Port cargo intelligent scheduling system and method based on big data analysis

Abstract

The invention discloses an intelligent port cargo scheduling system and method based on big data analysis, and relates to the technical field of port cargo scheduling data processing. The system comprises an environment acquisition and evaluation module, a cargo intelligent scheduling distributed computing node first comparative analysis calling module and a cargo intelligent scheduling distributed computing node second comparative analysis calling module. According to the invention, through cargo environment monitoring optimization, equipment operation efficiency optimization and dynamic allocation of computing resources, an environment-equipment-computing power intelligent closed-loop optimization system is formed; therefore, comprehensive efficiency improvement of port operation from physical infrastructure to a digital decision-making system is achieved, and the problem that in the prior art, an intelligent port cargo scheduling system is insufficient in response accuracy to a distributed scheduling environment in extreme weather is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of port cargo dispatching data processing, and particularly to an intelligent port cargo dispatching system and method based on big data analysis. Background Art

[0002] With the rapid development of international trade, the throughput of ports as logistics hubs has been continuously increasing. Traditional manual dispatching methods are inefficient due to problems such as information asymmetry and decision-making lag, and it is difficult to meet the demand. The maturity of technologies such as big data, the Internet of Things, and artificial intelligence provides new ideas for port dispatching. Optimizing resource allocation through real-time data analysis and intelligent algorithms has become an inevitable choice for industry upgrading. With the deep integration of technologies and automation upgrading, future port dispatching will deeply integrate big data, cloud computing, the Internet of Things, 5G, and AI technologies to achieve millisecond-level data response and full-process automation. The intelligent dispatching system will connect ports with inland transportation networks such as railways and highways to achieve cross-regional collaboration.

[0003] Existing intelligent port cargo dispatching systems based on big data analysis are implemented through the following technologies, including: using machine learning to predict cargo throughput, ship arrival time, etc., optimizing resource allocation. The LSTM time series model performs excellently in demand prediction, and combining operations research with reinforcement learning to generate the optimal loading and unloading sequence and path planning. Real-time collection of cargo and equipment status data through technologies such as sensors and RFID to support full-process tracking.

[0004] For example, a port management method, system, and device based on a digital intelligent algorithm disclosed in the patent application with the publication number CN119151403A includes: collecting cargo information, ship information, and vehicle information and performing preprocessing; performing an intelligent berth plan based on the preprocessed ship information to obtain berth information, and then performing an intelligent stowage plan based on the preprocessed cargo information, the preprocessed vehicle information, and the berth information to obtain stowage information; collecting port storage information, and combining the stowage information with the port storage information to perform an intelligent stacking plan to obtain stacking information; performing intelligent position selection based on the berth information, the stowage information, and the stacking information to obtain position selection parameters and position selection tasks, and performing automatic container release based on the position selection parameters and the position selection tasks to achieve real-time port dispatching.

[0005] For example, a port scheduling method and system disclosed in the invention patent with the publication number of CN116542488B includes: calculating the navigation parameters of each ship according to the nature of the goods, the tonnage of the ship, and the type of the ship; sorting each ship in descending order of the navigation parameters to obtain a navigation sequence; constructing a ship scheduling model and a berth allocation model; constructing an objective function of the ship scheduling model with the total scheduling time, the total waiting time, and the time value loss, and training the ship scheduling model with the minimum objective function of the ship scheduling model as the goal; calculating the scheduling time of each ship through the ship scheduling model according to the navigation sequence; constructing an objective function of the berth allocation model with the total time in port, and training the berth allocation model with the minimum objective function of the berth allocation model as the goal; and allocating berths to each ship through the ship scheduling model.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, it is found that the above technology has at least the following technical problems: In the prior art, due to extreme weather, the port intelligent scheduling system faces multi-level risks, including various factors such as the data perception layer, the algorithm decision layer, and the execution control layer, which greatly increases the risk of dynamic scheduling and multimodal transport suspension, greatly delays the scheduling response time, and has weak response timeliness to climate risk challenges. There is a problem of insufficient adaptability and response accuracy of the port cargo intelligent scheduling system to the distributed scheduling environment under extreme weather. Summary of the Invention

[0007] The embodiments of the present application provide a port cargo intelligent scheduling system and method based on big data analysis, which solve the problem of insufficient adaptability and response accuracy of the port cargo intelligent scheduling system to the distributed scheduling environment under extreme weather in the prior art, and realize the improvement of the adaptability and response accuracy of the port cargo intelligent scheduling system to the distributed scheduling environment under extreme weather.

[0008] The embodiments of the present application provide a port cargo intelligent scheduling system based on big data analysis, including: an environment collection and evaluation module, a first comparison analysis and call module for the distributed computing node of cargo intelligent scheduling, and a second comparison analysis and call module for the distributed computing node of cargo intelligent scheduling; wherein, the environment collection and evaluation module is used to evaluate and analyze the port cargo environment parameters, and make comparison analysis and adjustment according to the port cargo environment parameters; the first comparison analysis and call module for the distributed computing node of cargo intelligent scheduling is used to evaluate and analyze the fluctuation parameters of the port scheduling equipment, and make comparison analysis and adjustment according to the fluctuation parameters of the port scheduling equipment; the second comparison analysis and call module for the distributed computing node of cargo intelligent scheduling is used to comprehensively evaluate and analyze the equipment of the port scheduling distributed computing node, and make comparison analysis and adjustment according to the comprehensive evaluation and analysis results.

[0009] Further, conduct comparative analysis and adjustment based on port cargo environmental parameters, specifically including: collecting and obtaining the port environmental wind speed through a wind speed sensor, collecting and obtaining the maximum value of the port environmental seawater level through a water level sensor, and collecting and obtaining the maximum value of the rainfall per unit time through a rainfall sensor; if the maximum value of the port environmental seawater level is less than the port environmental seawater level maximum value threshold, the maximum value of the rainfall per unit time is less than the rainfall per unit time maximum value threshold, and the port environmental wind speed is less than the port environmental wind speed threshold, then conduct a mutation assessment of the port cargo intelligent scheduling environmental assessment; if the maximum value of the port environmental seawater level is equal to or greater than the port environmental seawater level maximum value threshold, or the maximum value of the rainfall per unit time is equal to or greater than the rainfall per unit time maximum value threshold, or the port environmental wind speed is equal to or greater than the port environmental wind speed threshold, then issue a warning and notify relevant personnel to raise the port cargo intelligent scheduling warning level to the highest level.

[0010] Further, conduct a mutation assessment of the port cargo intelligent scheduling environmental assessment, specifically including: collecting and obtaining the maximum value of the port environmental salt fog concentration through an on-line salt fog monitor using the laser scattering method; extracting from the port cargo intelligent scheduling environmental assessment database the historical average value of the port environmental seawater level, the historical average value of the port environmental salt fog concentration, the correction factor of the port environmental sea wind speed for the port environmental seawater level, the historical average value of the port environmental rainfall, the first scheduling proportion factor for changes in port cargo environmental characteristics, the second scheduling proportion factor for changes in port cargo environmental characteristics, and the third scheduling proportion factor for changes in port cargo environmental characteristics; conducting a ratio analysis of the maximum value of the port environmental seawater level and the historical average value of the port environmental seawater level, correcting it through the correction factor of the port environmental sea wind speed for the port environmental seawater level, and then correcting it through the first scheduling proportion factor for changes in port cargo environmental characteristics to obtain the first component of the port cargo intelligent scheduling environmental assessment mutation; conducting a ratio analysis of the maximum value of the port environmental salt fog concentration and the historical average value of the port environmental salt fog concentration, and correcting it through the second scheduling proportion factor for changes in port cargo environmental characteristics to obtain the second component of the port cargo intelligent scheduling environmental assessment mutation; conducting a ratio analysis of the maximum value of the port environmental rainfall and the historical average value of the port environmental rainfall, and correcting it through the third scheduling proportion factor for changes in port cargo environmental characteristics to obtain the third component of the port cargo intelligent scheduling environmental assessment mutation; conducting a coupling analysis through the first component of the port cargo intelligent scheduling environmental assessment mutation, the second component of the port cargo intelligent scheduling environmental assessment mutation, and the third component of the port cargo intelligent scheduling environmental assessment mutation to obtain the port cargo intelligent scheduling environmental assessment mutation value.

