CN117114559B - Weather factor optimization algorithm in dynamic programming of internal trade containerized route - Google Patents
Weather factor optimization algorithm in dynamic programming of internal trade containerized route Download PDFInfo
- Publication number
- CN117114559B CN117114559B CN202311376766.5A CN202311376766A CN117114559B CN 117114559 B CN117114559 B CN 117114559B CN 202311376766 A CN202311376766 A CN 202311376766A CN 117114559 B CN117114559 B CN 117114559B
- Authority
- CN
- China
- Prior art keywords
- data
- waypoint
- weather
- algorithm
- route
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 43
- 238000005457 optimization Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000008713 feedback mechanism Effects 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 210000002569 neuron Anatomy 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 16
- 238000013524 data verification Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 238000011478 gradient descent method Methods 0.000 claims description 5
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 8
- 238000007405 data analysis Methods 0.000 abstract description 6
- 238000013480 data collection Methods 0.000 abstract description 6
- 239000011159 matrix material Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000004806 packaging method and process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012795 verification Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000009022 nonlinear effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of data processing, in particular to a weather factor optimization algorithm in dynamic planning of a trade containerized route. Firstly, constructing a topological neural network to predict future weather conditions; then, calculating an optimal navigation path by adopting a dynamic planning algorithm, and optimizing route planning; then, designing a real-time data synchronization system; and finally, designing a data feedback mechanism, and continuously optimizing the model. The method solves the problems that the prior art possibly does not have a real-time data synchronization system and a data feedback mechanism, so that the used weather data is possibly not up to date, and the model cannot be updated and optimized in time according to the actual navigation data, thereby affecting the accuracy of the route planning; and the prior art may rely too much on external meteorological data sources, and does not build own data collection and analysis system, resulting in the problem that the optimization strategy is not flexible and personalized enough.
Description
Technical Field
The invention relates to the field of data processing, in particular to a weather factor optimization algorithm in dynamic planning of a trade containerized route.
Background
With the development of globalization, shipping is becoming increasingly important as the most prominent means of international trade transport. Container shipping has become a major means of cargo transportation, particularly in the field of internal commerce. The internal trade packaging line is an important component of cargo transportation, and the efficiency and safety of the internal trade packaging line directly influence the operation of the whole supply chain. Traditional route planning methods rely primarily on experience and simple algorithms, often without fully taking into account a variety of influencing factors, particularly weather conditions. Therefore, how to accurately consider weather factors in route planning to improve the safety and efficiency of navigation is a highly desirable problem.
Chinese patent application number: CN202211037203.9, publication date: 2022.11.25A container ship safe navigation system and method based on big data technology comprises a ship body stress monitoring module, a finite element strength analysis module, a loading computer module and a navigation line optimization module. By monitoring the stress of the ship body in real time, an alarm is given when the stress of the ship body exceeds a target value; the navigation direction with smaller stress is found by adopting a finite element strength analysis system, then the navigation direction of a ship relative to waves is changed, the wind waves are avoided, the stress caused by wave load is reduced, the distribution of ballast water in a ballast tank of the ship is adjusted, and the stress caused by static water load is reduced, so that the total stress level of the ship body is reduced together in two aspects, and the container ship body is prevented from breaking. On the premise of ensuring safety, the invention utilizes the navigation route optimization module to plan the most available route and speed, and ensures that the energy consumption of the ship in the whole course is the lowest, thereby being safe and energy-saving.
However, the above technology has at least the following technical problems: the prior art may not have a real-time data synchronization system and a data feedback mechanism, so that the used weather data may not be up-to-date, and the model cannot be updated and optimized in time according to the actual navigation data, thereby affecting the accuracy of route planning, and the prior art may rely too much on an external meteorological data source, and does not establish a data collection and analysis system, so that the optimization strategy is not flexible and personalized enough.
