Space-time data driven communication parameter dynamic optimization method, device and system

Abstract

The application discloses a kind of communication parameter dynamic optimization method, device and system based on space-time data driving, method is deployed in the server of communication system, communication system also includes first equipment and second equipment;Method is based on historical space-time data information and carries out offline modeling, constructs the constraint multi-objective optimization model of communication and power consumption to obtain multiple communication parameter combinations;Again, through real-time receiving first equipment position information and second equipment position information carries out online dynamic optimization, obtains target communication parameter combination in multiple communication parameter combinations based on first equipment quantity information in preset radius range, second equipment quantity information, and then dynamically optimizes first equipment, second equipment communication parameter, communication reliability and low-power communication are considered;Solve the technical problems of high communication power consumption caused by the lack of dynamic optimization capability of communication parameters between devices in large-scale communication positioning scenarios in the related art, and the high hardware cost of equipping each device with a positioning module.

Description

Technical Field

[0001] This invention relates to the field of wireless communication data processing technology, and in particular to a method, apparatus and system for dynamic optimization of communication parameters based on spatiotemporal data driven. Background Technology

[0002] In traditional related technologies, to meet the needs of device positioning and wireless communication, devices typically need to be equipped with network communication models and positioning modules. However, in large-scale application scenarios, such as battery swapping in the food delivery industry, equipping each battery with a primary communication module and positioning module would not only result in significant hardware costs but also generate greater power consumption during device operation, which is detrimental to the industry's development and promotion.

[0003] Therefore, how to reduce hardware costs by improving the hardware composition of devices in the system, and how to optimize the communication parameters between devices in the system to reduce power consumption, have become technical challenges that need to be overcome by those skilled in the art. Summary of the Invention

[0004] This invention proposes a method, apparatus, and system for dynamic optimization of communication parameters based on spatiotemporal data, in order to solve the technical problems of high system hardware cost and high system power consumption in large-scale communication and positioning scenarios.

[0005] In a first aspect, one embodiment of the present invention provides a method for dynamic optimization of communication parameters based on spatiotemporal data. The method is deployed in a server of a communication system, which further includes a first device and a second device. The first device is equipped with a first communication module, a positioning module, and a second communication module. The second device is equipped with a third communication module, and the second communication module and the third communication module are communicatively connected. The method includes:

[0006] In the offline modeling phase, based on historical spatiotemporal data, a model of the probability of device encounters and the duration of encounters under different device densities within a preset radius are constructed.

[0007] Based on the encounter probability model and the encounter duration model, an objective function for the communication success rate between the first device and the second device under different device ratios is constructed.

[0008] After establishing the overall power consumption function for communication between the first device and the second device, a constrained multi-objective optimization model for communication and power consumption is constructed by combining the communication success rate objective function.

[0009] Multiple sets of communication parameter combinations are obtained by solving the constrained multi-objective optimization model based on preset constraints.

[0010] During the online dynamic optimization phase, the location information of the first device and the location information of the second device are received in real time.

[0011] Calculate the number of first devices and the number of second devices within the preset radius based on the first device location information;

[0012] Based on the quantity information of the first device and the quantity information of the second device, a target communication parameter combination is obtained from the multiple sets of communication parameter combinations, and the target communication parameter combination is sent to the first device and the second device to achieve dynamic optimization of communication parameters.

[0013] The spatiotemporal data-driven dynamic optimization method for communication parameters in this invention has at least the following beneficial effects:

[0014] This invention discloses a method for dynamic optimization of communication parameters based on spatiotemporal data. The method is deployed on a server within a communication system, which also includes a first device and a second device. The first device is equipped with a first communication module, a positioning module, and a second communication module, while the second device is equipped with a third communication module. When the second and third communication modules establish a communication connection, the first device provides positioning services to the second device, reducing the hardware cost of the communication system. Simultaneously, offline modeling is performed based on historical spatiotemporal data to construct a constrained multi-objective optimization model for communication and power consumption, obtaining multiple sets of communication parameter combinations. Furthermore, online dynamic optimization is performed by receiving real-time location information from the first and second devices. Based on the number of first and second devices within a preset radius, a target communication parameter combination is obtained from the multiple sets of communication parameter combinations, thereby dynamically optimizing the communication parameters of the first and second devices, balancing communication reliability and low-power communication. This solves the technical problems in related technologies where the lack of dynamic optimization capabilities for communication parameters between devices in large-scale communication and positioning scenarios leads to high communication power consumption, and the high hardware cost of equipping each device with a positioning module. This provides a low-cost method for dynamic optimization of communication parameters that combines communication reliability and low power consumption.

[0015] According to other embodiments of the present invention, the construction of the device encounter probability model in the spatiotemporal data-driven dynamic optimization method for communication parameters includes:

[0016] Based on the historical trajectory of the historical spatiotemporal data, within the preset radius, the relationship between the probability of equipment encounter and the density of equipment is analyzed to establish the probability model of equipment encounter.

[0017] According to other embodiments of the present invention, the construction of the encounter duration model includes:

[0018] Based on the device encounter probability model, the encounter duration model is constructed by statistically summarizing the duration during which the distance between devices is below a preset distance threshold.

[0019] According to other embodiments of the present invention, the method for dynamic optimization of communication parameters based on spatiotemporal data driving includes, in which the objective function for constructing the communication success rate between the first device and the second device under different device ratios is described below:

[0020] A device discovery probability model is established based on the communication parameters between the first device and the second device and the encounter duration model.

[0021] Based on the aforementioned equipment encounter probability model, construct equipment pairing probability models under different equipment ratios;

[0022] The objective function for communication success rate is constructed based on the device encounter probability model, the device discovery probability model, and the device pairing probability model.

[0023] According to other embodiments of the present invention, the method for dynamic optimization of communication parameters based on spatiotemporal data driving establishes the overall power consumption function for communication between the first device and the second device, including:

[0024] Based on the scanning parameters used for communication between the first device and the second device, construct the scanning power consumption expression for the first device;

[0025] Based on the broadcast parameters of the communication between the second device and the first device, construct the broadcast power consumption expression of the second device;

[0026] The overall communication power consumption function is constructed by combining the first number of devices, the second number of devices, the first device scanning power consumption expression, and the second device broadcast power consumption expression.