[0011] Furthermore, the specific process for comparative analysis and adjustment based on port cargo environment parameters is as follows: If the mutation value of the port cargo intelligent scheduling environment assessment is less than the mutation threshold of the port cargo intelligent scheduling environment assessment, no adjustment is made; if the mutation value of the port cargo intelligent scheduling environment assessment is equal to or greater than the mutation threshold of the port cargo intelligent scheduling environment assessment, the mutation value of the port cargo intelligent scheduling environment assessment is coupled with the real-time centralized computing power load utilization rate of the port cargo intelligent scheduling resource center to obtain the port cargo intelligent scheduling resource center coupling value. The port cargo intelligent scheduling resource center coupling value is used to quantitatively represent the relative scarcity risk degree of the schedulable resources of the port cargo intelligent scheduling resource center. If the port cargo intelligent scheduling resource center coupling value is less than the port cargo intelligent scheduling resource center coupling threshold, a notice is sent to relevant personnel and the automated distributed resource scheduling is not started temporarily. If the port cargo intelligent scheduling resource center coupling value is equal to or greater than the port cargo intelligent scheduling resource center coupling threshold, the distributed resource scheduling is started.

[0012] Furthermore, the evaluation and analysis of the port scheduling equipment fluctuation parameters specifically include: Collecting the network delay of the port distributed scheduling equipment and the network error rate of the port distributed scheduling equipment through the tools built into the port distributed scheduling equipment; Directly extracting from the port cargo intelligent scheduling environment assessment database the network delay threshold of the port distributed scheduling equipment, the network error rate threshold of the port distributed scheduling equipment, the average failure rate threshold of the port distributed scheduling equipment, the first scheduling proportion factor for changes in port equipment scheduling characteristics, the second scheduling proportion factor for changes in port equipment scheduling characteristics, the third scheduling proportion factor for changes in port equipment scheduling characteristics, and the correction factor for the salt spray corrosion of the terminal interface of the port distributed scheduling equipment with respect to the usage duration; Conducting a ratio analysis of the network delay of the port distributed scheduling equipment and the network delay threshold of the port distributed scheduling equipment, and correcting it through the first scheduling proportion factor for changes in port equipment scheduling characteristics to obtain the first component of the port distributed scheduling equipment performance evaluation fluctuation; Conducting a ratio analysis of the network error rate of the port distributed scheduling equipment and the network error rate threshold of the port distributed scheduling equipment, and correcting it through the second scheduling proportion factor for changes in port equipment scheduling characteristics to obtain the second component of the port distributed scheduling equipment performance evaluation fluctuation; Conducting a ratio analysis of the average failure rate of the port distributed scheduling equipment and the average failure rate threshold of the port distributed scheduling equipment, and correcting it through the third scheduling proportion factor for changes in port equipment scheduling characteristics to obtain the third component of the port distributed scheduling equipment performance evaluation fluctuation; Conducting a coupling analysis through the first component of the port distributed scheduling equipment performance evaluation fluctuation, the second component of the port distributed scheduling equipment performance evaluation fluctuation, and the third component of the port distributed scheduling equipment performance evaluation fluctuation, and then correcting it through the correction factor for the salt spray corrosion of the terminal interface of the port distributed scheduling equipment with respect to the usage duration to obtain the mutation value of the port distributed scheduling equipment performance evaluation fluctuation.

[0013] Furthermore, comparative analysis and adjustment are carried out according to the port dispatching equipment fluctuation parameters, which specifically include: if the performance evaluation fluctuation mutation value of the port distributed dispatching equipment is less than the performance evaluation fluctuation mutation threshold of the port distributed dispatching equipment, record the corresponding port distributed dispatching equipment, denoted as the first node to be adjusted of the port distributed dispatching equipment; if the performance evaluation fluctuation mutation value of the port distributed dispatching equipment is equal to or greater than the performance evaluation fluctuation mutation threshold of the port distributed dispatching equipment, record the corresponding port distributed dispatching equipment, denoted as the second node to be adjusted of the port distributed dispatching equipment and conduct emergency anti-corrosion and dehumidification treatment. Arrange the performance evaluation fluctuation mutation values of the port distributed dispatching equipment corresponding to the second node to be adjusted of the port distributed dispatching equipment in descending order, and gradually migrate the corresponding computing tasks to the first node to be adjusted of the port distributed dispatching equipment in the descending order of the arranged second node to be adjusted of the port distributed dispatching equipment.

[0014] Furthermore, comprehensive evaluation and analysis are carried out on the port dispatching distributed computing node equipment, which specifically include: directly extracting from the port cargo intelligent dispatching environment evaluation database the comprehensive first dispatching proportion factor of the distributed computing power resources of the port cargo intelligent dispatching equipment, the comprehensive second dispatching proportion factor of the distributed computing power resources of the port cargo intelligent dispatching equipment, and the correction factor of the local temperature rise rate of the port distributed dispatching equipment for the comprehensive risk value of the distributed computing power resources of the port cargo intelligent dispatching equipment; conduct coupling analysis on the port cargo intelligent dispatching environment mutation value through the comprehensive first dispatching proportion factor of the distributed computing power resources of the port cargo intelligent dispatching equipment to obtain the first component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent dispatching equipment; conduct coupling analysis on the performance evaluation fluctuation mutation value of the port distributed dispatching equipment through the comprehensive second dispatching proportion factor of the distributed computing power resources of the port cargo intelligent dispatching equipment to obtain the second component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent dispatching equipment; conduct coupling analysis on the first component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent dispatching equipment and the second component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent dispatching equipment, and then correct through the correction factor of the local temperature rise rate of the port distributed dispatching equipment for the comprehensive risk value of the distributed computing power resources of the port cargo intelligent dispatching equipment to obtain the comprehensive risk value of the distributed computing power resources of the port cargo intelligent dispatching equipment.

[0015] Further, comparative analysis and adjustment are performed according to the comprehensive evaluation and analysis results, specifically including: if the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device is less than the comprehensive risk threshold of the distributed computing power resources of the port cargo intelligent scheduling device, the second nodes to be adjusted of the port distributed scheduling device after arrangement are gradually migrated to the first node to be adjusted of the port distributed scheduling device in the descending order, and the corresponding computing tasks are migrated. The port cargo intelligent scheduling devices corresponding to the predefined percentage are marked as secondary high-computing power nodes in the descending order, and the computing power resources with the predefined computing power percentage are reserved for the secondary high-computing power nodes.

[0016] Further, the comparative analysis and adjustment according to the comprehensive evaluation and analysis results also include: if the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device is equal to or greater than the comprehensive risk threshold of the distributed computing power resources of the port cargo intelligent scheduling device, the rotation speed of the cooling fan of the corresponding port cargo intelligent scheduling device is increased and the liquid cooling system of the corresponding port cargo intelligent scheduling device is started. The port cargo intelligent scheduling devices within the predefined percentage are marked as high-computing power nodes in the descending order according to the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device, the wireless link of the port cargo intelligent scheduling device is switched to the fiber optic private network, and the allocation of computing power tasks to it is stopped.

[0017] In the embodiment of the present application, a port cargo intelligent scheduling method based on big data analysis is provided, which is characterized in that the specific steps are as follows: evaluating and analyzing the port cargo environment parameters, and performing comparative analysis and adjustment according to the port cargo environment parameters; evaluating and analyzing the port scheduling device fluctuation parameters, and performing comparative analysis and adjustment according to the port scheduling device fluctuation parameters; comprehensively evaluating and analyzing the port scheduling distributed computing node devices, and performing comparative analysis and adjustment according to the comprehensive evaluation and analysis results.

[0018] One or more technical solutions provided in the embodiment of the present application have at least the following technical effects or advantages: 1. Through the optimization of cargo environment monitoring, the optimization of equipment operation efficiency, and the dynamic allocation of computing resources, the three form an intelligent closed-loop optimization system of "environment - equipment - computing power". Through data collection of the Internet of Things perception layer, digital twin modeling, and edge cloud computing, the all-round efficiency improvement of port operation from physical infrastructure to digital decision-making system is realized, and the problem that the port cargo intelligent scheduling system in the prior art has insufficient accuracy in adapting to and responding to the distributed scheduling environment under extreme weather is solved.

[0019] 2. Conduct comparative analysis and adjustment based on the fluctuation parameters of port scheduling equipment. Dynamically adjust the maintenance cycle through the salt spray corrosion correction factor. When the salt spray concentration surges during the typhoon season, reduce the energy consumption of task migration, and the nitrogen spraying system reduces corrosion loss, so that the port has the intelligent capabilities of environmental self - adaptation, risk self - disposal, and resource self - allocation, and improves the environmental adaptability of the port cargo intelligent scheduling system.