Disclosure of Invention
According to the embodiment of the application, by providing the weather factor optimization algorithm in the dynamic programming of the internal trade container airlines, the problem that in the prior art, a real-time data synchronization system and a data feedback mechanism are not available is solved, so that the used weather data is not up-to-date, the model cannot be updated and optimized in time according to the actual sailing data, the accuracy of the airlines is affected, the prior art can depend on an external meteorological data source too, and a data collection and analysis system of the prior art is not established, so that the optimization strategy is not flexible and personalized enough. The method and the system realize that a comprehensive, efficient and accurate weather factor optimization algorithm is provided for the internal trade containerized route, so that the safety and the efficiency of sailing can be improved, and more accurate and detailed sailing advice can be provided for the ship, thereby helping the ship to better cope with various weather conditions, improving the safety and the efficiency of sailing, saving the cost and improving the environmental friendliness.
The application provides a weather factor optimization algorithm in dynamic programming of an internal trade containerized route, which specifically comprises the following technical scheme:
the weather factor optimization algorithm in the dynamic programming of the inner trade containerized route comprises the following steps:
s100: constructing a topological neural network to predict future weather conditions;
s200: calculating an optimal navigation path by adopting a dynamic programming algorithm, and optimizing route planning;
s300: designing a real-time data synchronization system;
s400: and (5) designing a data feedback mechanism and continuously optimizing the model.
Preferably, the S100 specifically includes:
the topological neural network comprises an input layer, a topological ordering layer, a graph roll layer and an output layer.
Preferably, the step S100 further includes:
each neuron represents a meteorological data point and forms a directed graph with other neurons, and the connection between neurons is based on the similarity between the data points; sorting neurons using topological sorting, the output of which is a sorted data sequence; the graph convolution layer performs a convolution operation on the neighbors of the neuron.
Preferably, the S200 specifically includes:
and calculating an optimal navigation path by adopting a dynamic programming algorithm, scoring for reaching different navigation points at different times, wherein the core of the dynamic programming is a state transition equation.
Preferably, the step S300 specifically includes:
decomposing meteorological data into small data blocks by adopting a distributed synchronization algorithm, and then synchronizing the data blocks in parallel; the hash function is the key of the distributed synchronization algorithm, maps each data block to a specific synchronization task, and adopts a special hash function, wherein the special hash function considers the content and the size of the data.
Preferably, the step S300 further includes:
adopting an optimistic lock algorithm; the method comprises the steps of acquiring the version number of data before starting synchronization, and then checking whether the version number changes after synchronizing the data; when the version number changes, then the data has been modified by other tasks during the synchronization process, thus requiring resynchronization.
Preferably, the step S300 further includes:
because of the different importance of different meteorological data, priority synchronization is required; a priority queue algorithm is used to assign a priority to each data block, and then a priority queue is used to ensure that high priority data blocks are synchronized first.
Preferably, the step S400 specifically includes:
and calculating a predicted value and updating an estimated value according to the dynamic model and the observation model of the system by adopting a data verification method based on Kalman filtering.
Preferably, the step S400 further includes:
an online learning strategy based on a random gradient descent method is adopted, and a model is updated each time new data is received; calculating a gradient of the model error with respect to the parameter using the corrected data set; the model parameters are then updated online using a random gradient descent method.
The beneficial effects are that:
the technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
1. the weather conditions in the future can be predicted more accurately by acquiring and processing authoritative meteorological data in real time, so that more accurate reference information is provided for route planning; the importance of weather factors in route planning is considered, so that the ship is helped to avoid severe weather areas, and the sailing safety is improved; the optimal sailing path is provided for the ship through a dynamic planning algorithm, so that sailing time and oil consumption are reduced, and sailing efficiency is improved;
2. the model is ensured to always use the latest weather data through a real-time data synchronization system and a data feedback mechanism, and can be updated rapidly according to actual conditions; by the data verification method based on Kalman filtering, a large amount of meteorological data can be efficiently processed, and the accuracy and instantaneity of the data are ensured; by optimizing the route planning, the vessel can reduce unnecessary voyage time and oil consumption, thereby saving cost.
3. According to the technical scheme, the problem that in the prior art, a real-time data synchronization system and a data feedback mechanism are not available is effectively solved, so that used weather data are not up-to-date, a model cannot be updated and optimized in time according to actual navigation data, and therefore accuracy of route planning is affected, in the prior art, an external weather data source is excessively depended, a data collection and analysis system is not established, so that an optimization strategy is not flexible and personalized enough, a comprehensive, efficient and accurate weather factor optimization algorithm can be provided for an internal trade container route, safety and efficiency of navigation can be improved, more accurate and detailed navigation advice can be provided for a ship, the ship is helped to better cope with various weather conditions, safety and efficiency of navigation are improved, cost is saved, and environmental friendliness is improved.