[0027] According to other embodiments of the present invention, the communication parameter dynamic optimization method based on spatiotemporal data driving is provided, wherein the second communication module includes a first Bluetooth module, and the third communication module includes a second Bluetooth module; the scanning parameters include scanning window, scanning interval, and Bluetooth receive mode operating current; and the broadcast parameters include transmit mode operating current, duration of a single broadcast packet, broadcast interval, and number of broadcast event transmission channels.

[0028] The preset constraints include:

[0029] The scanning window is less than or equal to the scanning interval, and the scanning interval is less than or equal to the maximum upper limit of the broadcast interval;

[0030] The duration of a single broadcast packet is less than or equal to the scanning window;

[0031] The broadcast interval is less than or equal to the scan interval, and the broadcast interval is less than or equal to the maximum upper limit of the broadcast interval.

[0032] According to other embodiments of the present invention, the method for dynamic optimization of communication parameters based on spatiotemporal data driving includes calculating the number of first devices and the number of second devices within the preset radius based on the location information of the first device, including:

[0033] The grid is divided based on a preset area range to obtain multiple grid cells;

[0034] The first device location information and the second device location information are respectively mapped to the corresponding grid cells;

[0035] The target grid cells covered within the preset radius are obtained based on the location information of the first device.

[0036] In the target grid cell, the quantity information of the first device and the quantity information of the second device that satisfy the preset radius range are obtained.

[0037] The method for dynamic optimization of communication parameters based on spatiotemporal data driven by other embodiments of the present invention further includes:

[0038] A communication parameter adjustment strategy library is generated and sent to the edge server to enable the edge server to dynamically optimize communication parameters based on the first device quantity information and the second device quantity information.

[0039] Secondly, one embodiment of the present invention provides a communication parameter dynamic optimization device based on spatiotemporal data, comprising:

[0040] The offline model building module is used to build a device encounter probability model and an encounter duration model based on historical spatiotemporal data information under different device density conditions within a preset radius.

[0041] Based on the encounter probability model and the encounter duration model, an objective function for the communication success rate between the first device and the second device under different device ratios is constructed.

[0042] After establishing the overall power consumption function for communication between the first device and the second device, a constrained multi-objective optimization model for communication and power consumption is constructed by combining the communication success rate objective function.

[0043] Multiple sets of communication parameter combinations are obtained by solving the constrained multi-objective optimization model based on preset constraints.

[0044] The online dynamic parameter optimization module is used to receive the location information of the first device and the location information of the second device in real time.

[0045] Calculate the number of first devices and the number of second devices within the preset radius based on the first device location information;

[0046] Based on the quantity information of the first device and the quantity information of the second device, a target communication parameter combination is obtained from the multiple sets of communication parameter combinations, and the target communication parameter combination is sent to the first device and the second device to achieve dynamic optimization of communication parameters.

[0047] Thirdly, one embodiment of the present invention provides a communication parameter dynamic optimization system based on spatiotemporal data, comprising:

[0048] Multiple primary devices are used to realize data communication and location information collection functions;

[0049] Multiple second devices are configured to communicate with the first device, and the first device is used to obtain the location information of the second devices;

[0050] The server is communicatively connected to the first device and is used to execute the communication parameter dynamic optimization method described above to optimize the communication parameters of the first device and the second device. Attached Figure Description

[0051] Figure 1 This is a schematic diagram illustrating the steps of a specific embodiment of a spatiotemporal data-driven dynamic optimization method for communication parameters according to an embodiment of the present invention;

[0052] Figure 2 This is a schematic diagram of a specific embodiment of a method for dynamic optimization of communication parameters based on spatiotemporal data driven by the present invention, in which step S600 includes sub-steps;

[0053] Figure 3 This is a schematic diagram of a specific embodiment of a method for dynamic optimization of communication parameters based on spatiotemporal data driven by the present invention, which calculates the number of devices by mesh partitioning.

[0054] Figure 4 This is a schematic diagram of a specific embodiment of a method for dynamic optimization of communication parameters based on spatiotemporal data driven by the present invention, in which step S200 includes sub-steps;

[0055] Figure 5 This is a schematic diagram of a specific embodiment of a method for dynamic optimization of communication parameters based on spatiotemporal data driven by the present invention, in which step S300 includes sub-steps;

[0056] Figure 6 This is a schematic diagram of a specific embodiment of a method for dynamic optimization of communication parameters based on spatiotemporal data driven by the present invention, in which step S800 includes sub-steps.

[0057] Figure 7 This is a schematic diagram of the module composition of a specific embodiment of a communication parameter dynamic optimization device based on spatiotemporal data driven by the present invention;

[0058] Figure 8 This is a schematic diagram of the system composition of a specific embodiment of a communication parameter dynamic optimization system driven by spatiotemporal data according to an embodiment of the present invention. Detailed Implementation

[0059] The following will describe the inventive concept and its resulting technical effects clearly and completely with reference to embodiments, so as to fully understand the purpose, features and effects of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are all within the scope of protection of the present invention.

[0060] In the description of the embodiments of the present invention, the term "several" means one or more, and the term "multiple" means two or more. The terms "greater than," "less than," and "exceeding" should be understood as excluding the stated number, while the terms "above," "below," and "within" should be understood as including the stated number. The terms "first" and "second" should be understood as distinguishing technical features, and not as indicating or implying relative importance, the number of indicated technical features, or the order of the indicated technical features.