[0020] 3. Conduct comparative analysis and adjustment according to the results of comprehensive evaluation analysis. Trigger task migration based on the computing power risk value, reserve computing power resources to meet sudden demands, ensure zero interruption of high - priority tasks, improve the emergency response speed, automatically start enhanced heat dissipation, reduce the chip junction temperature, and reduce the probability of equipment frequency reduction; The pre - allocation mechanism for secondary high - level nodes improves the ability to handle sudden tasks, and then realizes the closed - loop of "real - time risk perception - dynamic resource adaptation - continuous efficiency optimization", reducing the comprehensive failure rate of port scheduling distributed computing node equipment in extreme weather and improving energy efficiency. Brief Description of the Drawings

[0021] Figure 1 It is a schematic structural diagram of the port cargo intelligent scheduling system based on big data analysis provided by the embodiment of the present application.

[0022] Figure 2 It is a schematic flow diagram of comparative analysis and adjustment according to the port cargo environmental parameters provided by the embodiment of the present application.

[0023] Figure 3 It is a schematic flow diagram of comparative analysis and adjustment according to the fluctuation parameters of port scheduling equipment provided by the embodiment of the present application.

[0024] Figure 4 It is a schematic flow diagram of comprehensive evaluation and analysis of port scheduling distributed computing node equipment provided by the embodiment of the present application.

[0025] Figure 5 It is a schematic flow diagram of the port cargo intelligent scheduling method based on big data analysis provided by the embodiment of the present application. Detailed Embodiment

[0026] By providing a port cargo intelligent scheduling system and method based on big data analysis, the embodiment of the present application solves the problem of insufficient accuracy of the port cargo intelligent scheduling system in adapting to and responding to the distributed scheduling environment under extreme weather. Through the optimization of cargo environment monitoring, the optimization of equipment operation efficiency, and the dynamic allocation of computing resources, the three form an intelligent closed - loop optimization system of "environment - equipment - computing power". Through data collection of the Internet of Things perception layer, digital twin modeling, and edge cloud computing, the all - round efficiency improvement of port operation from physical infrastructure to digital decision - making system is realized.

[0027] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0028] As Figure 1 shown, it is a schematic structural diagram of a port cargo intelligent scheduling system based on big data analysis provided by an embodiment of the present application. The port cargo intelligent scheduling system based on big data analysis provided by an embodiment of the present application includes an environment acquisition and evaluation module, a first comparison analysis and invocation module for a cargo intelligent scheduling distributed computing node, and a second comparison analysis and invocation module for a cargo intelligent scheduling distributed computing node. Among them, the environment acquisition and evaluation module is used to evaluate and analyze the port cargo environment parameters, and make comparison analysis and adjustment according to the port cargo environment parameters; the first comparison analysis and invocation module for the cargo intelligent scheduling distributed computing node is used to evaluate and analyze the port scheduling equipment fluctuation parameters, and make comparison analysis and adjustment according to the port scheduling equipment fluctuation parameters; the second comparison analysis and invocation module for the cargo intelligent scheduling distributed computing node is used to comprehensively evaluate and analyze the port scheduling distributed computing node equipment, and make comparison analysis and adjustment according to the comprehensive evaluation and analysis results.

[0029] Furthermore, making comparison analysis and adjustment according to the port cargo environment parameters specifically includes: collecting and obtaining the port environment wind speed through a wind speed sensor, collecting and obtaining the highest value of the port environment seawater level through a water level sensor, and collecting and obtaining the highest value of the rainfall per unit time through a rainfall sensor; if the highest value of the port environment seawater level is less than the highest value threshold of the port environment seawater level and the highest value of the rainfall per unit time is less than the highest value threshold of the rainfall per unit time and the port environment wind speed is less than the port environment wind speed threshold, then conduct a mutation assessment of the port cargo intelligent scheduling environment evaluation. If the highest value of the port environment seawater level is equal to or greater than the highest value threshold of the port environment seawater level or the highest value of the rainfall per unit time is equal to or greater than the highest value threshold of the rainfall per unit time or the port environment wind speed is equal to or greater than the port environment wind speed threshold, then issue a warning and notify relevant personnel to raise the port cargo intelligent scheduling warning level to the highest level.

[0030] In this embodiment, the port environment wind speed is collected and obtained through a wind speed sensor. For example, an ultrasonic wind speed sensing device without a mechanical transmission structure is adopted, which is configured at the top of a fixed structure with a vertical height exceeding a preset threshold in the port area, including but not limited to the top of the shore monitoring tower, the top platform of large loading and unloading equipment, and the top of the meteorological observation facility. The ultrasonic wind speed sensing device is coupled with an edge computing node through an industrial-grade communication gateway, where the edge computing node is built-in with a real-time data processing algorithm, and its response delay meets the preset timing requirements of the port operation safety control system.

[0031] Collect and obtain the maximum value of the sea water level in the port environment through a water level sensor. For example, the water level monitoring module uses an electromagnetic wave reflection type water level sensing device, and its installation location includes the port breakwater structure.

[0032] Collect and obtain the maximum rainfall per unit time through a rainfall sensor. For example, a mechanical tipping bucket metering device is installed at the elevation reference point of the yard area to detect the water accumulation risk parameters in the solid bulk storage area; a composite monitoring terminal is set at the key nodes of the drainage pipe network. The composite monitoring terminal integrates a flow detection unit and a liquid level sensing unit, and its output signal forms a closed-loop control circuit with the drainage pump station control system; an expandable communication module is set in the container storage area. The module connects multiple rainfall detection terminals through a standard industrial bus protocol to form a grid monitoring array.

[0033] Furthermore, conduct a mutation assessment of the intelligent dispatching environment evaluation of port cargo, which specifically includes: collecting and obtaining the maximum value of the port environment salt fog concentration through a laser scattering method salt fog online monitor; extracting from the intelligent dispatching environment evaluation database of port cargo the historical average value of the port environment sea water level, the historical average value of the port environment salt fog concentration, the correction factor of the port environment sea wind speed for the port environment sea water level, the historical average value of the port environment rainfall, the first dispatching proportion factor of the port cargo environment characteristic change, the second dispatching proportion factor of the port cargo environment characteristic change, and the third dispatching proportion factor of the port cargo environment characteristic change; conduct a ratio analysis of the maximum value of the port environment sea water level and the historical average value of the port environment sea water level, correct it through the correction factor of the port environment sea wind speed for the port environment sea water level, and then correct it through the first dispatching proportion factor of the port cargo environment characteristic change to obtain the first component of the mutation of the intelligent dispatching environment evaluation of port cargo; conduct a ratio analysis of the maximum value of the port environment salt fog concentration and the historical average value of the port environment salt fog concentration, and correct it through the second dispatching proportion factor of the port cargo environment characteristic change to obtain the second component of the mutation of the intelligent dispatching environment evaluation of port cargo; conduct a ratio analysis of the maximum value of the port environment rainfall and the historical average value of the port environment rainfall, and correct it through the third dispatching proportion factor of the port cargo environment characteristic change to obtain the third component of the mutation of the intelligent dispatching environment evaluation of port cargo; conduct a coupling analysis through the first component of the mutation of the intelligent dispatching environment evaluation of port cargo, the second component of the mutation of the intelligent dispatching environment evaluation of port cargo, and the third component of the mutation of the intelligent dispatching environment evaluation of port cargo to obtain the mutation value of the intelligent dispatching environment evaluation of port cargo.

[0034] In this embodiment, number the distributed intelligent dispatching environment monitoring points of port cargo, indicating the numbering of the distributed intelligent dispatching environment monitoring points of port cargo, , indicating the total number of the numbering of the distributed intelligent dispatching environment monitoring points of port cargo.

[0035] represents the mutation value of the intelligent scheduling environment assessment of port cargo for the th distributed port cargo intelligent scheduling environment monitoring point. The mutation value of the intelligent scheduling environment assessment of port cargo is used to quantify the mutation degree value of the environment where the software and hardware equipment required for intelligent scheduling of port cargo is located.

[0036] ; ; represents the th highest value of the sea water level in the port environment for the distributed port cargo intelligent scheduling environment monitoring point. The highest value of the sea water level in the port environment is collected through a water level sensor.

