Intelligent intercommunication network dynamic optimization method and device, and storage medium

Abstract

The invention discloses an intelligent intercommunication network dynamic optimization method and device and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining a traffic intercommunication network, and deploying a data perception module in the traffic intercommunication network; a traffic multi-dimensional operation data flow is acquired in real time through a data sensing module for data cleaning and standardization processing, and a standard traffic multi-dimensional operation data flow is obtained. And establishing a traffic condition prediction network, performing traffic prediction on the standard traffic multi-dimensional operation data flow, and outputting traffic prediction condition parameters. And constructing an intercommunication network optimization strategy space, and performing strategy analysis on the traffic intercommunication network and the traffic prediction condition parameters to obtain intercommunication network optimization strategy parameters. And introducing a feedback mechanism to carry out dynamic topology optimization on the traffic intercommunication network. The technical problems that in the prior art, real-time optimization is difficult to achieve through a traffic management method, an optimization strategy cannot be dynamically adjusted according to the traffic prediction condition, traffic control lags behind, and the traffic efficiency is low are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular, to a method, device, and storage medium for dynamically optimizing an intelligent interconnection network. Background Art

[0002] With the continuous acceleration of the urbanization process and the rapid growth of the motor vehicle ownership, the scale and complexity of the traffic network continue to increase, followed by problems such as road congestion and frequent traffic accidents. Traditional traffic management systems mostly rely on pre-set or empirical signal timing and guidance strategies, lacking the ability to fuse and dynamically update multi-source real-time data, and it is difficult to respond to sudden changes in traffic flow in a timely manner. Therefore, how to dynamically optimize the traffic interconnection network based on real-time data, improve road traffic efficiency, and reduce congestion has become one of the core challenges in intelligent traffic management.

[0003] Therefore, in the prior art, it is difficult for traffic management methods to achieve real-time optimization, and it is impossible to dynamically adjust optimization strategies according to traffic prediction conditions, resulting in technical problems such as lagging traffic regulation and low traffic efficiency. Summary of the Invention

[0004] This application provides a method, device, and storage medium for dynamically optimizing an intelligent interconnection network, which solves the technical problems in the prior art that traffic management methods are difficult to achieve real-time optimization, cannot dynamically adjust optimization strategies according to traffic prediction conditions, resulting in lagging traffic regulation and low traffic efficiency. Through the combination of data perception, traffic prediction, strategy optimization, and feedback mechanism, real-time monitoring, intelligent prediction, global optimization, and dynamic adjustment of the traffic interconnection network are realized, improving road traffic efficiency, reducing congestion duration, and enhancing the automation and intelligence level of traffic management.

[0005] This application provides a method for dynamically optimizing an intelligent interconnection network. The method includes: obtaining a traffic interconnection network, deploying a data perception module in the traffic interconnection network, where the data perception module includes a sensor group, a camera, and a vehicle networking device; acquiring traffic multi-dimensional operation data streams in real time through the data perception module, performing data cleaning and standardization processing on the traffic multi-dimensional operation data streams to obtain standard traffic multi-dimensional operation data streams; establishing a traffic condition prediction network, performing traffic prediction on the standard traffic multi-dimensional operation data streams based on the traffic condition prediction network, and outputting traffic prediction condition parameters; constructing an interconnection network optimization strategy space, using the interconnection network optimization strategy space to perform strategy analysis on the traffic interconnection network and the traffic prediction condition parameters to obtain interconnection network optimization strategy parameters; introducing a feedback mechanism to perform dynamic topology optimization on the traffic interconnection network based on the interconnection network optimization strategy parameters.

[0006] In the implementation manner, obtaining the standard traffic multi-dimensional operation data stream includes: converting the traffic multi-dimensional operation data stream into a unified format according to data application standards to obtain an available traffic multi-dimensional operation data stream; identifying outliers in the available traffic multi-dimensional operation data stream to obtain abnormal traffic operation data, where the abnormal traffic operation data includes missing values, duplicate values, and error values; performing data cleaning processing on the abnormal traffic operation data to obtain a standardized traffic multi-dimensional operation data stream; and performing standardization processing on the standardized traffic multi-dimensional operation data stream using Z-score standardization to obtain the standard traffic multi-dimensional operation data stream.

[0007] In the implementation manner, establishing the traffic condition prediction network includes: mining and obtaining a traffic operation historical data set, where the traffic operation historical data set includes historical traffic operation data and corresponding traffic condition data; performing feature selection and extraction on the traffic operation historical data set according to traffic prediction requirement objectives to obtain a traffic operation feature data set; performing time series annotation on the traffic operation feature data set to obtain a traffic operation sequence feature sample set; and using the ARIMA model to train, verify, and optimize the traffic operation sequence feature sample set to establish the traffic condition prediction network.