[0061] Reference Figure 1 and Figure 8This invention provides a method for dynamic optimization of communication parameters based on spatiotemporal data, deployed in a communication system comprising a first device, a second device, and a server. The first device includes a first communication module, a positioning module, and a second communication module, enabling long-distance communication with the server and GPS / BeiDou positioning. The second device includes a third communication module. When the second and third communication modules establish a communication connection, the first device provides positioning services to the second device through a hybrid positioning mechanism. The first communication module includes a 4G, 5G, or Wi-Fi module; the positioning module includes a GPS or BeiDou positioning module; the second communication module is a first Bluetooth module; and the corresponding third communication module is a second Bluetooth module. In this embodiment, the hybrid positioning mechanism includes: within a preset time period, if the second device is only connected to the current first device, the location information of the second device is obtained using the location information of the current first device as a reference; if the second device establishes communication connections with multiple first devices, the location information of the second device is obtained through triangulation. In practical applications, the second device will also send device-related information (such as device ID, timestamp, RSSI signal strength, device battery information, etc.) to the first device. Simultaneously, the first device will send its own location information, the second device's location information, its own device ID, its own battery information, and the received information from the second device to the server. This allows for data collection and positioning of all devices through a hybrid application of the first device with positioning capabilities and the second device without positioning capabilities. The server includes a cloud server, which establishes a connection with the first communication module in the first device to fulfill communication requirements. The cloud server executes the spatiotemporal data-driven dynamic optimization method for communication parameters according to this invention to dynamically optimize the communication parameters of the first and second devices, achieving a balance between communication power consumption and communication success rate while the first device provides positioning services to the second device. Specifically, the method includes an offline modeling stage and an online dynamic optimization stage. The offline modeling stage includes the following steps:

[0062] S100. Based on historical spatiotemporal data, construct a probability model and duration model of equipment encounters under different equipment densities within a preset radius.

[0063] Among them, historical spatiotemporal data information refers to the historical trajectory data information of the devices received by the server. By analyzing the probability of device encounters and the duration of device encounters under different device density conditions within a preset radius range based on a large amount of historical trajectory data information of the devices, a device encounter probability model and an encounter duration model are constructed.

[0064] S200. Based on the device encounter probability model and encounter duration model, construct an objective function for the communication success rate between the first and second devices under different device ratios.

[0065] In this embodiment, after constructing the device encounter probability model and encounter duration model based on step S100, the objective function for the communication success rate of the first device and the second device to successfully establish communication is as follows: under the same device density (total number of devices is determined), the first device has a different ratio to the second device.

[0066] S300. After establishing the overall power consumption function for communication between the first device and the second device, a constrained multi-objective optimization model for communication and power consumption is constructed by combining the communication success rate objective function.

[0067] The overall communication power consumption function represents the power consumption generated by all first devices communicating with all second devices within a preset radius. It is related to the number of first devices, the number of second devices, and the communication parameters between the first and second devices. After obtaining the communication success rate objective function in step S200, a constrained multi-objective optimization model for communication and power consumption is constructed by combining the overall communication power consumption function.

[0068] S400: Solve the constrained multi-objective optimization model based on preset constraints to obtain multiple sets of communication parameter combinations;

[0069] In this embodiment, a set of communication protocol specifications that the first and second devices must conform to when communicating is set as a preset constraint. Then, a multi-objective optimization model with constraints is solved to obtain multiple sets of communication parameter combinations. In this embodiment, the multiple sets of communication parameter combinations are the collection of communication parameter combinations obtained by solving the multi-objective optimization model under different device densities and different device ratios.

[0070] The online dynamic optimization phase, which is executed after the above model is built and put into testing or use, includes the following steps:

[0071] S500: Receive the location information of the first device and the location information of the second device;

[0072] That is, the first device sends its location information and the location information of the second device obtained thereon to the server periodically or in real time.

[0073] S600: Calculate the quantity information of the first device and the quantity information of the second device within a preset radius based on the location information of the first device;

[0074] Among them, the first device location information is the location information of the first device currently communicating with the server (equivalent to the current query device, each first device can become the current query device). After confirming the first device location information, the number of first devices and the number of second devices within a preset radius are queried with the first device location information as the center.

[0075] S700: Based on the quantity information of the first device and the quantity information of the second device, obtain the target communication parameter combination from multiple sets of communication parameter combinations, and send the target communication parameter combination to the first device and the second device to realize dynamic optimization of communication parameters.

[0076] Once the number of the first and second devices within the preset radius is known, their corresponding device density and device ratio can be obtained. Further, after obtaining the corresponding target communication parameter combination from the multiple sets of communication parameter combinations obtained in step S400, the target communication parameter combination is sent to the first device. The first device then transmits the part of the target communication parameter combination used to optimize the communication parameters of the second device to the second device, thereby achieving dynamic optimization of the communication parameters of the first and second devices.

[0077] This invention provides a method for dynamic optimization of communication parameters based on spatiotemporal data. For large-scale communication positioning scenarios, this method utilizes a high-end device (a first device with positioning capabilities) to assist a low-end device (a second device without positioning capabilities) in achieving positioning. Simultaneously, while balancing overall communication power consumption and success rate, the method dynamically optimizes the communication parameters of the first and second devices, reducing the overall system power consumption. Furthermore, it avoids requiring all devices needing positioning to use high-cost positioning modules, thereby reducing the overall system equipment cost.

[0078] Reference Figure 2 and Figure 3 In some embodiments, due to the existence of a large amount of first device location information and second device location information in large-scale communication positioning application scenarios, in the above embodiment step S600, when calculating the number of first devices and the number of second devices within a preset radius of the first device location information, the distance between most devices and the first device location information may have far exceeded the preset radius. Therefore, in order to reduce computational complexity and improve system operation response efficiency, in this embodiment, the above embodiment step S600 specifically includes the following sub-steps:

[0079] S610. Pre-define the mesh to obtain multiple mesh elements;

[0080] In this context, a grid cell consists of multiple uniformly sized grids obtained after global grid division. In applications, the location (latitude and longitude) of a device (including the first device and the second device) can be used to determine its corresponding grid cell. In classic applications, the grid cell size is 100m × 100m.

[0081] S620. Map the first device location information and the second device location information to the corresponding grid cells respectively;

[0082] In this embodiment, after receiving the first device location information and the second device location information sent by the first device in step S500 of the above embodiment, they are mapped to the corresponding grid cells respectively. This significantly reduces the computational load when calculating the device density within the preset radius of the current first device in subsequent steps. It is worth noting that there are a large number of first and second devices in the system, each with its corresponding device ID. The preset parameter information sent by the first device to the server also includes the device IDs of each device. When mapping the first and second device location information to the corresponding grid cells, the mapping of the same device ID should be eliminated to avoid duplicate mapping, which could lead to data corruption and a decrease in the accuracy of subsequent calculation results.