Drawings
FIG. 1 is a flow chart of a weather factor optimization algorithm in dynamic programming of an internal trade container route according to the present application;
Detailed Description
According to the embodiment of the application, by providing the weather factor optimization algorithm in the dynamic programming of the internal trade container airlines, the problem that in the prior art, a real-time data synchronization system and a data feedback mechanism are not available is solved, so that the used weather data is not up-to-date, the model cannot be updated and optimized in time according to the actual sailing data, the accuracy of the airlines is affected, the prior art can depend on an external meteorological data source too, and a data collection and analysis system of the prior art is not established, so that the optimization strategy is not flexible and personalized enough.
The technical scheme in the embodiment of the application aims to solve the problems, and the overall thought is as follows:
the weather conditions in the future can be predicted more accurately by acquiring and processing authoritative meteorological data in real time, so that more accurate reference information is provided for route planning; the importance of weather factors in route planning is considered, so that the ship is helped to avoid severe weather areas, and the sailing safety is improved; the optimal sailing path is provided for the ship through a dynamic planning algorithm, so that sailing time and oil consumption are reduced, and sailing efficiency is improved; the model is ensured to always use the latest weather data through a real-time data synchronization system and a data feedback mechanism, and can be updated rapidly according to actual conditions; by the data verification method based on Kalman filtering, a large amount of meteorological data can be efficiently processed, and the accuracy and instantaneity of the data are ensured; by optimizing the route planning, the vessel can reduce unnecessary voyage time and oil consumption, thereby saving cost.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
Referring to fig. 1, the weather factor optimization algorithm in the dynamic programming of the internal trade container airlines described in the application comprises the following steps:
s100: constructing a topological neural network to predict future weather conditions;
in the planning of the internal trade packaging airlines, weather factors play a key role in the selection and optimization of airlines. Acquiring future weather forecast data from authoritative weather data sources, including satellite remote sensing, weather radar and ground observation data; the weather forecast data includes wind speed, wind direction, wave height, rainfall, etc. Basic information of the route, such as a starting point, an ending point, a sailing distance and a ship type, is collected, and the collected data is cleaned and standardized to remove abnormal values and noise. Weather factors are accurately considered in dynamic planning to optimize the route.
A neural network model based on graph theory and topological ordering is constructed and is called a Topological Neural Network (TNN), and the topological neural network processes meteorological data and predicts future weather conditions. The topological neural network comprises an input layer, a topological ordering layer, a graph roll layer and an output layer. The method comprises the following specific steps:
input layer: receiving normalized data, expressed asThe input layer passes the data to the topology ordering layer.
Topology ordering layer: each neuron represents a meteorological data point and forms a directed graph with other neurons, with the connections between neurons being based on similarities between the data points. Ordering neurons using topological ordering to ensure temporal continuity of data, the output of which is an ordered sequence of data, expressed asThe specific formula is as follows:
，
wherein,is a topological ordering matrix for ordering neurons, < >>Is an activation function->Is the bias of the topology ordering layer. The topology ordering layer will output +.>Passed to the graph convolution layer.
Graph convolution layer: the graph convolution layer performs convolution operation on the neighbors of the neurons, and takes the relationship between data points into consideration, and outputs the relationship as follows:
，
wherein,is the output of the picture scroll laminate, +.>Is an adjacency matrix representing the connection relationship between neurons, < ->Is the bias of the picture volume lamination, +.>Is a mask matrix used for hadamard product operations in the convolutional layer of the graph. The graph convolution layer will output +.>To the output layer.
Output layer: predicting future weather conditions, and outputting:
，
wherein,is the output of the output layer, representing predicted future weather conditions,/or->Is the weight matrix of the output layer, +.>Is the bias of the output layer, +.>Is a weight parameter for adjusting the influence of the activation function.