[0008] In the implementation manner, constructing the interchange network optimization strategy space includes: analyzing and obtaining a set of key factors affecting the interchange network, where the set of key factors affecting the interchange network includes traffic flow, road conditions, traffic signal control, weather conditions, and traffic accidents; obtaining the interchange network optimization objective, and designing strategies based on the interchange network optimization objective and the set of key factors affecting the interchange network to obtain an interchange network optimization strategy set; and collecting historical optimization data based on the interchange network optimization strategy set to construct the interchange network optimization strategy space.

[0009] In the implementation manner, obtaining the interchange network optimization strategy parameters includes: using the traffic interchange network and the traffic prediction condition parameters as constraint information, performing matching and screening in the interchange network optimization strategy space to obtain an interchange network optimization strategy memory bank; constructing an interchange network optimization fitness function according to the interchange network optimization objective; and using the interchange network optimization fitness function to perform global optimization in the interchange network optimization strategy memory bank to obtain the interchange network optimization strategy parameters.

[0010] In the implementation manner, obtaining the intercommunication network optimization strategy parameters includes: randomly selecting a plurality of network optimization strategy parameters in the intercommunication network optimization strategy memory bank, evaluating the plurality of network optimization strategy parameters by using the intercommunication network optimization fitness function to obtain a plurality of strategy parameter fitnesses; and performing an optimization direction selection and global optimization on the intercommunication network optimization strategy memory bank based on the plurality of strategy parameter fitnesses to obtain the intercommunication network optimization strategy parameters.

[0011] In the implementation manner, the introduction of the feedback mechanism for dynamically optimizing the topology of the traffic intercommunication network based on the intercommunication network optimization strategy parameters includes: determining a dynamic feedback period according to the feedback mechanism, and performing control monitoring on the traffic intercommunication network based on the intercommunication network optimization strategy parameters according to the dynamic feedback period to obtain intercommunication network feedback parameters; correcting the intercommunication network optimization strategy parameters based on the intercommunication network feedback parameters, and performing intercommunication network topology control by using the corrected intercommunication network optimization strategy parameters.

[0012] The present application further provides an electronic device, including: a memory for storing executable instructions; and a processor for implementing a dynamic optimization method for an intelligent intercommunication network provided by the present application when executing the executable instructions stored in the memory.

[0013] The present application provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements a dynamic optimization method for an intelligent intercommunication network provided by the present application.

[0014] A dynamic optimization method, device, and storage medium for an intelligent interconnection network are proposed in this application. By obtaining a traffic interconnection network, a data perception module is deployed in the traffic interconnection network, and the data perception module includes a sensor group, cameras, and vehicle networking devices. By using the data perception module to collect traffic multi-dimensional operation data streams in real time, data cleaning and standardization processing are performed on the traffic multi-dimensional operation data streams to obtain standard traffic multi-dimensional operation data streams. A traffic condition prediction network is established, and traffic prediction is performed on the standard traffic multi-dimensional operation data streams based on the traffic condition prediction network, and traffic prediction condition parameters are output. An interconnection network optimization strategy space is constructed, and the traffic interconnection network and the traffic prediction condition parameters are analyzed using the interconnection network optimization strategy space to obtain interconnection network optimization strategy parameters. A feedback mechanism is introduced to perform dynamic topology optimization on the traffic interconnection network based on the interconnection network optimization strategy parameters. This solves the technical problem that in the prior art, traffic management methods are difficult to achieve real-time optimization and cannot dynamically adjust optimization strategies according to traffic prediction conditions, resulting in traffic regulation lag and low traffic efficiency. Through the combination of data perception, traffic prediction, strategy optimization, and feedback mechanism, real-time monitoring, intelligent prediction, global optimization, and dynamic adjustment of the traffic interconnection network are realized, improving road traffic efficiency, reducing congestion duration, and enhancing the automation and intelligence level of traffic management.

[0015] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically described below. Brief Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0017] Figure 1 It is a schematic flowchart of a dynamic optimization method for an intelligent interconnection network provided by an embodiment of this application;

[0018] Figure 2 It is a schematic flowchart of a process for obtaining standard traffic multi-dimensional operation data streams in a dynamic optimization method for an intelligent interconnection network provided by an embodiment of this application;

[0019] Figure 3Schematic structural diagram of an electronic device corresponding to a dynamic optimization method for an intelligent interconnection network provided by an embodiment of the present application.

[0020] Explanation of reference numerals: Processor 31, memory 32, input device 33, output device 34. Detailed implementation manners

[0021] Embodiment 1

[0022] The above description is only an overview of the technical solution of the present application. In order to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other objects, features and advantages of the present application more obvious and understandable, the specific implementation manners of the present application are hereinafter specifically exemplified.

[0023] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0024] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first\second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0025] As Figure 1 shown, an embodiment of the present application provides a dynamic optimization method for an intelligent interconnection network, and the method includes:

[0026] Obtain a traffic interchange network, deploy a data perception module in the traffic interchange network, and the data perception module includes a sensor group, a camera, and vehicle networking devices; collect and obtain multi-dimensional traffic operation data streams in real time through the data perception module, perform data cleaning and standardization processing on the multi-dimensional traffic operation data streams to obtain standard multi-dimensional traffic operation data streams; establish a traffic condition prediction network, and perform traffic prediction on the standard multi-dimensional traffic operation data streams based on the traffic condition prediction network, and output traffic prediction condition parameters.

[0027] Determine the scope of the traffic interchange network to be managed and optimized, and obtain the traffic interchange network. The traffic interchange network is a traffic network that needs to be managed and optimized. This network can be a traffic road network in a city or region that includes multiple main roads and branch roads, or a comprehensive road network where highways and ordinary roads intersect and interchange. After clarifying the spatial and functional scope of the network, form the basic topological structure data of the interchange network, including the connection relationship between roads, the location of intersection nodes, and lane information, etc. Further, deploy a data perception module in the traffic interchange network, and the data perception module includes a sensor group, a camera, and vehicle networking devices. The sensor group is used to collect basic traffic data such as the traffic flow and speed of vehicles passing through certain key sections or intersections. The camera is used to monitor traffic conditions, identify traffic accidents, and capture traffic flow characteristics (such as vehicle types, lane usage conditions, etc.). Vehicle networking devices refer to in-vehicle terminal devices installed on vehicles, which can transmit information such as the real-time position, speed, and driving trajectory of vehicles back to the traffic management center. Subsequently, collect and obtain multi-dimensional traffic operation data streams in real time through the data perception module, perform data cleaning and standardization processing on the multi-dimensional traffic operation data streams to obtain standard multi-dimensional traffic operation data streams, and further obtain normalized traffic data. Establish a traffic condition prediction network, and perform traffic prediction on the standard multi-dimensional traffic operation data streams based on the traffic condition prediction network, and output traffic prediction condition parameters.

[0028] As Figure 2 shown, the method provided by the embodiment of the present application further includes: converting the multi-dimensional traffic operation data stream into a unified format according to the data application standard to obtain an available multi-dimensional traffic operation data stream; performing outlier identification on the available multi-dimensional traffic operation data stream to obtain abnormal traffic operation data, and the abnormal traffic operation data includes missing values, duplicate values, and error values; performing data cleaning processing on the abnormal traffic operation data to obtain a standard multi-dimensional traffic operation data stream; performing standardization processing on the standard multi-dimensional traffic operation data stream using Z-score standardization to obtain the standard multi-dimensional traffic operation data stream.

[0029] The obtaining of the standard traffic multi-dimensional operation data stream includes: converting the traffic multi-dimensional operation data stream into a unified format according to data application standards, and completing the alignment of data from different sources to the same time interval, unit specification, and field naming. For example, a speed sensor outputs vehicle speed data once per minute, with the unit being meters per second, while a vehicle networking device transmits vehicle speed information every 30 seconds, with the unit being kilometers per hour. In this case, it is necessary to first align the time intervals (for example, with a sampling granularity of 30 seconds), convert meters per second to kilometers per hour, and unify the field naming to "speed", so as to ensure that all data has the same dimension and meaning. After this step, a preliminary available traffic multi-dimensional operation data stream is obtained, that is, traffic data that can be directly recognized and used by subsequent processing units in terms of format. Further, outlier identification is performed on the available traffic multi-dimensional operation data stream, such as detecting missing values (i.e., data interruption may be caused by sensor failure), duplicate values (i.e., overlapping data caused by simultaneous collection by multiple devices), and error values (i.e., sensor reading errors). Through the above identification process, all missing values, duplicate values, and error values are marked and extracted one by one to form a list of abnormal data for targeted cleaning processing in the next step. Subsequently, data cleaning processing is performed on the abnormal traffic operation data. For example, for missing value processing, interpolation (such as linear interpolation, time series interpolation) or reasonable average / median / adjacent period values can be used to replace. For duplicate value processing, for duplicate information in the same time period and on the same road section, only one most reliable and complete data record needs to be retained. For error value processing, if a piece of data is seriously inconsistent with the context and cannot be corrected, it is directly excluded. After the cleaning process, a standardized traffic multi-dimensional operation data stream is obtained. After cleaning, missing values or error values in each field are reasonably corrected or deleted, and duplicate values are also excluded, thus ensuring the overall consistency and integrity of the data. Finally, Z-score standardization is used to perform standardization processing on the standardized traffic multi-dimensional operation data stream to obtain the standard traffic multi-dimensional operation data stream.

[0030] The method provided by the embodiment of the present application further includes: mining and obtaining a traffic operation historical data set, where the traffic operation historical data set includes historical traffic operation data and corresponding traffic condition data; performing feature selection and extraction on the traffic operation historical data set according to traffic prediction demand targets to obtain a traffic operation feature data set; performing time series annotation on the traffic operation feature data set to obtain a traffic operation sequence feature sample set; using the ARIMA model to train, verify, and optimize the traffic operation sequence feature sample set to establish the traffic condition prediction network.

[0031] The establishment of the traffic condition prediction network includes: mining and obtaining the historical traffic operation data set, which acquires the traffic operation-related data accumulated over a certain period of time (which can be several weeks, months or even years). The historical traffic operation data set includes historical traffic operation data and corresponding traffic condition data. The historical traffic operation data is the traffic flow, vehicle speed, traffic density, vehicle queue length, etc. at each time period, and the historical traffic operation data is data after cleaning and standardization. The traffic condition data refers to the status labels or indicators during traffic operation, such as whether it is congested, unobstructed, affected by accidents, peak hours on holidays, etc. Further, before establishing the traffic condition prediction network, it is necessary to clarify the prediction demand target, which is the length of the prediction time, such as predicting parameters such as the congestion degree from 8 to 10 o'clock. Feature selection and extraction are performed on the historical traffic operation data set according to the traffic prediction demand target to obtain the traffic operation data corresponding to the prediction time recorded in the historical data set, and a traffic operation feature data set corresponding to the traffic prediction demand target is obtained. The traffic operation feature data set is marked in time series according to the time sequence to obtain a traffic operation sequence feature sample set. The traffic operation sequence feature sample set contains all features with timestamps arranged in chronological order. Finally, the ARIMA model is used to train, verify and optimize the traffic operation sequence feature sample set. The ARIMA model needs to select three core parameters: the autoregressive order, the differencing order and the moving average order, and gradually find the optimal combination through an automatic order determination algorithm or manual experiments to obtain the core parameters. Further, in the traffic operation sequence feature sample set, with the target variable (such as the vehicle speed at the next moment, the specific target variable of the congestion degree corresponding to the prediction demand target) as the prediction object, model fitting is performed using the determined parameters. Using the reserved validation set or through cross-validation, the prediction effect of the model is evaluated. After the evaluation is provided, the construction of the traffic condition prediction network is completed.

[0032] Construct an optimization strategy space for the interconnection network, and use the optimization strategy space for the interconnection network to analyze the traffic interconnection network and the traffic prediction condition parameters to obtain interconnection network optimization strategy parameters; introduce a feedback mechanism to perform dynamic topology optimization on the traffic interconnection network based on the interconnection network optimization strategy parameters.

[0033] Construct an interoperable network optimization strategy space, perform strategy analysis in the interoperable network optimization strategy space based on the traffic interoperable network and the traffic prediction status parameters, obtain the corresponding interoperable network optimization strategy memory bank, and perform optimization based on the fitness function to obtain the interoperable network optimization strategy parameters. Finally, introduce a feedback mechanism to perform dynamic topology optimization on the traffic interoperable network based on the interoperable network optimization strategy parameters. This solves the technical problem that in the prior art, traffic management methods are difficult to achieve real-time optimization and cannot dynamically adjust optimization strategies according to traffic prediction status, resulting in lagging traffic regulation and low traffic efficiency. Through the combination of data perception, traffic prediction, strategy optimization, and feedback mechanism, real-time monitoring, intelligent prediction, global optimization, and dynamic adjustment of the traffic interoperable network are realized, improving road traffic efficiency, reducing congestion duration, and enhancing the automation and intelligence level of traffic management.

[0034] The method provided by the embodiment of the present application further includes: analyzing and obtaining a set of key factors affecting the interoperable network, where the set of key factors affecting the interoperable network includes traffic flow, road conditions, traffic signal control, weather conditions, and traffic accidents; obtaining an interoperable network optimization target, and performing strategy design based on the interoperable network optimization target and the set of key factors affecting the interoperable network to obtain an interoperable network optimization strategy set; collecting historical optimization data based on the interoperable network optimization strategy set to construct the interoperable network optimization strategy space.

[0035] The construction of the interchange network optimization strategy space includes: Before implementing network optimization, it is necessary to first identify and collect factors that have a significant impact on the overall operation of the interchange network. The set of key factors affecting the interchange network includes traffic flow, road conditions, traffic signal control, weather conditions, and traffic accidents. Further, obtain the interchange network optimization goal, which is the management and control purpose to be achieved, such as alleviating congestion, reducing the vehicle queuing length and congestion duration, improving traffic efficiency, etc. Based on the interchange network optimization goal and the set of key factors affecting the interchange network, conduct strategy design to obtain the interchange network optimization strategy, and the interchange network optimization strategy corresponds to the interchange network optimization goal. The specific strategy set can be set based on historical setting experience or manually, such as adjusting the green light duration of intersection or ramp signal lights to avoid excessive backlog of main line traffic during peak hours. At the interchange of expressways and urban roads, by extending or shortening the green light time of ramp lights, control the rate of vehicles entering the main line, thereby regulating the main line traffic flow. Utilize variable message signs (VMS) or in-vehicle navigation systems to guide vehicles to take other roads in advance when accidents or congestion occur, reducing the degree of local congestion. At multi-lane highways or interchanges, dynamically adjust the lane usage or direction, for example, increase variable lanes for the direction with large traffic flow during peak hours. When bad weather approaches, reduce the speed limit or remind drivers to drive carefully to prioritize safety, etc. Based on the set of interchange network optimization strategies, collect historical optimization data, and obtain the data records of the corresponding interchange network optimization strategies in the historical optimization data. The historical optimization data also records the corresponding traffic interchange network and the traffic prediction status parameters. Such as the specific duration range of adjusting the green light of intersection or ramp signal lights, the range of extending or shortening the green light time of ramp lights, the number of variable lanes increased during peak hours, and the extent of speed limit reduction when bad weather approaches. According to the historical optimization data records, construct the interchange network optimization strategy space for each interchange network optimization strategy. The interchange network optimization strategy space also includes the corresponding traffic interchange network and the traffic prediction status parameters, so as to facilitate the subsequent execution of the specific setting method of the corresponding strategy according to the interchange network optimization strategy space.

[0036] The method provided by the embodiments of this application further includes: Using the traffic interchange network and the traffic prediction status parameters as constraint information, perform matching and screening within the interchange network optimization strategy space to obtain the interchange network optimization strategy memory bank; According to the interchange network optimization goal, construct the interchange network optimization fitness function; Use the interchange network optimization fitness function to perform global optimization within the interchange network optimization strategy memory bank to obtain the interchange network optimization strategy parameters.

[0037] Obtaining the interconnection network optimization strategy parameters includes: using the traffic interconnection network and the traffic prediction status parameters as constraint information, performing matching and screening within the interconnection network optimization strategy space to obtain all executable interconnection network optimization strategies corresponding to the traffic interconnection network and the traffic prediction status parameters, and obtaining an interconnection network optimization strategy memory bank. The interconnection network optimization strategy memory bank records multiple executable interconnection network optimization strategies corresponding to the current traffic interconnection network and the traffic prediction status parameters. Further, according to the interconnection network optimization objective, an interconnection network optimization fitness function is constructed. The specific interconnection network optimization fitness function can be set based on the actual optimization objective. Taking the optimization objective of minimizing the congestion duration as an example, F = A * (1 / adjusted average vehicle speed) + B * adjusted congestion duration. Where F is the calculated fitness, and A and B are weight parameters corresponding to the adjusted average vehicle speed and the adjusted congestion duration. Further, the interconnection network optimization fitness function is used to perform global optimization within the interconnection network optimization strategy memory bank to obtain the required parameters in the fitness function corresponding to the records in the interconnection network optimization strategy memory bank, such as the adjusted average vehicle speed and the congestion duration, to obtain the interconnection network optimization strategy parameters.

[0038] The method provided by the embodiment of the present application further includes: randomly selecting multiple network optimization strategy parameters within the interconnection network optimization strategy memory bank, using the interconnection network optimization fitness function to evaluate the multiple network optimization strategy parameters to obtain multiple strategy parameter fitnesses; based on the multiple strategy parameter fitnesses, performing optimization direction selection and global optimization on the interconnection network optimization strategy memory bank to obtain the interconnection network optimization strategy parameters.

[0039] Obtaining the interconnection network optimization strategy parameters includes: randomly selecting multiple network optimization strategy parameters within the interconnection network optimization strategy memory bank, using the interconnection network optimization fitness function to evaluate the multiple network optimization strategy parameters to obtain the calculated multiple strategy parameter fitnesses. Finally, based on the multiple strategy parameter fitnesses, perform optimization direction selection and global optimization on the interconnection network optimization strategy memory bank. The optimization direction is the direction where the parameter with the highest fitness among the multiple strategy parameter fitnesses is located as the optimization direction, and perform optimization in the interconnection network optimization strategy memory bank according to the optimization direction until the iteration number is reached or the preset fitness requirement is met, to obtain the interconnection network optimization strategy parameters.