[0083] S630. Obtain the target grid cells covered within a preset radius based on the location information of the first device;

[0084] Specifically, the current location information of the first device is mapped to the corresponding grid cell, and the surrounding grid cells it covers, i.e. the target grid cell, are obtained according to the preset radius range.

[0085] S640. Obtain the first device quantity information and the second device quantity information that meet the preset radius range in the target grid cell.

[0086] The number of first and second devices can be obtained by calculating the distance between the devices (including the second device and other first devices) in the target grid cell and the current first device, and then determining the relationship with a preset radius, thereby greatly reducing the amount of computation. After obtaining the number of first and second devices, the device density information is calculated using the following formula:

[0087] (1)

[0088] in, For equipment density, The sum of the number of the first device and the number of the second device within a preset radius. The preset radius is (m).

[0089] In some embodiments, the method of calculating the first and second equipment quantity information in steps S610 to S640 of the above implementation is also applicable to the offline modeling stage. In the offline modeling stage, when calculating information such as equipment density and equipment ratio, steps S610 to S640 can be used to reduce the computational load.

[0090] In some embodiments, during the offline modeling phase, the device encounter probability model is used to represent the relationship between device density and the probability of any two devices encountering each other within a defined space of a preset radius. Specifically, the server-side construction of the device encounter probability model includes the following steps:

[0091] S110. Based on historical trajectory information of historical spatiotemporal data, within a preset radius, analyze the relationship between the probability of equipment encounter and the density of equipment to establish a probability model of equipment encounter.

[0092] In this embodiment, the device encounter probability model is based on simulation of the probability of any two devices encountering within a preset radius under different device densities, thereby obtaining a device encounter probability model to describe the relationship between device density information and encounter probability. Specifically, the historical location trajectory sent by the device with positioning function (the first device) is preprocessed and time-aligned: In the received raw data (the location information trajectory sent by the first device), although the location information data of each first device is updated at the same period, the sampling phase of different devices is inconsistent, resulting in time misalignment of the data of different devices at the same moment. In order to improve the time resolution of the data and realize the alignment of multi-device data, an interpolation method is used to process the raw data, and the time granularity is uniformly increased to 1 second. In specific implementation, the device trajectory is reconstructed by using methods such as Lagrange interpolation to obtain device location data under a unified time axis. Density statistics: The device density information within the preset radius is calculated by using the method in steps S610 to S640. Encounter Determination: In the above process, after time alignment, for each timestamp, the spatial distance between any two devices within a preset radius is calculated. When the distance is less than or equal to a preset distance threshold, it is determined as an "encounter event." In specific implementation, the preset distance threshold is set according to the communication method between the second and first devices. For example, if the second device communicates with the first device via Bluetooth (i.e., both the second and third communication modules are Bluetooth modules), then based on the effective range of Bluetooth communication (0-20m), the preset distance threshold can be appropriately set to 10m. Data Integration and Processing: The integration reveals that the probability of encounters between devices exhibits a clear "S-shaped trend" as device density increases under different device densities. In low-density areas, the encounter probability is low and increases slowly; in medium-density areas, the encounter probability rises rapidly; and in high-density areas, the encounter probability gradually saturates. Through the above steps, a regression model is constructed and fitted using machine learning on the historical location trajectory data of the first device under different device densities to obtain a device encounter probability model.

[0093] (2)

[0094] in, This indicates the probability that the devices will meet. The density of equipment per unit area. The model parameters are obtained by fitting the historical trajectory data of the first device. Specifically, a loss function (MSE) is constructed, and the parameters are iteratively updated using gradient descent to gradually reduce the loss function until the function converges. This represents the natural constant, approximately 2.71828.

[0095] In some embodiments, during the offline modeling phase, based on the device encounter probability model, the server constructs an encounter duration model including the following steps:

[0096] S120. Based on the device encounter probability model, construct an encounter duration model by statistically summarizing the duration of time when the distance between devices is below a preset distance threshold.

[0097] Specifically, taking the aforementioned preset distance threshold adaptation setting of 10m as an example, the duration of continuous distance between devices being less than or equal to the preset threshold (10m) is statistically summarized, and the distribution of the duration of device encounters under different device densities is obtained, thereby obtaining the encounter duration model:

[0098] (3)

[0099] in, Indicates the duration of the device encounter. The density of equipment per unit area. The model parameters are obtained by fitting the historical location trajectory data of the first device. Specifically, a loss function (MSE) is constructed, and the parameters are iteratively updated using the gradient descent method to gradually reduce the loss function until the function converges. This represents the natural constant, approximately 2.71828. An offset is introduced... It can better describe the changing trend of the duration of equipment encounters under different equipment density environments.

[0100] Reference Figure 4 In some embodiments, after constructing the device encounter probability model and encounter duration model through the above embodiments, the objective function for the communication success rate between the first device and the second device under different device ratios includes:

[0101] S210. Establish a device discovery probability model based on the communication parameters between the first device and the second device and the encounter duration model.

[0102] The device discovery probability model represents the probability that a device will be successfully discovered at least once during an encounter, given the current device density. It is related to the communication parameters between the first and second devices. In this embodiment, Bluetooth communication is used as an example for the communication method between the first and second devices, and the following parameters are defined: This represents the ratio of the broadcast interval to the scan interval; This represents the ratio of the scan window to the scan interval (i.e., the scan duty cycle). , indicates the scan interval; This indicates the duration of a single broadcast packet, which is determined by the Bluetooth communication protocol physical layer; in this embodiment, it is taken as a constant. This represents the time interval between consecutive broadcast packets within a single broadcast session, with a value of 0.15ms. Based on the parameters defined above, the expected Bluetooth discovery latency is... The calculation can be divided into two specific cases:

[0103] 1. When hour:

[0104] (4)

[0105] 2. When hour:

[0106] (5)

[0107] Determining Bluetooth discovery latency expectations Then, the duration of the device encounter. Internally, the Bluetooth discovery process is viewed as a repetitive attempt process of independent events, with the expected number of attempts... Represented as:

[0108] (6)

[0109] Finally, based on Poisson process modeling, the probability that a device successfully discovers another device at least once during the encounter period, i.e., the device discovery probability model, is expressed as:

[0110] (7)

[0111] in, This indicates the probability of the device being detected.