To evaluate the performance of the topological neural network model, k-fold cross-validation was employed. Data setIs randomly divided into k subsets. In each verification, a subset is used as the test set, whichYu Ziji is used as a training set. The average performance of the model is the average of k verifications. Specifically, for each fold, the accuracy is calculated as:
，
wherein,representing the accuracy of the model, +.>Representing the correct predicted number->Representing the total number of predictions.
S200: calculating an optimal navigation path by adopting a dynamic programming algorithm, and optimizing route planning;
in order to optimize the route planning, a dynamic planning algorithm is introduced. The optimal navigation path is calculated by adopting a dynamic programming algorithm, the influence of weather factors is considered, scoring is carried out on different navigation points reached at different times, and the core of dynamic programming is a state transition equation. Specifically, define statesThe best score for the ith day to reach the jth waypoint. The state transition equation is:
，
wherein,representing the base score from waypoint k to waypoint j,/->Indicating weather penalty on day i at waypoint j, +.>Is a weight parameter, considerAll possible routes from the 1 st waypoint to the nth waypoint are taken to find the best route plan, thus +.>Is an integer representing the total number of waypoints in the route, < >>，. Basic score->Is mainly calculated based on the factors of distance between two waypoints, expected navigation time, straightness of a route, safety, economy, environmental influence and the like, and punishment function ∈ ->Based primarily on predicted weather conditions that are adverse to navigation, such as strong winds, rough waves, or storms. As one example, the base score and penalty function may be calculated by the following formula:
，
，
wherein,represents the distance from waypoint k to waypoint j, +.>Represents the expected time from waypoint k to waypoint j, +.>Representing the course safety score from waypoint k to waypoint j, +.>Environmental impact score representing airline, +.>And->Is an exponential parameter that can adjust the nonlinear effects of distance and time. />And->Is a weight parameter, ++>Is a weight parameter for time. />Represents the wind intensity at waypoint j on day i, +.>Representing the wave height at waypoint j on day i, +.>Indicating the amount of rain at waypoint j on day i,/->Is the temperature change at waypoint j on day i,/->Is a weight parameter for balancing the parts in the formula,/->、/>、/>Is a weight parameter for various weather factors.
According to the result of the algorithm, the optimal route selection and navigation path can be obtained. In order to ensure safe sailing of the ship, detailed sailing advice is also provided, including advice for sailing speed, heading adjustment and avoiding bad weather areas.
S300: a real-time data synchronization system is designed, so that the real-time performance of weather data is ensured;
in order to ensure the real-time performance of weather data, a real-time data synchronization system is designed. The system uses APIs to acquire data from authoritative weather data sources and synchronize the data to the database, ensuring that the algorithm always uses the latest weather data.
In order to ensure the efficiency and accuracy of data synchronization, a distributed synchronization algorithm is employed. The core idea of this approach is to break up a large amount of meteorological data into smaller data blocks, which are then synchronized in parallel. The hash function is the key to this approach. It maps each data block to a specific synchronization task. To ensure even data distribution, a special hash function is used that takes into account the content and size of the data.
，
Wherein,is a data block->Which is a function of mapping the data block to a particular sync task. />Is the +.>And each element represents the specific content of the data block. />Is the size of the data block and represents the number of elements in the data block. />And->Is a randomly selected constant for ensuring the randomness and distribution uniformity of the hash function. />Is the number of synchronous tasks, representing the number of parallel tasks in the system.
To ensure consistency of the data, an optimistic lock algorithm is employed. The version number of the data is acquired before synchronization is started, and then it is checked whether the version number is changed after synchronization of the data. If the version number changes, this means that the data has been modified by other tasks during the synchronization process, and therefore a resynchronization is required.
，
Wherein,is the version number of the data block after synchronizing the data, < >>Is the version number of the data block before the synchronization data.
Because of the different importance of the different meteorological data, some meteorological data is more important than others, and therefore priority synchronization is required. To achieve this goal, a priority queue algorithm is employed to assign each data block a priority, and then use the priority queue to ensure that the high priority data blocks are synchronized first.
，
Wherein,is a data block->Representing the importance of the data. />Is the value of the data. />Is a data block->Representing the number of elements in the data block. />Is a data block->And the update frequency of the data is represented as the update times of the data.
S400: and (5) designing a data feedback mechanism and continuously optimizing the model.