[0037] represents the historical average value of the sea water level in the port environment, which is extracted from the intelligent scheduling environment assessment database of port cargo.

[0038] Continuous sea breeze will generate tangential stress on the sea surface, resulting in momentum transfer of the water body in the wind field direction. When the wind direction forms a specific angle with the coastline, under the continuous action of the onshore wind, the surface sea water is transported and accumulated towards the shore, resulting in the actual water level being significantly higher than the theoretical value predicted by the tidal model. The wave breaking generated by high-frequency gusts will form a climbing effect in the nearshore area, further raising the instantaneous water level. At the same time, when a typhoon or strong cyclone passes by, the combined action of the sea breeze speed and the sudden drop in air pressure may trigger a storm surge. At this time, the water level correction factor needs to be dynamically amplified to reflect the non-linear impact of the coupling of the wind field and air pressure on the water level.

[0039] represents the The correction factor of the port environment sea wind speed for the port environment sea water level of each distributed port cargo intelligent dispatching environmental monitoring point. The value range is 0 to 1. The correction factor of the port environment sea wind speed for the port environment sea water level is extracted from the port cargo intelligent dispatching environmental assessment database. The specific acquisition example is as follows: Ultrasonic wind speed and direction meters are deployed in high-exposure areas of the port (such as lighthouses and elevated monitoring towers) to ensure coverage of major waterways and loading and unloading operation areas to avoid building obstruction. Real-time water level data is obtained from the port tide monitoring station and combined with historical average values (such as chart depth datum). The wind speed and tide data are timestamped and outliers (such as mutation values caused by sensor failure) are removed. Interpolation algorithms (such as cubic splines) are used to fill in missing data. The fitting coefficient is determined by fitting historical data using the least squares method, and cross-validation is required to avoid overfitting. The training set (70%) and the test set (30%) are divided. The mapping relationship between the real-time wind speed value and the corresponding port environment sea wind speed for the port environment sea water level correction factor is obtained. The real-time wind speed value is input to obtain the corresponding port environment sea wind speed for the port environment sea water level correction factor.

[0040] Indicates The maximum value of the salt spray concentration in the port environment of the distributed port cargo intelligent dispatching environmental monitoring point is collected by the laser scattering method salt spray online monitor. The laser scattering method salt spray online monitor measures the concentration of salt particles in the air through the laser scattering principle, and outputs the salt spray content in real time in combination with environmental parameters such as temperature and humidity. The laser scattering method salt spray online monitor supports wall-mounted or rail-mounted installation, which is suitable for small spaces and easy to integrate with the monitoring system. It is suitable for coastal and offshore high salt spray environments and can operate stably for a long time.

[0041] It represents the historical average value of salt spray concentration in the port environment, which is extracted from the port cargo intelligent scheduling environmental assessment database.

[0042] Indicates The maximum value of port environmental rainfall at a distributed port cargo intelligent scheduling environmental monitoring point is collected through the mechanical tipping bucket metering device in the example above.

[0043] It represents the historical average rainfall in the port environment, which is extracted from the port cargo intelligent scheduling environmental assessment database.

[0044] The first dispatch weight factor representing the change in port cargo environmental characteristics is directly extracted from the port cargo intelligent dispatch environmental assessment database.

[0045] It represents the second scheduling proportion factor of the environmental characteristics change of port goods, which is directly extracted from the intelligent scheduling environment assessment database of port goods.

[0046] It represents the third scheduling proportion factor of the environmental characteristics change of port goods, which is directly extracted from the intelligent scheduling environment assessment database of port goods.

[0047] The sudden change in environmental temperature, such as an abnormal fluctuation in the temperature change range exceeding the historical average within 24 hours (for example: cold snap or heat wave). The sudden drop in temperature causes an increase in seawater density and a contraction in volume, which may trigger abnormal tide levels; extreme high temperatures accelerate evaporation and indirectly affect the water level balance. The sudden change in temperature (such as the passage of a cold front) is often accompanied by heavy rainfall or rainstorms, directly affecting the load of the port drainage system. High temperatures accelerate the evaporation of seawater and increase the salt mist concentration; low temperatures inhibit evaporation but may indirectly affect the salt mist distribution by changing the humidity.

[0048] An example of constructing the mapping relationship between environmental temperature and the corresponding proportion is as follows: Deploy high-precision temperature sensors in key areas of the port (such as docks, warehouses) to collect temperature data in real time. Extract historical temperature sudden change events (such as cold snaps, heat waves) and their corresponding port operation data. Eliminate outliers (such as mutation values caused by sensor failures), and use the moving average method to fill in missing data. Normalize the temperature and calculate the temperature change rate. Dynamically map the sudden change in temperature to the three scheduling proportion factors, and statistically count the mutation frequencies of the three evaluation dimensions in different temperature change intervals. Construct the contribution degree mapping relationships of water level, salt mist, and rainfall in different intervals to obtain the mapping relationships between environmental temperature and the first scheduling proportion factor of the environmental characteristics change of port goods, the second scheduling proportion factor of the environmental characteristics change of port goods, and the third scheduling proportion factor of the environmental characteristics change of port goods. Input the environmental temperature to obtain the corresponding first scheduling proportion factor of the environmental characteristics change of port goods, the second scheduling proportion factor of the environmental characteristics change of port goods, and the third scheduling proportion factor of the environmental characteristics change of port goods.

[0049] Further, the specific process of comparing, analyzing, and adjusting according to the port cargo environment parameters is as follows: If the mutation value of the port cargo intelligent scheduling environment assessment is less than the mutation threshold of the port cargo intelligent scheduling environment assessment, no adjustment is made; if the mutation value of the port cargo intelligent scheduling environment assessment is equal to or greater than the mutation threshold of the port cargo intelligent scheduling environment assessment, the mutation value of the port cargo intelligent scheduling environment assessment is multiplied by the real-time centralized computing power load utilization rate of the port cargo intelligent scheduling resource center to obtain the port cargo intelligent scheduling resource center coupling value. The port cargo intelligent scheduling resource center coupling value is used to quantitatively represent the relative scarcity risk degree of the schedulable resources of the port cargo intelligent scheduling resource center. If the port cargo intelligent scheduling resource center coupling value is less than the port cargo intelligent scheduling resource center coupling threshold, a notice is sent to relevant personnel and the automated distributed resource scheduling is not started temporarily. If the port cargo intelligent scheduling resource center coupling value is equal to or greater than the port cargo intelligent scheduling resource center coupling threshold, the distributed resource scheduling is started.

[0050] In this embodiment, as Figure 2 shown, it is a schematic flowchart of the process of comparing, analyzing, and adjusting according to the port cargo environment parameters provided by the embodiment of the present application.

[0051] Sending a notice to relevant personnel and not starting the automated distributed resource scheduling temporarily is to let relevant personnel judge whether manual adjustment of the distributed resource scheduling is needed.

[0052] In the distributed port cargo intelligent scheduling system, judging whether to schedule distributed computing power resources (edge computing) needs to be based on the real-time assessment of the environment mutation value and combined with the system load and business requirements. The following are the specific judgment logic, technical steps, and system adjustment plan: Status monitoring: Real-time monitor the computing power (CPU / GPU utilization rate), storage, and network status of edge nodes.

[0053] Task splitting and distribution: Task splitting: Split the centralized task into subtasks (such as water level prediction, salt spray diffusion simulation, path planning).

[0054] Distribution rules: Priority tasks: High-real-time tasks (such as typhoon path prediction) are assigned to the nearest edge nodes. Data-intensive tasks: Salt spray concentration analysis is assigned to nodes with sufficient storage resources.

[0055] Edge Node Task Execution: Salt Spray Diffusion Simulation: Based on temperature abrupt change data, run the Gaussian diffusion model on the edge node, obtain the specific salt spray diffusion simulation situation according to the Gaussian diffusion model, construct a diffusion kinetics model based on the Navier-Stokes equation, and simulate the influence of wind speed and temperature on salt spray migration. Train the DQN model, define the reward function (obstacle avoidance, low energy consumption, short delay), and generate the globally optimal path. Automatically schedule the transport vehicle to transport through the globally optimal path.

[0056] An example of the adjustment plan for the intelligent scheduling system of port goods called by the distributed resource scheduling is as follows: Reallocation of task priorities: When the temperature rises by more than 30 degrees: The priority of the salt spray anti-corrosion operation is raised to the highest level, and low-priority tasks (such as inventory counting) are suspended. When the temperature drops by more than 30 degrees: The scheduling frequency of the antifreeze spraying equipment is increased by 3 times.