[0112] S220. Based on the equipment encounter probability model, construct equipment pairing probability models under different equipment ratios;

[0113] Based on the confirmed device encounter event, any second device (equipped with a Bluetooth module) can be represented as follows:

[0114] (8)

[0115] in, This represents the probability that the second device will be paired with the first device. This indicates the number of the first devices within a preset radius. This indicates the number of second devices within a preset radius.

[0116] S230. Construct a communication success rate objective function based on the device encounter probability model, device discovery probability model, and device pairing probability model.

[0117] In this embodiment, after obtaining the device discovery probability model and the device pairing probability model through the above steps S210 to S220, and combining the device encounter probability model constructed in step S110, the objective function for the communication success rate between the first device and the second device can be expressed as:

[0118] (9)

[0119] in, This represents the communication success rate between the first device and the second device. This invention, through the introduction of a device encounter probability model, an encounter duration model, a device discovery probability model, and a device pairing probability model, performs phased modeling and coupling analysis of the communication process. This enables a more accurate prediction of the overall communication success rate and provides a theoretical basis for parameter optimization of Bluetooth communication between the first and second devices.

[0120] Reference Figure 5 In some embodiments, to accurately calculate the total communication power consumption of the first device and the second device within a preset radius, the step S300 in the above embodiments, which establishes the total communication power consumption function between the first device and the second device, includes the following steps:

[0121] S310. Based on the scanning parameters used for communication between the first device and the second device, construct the scanning power consumption expression for the first device;

[0122] In this embodiment, taking the second communication module in the first device as the first Bluetooth module and the third communication module in the second device as the second Bluetooth module as an example, the second device sends a broadcast signal through the second Bluetooth module to seek the establishment of a communication connection, and the first device sends a scanning signal through the first Bluetooth module. When the first device scans the broadcast signal sent by the second device, the two establish a communication connection (i.e., the device encounter event described in the above embodiment). In this embodiment, given the device density information, the communication parameter optimization variables for communication between the first device and the second device include the scanning interval. Scanning window and broadcast interval At this point, the scanning power consumption of a single first device... The expression is:

[0123] (10)

[0124] in, This represents the operating current in Bluetooth receiving mode, which is considered a constant in this embodiment.

[0125] S320. Construct the broadcast power consumption expression of the second device based on the broadcast parameters of the communication between the second device and the first device;

[0126] Corresponding to step S310, the broadcast power consumption of a single second device The expression is:

[0127] (11)

[0128] Wherein, coefficient 3 represents the number of channels through which the broadcast event is sent, that is, each broadcast event sends a broadcast packet once on each of the three channels; This represents the operating current in Bluetooth transmission mode and is considered a constant. This represents the duration of a single broadcast packet and is considered a constant.

[0129] S330. Combine the first device quantity information, the second device quantity information, the first device scanning power consumption expression, and the second device broadcast power consumption expression to construct the overall communication power consumption function.

[0130] Based on the scanning power consumption expression for a single first device and the broadcast power consumption expression for a single second device obtained in steps S310 and S320, and combined with the information on the number of first devices and the number of second devices within a preset radius obtained in the aforementioned embodiments, the overall communication power consumption function is as follows:

[0131] (12)

[0132] in, This indicates the number of devices within a preset radius. This indicates the number of second devices within a preset radius. In this embodiment, by constructing a total communication power consumption function (12) and combining it with the communication success rate objective function (9) constructed in the above embodiment, the minimization of power consumption and the maximization of communication success rate are taken as a dual-objective optimization problem, that is, a constrained multi-objective optimization model for communication and power consumption is constructed.

[0133] In some embodiments, the first communication module in the first device includes a 4G communication module or a 5G communication module, the positioning module includes a GPS positioning module or a BeiDou positioning module, and the second communication module includes a first Bluetooth module. The third communication module in the second device includes a second Bluetooth module. The separate second Bluetooth module in the second device has lower hardware costs and lower power consumption compared to the first communication module, positioning module, and first Bluetooth module in the first device. In this embodiment, when the first device and the second device communicate via Bluetooth, to ensure the feasibility of the Bluetooth communication parameters and compliance with the Bluetooth communication protocol specifications, the preset constraints in step S400 of the above embodiment include:

[0134] 1. Scanning window ≤ Scan interval The scanning window is constrained to be no larger than the scanning interval, ensuring a duty cycle of ≤100%.

[0135] 2. Scan interval ≤10.24 seconds, the constraint scan interval meets the upper limit of the Bluetooth protocol;

[0136] 3. Duration of a single broadcast package ≤ Scan window The duration of a single broadcast packet is constrained to be less than the scanning window to ensure that detection is completed.

[0137] 4. Broadcast intervals ≤ Scan interval The broadcast interval is constrained to be no greater than the scanning interval, thereby increasing the chance of detection.

[0138] 5. Broadcast intervals ≤10.24 seconds, constraining the broadcast interval to meet the upper limit of the Bluetooth protocol.

[0139] In some embodiments, the constrained multi-objective optimization model is obtained by combining the communication success rate objective function and the overall communication power consumption function in the preceding embodiments. In this embodiment, based on the aforementioned preset constraints, a constrained multi-objective algorithm is used to optimize the aforementioned communication success rate objective function. and overall power consumption function of communication After performing joint optimization of formulas (9) and (12), the Pareto optimal feasible solution set is obtained. :

[0140]

[0141] in, To optimize the combination of variables (i.e., the optimal combination of target communication parameters). This is the space of all feasible solutions.