To ensure continuous optimization of the model, a data feedback mechanism is designed. In actual sailing, actual sailing data of the ship, such as sailing time, oil consumption, actual weather conditions encountered, etc., are fed back into the system in real time, and accuracy of the real-time data collected from the various data sources needs to be ensured. In order to adapt to changing weather conditions, the model needs to be able to be updated quickly.
Specifically, in order to ensure accuracy of real-time data, a data verification method based on Kalman filtering is adopted. The Kalman filter is a recursive algorithm that can estimate the current state of the system, and can get an accurate estimate even in the presence of noise. According to a dynamic model and an observation model of the system, calculating a predicted value and an updated estimated value, wherein the specific formula is as follows:
predicting the next state based on the model and the previous state estimate, a predicting step:
，
，
wherein,is the predicted value of the state at time t, +.>Is the covariance of the prediction error, C is the state transition matrix, Q is the covariance of the process noise,/>Is a transpose of the matrix.
Using the new observation data to correct the predicted state, an updating step:
，
，
，
wherein,is Kalman gain, +.>Is an observation model matrix, < >>Is the covariance of the observed noise, +.>Is a modified estimate of the state at time t, +.>Is the observed value at the time t,/>is the covariance matrix of the state estimation error at time t,>is an identity matrix. Less->The value means less uncertainty in the state estimation and therefore more accurate estimation. Conversely, larger ∈>The value means that the uncertainty of the state estimation is large. If->Continuously increasing and without convergence, which may mean that the filter is unstable, requiring redesign or adjustment of the parameters of the filter.
In order to quickly update the model under limited computing resources, an online learning strategy based on a random gradient descent method is adopted, and the model is updated each time new data is received. First, a corrected data set is usedThe gradient of the model error with respect to the parameter is calculated. Then, the model parameters are updated online using a random gradient descent method. The specific formula is as follows:
，
，
，
wherein,is to use the corrected data set and parameters +.>Error of calculation +.>Is a model function describing the relation between the output of the model and its parameters>Is the gradient of the error function with respect to the parameter, describes how the error varies with the variation of the parameter, learning rate +.>Controls the update speed of model parameters, +.>Is a parameter of the model that needs to be updated in each iteration to reduce prediction errors and improve the performance of the model, is>And->Is a new and old model parameter.
The algorithm can effectively solve the problems of accuracy of real-time data and quick updating of the model, thereby realizing an efficient and accurate data feedback mechanism and being used for dynamic planning and weather factor optimization of the internal trade packaging airlines.
In conclusion, the weather factor optimization algorithm in the dynamic planning of the internal trade packaging route is completed.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
1. the weather conditions in the future can be predicted more accurately by acquiring and processing authoritative meteorological data in real time, so that more accurate reference information is provided for route planning; the importance of weather factors in route planning is considered, so that the ship is helped to avoid severe weather areas, and the sailing safety is improved; the optimal sailing path is provided for the ship through a dynamic planning algorithm, so that sailing time and oil consumption are reduced, and sailing efficiency is improved;
2. the model is ensured to always use the latest weather data through a real-time data synchronization system and a data feedback mechanism, and can be updated rapidly according to actual conditions; by the data verification method based on Kalman filtering, a large amount of meteorological data can be efficiently processed, and the accuracy and instantaneity of the data are ensured; by optimizing the route planning, the vessel can reduce unnecessary voyage time and oil consumption, thereby saving cost.
