wherein, is the fuel cost, is the total voyage (nautical miles) of the ship, ; is the average speed of the ship, ; is the main engine fuel consumption rate (tons per day), related to the deadweight tonnage of the ship; is the unit price of fuel (yuan per ton);

[0200] wherein, is the port cost, , is the basic berthing cost of the port, ; is the total number of containers at the port, ; is the single - container handling fee for the port , and is the port set;

[0201] Among them, is the canal passage fee (charged according to ship size), is the total ship length (m), is the ship width (m), is the deadweight tonnage;

[0202] Among them, is other costs;

[0203] The calculation formula for the capacity utilization rate is as follows:

[0204]

[0205] Among them, is the actual number of loaded containers of the ship , and is the maximum number of loaded containers of the ship , and is the ship set;

[0206] (3) The network robustness indicators include the node betweenness centrality and the edge redundancy index with two sub - indicators:

[0207] The calculation formula for the node betweenness centrality is as follows:

[0208]

[0209] Among them, is the total number of shortest paths from node s to node t; is the number of shortest paths passing through node v; among them, the summation range is for all node pairs summation (that is and are not equal to v);

[0210] Normalize the node betweenness centrality :

[0211] Among them, V is the total number of nodes in the spatio - temporal weighted container sea - motion dynamic network; is the normalized node betweenness centrality, and the range is between [0, 1];

[0212] The calculation formula for the edge redundancy index is as follows:

[0213]

[0214] Among them, the edge redundancy index ranges between [0, 1]; is the number of paths with alternative paths in the path set ; is the total number of edges in the spatio-temporal weighted container sea transportation dynamic network; For the edge , it is the path ratio with alternative paths;

[0215] Among them, the definition of the alternative path: First, for each edge (u→v), find all the path sets using this edge; for each path , then check whether there is an alternative path p' that satisfies: p' does not pass through the edge e, and the weight of p' ≤ 1.2 × the weight of the original path (allowing a 20% cost increase); finally, count the path ratio with alternative paths;

[0216] In the third step, calculate the comprehensive efficiency index of the spatio-temporal weighted container sea transportation dynamic network according to the three-layer index system; among them, the comprehensive efficiency index of the spatio-temporal weighted container sea transportation dynamic network has the following calculation formula:

[0217]

[0218] Among them, are weights respectively. For example, are 0.18, 0.22, 0.25, 0.15, 0.12, 0.08 respectively.

[0219] Step S3: Quantify the resilience index of the spatio-temporal weighted container sea transportation dynamic network under extreme weather events based on the resilience triangle theory;

[0220] Preferably, in the quantification of the resilience index of the spatio-temporal weighted container sea transportation dynamic network under extreme weather events based on the resilience triangle theory, it further includes:

[0221] The calculation formula of the resilience index Re of the spatio-temporal weighted container sea transportation dynamic network under extreme weather events is as follows:

[0222]

[0223] In the formula, is between 0 and 1, the higher the value, the smaller the resilience loss of the shipping network and the greater the structural resilience; represents the starting moment when the spatio-temporal weighted container sea transportation dynamic network is affected by extreme weather events, Denotes the moment when the spatio-temporal weighted container sea transportation dynamic network returns to its original state. Denotes the moment of the global network efficiency; Denotes the initial network efficiency;

[0224] Where, if , it means that the spatio-temporal weighted container sea transportation dynamic network is not affected by extreme weather events, and the performance of the spatio-temporal weighted container sea transportation dynamic network remains in its original state;

[0225] Where, if , it means that extreme weather events have a negative impact on the spatio-temporal weighted container sea transportation dynamic network, and recovery strategies need to be adopted to restore the performance of the spatio-temporal weighted container sea transportation dynamic network;

[0226] Where, if , it means that the spatio-temporal weighted container sea transportation dynamic network is severely damaged by destructive events and takes a long time to recover.