[0142] Furthermore, calculating the target communication parameter combination based on business requirements within the aforementioned Pareto optimal feasible solution set specifically includes: within the Pareto optimal feasible solution set... To balance overall power consumption and communication success rate, the ideal-to-anti-ideal-point normalized distance method is used to screen and determine the final parameter combination, i.e., the target communication parameter combination. Specifically:

[0143] Ideal points and anti-ideal points are represented as follows:

[0144] ,

[0145] Normalization results:

[0146] ,

[0147] Euclidean distance was calculated on the normalized results:

[0148] (13)

[0149] Choose the optimal compromise solution from the calculation results:

[0150] (14)

[0151] in, The final, compromised optimal Bluetooth communication parameter combination is the target communication parameter combination. In this embodiment, the cloud server constructs a constrained multi-objective optimization model that maximizes communication success rate and minimizes communication power consumption under different device density and device ratio conditions, combining the objective function of communication success rate between the first and second devices and the corresponding overall communication power consumption function. Based on preset constraints, the cloud server solves this constrained multi-objective optimization model to obtain multiple sets of communication parameter combinations under different device density and device ratio conditions. A communication parameter adjustment strategy library is generated by mapping the device density and device ratio conditions to their corresponding target communication parameter combinations. Subsequently, the cloud server can directly issue the corresponding target communication parameter combination from the communication parameter adjustment strategy library based on the device density and device ratio, thereby dynamically optimizing the communication parameters of the first and second devices in the system.

[0152] In some embodiments, after establishing a mapping relationship between device density, device ratio conditions, and target communication parameter combinations through the above embodiments to generate a communication parameter adjustment strategy library, the system enters the online dynamic optimization stage. In this embodiment, after periodically or in real-time receiving the location information of the first and second devices, based on steps S610 to S640 of the above embodiments, the system queries the number of first and second devices within a preset radius of the first device location information. This allows the system to determine the device density and device ratio information within the preset radius of the current first device (each first device communicates with the server periodically or in real-time, triggering dynamic optimization of communication parameters). The server then obtains the corresponding target communication parameter combination from the communication parameter adjustment strategy library based on the device density and device ratio information and sends it to the first device, thereby optimizing the scanning window in the first device. Scan interval Dynamic optimization and adjustment are performed, and when communicating with a second device, the scanning interval in the target communication parameter combination is adjusted. The parameters are sent to the second device to dynamically optimize and adjust the communication parameters of the second device. In this embodiment, by dynamically optimizing the communication parameters of the first and second devices, the overall communication power consumption of the system is reduced while ensuring the communication success rate.

[0153] Reference Figure 6 In some embodiments, the method for dynamic optimization of communication parameters based on spatiotemporal data driven by the present invention further includes step 800: generating a communication parameter adjustment strategy library and sending it to the edge server, so as to enable the edge server to dynamically optimize communication parameters based on the first device quantity information and the second device quantity information. Specifically, it includes the following sub-steps:

[0154] S810, continuous spatial classification of equipment density and equipment quantity;

[0155] For example, based on equipment density, equipment density levels can be divided into: low density, medium density, and high density (the specific levels can be further refined according to actual applications); equipment quantity levels can be divided into: for the low density level, the sum of the first and second equipment quantities is within a preset first quantity range, and each corresponds to a continuous equipment ratio (the total number of equipment remains constant, while the ratio of the first to the second equipment quantities changes continuously); for the medium density level, the sum of the first and second equipment quantities is within a preset second quantity range, and each corresponds to a continuous equipment ratio; for the high density level, the sum of the first and second equipment quantities is within a preset third quantity range, and each corresponds to a continuous equipment ratio.

[0156] S820: Discretize and summarize the optimization strategies under all simulation scenarios to generate a communication parameter adjustment strategy library;

[0157] Specifically, the target communication parameter combinations are calculated for all device configurations at all density levels and for all scenarios, using the methods described in the previous embodiments. For example, within a preset radius, an area with a total number of devices less than 10 is defined as a low-density area. The calculations then cover various device configurations within this area, where the number of devices is the first and the total number of devices is 10 or less, to obtain the corresponding target communication parameter combinations. The same logic applies to medium and high density levels, thereby obtaining the first device quantity information, the second device quantity information, and the scanning window. Scan interval Broadcast interval The mapping relationship of communication parameters is stored in a structured strategy library, namely the communication parameter adjustment strategy library, for all scenarios.

[0158] S830: Distribute the communication parameter adjustment strategy library to the edge server.

[0159] In this embodiment, after generating the communication parameter adjustment strategy library through step S820, the cloud server sends it to the edge server. During system operation, the edge server queries the number of first and second devices within a preset radius of the current location information based on the received location information of the first device, thereby obtaining device density and device ratio information. Then, it matches the corresponding scanning window in the communication parameter adjustment strategy library. Scan interval Broadcast interval Communication parameters are sent to the first device, which then dynamically adjusts the scanning window. Scan interval Parameters, and when communicating with the second device within a preset radius, the broadcast interval will be... Send to the second device to specify the broadcast interval for the second device. Communication parameters are dynamically adjusted.

[0160] Furthermore, in other embodiments, if the communication parameter adjustment strategy library does not contain a corresponding communication parameter adjustment strategy for the current number of first and second devices, the current number of first and second devices is substituted into the constrained multi-objective optimization model established in step S300, and then the constrained multi-objective optimization model is solved in step S400. This yields the target communication parameter combination corresponding to the current number of first and second devices, which is then distributed to dynamically adjust the communication parameters of the first and second devices within the preset radius. Simultaneously, based on the current number of first and second devices, the corresponding device density and device ratio are obtained, and a mapping relationship between the current device density / ratio and the target communication parameter combination is established. This mapping relationship is updated and stored in the communication parameter adjustment strategy library for rapid response to dynamic communication parameter adjustments in the same scenario.

[0161] The following specific embodiments illustrate the application of the spatiotemporal data-driven dynamic optimization method for communication parameters in real-world scenarios:

[0162] Example 1: Low-density level, first equipment accounts for 25%;

[0163] Scenario description: Preset radius R=1000m, a total of 20 devices, of which 5 are the first type of device and 15 are the second type of device;

[0164] Equipment density information calculation: Approximately 6.37 units per square kilometer;

[0165] Meeting characteristic calculation: probability of equipment meeting Approximately 0.0110, duration of the encounter Approximately 1285.15ms;

[0166] Optimize communication parameters: scan interval The scan window is 230ms. 35ms; broadcast interval It takes 35ms;

[0167] Performance evaluation: Device pairing probability Discover the expected delay ms; Device discovery probability Communication success rate (0.1802%); Total power consumption for regional communication: Milliampere.