[0057] Automation Equipment Linkage: The edge node directly controls the quay crane to decelerate (such as when the wind speed is greater than 15 m / s) and the container stacker to lock (such as when the salt spray concentration is greater than 100 μg / m³).

[0058] Energy Management: The edge computing node dynamically adjusts the power consumption according to the task load (such as entering the low-power mode when idle).

[0059] Incremental Learning: The edge node regularly uploads local data to the cloud to update the global model parameters.

[0060] Through the above solutions, the centralized computing power bottleneck can be effectively alleviated, and the real-time performance and environmental adaptability of the port intelligent scheduling system can be improved.

[0061] Furthermore, the fluctuation parameters of the port scheduling equipment are evaluated and analyzed, specifically including: collecting the network delay of the port distributed scheduling equipment and the network bit error rate of the port distributed scheduling equipment through the tools built in the port distributed scheduling equipment; directly extracting from the port cargo intelligent scheduling environment evaluation database the network delay threshold of the port distributed scheduling equipment, the network bit error rate threshold of the port distributed scheduling equipment, the average failure rate threshold of the port distributed scheduling equipment, the first scheduling proportion factor for the change of port equipment scheduling characteristics, the second scheduling proportion factor for the change of port equipment scheduling characteristics, the third scheduling proportion factor for the change of port equipment scheduling characteristics, and the correction factor for the salt spray corrosion of the terminal interface of the port distributed scheduling equipment with respect to the usage duration; performing a ratio analysis of the network delay of the port distributed scheduling equipment and the network delay threshold of the port distributed scheduling equipment, and correcting it through the first scheduling proportion factor for the change of port equipment scheduling characteristics to obtain the first component of the performance evaluation fluctuation of the port distributed scheduling equipment; performing a ratio analysis of the network bit error rate of the port distributed scheduling equipment and the network bit error rate threshold of the port distributed scheduling equipment, and correcting it through the second scheduling proportion factor for the change of port equipment scheduling characteristics to obtain the second component of the performance evaluation fluctuation of the port distributed scheduling equipment; performing a ratio analysis of the average failure rate of the port distributed scheduling equipment and the average failure rate threshold of the port distributed scheduling equipment, and correcting it through the third scheduling proportion factor for the change of port equipment scheduling characteristics to obtain the third component of the performance evaluation fluctuation of the port distributed scheduling equipment; performing a coupling analysis on the first component of the performance evaluation fluctuation of the port distributed scheduling equipment, the second component of the performance evaluation fluctuation of the port distributed scheduling equipment, and the third component of the performance evaluation fluctuation of the port distributed scheduling equipment, and then correcting it through the correction factor for the salt spray corrosion of the terminal interface of the port distributed scheduling equipment with respect to the usage duration to obtain the mutation value of the performance evaluation fluctuation of the port distributed scheduling equipment.

[0062] In this embodiment, for the collected device parameters, it specifically refers to the distributed computing power scheduling equipment called for starting the distributed resource scheduling in the above text.

[0063] Number the monitoring points of the distributed port scheduling equipment. Indicates the numbering of the monitoring points of the distributed port scheduling equipment. , Indicates the total number of the numbering of the monitoring points of the distributed port scheduling equipment.

[0064] Indicates the th mutation value of the performance evaluation fluctuation of the port distributed scheduling equipment at the th monitoring point of the distributed port scheduling equipment for the

[0065] The environmental monitoring points for the intelligent scheduling of port goods in a distributed manner correspond to at least one monitoring point for the distributed port scheduling equipment. In actual deployment, multiple monitoring points for the distributed port scheduling equipment are set inside the specific distributed port scheduling equipment, and at least one environmental monitoring point for the intelligent scheduling of port goods in a distributed manner is set outside the distributed port scheduling equipment.

[0066] ; ; The network probe built into the port distributed scheduling equipment performs real-time packet capture and analysis to obtain the network latency and network error rate of the port distributed scheduling equipment.

[0067] represents the th network latency of the th monitoring point of the distributed port scheduling equipment for the th environmental monitoring point for the intelligent scheduling of port goods in a distributed manner.

[0068]

[0069] represents the th network error rate of the th monitoring point of the distributed port scheduling equipment for the

[0070] th environmental monitoring point for the intelligent scheduling of port goods in a distributed manner.

[0071] The historical operation data of the corresponding equipment, including the operation time of the equipment, the time of fault occurrence, and the type of fault, etc. These data can be obtained through equipment maintenance records, fault logs, or equipment monitoring systems. According to the collected data, calculate the operation time between each fault. This can be calculated by the difference between the time points of fault occurrence. Add up the operation times between all faults, and then divide by the number of faults to obtain the mean time between failures and the average failure rate of the equipment.

[0072] represents the th average failure rate of the th monitoring point of the distributed port scheduling equipment for the

[0073] It represents the average failure rate threshold of the port distributed scheduling device, which is directly extracted from the port cargo intelligent scheduling environment assessment database.

[0074] Through the electrochemistry corrosion rate probe (such as Rohrback Cosasco) built in the port distributed scheduling device: The basic rate of salt spray corrosion of the terminal interface of the port distributed scheduling device in the following text is measured (unit: μm / year).

[0075] Deployment location: The device interface panel (next to RJ45 / USB ports) or the grounding copper bar of the power distribution cabinet: Monitor the corrosion risk of the grounding system.

[0076] It represents the th correction factor of the salt spray corrosion of the terminal interface of the port distributed scheduling device for the th distributed port cargo intelligent scheduling environment monitoring point. The correction factor of the salt spray corrosion of the terminal interface of the port distributed scheduling device for the usage duration is extracted from the port cargo intelligent scheduling environment assessment database.

[0077] The correction factor of the salt spray corrosion of the terminal interface of the port distributed scheduling device for the usage duration is a dynamic parameter used to quantify the impact of the corrosion rate of the terminal interface of the port distributed scheduling device in the salt spray environment on the service life of the device. Its core purpose is to predict the degree of life attenuation of the device interface by real-time monitoring of the environmental corrosion intensity, device material characteristics and historical data models.

[0078] When is greater than 1: It indicates that the current corrosion rate exceeds the reference value, the device life accelerates to decay, and the maintenance cycle needs to be shortened or the task load needs to be reduced. When is less than 1: It indicates that the corrosion rate is lower than expected, and the device life can be appropriately extended.

[0079] Salt spray concentration: The concentration of chloride ions in the air is monitored by a laser scattering sensor (unit: micrograms per cubic meter), which is positively correlated with the corrosion rate.

[0080] Temperature and humidity: High temperature and high humidity environments will significantly accelerate corrosion, which needs to be collected in real time through temperature and humidity sensors. For example, in an environment with a temperature greater than 40°C and a humidity greater than 80%, the interface corrosion rate accelerates by 10%.

[0081] The calculation example of the correction factor of the salt spray corrosion of the terminal interface of the port distributed scheduling device for the usage duration is as follows: Reference corrosion rate: Measured through an accelerated aging test under laboratory standard conditions (salt spray concentration 50 micrograms per cubic meter, temperature 25°C, humidity 60%).

[0082] Material corrosion resistance coefficient: Different materials correspond to different corrosion resistance capabilities (for example, the corrosion resistance of a gold-plated interface is 3 times that of a tin-plated interface).

[0083] Environmental correction coefficient: Based on the historical data, a joint mapping model of temperature, humidity, and salt spray concentration on the corrosion rate is fitted to obtain a joint mapping model of salt spray concentration, temperature, and humidity and the correction factor of the salt spray corrosion of the terminal interface of the port distributed scheduling equipment with respect to the usage duration. By inputting the real-time salt spray concentration, temperature, and humidity, the correction factor of the salt spray corrosion of the terminal interface of the port distributed scheduling equipment with respect to the usage duration is obtained.

[0084] It represents the first scheduling proportion factor of the port equipment scheduling characteristic change, which is directly extracted from the port cargo intelligent scheduling environment evaluation database.

[0085] It represents the second scheduling proportion factor of the port equipment scheduling characteristic change, which is directly extracted from the port cargo intelligent scheduling environment evaluation database.

[0086] It represents the third scheduling proportion factor of the port equipment scheduling characteristic change, which is directly extracted from the port cargo intelligent scheduling environment evaluation database.