[0227] Step S4: Evaluate the cost-benefit of the climate suitability improvement strategy for the spatio-temporal weighted container sea transportation dynamic network.

[0228] Preferably, in the evaluation of the cost-benefit of the climate suitability improvement strategy for the spatio-temporal weighted container sea transportation dynamic network, it also includes:

[0229] Construct an improved greedy algorithm based on a multi-constraint marginal cost optimization model;

[0230] Specifically, in the construction of the improved greedy algorithm based on the multi-constraint marginal cost optimization model, it also includes:

[0231] First, define a four-dimensional cost vector: C = [economic cost, carbon emissions, recovery time, climate vulnerability];

[0232] Secondly, construct the multi-constraint marginal cost optimization model :

[0233]

[0234] Where, is the implementation intensity of the th climate suitability improvement strategy; is the climate vulnerability index of port (based on historical disaster frequencies and sea level rise predictions); is the climate risk sensitivity coefficient (calibrated through Monte Carlo simulation); The economic costs for implementing climate suitability improvement strategies (such as costs for port facility upgrades, route adjustments, etc.); The carbon emissions resulting from the implementation of climate suitability improvement strategies (considering ship fuel consumption, port operation equipment, etc.); The recovery time of the port or route after a climate disaster (reflecting network resilience); The climate vulnerability threshold, used to distinguish the climate risk levels of ports, indicating that ports with a climate vulnerability index exceeding 0.5 require key attention; 、 、 The weight coefficients, used to balance the importance of economic costs, carbon emissions, and recovery time, + + = 1; is the partial derivative with respect to the strategy implementation intensity to calculate the rate of change of the weighted total cost (a linear combination of economic costs, carbon emissions, and recovery time) when changes;

[0235] The NSGA-II multi-objective optimization framework is used to dynamically update the weight coefficients in the 、 、 of the multi-constraint marginal cost optimization model.

[0236] The innovation of the improved greedy algorithm of the present invention compared with the traditional greedy algorithm is shown in Table 1 below:

[0237] Table 1

[0238] Dimension Traditional method This method Target dimension Single economic cost Four-dimensional target + climate vulnerability adjustment Parameter staticity Fixed weight Dynamic weight Decision granularity Port-level strategy Port-route-ship collaborative strategy

[0239] Based on the improved greedy algorithm, evaluate the cost-benefit of different climate suitability improvement strategies of the spatio-temporal weighted container sea movement dynamic network to determine the climate suitability improvement strategy with the optimal cost-benefit;

[0240] Based on the dynamic adaptive policy path (DAPP) enhancement framework, formulate the climate adaptation recovery strategy of the spatio-temporal weighted container sea movement dynamic network to ensure the rapid recovery of the spatio-temporal weighted container sea movement dynamic network under extreme weather events.

[0241] It should be noted that the dynamic adaptive policy path enhancement framework sets system failure signals (ATP) and formulates scheme adjustment countermeasures for each system failure signal in advance to ensure the rapid recovery of the spatio-temporal weighted container sea movement dynamic network under extreme weather events.

[0242] In the embodiments of the present invention, asFigure 2 As shown in, the dynamic adaptive policy path enhancement framework specifically includes:

[0243] (1) Construct a system failure signal quantification system:

[0244] For example, construct a three-level warning signal as shown in Table 2 below:

[0245] Table 2

[0246] ATP level Trigger condition Response mechanism ATP1 Wind force at the port ≥ 10 levels within 3 days Initiate the ship diversion plan ATP2 Weekly cumulative rainfall > 95% historical quantile Activate the standby terminal + reinforce with loading and unloading robots ATP3 Real-time sea level monitoring exceeds the warning line by 0.5m Execute full network cascading shutdown and diversion

[0247] ATP calculation model:

[0248]