[0168] Example 2: Medium density level, first equipment accounts for 50%.

[0169] Scenario description: The preset radius R = 1000m, there are a total of 200 devices, of which 100 are the first type of device and 100 are the second type of device;

[0170] Equipment density information calculation: Approximately 66.36 units per square kilometer;

[0171] Meeting characteristic calculation: probability of equipment meeting Approximately 0.0499, duration of the encounter Approximately 6469.00 ms;

[0172] Optimize communication parameters: scan interval The scan window time is 413ms. The broadcast interval is 27ms. It takes 27ms;

[0173] Performance evaluation: Device pairing probability Discover the expected delay ms; Device discovery probability Communication success rate (1.0955%); Total power consumption for regional communication: Milliampere.

[0174] Example 3: High-density level, first-level equipment accounts for 75%;

[0175] Scenario description: The preset radius R = 1000m, there are a total of 2000 devices, of which 1500 are the first type of devices and 500 are the second type of devices;

[0176] Equipment density information calculation: Approximately 636.62 units per square kilometer;

[0177] Meeting characteristic calculation: probability of equipment meeting Approximately 0.9834, duration of encounter Approximately 518332.71ms;

[0178] Optimize communication parameters: scan interval The scan window time was 4369ms. The broadcast interval is 51ms. It takes 51ms;

[0179] Performance evaluation: Device pairing probability Discover the expected delay ms; Device discovery probability Communication success rate (17.2648%); Total power consumption for regional communication: Milliampere.

[0180] In some specific application embodiments, when the second device encounters the first device and conducts data communication, the first device not only provides positioning services for the second device, but the second device also transmits its collected device information to a cloud server / edge server through the first device. For example, in a battery / battery swapping scenario, by equipping some devices' batteries / batteries with a first communication module, a positioning module, and a second communication module (first device), and equipping others with a third communication module (second device), the second device, while communicating with the first device, simultaneously sends its collected battery information to the first device. This enables positioning services and battery status monitoring services for all operating devices in the system, reducing hardware investment costs. Simultaneously, adjusting the communication parameters between the first and second devices reduces overall power consumption within the communication area while ensuring communication success rate.

[0181] Reference Figure 7 This invention also provides a communication parameter dynamic optimization device driven by spatiotemporal data, comprising an offline model building module and an online dynamic parameter optimization module. The offline model building module is used to construct a device encounter probability model and an encounter duration model under different device densities within a preset radius based on historical spatiotemporal data. Based on the encounter probability model and encounter duration model, it constructs a communication success rate objective function between the first and second devices under different device ratios. Simultaneously, after establishing a total communication power consumption function between the first and second devices, it combines the communication success rate objective function to construct a constrained multi-objective optimization model of communication and power consumption. Finally, it solves the constrained multi-objective optimization model based on preset constraints to obtain multiple sets of communication parameter combinations. The online dynamic parameter optimization module is used to receive the location information of the first and second devices in real time. Based on the location information of the first devices, it calculates the number of first and second devices within a preset radius. Based on the number of first and second devices, it obtains a target communication parameter combination from multiple sets of communication parameter combinations and sends the target communication parameter combination to the first and second devices to achieve dynamic optimization of communication parameters. In this embodiment, the working principle of each module in the communication parameter optimization process of the communication parameter dynamic optimization device corresponds to the method described in the above embodiments, and will not be repeated here.

[0182] Reference Figure 8An embodiment of the present invention also provides a communication parameter dynamic optimization system based on spatiotemporal data, which includes multiple first devices, multiple second devices, and a server; wherein the multiple first devices are respectively communicatively connected to the multiple second devices and the server, each of the first devices is provided with a first communication module, a positioning module, and a second communication module, and each of the second devices is provided with a third communication module; when the second device and the first device meet and communicate data through the second communication module and the third communication module, the first device provides positioning services for the second device, and then sends preset parameter information containing at least the location information of the first device and the location information of the second device to the server through the first device, and the server is used to execute the communication parameter dynamic optimization method as described in any of the above embodiments to dynamically optimize the communication parameters between the first device and the second device, so as to ensure the communication success rate while taking into account the overall communication power consumption in the area.

[0183] In some embodiments, the communication parameter dynamic optimization system further includes an edge server; the cloud server generates a communication parameter adjustment strategy library based on the communication parameter dynamic optimization method described in the above embodiments and distributes it to the edge server; after configuring the communication parameter adjustment strategy library, the edge server queries the number of first devices and the number of second devices within a preset radius based on the received first device location information, and obtains the corresponding scanning window according to the mapping relationship in the communication parameter adjustment strategy library. Scan interval and broadcast interval After obtaining the parameters, they are sent to the first device and then transmitted to the second device, thus enabling the scanning window of the first device to be scanned. Scan interval Parameter adjustment, second device broadcast interval Adjusting the parameters.

[0184] In other embodiments, the cloud server can generate different communication parameter adjustment strategy libraries according to various application scenarios, and can manage multiple edge servers below it, thereby issuing different communication parameter adjustment strategy libraries according to the application scenario to meet communication needs.

[0185] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments, and various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention. Furthermore, the embodiments of the present invention and the features thereof can be combined with each other unless otherwise specified.