[0087] Relative humidity is another natural factor in the port environment that can significantly affect the network latency, network error rate, and average failure rate of the distributed scheduling equipment at the same time. Heat dissipation suppression: A high-humidity environment reduces the air thermal conductivity efficiency, resulting in a decrease in the equipment's heat dissipation capacity, an increase in the chip temperature, and thus a performance degradation. Electrical performance degradation: Moisture penetrates into electronic components, increasing the leakage current and signal noise, and affecting the communication stability. Accelerated material corrosion: The combined action of high humidity and environmental factors such as salt spray accelerates metal oxidation and electrochemical corrosion, shortening the equipment life.

[0088] The increase in humidity leads to a decrease in the heat sink efficiency. For every 10°C increase in the chip junction temperature, the processing delay increases by about 5%. When the environmental humidity rises from 50% to 90%, the FPGA task processing delay increases by 20% to 35%. Through constant humidity experiments, it is found that for every 10% increase in humidity, the equipment's heat dissipation efficiency decreases by 2% to 5%, and the chip temperature rises by 3 to 8°C.

[0089] When the moisture reduces the insulation resistance of the equipment communication module from 1 GΩ to 100 MΩ, the signal-to-noise ratio decreases by 3 to 6 dB. Condensation on the end face of the fiber optic connector increases the optical reflection loss by 0.2 to 0.8 dB, and the error rate increases significantly. When the humidity is greater than 80%, the fiber optic error rate increases by one order of magnitude.

[0090] High humidity accelerates electrochemical migration, triggering dendritic short circuits in the device communication module. When the humidity is greater than 70%, the migration rate of copper ions increases exponentially. The lifespan of aluminum electrolytic capacitors in an environment with 90% humidity is shortened by 60% to 80% compared to that in an environment with 50% humidity.

[0091] An example of the extraction and calculation method of the scheduling proportion factor is as follows: Environmental simulation: Simulate an environment with a humidity of 30% to 95% in a humidity chamber and record the device performance data.

[0092] Key tests: Use an infrared thermal imager to monitor the temperature change of the chip, an LCR meter to measure the insulation resistance of the PCB, and a HALT test to evaluate the failure rate.

[0093] Parameter calibration: Determine the sensitivity coefficients of humidity to delay, bit error rate, and failure rate through multiple regression analysis. Normalize the three types of scheduling proportion factors to the range of 0 to 1 to ensure that the sum of the comprehensive proportions is 1, and construct the mapping relationship between the environmental humidity of the monitoring points of the distributed port scheduling device and the first scheduling proportion factor of the corresponding port device scheduling characteristic change, the second scheduling proportion factor of the port device scheduling characteristic change, and the third scheduling proportion factor of the port device scheduling characteristic change. Input the real-time environmental humidity of the monitoring points of the distributed port scheduling device to obtain the corresponding first scheduling proportion factor of the port device scheduling characteristic change, the second scheduling proportion factor of the port device scheduling characteristic change, and the third scheduling proportion factor of the port device scheduling characteristic change.

[0094] Furthermore, comparative analysis and adjustment are carried out according to the fluctuation parameters of the port scheduling device, specifically including: If the fluctuation mutation value of the performance evaluation of the port distributed scheduling device is less than the fluctuation mutation threshold of the performance evaluation of the port distributed scheduling device, record the corresponding port distributed scheduling device, denoted as the first node to be adjusted of the port distributed scheduling device; If the fluctuation mutation value of the performance evaluation of the port distributed scheduling device is equal to or greater than the fluctuation mutation threshold of the performance evaluation of the port distributed scheduling device, record the corresponding port distributed scheduling device, denoted as the second node to be adjusted of the port distributed scheduling device and perform emergency anti-corrosion and dehumidification treatment. Arrange the fluctuation mutation values of the performance evaluations of the port distributed scheduling devices corresponding to the second node to be adjusted of the port distributed scheduling device in descending order, and gradually migrate the corresponding computing tasks to the first node to be adjusted of the port distributed scheduling device in the descending order of the second node to be adjusted of the port distributed scheduling device arranged.

[0095] In this embodiment, as Figure 3 shown, it is a schematic flowchart of comparative analysis and adjustment according to the fluctuation parameters of the port scheduling device provided by the embodiment of the present application.

[0096] Perform emergency anti-corrosion and dehumidification treatments. For example, start the high-pressure nitrogen anti-corrosion spraying device, trigger the anti-corrosion spraying once every ten minutes, and at the same time start the dehumidifier to maintain the humidity below 60%.

[0097] Sequentially arrange the second nodes to be adjusted of the port distributed scheduling device in descending order, and gradually migrate the corresponding computing tasks to the first node to be adjusted of the port distributed scheduling device, that is, migrate the computing tasks of the high-load node to the low-load or low-environment-risk node. The task migration is achieved through the 5G TSN network (end-to-end delay is less than 10 ms). Based on the task-to-node matching model of the Hungarian algorithm, minimize the migration cost (delay + energy consumption).

[0098] Furthermore, conduct a comprehensive evaluation and analysis of the port scheduling distributed computing node device, specifically including: directly extracting from the port cargo intelligent scheduling environment evaluation database the comprehensive first scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device, the comprehensive second scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device, and the correction factor of the local temperature rise rate of the port distributed scheduling device for the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device; perform coupling analysis on the port cargo intelligent scheduling environment evaluation mutation value through the comprehensive first scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device to obtain the first component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent scheduling device; perform coupling analysis on the performance evaluation fluctuation mutation value of the port distributed scheduling device through the comprehensive second scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device to obtain the second component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent scheduling device; perform coupling analysis on the first component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent scheduling device and the second component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent scheduling device, and then correct through the correction factor of the local temperature rise rate of the port distributed scheduling device for the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device to obtain the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device.

[0099] In this embodiment, as Figure 4 shown, it is a schematic flow diagram of the comprehensive evaluation and analysis of the port scheduling distributed computing node device provided by the embodiment of the present application. Number the distributed port cargo intelligent scheduling environment monitoring points, represents the numbering of the distributed port cargo intelligent scheduling environment monitoring points, , represents the total number of the numbering of the distributed port cargo intelligent scheduling environment monitoring points.

[0100] ; ; Indicates the th integrated risk value of distributed computing power resources of port cargo intelligent scheduling equipment for the th distributed port scheduling equipment monitoring point among the

[0101] Indicates the mutation value of the port cargo intelligent scheduling environment assessment for the

[0102] Indicates the th distributed port scheduling equipment monitoring point among the fluctuation mutation value of the performance assessment of port distributed scheduling equipment for the

[0103] Indicates the th distributed port scheduling equipment monitoring point among the th correction factor of the local temperature rise rate of port distributed scheduling equipment for the integrated risk value of distributed computing power resources of port cargo intelligent scheduling equipment, and the correction factor of the salt spray corrosion of the terminal interface of port distributed scheduling equipment for the usage duration are obtained from the port cargo intelligent scheduling environment assessment database. The mapping relationship between the local temperature rise rate of port distributed scheduling equipment and the correction factor of the local temperature rise rate of port distributed scheduling equipment for the integrated risk value of distributed computing power resources of port cargo intelligent scheduling equipment is obtained through actual port historical data. By inputting the real-time local temperature rise rate of port distributed scheduling equipment, the correction factor of the local temperature rise rate of port distributed scheduling equipment for the integrated risk value of distributed computing power resources of port cargo intelligent scheduling equipment is obtained.

[0104] Local temperature rise rate, which is the rising amplitude of the temperature of the equipment or environmental monitoring point per unit time, reflecting the state of heat accumulation and heat dissipation imbalance. High temperature gradients cause local air flow disturbances, resulting in abnormal data of wind speed sensors. The local temperature rise rate accelerates the evaporation of the surrounding seawater, increasing the concentration of nearshore salt spray. Hardware frequency reduction: When the local temperature rise rate exceeds the corresponding threshold, it triggers the CPU to reduce the frequency urgently, leading to a mismatch in the thermal expansion coefficient of the PCB and increasing the risk of solder joint cracking. The high temperature rise rate causes the wavelength drift of the optical module to accelerate, significantly increasing the bit error rate of the optical fiber. The coupling effect of the local temperature rise rate and other factors, the combination of high temperature rise rate and salt spray increases the corrosion rate. Interaction with humidity: The high temperature rise rate causes condensate to accumulate inside the equipment, increasing the probability of short circuits. Interaction with network load: When the computing power load is high, the local temperature rise rate is linearly positively correlated with the load. It represents the comprehensive first scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device, which is directly extracted from the port cargo intelligent scheduling environment evaluation database. It represents the comprehensive second scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device, which is directly extracted from the port cargo intelligent scheduling environment evaluation database. The comprehensive second scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device is used to correct the current load and temperature changes of the monitoring device, quantify the risk of sudden failures, and facilitate triggering the load diversion mechanism.