[0249] Wherein, is the real-time wind speed of the port, unit: m / s or knots; is the historical maximum wind speed of the port; is the cumulative rainfall of the port, unit: mm; is the historical maximum cumulative rainfall of the port; is the hinterland economic equivalent of the port, unit: GDP / year; is the sum of the hinterland economic equivalents of all ports (for weight normalization); is the total number of ports; is the historical maximum cumulative rainfall of the port; is the hinterland economic equivalent of the port, unit: GDP / year; is the sum of the hinterland economic equivalents of all ports (for weight normalization); is the total number of ports; is the total number of ports;

[0250] (2) Dynamic generation of policy paths:

[0251] Construction of a policy tree based on deep reinforcement learning (DRL):

[0252] State space: ATP level, network connectivity, ship occupancy rate;

[0253] Action space: {reroute, temporary additional call, activate alternate port, initiate land transport connection};

[0254] Reward function: ;

[0255] Wherein, and are weight coefficients, and the sum of the two is 1, used to balance the importance of cost and time (can be determined by the expert scoring method); is the cost change after the implementation of the climate adaptation recovery strategy (such as rerouting cost, land transport cost, unit: 10,000 yuan); is the time change after the implementation of the climate adaptation recovery strategy (such as ship delay time, unit: hours); is the reward coefficient, used to amplify the impact of restoration benefits (to be calibrated according to the network resilience target); is the restoration benefit after the implementation of climate adaptation restoration strategies (such as reduced carbon emissions, increased network connectivity).

[0256] Compared with the traditional emergency response mechanism (strategy), as shown in Table 3 below:

[0257] Table 3

[0258] In the embodiments of the present invention, coping strategies will also be proposed for the cost-benefit of the solution and climate suitability: Coping strategies for the container shipping network to adapt to climate change integrating resilience theory are proposed from three perspectives of improving the structural resilience, timeliness, and sustainability of the container shipping network. Specifically: One is to improve the transportation capacity and bearing capacity of the container transportation network to alleviate the congestion of the logistics network and improve the overall resilience. In particular, attention should be paid to those facilities located in climate-sensitive areas to ensure that they can withstand the impact of extreme weather events.

[0259] The second is to formulate a detailed transportation plan according to the nature of the goods and the route conditions, and set up an early warning mechanism based on real-time shipping data information. Alarms should be issued in a timely manner for any delays, anomalies, etc., so as to handle them in a timely manner and ensure the timeliness of the goods.

[0260] The third is to use low-carbon fuels such as ammonia and liquefied natural gas (LNG) to replace traditional fuels to reduce the carbon emissions of ships. At the same time, try to install auxiliary power systems such as sails and solar panels on the ships to reduce fuel consumption and carbon dioxide emissions.

[0261] In summary, the method for the climate adaptation restoration of the container shipping network integrating resilience theory provided by the embodiments of the present invention includes: (1) The construction method of the container shipping network topology: By collecting the liner route data of shipping companies, the topology of the container shipping network is constructed to reveal the cascade effect of the network; (2) The evaluation method of the container shipping network efficiency: Based on complex network theory, an evaluation method for the container shipping network efficiency is proposed to quantitatively analyze the impact of extreme weather events on the network efficiency; (3) The quantitative evaluation method of the container shipping network resilience: Based on the resilience triangle theory, the resilience of the container shipping network under extreme weather events is quantified to evaluate the network's recovery ability and adaptability; (4) The greedy strategy based on marginal cost minimization: A greedy strategy based on marginal cost minimization is proposed to evaluate the cost-benefit of different restoration strategies; (5) The dynamic adaptive policy path (DAPP): Through the dynamic adaptive policy path method, the climate adaptation restoration strategy of the container shipping network is formulated to ensure the rapid recovery of the network under extreme weather events.