Claims

1. A method for dynamic optimization of communication parameters based on spatiotemporal data, characterized in that, The method is deployed in a server of a communication system, which further includes a first device and a second device; the first device is equipped with a first communication module, a positioning module, and a second communication module, and the second device is equipped with a third communication module, the second communication module and the third communication module being communicatively connected; the method includes: In the offline modeling phase, based on historical spatiotemporal data, a model of the probability of device encounters and the duration of encounters under different device densities within a preset radius are constructed. Based on the device encounter probability model and the encounter duration model, an objective function for the communication success rate between the first device and the second device under different device ratios is constructed. After establishing the overall power consumption function for communication between the first device and the second device, a constrained multi-objective optimization model for communication and power consumption is constructed by combining the communication success rate objective function. Multiple sets of communication parameter combinations are obtained by solving the constrained multi-objective optimization model based on preset constraints. During the online dynamic optimization phase, the location information of the first device and the location information of the second device are received. Calculate the number of first devices and the number of second devices within the preset radius based on the first device location information; Based on the first device quantity information and the second device quantity information, a target communication parameter combination is obtained from the multiple sets of communication parameter combinations, and the target communication parameter combination is sent to the first device and the second device to achieve dynamic optimization of communication parameters. The device encounter probability model is expressed as follows: This indicates the probability that the devices will meet. The density of equipment per unit area. These are the model parameters obtained by fitting the historical trajectory data of the first device. Represents the natural constant; The encounter duration model is expressed as follows: in, Indicates the duration of the device encounter. These are the model parameters obtained by fitting the historical location trajectory data of the first device. Represents the natural constant; The objective function for communication success rate is expressed as: in, This indicates the communication success rate between the first and second devices. This represents the probability that the second device will pair with the first device. This indicates the probability of the device being detected.

2. The method for dynamic optimization of communication parameters based on spatiotemporal data as described in claim 1, characterized in that, The construction of the device encounter probability model includes: Based on the historical trajectory of the historical spatiotemporal data, within the preset radius, the relationship between the probability of equipment encounter and the density of equipment is analyzed to establish the probability model of equipment encounter.

3. The method for dynamic optimization of communication parameters based on spatiotemporal data as described in claim 2, characterized in that, The construction of the encounter duration model includes: Based on the device encounter probability model, the encounter duration model is constructed by statistically summarizing the duration during which the distance between devices is below a preset distance threshold.

4. The method for dynamic optimization of communication parameters based on spatiotemporal data as described in claim 3, characterized in that, The objective function for the communication success rate between the first device and the second device under different device ratios includes: A device discovery probability model is established based on the communication parameters between the first device and the second device and the encounter duration model. Based on the aforementioned equipment encounter probability model, construct equipment pairing probability models under different equipment ratios; The objective function for communication success rate is constructed based on the device encounter probability model, the device discovery probability model, and the device pairing probability model.

5. The method for dynamic optimization of communication parameters based on spatiotemporal data-driven approach according to any one of claims 1 to 4, characterized in that, Establishing the overall power consumption function for communication between the first device and the second device includes: Based on the scanning parameters used for communication between the first device and the second device, construct the scanning power consumption expression for the first device; Based on the broadcast parameters of the communication between the second device and the first device, construct the broadcast power consumption expression of the second device; The overall communication power consumption function is constructed by combining the first number of devices, the second number of devices, the first device scanning power consumption expression, and the second device broadcast power consumption expression.

6. The method for dynamic optimization of communication parameters based on spatiotemporal data as described in claim 5, characterized in that, The second communication module includes a first Bluetooth module, and the third communication module includes a second Bluetooth module; the scanning parameters include scanning window, scanning interval, and Bluetooth receive mode operating current; the broadcast parameters include transmit mode operating current, duration of a single broadcast packet, broadcast interval, and number of broadcast event transmission channels. The preset constraints include: The scanning window is less than or equal to the scanning interval, and the scanning interval is less than or equal to the maximum upper limit of the broadcast interval; The duration of a single broadcast packet is less than or equal to the scanning window; The broadcast interval is less than or equal to the scan interval, and the broadcast interval is less than or equal to the maximum upper limit of the broadcast interval.

7. The method for dynamic optimization of communication parameters based on spatiotemporal data-driven approach according to any one of claims 1 to 3, characterized in that, The calculation of the number of first devices and the number of second devices within the preset radius based on the first device location information includes: The grid is divided based on a preset area range to obtain multiple grid cells; The first device location information and the second device location information are respectively mapped to the corresponding grid cells; The target grid cells covered within the preset radius are obtained based on the location information of the first device. In the target grid cell, the quantity information of the first device and the quantity information of the second device that satisfy the preset radius range are obtained.

8. The method for dynamic optimization of communication parameters based on spatiotemporal data-driven approach according to any one of claims 1 to 3, characterized in that, Also includes: A communication parameter adjustment strategy library is generated and sent to the edge server to enable the edge server to dynamically optimize communication parameters based on the first device quantity information and the second device quantity information.

9. A communication parameter dynamic optimization device based on spatiotemporal data, characterized in that, include: The offline model building module is used to build a device encounter probability model and an encounter duration model based on historical spatiotemporal data information under different device density conditions within a preset radius. Based on the encounter probability model and the encounter duration model, an objective function for the communication success rate between the first device and the second device under different device ratios is constructed. After establishing the overall power consumption function for communication between the first device and the second device, a constrained multi-objective optimization model for communication and power consumption is constructed by combining the communication success rate objective function. Multiple sets of communication parameter combinations are obtained by solving the constrained multi-objective optimization model based on preset constraints. The online dynamic parameter optimization module is used to receive the location information of the first device and the location information of the second device in real time. Calculate the number of first devices and the number of second devices within the preset radius based on the first device location information; Based on the first device quantity information and the second device quantity information, a target communication parameter combination is obtained from the multiple sets of communication parameter combinations, and the target communication parameter combination is sent to the first device and the second device to achieve dynamic optimization of communication parameters. The device encounter probability model is expressed as follows: This indicates the probability that the devices will meet. The density of equipment per unit area. These are the model parameters obtained by fitting the historical trajectory data of the first device. Represents the natural constant; The encounter duration model is expressed as follows: in, Indicates the duration of the device encounter. These are the model parameters obtained by fitting the historical location trajectory data of the first device. Represents the natural constant; The objective function for communication success rate is expressed as: in, This indicates the communication success rate between the first and second devices. This represents the probability that the second device will pair with the first device. This indicates the probability of the device being detected.

10. A communication parameter dynamic optimization system based on spatiotemporal data-driven approach, characterized in that, include: Multiple primary devices are used to realize data communication and location information collection functions; Multiple second devices are configured to communicate with the first device, and the first device is used to obtain the location information of the second devices; The server is communicatively connected to the first device and is used to execute the communication parameter dynamic optimization method as described in any one of claims 1 to 8 to optimize the communication parameters of the first device and the second device.

Images