[0105] The comprehensive first scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device is used to combine historical load data and the salt spray corrosion environment to predict the equipment life attenuation. Long-term high load will accelerate salt spray corrosion and hardware fatigue.

[0106] Construct the relationship between the distributed computing power utilization rate of the port cargo intelligent scheduling device, the comprehensive first scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device, and the comprehensive second scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device, and obtain the mapping model of the distributed computing power utilization rate of the port cargo intelligent scheduling device, the comprehensive first scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device, and the comprehensive second scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device. Input the distributed computing power utilization rate of the port cargo intelligent scheduling device to obtain the corresponding comprehensive first scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device and the comprehensive second scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device.

[0107] Furthermore, conduct comparative analysis and adjustment according to the comprehensive evaluation analysis results, specifically including: if the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device is less than the comprehensive risk threshold of the distributed computing power resources of the port cargo intelligent scheduling device, then gradually migrate the corresponding computing tasks to the first node to be adjusted of the port distributed scheduling device in the descending order of the second nodes to be adjusted of the port distributed scheduling device arranged in descending order, and mark the corresponding port cargo intelligent scheduling devices as secondary high-level computing power nodes according to the predefined percentage in the descending order, and reserve the computing power resources with the predefined computing power percentage for the secondary high-level computing power nodes.

[0108] In this embodiment, when the system comprehensive risk value is lower than the preset threshold, it indicates that the current operating environment is relatively stable, but preventive measures still need to be taken to maintain the high efficiency and security of the system.

[0109] Intelligent task scheduling: Through the Kubernetes cluster management system, real-time monitor the computing resource usage of each edge node (such as CPU and GPU utilization rate). If the resource occupancy rate of a certain node exceeds 80%, automatically migrate some tasks to the idle node to ensure overall load balancing.

[0110] Reserve computing power resources for secondary high-level computing power nodes with a predefined percentage of computing power. For example, reserve 10% of the computing power resources in advance to handle sudden tasks such as typhoon warning data processing, and avoid response delays caused by resource occupation.

[0111] Furthermore, according to the comparative analysis and adjustment based on the comprehensive evaluation analysis results, it also includes: if the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device is equal to or greater than the comprehensive risk threshold of the distributed computing power resources of the port cargo intelligent scheduling device, then increase the rotation speed of the cooling fan of the corresponding port cargo intelligent scheduling device and start the liquid cooling system of the corresponding port cargo intelligent scheduling device. Arrange the comprehensive risk values of the distributed computing power resources of the port cargo intelligent scheduling device in descending order, and mark the port cargo intelligent scheduling devices within the corresponding predefined percentage as high-level computing power nodes according to the predefined percentage. Switch the wireless link of the port cargo intelligent scheduling device to the fiber-optic private network and stop allocating computing power tasks to it.

[0112] In this embodiment, increase the rotation speed of the cooling fan of the corresponding port cargo intelligent scheduling device and start the liquid cooling system of the corresponding port cargo intelligent scheduling device. For example, increase the rotation speed of the cooling fan in advance and start the liquid cooling system at the same time to forcibly limit the maximum power consumption of the device to 70% of the nominal value.

[0113] Prevent the chip from triggering frequency reduction protection due to overheating. If the chip triggers frequency reduction protection due to overheating, the distributed computing power resources of the corresponding port cargo intelligent scheduling device will drop significantly, and it will no longer be possible to meet the timeliness requirements by then when calling the distributed computing power resources. Mark the corresponding port cargo intelligent scheduling devices as high-level computing power nodes according to the predefined percentage, stop allocating computing power tasks to them, sort the nodes according to the performance fluctuation value, and mark the nodes in the top predefined percentage as "high-risk nodes" and stop allocating new tasks to them. If the failure rate of a certain node surges due to too high salt spray concentration, the system will automatically freeze its task queue. Immediately switch the wireless link used for communication to the fiber-optic private network and enable forward error correction coding to reduce the bit error rate.

[0114] Through the above hierarchical adjustment strategy, the system provides high-reliability and adaptive intelligent scheduling guarantee for port operations through the deep integration of environment perception, real-time decision-making, and multi-dimensional control.

[0115] As Figure 5 shown, it is a schematic flowchart of the method for intelligent scheduling of port cargo based on big data analysis provided by the embodiment of the present application. The embodiment of the present application provides a method for intelligent scheduling of port cargo based on big data analysis, which is characterized in that the specific steps are as follows: Evaluate and analyze the port cargo environment parameters, and conduct comparative analysis and adjustment according to the port cargo environment parameters; Evaluate and analyze the fluctuation parameters of port scheduling equipment, and make comparative analysis and adjustment according to the fluctuation parameters of port scheduling equipment; Comprehensively evaluate and analyze the port scheduling distributed computing node equipment, and make comparative analysis and adjustment according to the comprehensive evaluation and analysis results.

[0116] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CDROM, optical storage, etc.) containing computer-usable program code.

[0117] The present invention is described with reference to the flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0118] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0120] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0121] Obviously, those skilled in the art can make various changes and deformations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and deformations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and deformations.

Claims

1. An intelligent port cargo scheduling system based on big data analysis, characterized in that, It includes an environmental acquisition and evaluation module, a first comparative analysis and invocation module of the cargo intelligent scheduling distributed computing node, and a second comparative analysis and invocation module of the cargo intelligent scheduling distributed computing node; Among them, the environmental acquisition and evaluation module is used to evaluate and analyze the port cargo environmental parameters, and make comparative analysis and adjustment according to the port cargo environmental parameters; The first comparative analysis and invocation module of the cargo intelligent scheduling distributed computing node is used to evaluate and analyze the port scheduling equipment fluctuation parameters, and make comparative analysis and adjustment according to the port scheduling equipment fluctuation parameters; The second comparative analysis and invocation module of the cargo intelligent scheduling distributed computing node is used to comprehensively evaluate and analyze the port scheduling distributed computing node equipment, and make comparative analysis and adjustment according to the comprehensive evaluation and analysis results.

2. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein The making of comparative analysis and adjustment according to the port cargo environmental parameters specifically includes: Collect and obtain the port environmental wind speed through a wind speed sensor, collect and obtain the highest value of the port environmental seawater level through a water level sensor, and collect and obtain the highest value of the rainfall per unit time through a rainfall sensor; If the highest value of the port environmental seawater level is less than the highest value threshold of the port environmental seawater level and the highest value of the rainfall per unit time is less than the highest value threshold of the rainfall per unit time and the port environmental wind speed is less than the port environmental wind speed threshold, then conduct a mutation assessment of the port cargo intelligent scheduling environment assessment. If the highest value of the port environmental seawater level is equal to or greater than the highest value threshold of the port environmental seawater level or the highest value of the rainfall per unit time is equal to or greater than the highest value threshold of the rainfall per unit time or the port environmental wind speed is equal to or greater than the port environmental wind speed threshold, then issue a warning and notify the relevant personnel to raise the port cargo intelligent scheduling warning level to the highest level.

3. The intelligent port cargo scheduling system based on big data analysis according to claim 2, characterized in that, The conducting of the mutation assessment of the port cargo intelligent scheduling environment assessment specifically includes: Collect and obtain the highest value of the port environmental salt fog concentration through an online salt fog monitor by laser scattering method; Extract from the port cargo intelligent scheduling environment assessment database the historical average value of the port environmental seawater level, the historical average value of the port environmental salt fog concentration, the correction factor of the port environmental sea wind speed for the port environmental seawater level, the historical average value of the port environmental rainfall, the first scheduling proportion factor of the port cargo environmental characteristic change, the second scheduling proportion factor of the port cargo environmental characteristic change, and the third scheduling proportion factor of the port cargo environmental characteristic change; Conduct a ratio analysis of the highest value of the port environmental seawater level and the historical average value of the port environmental seawater level, correct it through the correction factor of the port environmental sea wind speed for the port environmental seawater level, and then correct it through the first scheduling proportion factor of the port cargo environmental characteristic change to obtain the first component of the port cargo intelligent scheduling environment assessment mutation; Conduct a ratio analysis of the highest value of the port environmental salt fog concentration and the historical average value of the port environmental salt fog concentration, and correct it through the second scheduling proportion factor of the port cargo environmental characteristic change to obtain the second component of the port cargo intelligent scheduling environment assessment mutation; Perform a ratio analysis of the maximum value of the port environmental rainfall and the historical average value of the port environmental rainfall, and correct it through the third scheduling proportion factor of the port cargo environmental characteristic change to obtain the third component of the port cargo intelligent scheduling environment evaluation mutation; Perform a coupling analysis through the first component of the port cargo intelligent scheduling environment evaluation mutation, the second component of the port cargo intelligent scheduling environment evaluation mutation, and the third component of the port cargo intelligent scheduling environment evaluation mutation to obtain the port cargo intelligent scheduling environment evaluation mutation value.

4. The intelligent port cargo scheduling system based on big data analysis according to claim 1, characterized in that, The specific process of comparative analysis and adjustment according to the port cargo environmental parameters is as follows: If the port cargo intelligent scheduling environment evaluation mutation value is less than the port cargo intelligent scheduling environment evaluation mutation threshold, no adjustment is made; If the port cargo intelligent scheduling environment evaluation mutation value is equal to or greater than the port cargo intelligent scheduling environment evaluation mutation threshold, perform a coupling analysis of the port cargo intelligent scheduling environment evaluation mutation value and the real-time centralized computing power load utilization rate of the port cargo intelligent scheduling resource center to obtain the port cargo intelligent scheduling resource center coupling value. The port cargo intelligent scheduling resource center coupling value is used to quantitatively represent the relative scarcity risk degree of the schedulable resources of the port cargo intelligent scheduling resource center. If the port cargo intelligent scheduling resource center coupling value is less than the port cargo intelligent scheduling resource center coupling threshold, send a notice to relevant personnel and do not start the automated distributed resource scheduling temporarily. If the port cargo intelligent scheduling resource center coupling value is equal to or greater than the port cargo intelligent scheduling resource center coupling threshold, start the distributed resource scheduling.

5. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein The evaluation and analysis of the port scheduling equipment fluctuation parameters specifically include: Collect the port distributed scheduling equipment network delay and the port distributed scheduling equipment network error rate through the tools built in the port distributed scheduling equipment; Directly extract from the port cargo intelligent scheduling environment evaluation database the port distributed scheduling equipment network delay threshold, the port distributed scheduling equipment network error rate threshold, the port distributed scheduling equipment average failure rate threshold, the first scheduling proportion factor of the port equipment scheduling characteristic change, the second scheduling proportion factor of the port equipment scheduling characteristic change, the third scheduling proportion factor of the port equipment scheduling characteristic change, and the correction factor of the port distributed scheduling equipment terminal interface salt spray corrosion for the usage duration; Perform a ratio analysis of the port distributed scheduling equipment network delay and the port distributed scheduling equipment network delay threshold, and correct it through the first scheduling proportion factor of the port equipment scheduling characteristic change to obtain the first component of the port distributed scheduling equipment performance evaluation fluctuation; Perform a ratio analysis of the port distributed scheduling equipment network error rate and the port distributed scheduling equipment network error rate threshold, and correct it through the second scheduling proportion factor of the port equipment scheduling characteristic change to obtain the second component of the port distributed scheduling equipment performance evaluation fluctuation; Perform a ratio analysis of the port distributed scheduling equipment average failure rate and the port distributed scheduling equipment average failure rate threshold, and correct it through the third scheduling proportion factor of the port equipment scheduling characteristic change to obtain the third component of the port distributed scheduling equipment performance evaluation fluctuation; Perform coupling analysis on the first component of the performance evaluation fluctuation of the port distributed scheduling device, the second component of the performance evaluation fluctuation of the port distributed scheduling device, and the third component of the performance evaluation fluctuation of the port distributed scheduling device, and then correct it through the correction factor of the salt spray corrosion of the terminal interface of the port distributed scheduling device for the service life to obtain the mutation value of the performance evaluation fluctuation of the port distributed scheduling device.

6. The intelligent port cargo scheduling system based on big data analysis according to claim 1, characterized in that The comparison analysis and adjustment according to the port scheduling device fluctuation parameters specifically include: If the mutation value of the performance evaluation fluctuation of the port distributed scheduling device is less than the mutation threshold of the performance evaluation fluctuation of the port distributed scheduling device, record the corresponding port distributed scheduling device, denoted as the first node to be adjusted of the port distributed scheduling device; If the mutation value of the performance evaluation fluctuation of the port distributed scheduling device is equal to or greater than the mutation threshold of the performance evaluation fluctuation of the port distributed scheduling device, record the corresponding port distributed scheduling device, denoted as the second node to be adjusted of the port distributed scheduling device and perform emergency anti-corrosion and dehumidification treatment. Arrange the mutation values of the performance evaluation fluctuations of the port distributed scheduling devices corresponding to the second node to be adjusted of the port distributed scheduling device in descending order, and gradually migrate the corresponding computing tasks to the first node to be adjusted of the port distributed scheduling device in the descending order of the second node to be adjusted of the port distributed scheduling device after arrangement.

7. The intelligent port cargo scheduling system based on big data analysis according to claim 1, characterized in that, The comprehensive evaluation and analysis of the port scheduling distributed computing node device specifically include: Directly extract from the port cargo intelligent scheduling environment evaluation database the comprehensive first scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device, the comprehensive second scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device, and the correction factor of the local temperature rise rate of the port distributed scheduling device for the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device; Perform coupling analysis on the mutation value of the port cargo intelligent scheduling environment evaluation through the comprehensive first scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device to obtain the first component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent scheduling device; Perform coupling analysis on the mutation value of the performance evaluation fluctuation of the port distributed scheduling device through the comprehensive second scheduling proportion factor of the distributed computing power resources of the port cargo intelligent scheduling device to obtain the second component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent scheduling device; Perform coupling analysis on the first component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent scheduling device and the second component of the comprehensive risk of the distributed computing power resources of the port cargo intelligent scheduling device, and then correct it through the correction factor of the local temperature rise rate of the port distributed scheduling device for the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device to obtain the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device.

8. The intelligent port cargo scheduling system based on big data analysis according to claim 1, wherein The comparison analysis and adjustment according to the comprehensive evaluation and analysis results specifically include: If the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device is less than the comprehensive risk threshold of the distributed computing power resources of the port cargo intelligent scheduling device, the second nodes to be adjusted of the port distributed scheduling device after sorting will be gradually migrated to the first nodes to be adjusted of the port distributed scheduling device in the descending order, and the corresponding port cargo intelligent scheduling devices will be marked as secondary high computing power nodes according to the predefined percentage after sorting in the descending order, and the computing power resources with the predefined computing power percentage will be reserved for the secondary high computing power nodes.

9. The intelligent port cargo scheduling system based on big data analysis according to claim 1, characterized in that The comparison and analysis adjustment according to the comprehensive evaluation analysis results further includes: If the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device is equal to or greater than the comprehensive risk threshold of the distributed computing power resources of the port cargo intelligent scheduling device, the rotation speed of the cooling fan of the corresponding port cargo intelligent scheduling device will be increased and the liquid cooling system of the corresponding port cargo intelligent scheduling device will be started, and the port cargo intelligent scheduling devices will be sorted in the descending order according to the comprehensive risk value of the distributed computing power resources of the port cargo intelligent scheduling device. The port cargo intelligent scheduling devices within the corresponding predefined percentage will be marked as high computing power nodes, the wireless link of the port cargo intelligent scheduling device will be switched to the fiber optic private network, and the allocation of computing power tasks to it will be stopped.

10. The intelligent scheduling method for port cargo based on big data analysis is characterized in that, The specific steps are as follows: Evaluate and analyze the port cargo environmental parameters, and make comparison and analysis adjustments according to the port cargo environmental parameters; Evaluate and analyze the port scheduling device fluctuation parameters, and make comparison and analysis adjustments according to the port scheduling device fluctuation parameters; Conduct a comprehensive evaluation and analysis of the port scheduling distributed computing node devices, and make comparison and analysis adjustments according to the comprehensive evaluation and analysis results.

Images