[0262] The above only describes in detail the preferred embodiments of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0263] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0264] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0265] Other embodiments of the present disclosure will be readily contemplated by those skilled in the art after considering the disclosure in the specification and the embodiments. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

Claims

1. A method for climate adaptive recovery of container shipping network integrating resilience theory, characterized by: The proposed climate-resilient recovery approach for container shipping networks that incorporates resilience theory includes the following steps: Obtain liner schedule data, ship dynamic data, route adjustment data, port geographic coordinate data and multi-scale geographic fence data, and introduce time dimension parameters to construct a spatiotemporal weighted container shipping dynamic network; Quantifying the strength of cascading failures of the spatiotemporal weighted container shipping dynamic network based on a cascading failure propagation model, and then calculating a comprehensive efficiency index of the spatiotemporal weighted container shipping dynamic network based on transportation timeliness, operational economy, and network robustness; Based on the resilience triangle theory, the resilience index of the spatiotemporal weighted container shipping dynamic network under extreme weather events is quantified; Evaluate the cost-effectiveness of climate suitability improvement strategies for the proposed spatiotemporally weighted container shipping dynamic network.

2. The method for climate adaptability recovery of container shipping network integrating resilience theory according to claim 1 is characterized in that: The liner plan data includes the route code, starting and ending ports and the name of the shipping company, and the ship dynamic data includes the latitude and longitude coordinates, speed, heading, current status and next port of call.

3. The method for climate adaptability recovery of container shipping network integrating resilience theory according to claim 1 is characterized in that: The step of constructing a spatiotemporal weighted container shipping dynamic network also includes: (1) First, the traditional topology definition is performed: Node collection: ,in, For the indivual ; Edge collection: ,in, for The starting point, for The end point; Static weight: ; (2) Secondly, expand the time dimension: The first step is to discretize the time layer and divide the continuous time axis into equally spaced time periods: ； in, is the number of days; The second step is to build a three-dimensional space-time network , where each spatiotemporal node is ; The third step is to define the spatiotemporal edge weights as multidimensional vectors : ； in, ; for During the period Actual sailing time; for During the period liner frequency; for During the period Available capacity; (3) Again, dynamic parameter quantization is performed: The first step is to calculate During the period Actual sailing time : ； in, For distance, It is the non-interference speed; for Wind and wave level coefficient during the time period; for Actual route cost index during the period; , is the calibration parameter, for The maximum route cost index during the time period; The second step is to calculate During the period Frequencies : ； in, for Annual benchmark flights; is the seasonal fluctuation range; for During the period Temporary increase or decrease of shifts; The third step is to calculate During the period Available capacity : ； in, for Number of ships deployed during the period; For ships The actual utilization rate of the voyage; For ships Rated container capacity; for Ship schedule reliability factor within the time period; Based on the above steps, the time-space weighted container shipping dynamic network is constructed, wherein the time-space weighted container shipping dynamic network is a physical layer network.

4. The method for climate adaptive recovery of container shipping network integrating resilience theory according to claim 3 is characterized in that: The quantification of the strength of the cascading failure of the spatiotemporal weighted container shipping dynamic network based on the cascading failure propagation model also includes: (1) First, after the construction of the spatiotemporal weighted container shipping dynamic network is completed, the logical layer network is further constructed. , where the logical node It is a set of cargo flow paths, indicating the transportation path of cargo from the starting point to the end point; logical edge is a set of transport capacity scheduling relationships, which represents the transport capacity allocation or scheduling relationship between paths; (2) Secondly, define the bidirectional impact factor between nodes : ； When the physical node When a failure occurs, the logical node The load will be Proportional interruption; (3) Again, construct a cascading failure propagation model: First define the initial load: the load of the physical node is the port weekly throughput , the load of the logical node is the capacity demand of the path ; When the node When a node fails, its load is distributed according to the capacity ratio of adjacent nodes: ； in, Is a node New load added; is the allocation preference coefficient, when σ>1, the nodes with high degree are preferred; when σ<1, the nodes with low degree are preferred; The capacity transfer efficiency represents the proportion of the load of the failed node transferred to the adjacent nodes; Is a failed node The original load; Is a node The degree of Power, indicating a node influence; is the degree of all adjacent nodes The sum of powers; Wherein, in constructing the cascading failure propagation model, it also includes: Construct the propagation dynamics equation: ； in, is the elasticity coefficient of the physical facility; For physical node p The failure state at the moment; Logical Node In time Load; Logical Node In time Load; Logical Node In time Load; For physical nodes In time Load; For physical nodes In time Load; (4) Finally, based on the cascading failure propagation model, the strength of the cascading failure of the spatiotemporal weighted container shipping dynamic network is quantified, revealing the cascading effect of the spatiotemporal weighted container shipping dynamic network.

5. The method for climate adaptive recovery of container shipping network integrating resilience theory according to claim 1 is characterized in that: After the spatiotemporal weighted container shipping dynamic network is constructed, the following steps are also included: Construct linear programming models; Performing data cleaning and entity alignment on the spatiotemporal weighted container shipping dynamic network through the linear programming model; Wherein, the construction of the linear programming model also includes: Define the decision variables: ; Objective function: ; Constraints: ; in, Assemble for routes; for gather; For ships Rated container capacity; For routes Total capacity demand; The loading and unloading time for a single vessel, , For the efficiency of the quay crane, is the number of quay cranes; For ships The maximum total available laytime, For ships The maximum number of available shifts.

6. The method for climate adaptive recovery of container shipping network integrating resilience theory according to claim 1 is characterized in that: The comprehensive efficiency index of the time-space weighted container shipping dynamic network calculated based on transportation timeliness, operational economy and network robustness also includes: The first step is to determine the boundaries of the spatiotemporal weighted container shipping dynamic network, and determine the number of nodes, routes and cargo flows covered in the evaluation area; The second step is to establish a three-tier indicator system including transportation timeliness, operational economy and network robustness; (1) Transport timeliness indicators include average speed ratio and on-time arrival rate Two sub-indicators: Average speed ratio The calculation formula is: ； in, For routes Design speed; For routes Actual average speed; For routes any vessel on board; For routes The ships on the assembly; Assemble for ships China Shipbuilding Total number of On-time arrival rate The calculation formula is: ； in, For ships The planned arrival time of For ships The actual arrival time of mustering for the ship; is the allowed time deviation threshold; is an indicator function, which takes 1 when the condition is met, otherwise it takes 0; (2) Operational economic indicators include unit TEU cost and capacity utilization Two sub-indicators: Unit TEU cost The calculation formula is: ； in, For fuel costs, For ships Total voyage distance, For ships The average speed of is the main engine fuel consumption rate, is the unit price of fuel; in, For port charges, , For the port Basic berthing fee, It is a port Total number of containers, For the port Single box loading and unloading fee, Assemble for the port; in, Tolls for canal passage. is the overall length of the ship, For the width of the ship, is the deadweight tonnage; in, For other costs; Capacity Utilization The calculation formula is: ； in, For ships The actual loading volume, For ships Maximum loading box volume, mustering for the ship; (3) Network robustness indicators include node betweenness centrality and edge redundancy index Two sub-indicators: Node betweenness centrality The calculation formula is: ； in, is the total number of shortest paths from node s to node t; is the number of shortest paths passing through node v; where the summation range is for all node pairs sum; Betweenness Centrality Perform normalization: ; Wherein, V is the total number of nodes of the spatiotemporal weighted container shipping dynamic network; is the normalized node betweenness centrality, ranging from [0, 1]; Edge redundancy index The calculation formula is: ； in, For the path collection , the number of paths for which there are alternative paths; is the total number of edges in the spatiotemporal weighted container shipping dynamic network; For the edge , the proportion of paths with alternative paths; The definition of alternative paths is: first, for each edge (u→v), find the set of all paths that use this edge ; For each path Then check whether there is an alternative path p' that satisfies: p' does not pass through edge e, and the weight of p' is ≤ 1.2 × the weight of the original path; finally, count the proportion of paths with alternative paths; The third step is to calculate the comprehensive efficiency index of the time-space weighted container shipping dynamic network according to the three-layer index system; wherein the comprehensive efficiency index of the time-space weighted container shipping dynamic network is The calculation formula is: ； in, are weights respectively.

7. The method for climate adaptive recovery of container shipping network integrating resilience theory according to claim 1 is characterized in that: The resilience index of the spatiotemporal weighted container shipping dynamic network under extreme weather events quantified based on the resilience triangle theory also includes: The calculation formula of the resilience index Re of the spatiotemporal weighted container shipping dynamic network under extreme weather events is as follows: ； In the formula, Between 0 and 1; represents the starting time when the spatiotemporal weighted container shipping dynamic network is affected by extreme weather events, represents the time when the spatiotemporal weighted container shipping dynamic network returns to its original state, Indicates time Global network efficiency; represents the initial network efficiency; Among them, if , indicating that the spatiotemporal weighted container shipping dynamic network is not affected by extreme weather events, and the performance of the spatiotemporal weighted container shipping dynamic network remains in its original state; Among them, if , indicating that the extreme weather event has a negative impact on the spatiotemporal weighted container shipping dynamic network, and a recovery strategy is needed to restore the performance of the spatiotemporal weighted container shipping dynamic network; Among them, if , indicating that the spatiotemporal weighted container shipping dynamic network is severely damaged by destructive events and will take a long time to recover.

8. The method for climate adaptive recovery of container shipping network integrating resilience theory according to claim 1 is characterized in that: The cost-effectiveness of the climate suitability improvement strategy for the spatiotemporal weighted container shipping dynamic network is evaluated, and further includes: Construct an improved greedy algorithm based on a multi-constrained marginal cost optimization model; Evaluate the cost-effectiveness of different climate suitability improvement strategies for the spatiotemporal weighted container shipping dynamic network based on the improved greedy algorithm to determine the climate suitability improvement strategy with the best cost-effectiveness; A climate-adaptive recovery strategy for the spatiotemporal weighted container shipping dynamic network is formulated based on a dynamic adaptive policy path enhancement framework to ensure rapid recovery of the spatiotemporal weighted container shipping dynamic network under extreme weather events.

9. The method for climate adaptive recovery of container shipping network integrating resilience theory according to claim 8 is characterized in that: The improved greedy algorithm based on the multi-constrained marginal cost optimization model also includes: First, define a four-dimensional cost vector: C = [economic cost, carbon emissions, recovery time, climate vulnerability]; Secondly, construct the multi-constrained marginal cost optimization model : ； in, For the The implementation intensity of the climate suitability improvement strategies; For the port Climate Vulnerability Index; is the climate risk sensitivity coefficient; The economic costs of implementing climate suitability improvement strategies; Carbon emissions resulting from the implementation of strategies to improve climate suitability; The recovery time of ports or shipping lines after climate disasters; is the climate vulnerability threshold; , , is the weight coefficient; To implement the strategy Find partial derivatives; The multi-constrained marginal cost optimization model is dynamically updated using the NSGA-II multi-objective optimization framework The weight coefficient in , , .

10. The method for climate adaptive recovery of container shipping network integrating resilience theory according to claim 8 is characterized in that: The dynamic adaptive policy path enhancement framework specifically includes: (1) Constructing a system failure signal quantification system: ATP calculation model: ； in, For the port Real-time wind speed; For the port The highest wind speed in history; For the port The cumulative rainfall of port The maximum cumulative rainfall in history; For the port of hinterland economy equivalent; is the sum of all port hinterland economic equivalents; is the total number of ports; (2) Strategy tree construction based on deep reinforcement learning: State space: ATP level, network connectivity, ship presence rate; Action space: {reroute, temporarily add a berth, activate an alternate port, start land transport connection}; Reward function: ; in, and is the weight coefficient; Changes in costs after implementation of climate-resilient restoration strategies; Temporal changes after implementation of climate-adaptive restoration strategies; is the reward coefficient; Restoration benefits after implementation of climate-resilient restoration strategies.

Images