[0040] The method provided by the embodiments of this application further includes: according to the feedback mechanism, determining a dynamic feedback period, and based on the dynamic feedback period, controlling and monitoring the traffic interchange network according to the interchange network optimization strategy parameters to obtain interchange network feedback parameters; based on the interchange network feedback parameters, correcting the interchange network optimization strategy parameters, and performing interchange network topology control through the corrected interchange network optimization strategy parameters.

[0041] The introduction of the feedback mechanism for dynamically optimizing the topology of the traffic interchange network based on the interchange network optimization strategy parameters includes: according to the feedback mechanism, determining a dynamic feedback period, which is a monitoring period with a fixed time interval, such as every 5 minutes or every 10 minutes. Based on the dynamic feedback period, controlling and monitoring the traffic interchange network according to the interchange network optimization strategy parameters to obtain interchange network feedback parameters. The interchange network feedback parameters are real-time data or short-term statistical data obtained through control and monitoring, used to compare the effects before and after the implementation of the strategy and measure whether the strategy meets the expectations. Such as vehicle queue length, average vehicle speed, congestion duration, etc. Based on the interchange network feedback parameters, correcting the interchange network optimization strategy parameters, comparing the actually observed interchange network feedback parameters with expected target indicators such as vehicle speed, traffic flow, and congestion duration, finding the gap between the strategy and reality, and if the gap exceeds the threshold, re-executing the acquisition of the interchange network optimization strategy parameters. And performing interchange network topology control through the corrected interchange network optimization strategy parameters.

[0042] The technical solution provided by the embodiments of the present invention obtains a traffic interchange network, deploys a data perception module in the traffic interchange network, and the data perception module includes a sensor group, a camera, and a vehicle networking device; through the data perception module, real-time collection and acquisition of traffic multi-dimensional operation data streams are performed, and the traffic multi-dimensional operation data streams are subjected to data cleaning and standardization processing to obtain standard traffic multi-dimensional operation data streams; a traffic condition prediction network is established, and based on the traffic condition prediction network, traffic prediction is performed on the standard traffic multi-dimensional operation data streams, and traffic prediction condition parameters are output; an interchange network optimization strategy space is constructed, and the interchange network optimization strategy space is used to perform strategy analysis on the traffic interchange network and the traffic prediction condition parameters to obtain interchange network optimization strategy parameters; a feedback mechanism is introduced to perform dynamic topology optimization on the traffic interchange network based on the interchange network optimization strategy parameters. This solves the technical problem in the prior art that traffic management methods are difficult to achieve real-time optimization and cannot dynamically adjust optimization strategies according to traffic prediction conditions, resulting in lagging traffic regulation and low traffic efficiency. Through the combination of data perception, traffic prediction, strategy optimization, and feedback mechanism, real-time monitoring, intelligent prediction, global optimization, and dynamic adjustment of the traffic interchange network are realized, improving road traffic efficiency, reducing congestion duration, and enhancing the automation and intelligence level of traffic management.

[0043] Embodiment 2

[0044] Based on the same inventive concept as a method for dynamically optimizing an intelligent interconnection network in the foregoing embodiments, the present invention further provides an intelligent interconnection network dynamic optimization system. The system can be implemented in a hardware and / or software manner and is generally integrated into an electronic device for executing the method provided in any embodiment of the present invention. The system includes:

[0045] A data acquisition module for acquiring a traffic interconnection network and deploying a data perception module in the traffic interconnection network. The data perception module includes a sensor group, a camera, and a vehicle networking device; a data flow acquisition module for real-time collecting and acquiring traffic multi-dimensional operation data flows through the data perception module, performing data cleaning and standardization processing on the traffic multi-dimensional operation data flows to obtain standard traffic multi-dimensional operation data flows; a traffic condition prediction module for establishing a traffic condition prediction network, performing traffic prediction on the standard traffic multi-dimensional operation data flows based on the traffic condition prediction network, and outputting traffic prediction condition parameters; an optimization strategy acquisition module for constructing an interconnection network optimization strategy space, and performing strategy analysis on the traffic interconnection network and the traffic prediction condition parameters by using the interconnection network optimization strategy space to obtain interconnection network optimization strategy parameters; a topology optimization module for introducing a feedback mechanism to perform dynamic topology optimization on the traffic interconnection network based on the interconnection network optimization strategy parameters.

[0046] Next, the specific configuration of the data flow acquisition module will be described in detail. The data flow acquisition module may further include: obtaining the standard traffic multi-dimensional operation data flows includes: converting the traffic multi-dimensional operation data flows into a unified format according to data application standards to obtain available traffic multi-dimensional operation data flows; performing outlier identification on the available traffic multi-dimensional operation data flows to obtain abnormal traffic operation data, where the abnormal traffic operation data includes missing values, duplicate values, and error values; performing data cleaning processing on the abnormal traffic operation data to obtain a standardized traffic multi-dimensional operation data flow; and performing standardization processing on the standardized traffic multi-dimensional operation data flow by using Z-score standardization to obtain the standard traffic multi-dimensional operation data flows.

[0047] Next, the specific configuration of the traffic condition prediction module will be further described in detail. The traffic condition prediction module further includes: establishing a traffic condition prediction network, including: mining and obtaining a traffic operation historical data set, which includes historical traffic operation data and corresponding traffic condition data; performing feature selection and extraction on the traffic operation historical data set according to the traffic prediction requirement target to obtain a traffic operation feature data set; performing time series annotation on the traffic operation feature data set to obtain a traffic operation sequence feature sample set; using the ARIMA model to train, verify and optimize the traffic operation sequence feature sample set to establish the traffic condition prediction network.

[0048] Next, the specific configuration of the optimization strategy acquisition module will be described in detail. The optimization strategy acquisition module may further include: constructing an interchange network optimization strategy space, including: analyzing and obtaining a set of key factors affecting the interchange network, which includes traffic flow, road conditions, traffic signal control, weather conditions and traffic accidents; obtaining the interchange network optimization target, and designing strategies based on the interchange network optimization target and the set of key factors affecting the interchange network to obtain an interchange network optimization strategy set; collecting historical optimization data based on the interchange network optimization strategy set to construct the interchange network optimization strategy space.

[0049] Next, the specific configuration of the topology optimization module will be described in detail. The topology optimization module further includes: obtaining the interchange network optimization strategy parameters, including: using the traffic interchange network and the traffic prediction condition parameters as constraint information, performing matching and screening in the interchange network optimization strategy space to obtain an interchange network optimization strategy memory bank; constructing an interchange network optimization fitness function according to the interchange network optimization target; using the interchange network optimization fitness function to perform global optimization in the interchange network optimization strategy memory bank to obtain the interchange network optimization strategy parameters.

[0050] Next, the specific configuration of the topology optimization module will be further described in detail. The topology optimization module further includes: obtaining the interchange network optimization strategy parameters, including: randomly selecting multiple network optimization strategy parameters in the interchange network optimization strategy memory bank, using the interchange network optimization fitness function to evaluate the multiple network optimization strategy parameters to obtain multiple strategy parameter fitness values; performing optimization direction selection and global optimization on the interchange network optimization strategy memory bank based on the multiple strategy parameter fitness values to obtain the interchange network optimization strategy parameters.

[0051] Next, the specific configuration of the topology optimization module will be described in detail. The topology optimization module further includes: The introduction of the feedback mechanism performs dynamic topology optimization on the traffic interchange network based on the interchange network optimization strategy parameters, including: according to the feedback mechanism, determining a dynamic feedback period, and based on the dynamic feedback period, controlling and monitoring the traffic interchange network based on the interchange network optimization strategy parameters to obtain interchange network feedback parameters; correcting the interchange network optimization strategy parameters based on the interchange network feedback parameters, and performing interchange network topology control through the corrected interchange network optimization strategy parameters.

[0052] The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0053] Embodiment III

[0054] Figure 3 FIG. is a schematic structural diagram of an electronic device provided in Embodiment III of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 3 The displayed electronic device is only an example and should not bring any limitations to the functions and usage scope of the embodiments of the present invention. As Figure 3 shown, the electronic device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the electronic device can be one or more, Figure 3 taking one processor 31 as an example, the processor 31, the memory 32, the input device 33, and the output device 34 in the electronic device can be connected through a bus or other means, Figure 3 taking the connection through a bus as an example.

[0055] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to a method for dynamically optimizing an intelligent interchange network in an embodiment of the present invention. The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 32, that is, implementing the above-mentioned method for dynamically optimizing an intelligent interchange network.

[0056] Note that the above is only a preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for dynamic optimization of a smart interconnection network, characterized in that: The method comprises: Acquire a traffic interconnection network, and deploy a data perception module in the traffic interconnection network, wherein the data perception module includes a sensor group, a camera, and a vehicle networking device; The data sensing module collects and acquires the multi-dimensional traffic operation data stream in real time, performs data cleaning and standardization processing on the multi-dimensional traffic operation data stream, and obtains a standard multi-dimensional traffic operation data stream; Establishing a traffic condition prediction network, performing traffic prediction on the standard traffic multi-dimensional operation data stream based on the traffic condition prediction network, and outputting traffic prediction condition parameters; Constructing an interconnection network optimization strategy space, and using the interconnection network optimization strategy space to perform strategy analysis on the traffic interconnection network and the traffic prediction status parameters to obtain interconnection network optimization strategy parameters; A feedback mechanism is introduced to perform dynamic topology optimization on the traffic interconnection network based on the interconnection network optimization strategy parameters.

2. A method for dynamic optimization of a smart interconnection network as claimed in claim 1, characterized in that: The method of obtaining the standard traffic multi-dimensional operation data stream includes: Converting the multi-dimensional traffic operation data stream into a unified format according to a data application standard to obtain a usable multi-dimensional traffic operation data stream; Performing outlier identification on the available multi-dimensional traffic operation data stream to obtain abnormal traffic operation data, wherein the abnormal traffic operation data includes missing values, duplicate values ​​and error values; Performing data cleaning on the abnormal traffic operation data to obtain a standardized traffic multi-dimensional operation data flow; The standard traffic multi-dimensional operation data flow is standardized by using Z-score standardization to obtain the standard traffic multi-dimensional operation data flow.

3. A method for dynamic optimization of a smart interconnection network as claimed in claim 1, characterized in that: The establishing of the traffic condition prediction network comprises: Mining and acquiring a traffic operation history data set, wherein the traffic operation history data set includes historical traffic operation data and corresponding traffic condition data; Performing feature selection and extraction on the traffic operation history data set according to the traffic forecast demand target to obtain a traffic operation feature data set; Performing time series annotation on the traffic operation characteristic data set to obtain a traffic operation sequence characteristic sample set; The ARIMA model is used to train, validate and optimize the traffic operation sequence feature sample set to establish the traffic condition prediction network.

4. A method for dynamic optimization of a smart interconnection network as claimed in claim 1, characterized in that: The constructing of the intercommunication network optimization strategy space includes: Analyze and obtain a set of key factors affecting the interconnection network, wherein the set of key factors affecting the interconnection network includes traffic flow, road conditions, traffic signal control, weather conditions and traffic accidents; Acquire an intercommunication network optimization target, perform strategy design based on the intercommunication network optimization target and the intercommunication network influencing key factor set, and obtain an intercommunication network optimization strategy set; Based on the intercommunication network optimization strategy set, historical optimization data is collected to construct the intercommunication network optimization strategy space.

5. A method for dynamic optimization of a smart interconnection network as claimed in claim 4, characterized in that: The obtaining of the intercommunication network optimization strategy parameters includes: Using the traffic interconnection network and the traffic forecast condition parameters as constraint information, performing matching screening in the interconnection network optimization strategy space to obtain an interconnection network optimization strategy memory library; According to the interconnection network optimization goal, construct an interconnection network optimization fitness function; The intercommunication network optimization fitness function is used to perform global optimization in the intercommunication network optimization strategy memory library to obtain the intercommunication network optimization strategy parameters.

6. A method for dynamic optimization of a smart interconnection network as claimed in claim 5, characterized in that: The obtaining of the intercommunication network optimization strategy parameters includes: Randomly selecting a plurality of network optimization strategy parameters in the intercommunication network optimization strategy memory library, and evaluating the plurality of network optimization strategy parameters using the intercommunication network optimization fitness function to obtain a plurality of strategy parameter fitnesses; Based on the fitness of the multiple strategy parameters, the intercommunication network optimization strategy memory library is optimized in an optimization direction and globally optimized to obtain the intercommunication network optimization strategy parameters.

7. A method for dynamic optimization of a smart interconnection network as claimed in claim 6, characterized in that: The introducing of the feedback mechanism to dynamically optimize the traffic interconnection network topology based on the interconnection network optimization strategy parameters includes: According to the feedback mechanism, a dynamic feedback cycle is determined, and the traffic interconnection network is controlled and monitored based on the interconnection network optimization strategy parameters according to the dynamic feedback cycle to obtain interconnection network feedback parameters; The interconnection network optimization strategy parameters are modified based on the interconnection network feedback parameters, and the interconnection network topology control is performed through the modified interconnection network optimization strategy parameters.

8. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; A processor is used to implement a method for dynamic optimization of an intelligent intercommunication network as described in any one of claims 1 to 7 when executing executable instructions stored in the memory.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a method for dynamic optimization of an intelligent interconnection network as described in any one of claims 1 to 7 is implemented.

Images