Effect investigation:
according to the technical scheme, the problem that in the prior art, a real-time data synchronization system and a data feedback mechanism are not available is effectively solved, so that used weather data may not be up-to-date, a model cannot be updated and optimized in time according to actual navigation data, accuracy of route planning is affected, the prior art may depend too much on an external weather data source, a data collection and analysis system of the system is not established, so that an optimization strategy is inflexible and personalized, a series of effect researches are conducted through the system or the method, through verification, a comprehensive, efficient and accurate weather factor optimization algorithm can be provided for an internal trade integrated route, safety and efficiency of navigation can be improved, more accurate and detailed navigation advice can be provided for a ship, accordingly, the ship can be helped to better cope with various weather conditions, safety and efficiency of navigation are improved, cost is saved, and environmental friendliness is improved.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (2)
1. The weather factor optimization algorithm in the dynamic programming of the internal trade containerized route is characterized by comprising the following steps:
s100: constructing a topological neural network to predict future weather conditions; the topological neural network comprises an input layer, a topological ordering layer, a graph roll layer and an output layer; the topology ordering layer: each neuron represents a meteorological data point and forms a directed graph with other neurons, and the connection between neurons is based on the similarity between the data points; sorting neurons using topological sorting, the output of which is a sorted data sequence; the graph convolution layer carries out convolution operation on the neighbors of the neurons;
s200: by movingCalculating an optimal navigation path by a state planning algorithm, scoring for reaching different navigation points at different time, optimizing route planning, and defining a state transition equation; specifically, define statesThe best score for the ith day to reach the jth waypoint; the state transition equation is:
，
wherein,representing the base score from waypoint k to waypoint j,/->Indicating weather penalty on day i at waypoint j, +.>Is a weight parameter, ++>Is an integer representing the total number of waypoints in the route, < >>，The method comprises the steps of carrying out a first treatment on the surface of the The base score and weather penalty function are calculated by the following formula:
，
，
wherein,represents the distance from waypoint k to waypoint j, +.>Represents the expected time from waypoint k to waypoint j, +.>Representing the course safety score from waypoint k to waypoint j, +.>Environmental impact score representing airline, +.>And->Is an exponential parameter for adjusting the nonlinear influence of distance and time, +.>And->Is a weight parameter, ++>Is a weight parameter of time; />Represents the wind intensity at waypoint j on day i, +.>Representing the wave height at waypoint j on day i, +.>Indicating the amount of rain at waypoint j on day i,/->Is the temperature change at waypoint j on day i,/->Is a weight parameter, ++>、/>、/>Is a weight parameter of various weather factors;
s300: designing a real-time data synchronization system, decomposing meteorological data into small data blocks by adopting a distributed synchronization algorithm, and then synchronizing the data blocks in parallel; introducing an optimistic lock algorithm and a priority queue algorithm, wherein the optimistic lock algorithm is used for ensuring consistency of data, and the priority queue algorithm is used for ensuring that data blocks with high priority are synchronized first;
s400: designing a data feedback mechanism, and continuously optimizing a model; adopting a data verification method based on Kalman filtering, and calculating a predicted value and an updated estimated value according to a dynamic model and an observation model of the system; an online learning strategy based on a random gradient descent method is adopted, and a model is updated each time new data is received.
2. The weather factor optimization algorithm in the dynamic programming of the internal trade container ship according to claim 1, wherein said S300 further comprises:
each data block is mapped to a specific synchronization task using a special hash function that takes into account the content and size of the data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311376766.5A CN117114559B (en) | 2023-10-24 | 2023-10-24 | Weather factor optimization algorithm in dynamic programming of internal trade containerized route |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311376766.5A CN117114559B (en) | 2023-10-24 | 2023-10-24 | Weather factor optimization algorithm in dynamic programming of internal trade containerized route |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117114559A CN117114559A (en) | 2023-11-24 |
| CN117114559B true CN117114559B (en) | 2024-01-23 |
Family
ID=88811392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311376766.5A Active CN117114559B (en) | 2023-10-24 | 2023-10-24 | Weather factor optimization algorithm in dynamic programming of internal trade containerized route |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117114559B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314301B (en) * | 2023-11-29 | 2024-03-22 | 广州一链通互联网科技有限公司 | Transportation route planning method, system and computer equipment for internal trade gathering and transportation |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017033378A (en) * | 2015-08-04 | 2017-02-09 | 国立研究開発法人 海上・港湾・航空技術研究所 | Assignment of ships plan development support method and assignment of ships plan development support system |
| CN110146087A (en) * | 2019-06-14 | 2019-08-20 | 哈尔滨工程大学 | A kind of ship paths planning method based on Dynamic Programming Idea |
| CN110608738A (en) * | 2019-08-14 | 2019-12-24 | 青岛科技大学 | Unmanned ship global meteorological air route dynamic planning method and system |
| EP3633318A1 (en) * | 2018-10-05 | 2020-04-08 | Offshore Navigation Limited | An apparatus for determining an optimal route of a maritime ship |
| CN112328637A (en) * | 2020-10-30 | 2021-02-05 | 中国平安人寿保险股份有限公司 | High-speed distributed data caching method and device, computer equipment and storage medium |
| CN113722127A (en) * | 2021-09-24 | 2021-11-30 | 高小翎 | Efficient lightweight easy-to-use distributed network message middleware |
| CN116234746A (en) * | 2019-11-27 | 2023-06-06 | 株式会社地球气象 | Ship route prediction system and program for the same |
-
2023
- 2023-10-24 CN CN202311376766.5A patent/CN117114559B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017033378A (en) * | 2015-08-04 | 2017-02-09 | 国立研究開発法人 海上・港湾・航空技術研究所 | Assignment of ships plan development support method and assignment of ships plan development support system |
| EP3633318A1 (en) * | 2018-10-05 | 2020-04-08 | Offshore Navigation Limited | An apparatus for determining an optimal route of a maritime ship |
| CN110146087A (en) * | 2019-06-14 | 2019-08-20 | 哈尔滨工程大学 | A kind of ship paths planning method based on Dynamic Programming Idea |
| CN110608738A (en) * | 2019-08-14 | 2019-12-24 | 青岛科技大学 | Unmanned ship global meteorological air route dynamic planning method and system |
| CN116234746A (en) * | 2019-11-27 | 2023-06-06 | 株式会社地球气象 | Ship route prediction system and program for the same |
| CN112328637A (en) * | 2020-10-30 | 2021-02-05 | 中国平安人寿保险股份有限公司 | High-speed distributed data caching method and device, computer equipment and storage medium |
| CN113722127A (en) * | 2021-09-24 | 2021-11-30 | 高小翎 | Efficient lightweight easy-to-use distributed network message middleware |
Non-Patent Citations (1)
| Title |
|---|
| 焦李成等.《现代机器学习 第1版》.西安电子科技大学出版社,2022,第132页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117114559A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117114559B (en) | Weather factor optimization algorithm in dynamic programming of internal trade containerized route | |
| CN113658214B (en) | Trajectory prediction method, collision detection method, apparatus, electronic device, and medium | |
| CN109214559B (en) | Logistics service prediction method and device and readable storage medium | |
| Okoro et al. | Optimization of Maintenance Task Interval of Aircraft Systems. | |
| CN109858681B (en) | Traffic short-time passenger flow prediction method and related device based on IC card | |
| US11830090B2 (en) | Methods and systems for an enhanced energy grid system | |
| US20230104214A1 (en) | Method and system for real time trajectory optimization | |
| EP3502978A1 (en) | Meta-learning system | |
| CN112257947A (en) | Method, device and equipment for predicting temperature and humidity of cigarette making environment | |
| CN110826757B (en) | Flight scheduling method, device and equipment thereof | |
| CN116843071B (en) | Transportation network operation index prediction method and device for intelligent port | |
| CN111582584A (en) | Airline fairness-based flight segment operation time optimization method | |
| CN113379168A (en) | Time series prediction processing method, device and equipment | |
| CN112070272A (en) | Method and device for predicting icing thickness of power transmission line | |
| CN113341919A (en) | Computing system fault prediction method based on time sequence data length optimization | |
| Irawan et al. | Routing in offshore wind farms: A multi-period location and maintenance problem with joint use of a service operation vessel and a safe transfer boat | |
| CN113485443B (en) | Unmanned aerial vehicle control method based on deep learning, storage medium and equipment | |
| CN110009939A (en) | Flight delay prediction and conformance analysis method based on ASM | |
| Shrivastava et al. | Deep learning model for temperature prediction: an empirical study | |
| CN115630979A (en) | Day-ahead electricity price prediction method and device, storage medium and computer equipment | |
| CN111310964B (en) | Load prediction method and device | |
| CN116485162B (en) | Satellite observation task planning method, system and device based on graph calculation | |
| Hernandez | Flex scheduling for bus arrival time prediction | |
| Huang et al. | Data-driven prediction of one-way bus running time: an integrated model | |
| CN111310960A (en) | Energy consumption prediction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |