Atmospheric waveguide interference prediction method, electronic equipment, storage medium and program product

Abstract

The invention provides an atmospheric waveguide interference prediction method, electronic equipment, a storage medium and a program product, relates to the technical field of communication, and is used for improving the accuracy of an atmospheric waveguide interference prediction result. The method comprises the steps of obtaining weather parameters of a to-be-predicted target set area in a preset time period; based on the weather parameters and an atmospheric waveguide prediction model, determining a prediction result of an atmospheric waveguide event of the target set area in a preset time period; and under the condition that the prediction result of the atmospheric waveguide event indicates that the atmospheric waveguide event will occur in the target set area within the preset time period, determining a cell in which the atmospheric waveguide event will occur in the target set area within the preset time period based on the cell in which the atmospheric waveguide event occurs in the target set area within the historical time period.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to an atmospheric ducting interference prediction method, an electronic device, a storage medium, and a program product. Background Art

[0002] The atmospheric ducting interference (ADI) phenomenon is mainly caused by specific meteorological conditions. When there are some special changes in the temperature and humidity in the atmosphere, the electromagnetic waves propagating in the atmosphere will be confined to a thin layer in the atmosphere and propagate like in a metal waveguide. This phenomenon can cause the electromagnetic waves to propagate farther along the ground, beyond the normal line of sight (LOS), thus interfering with the signal receiving points in the distance.

[0003] ADI will have an adverse impact on modern wireless communication systems, especially mobile communication networks. Currently, the prediction technology for ADI cannot accurately predict the results to the base station level, and operators or relevant staff cannot take targeted countermeasures against ADI, resulting in some base stations in the communication network being possibly affected by long-distance co-channel interference generated by atmospheric ducts, causing signal crosstalk between base stations, reducing the network service quality, and also affecting the data transmission rate. Summary of the Invention

[0004] This application provides an atmospheric ducting interference prediction method, an electronic device, a storage medium, and a program product, which are used to improve the accuracy of the atmospheric ducting interference prediction results.

[0005] In a first aspect, this application provides an atmospheric ducting interference prediction method, including: obtaining weather parameters of a target set area to be predicted in a preset time period; determining a prediction result of an atmospheric ducting event in the target set area in the preset time period based on the weather parameters and an atmospheric ducting prediction model; and when the prediction result of the atmospheric ducting event indicates that an atmospheric ducting event will occur in the target set area in the preset time period, determining the cells in the target set area where an atmospheric ducting event will occur in the preset time period based on the cells in the target set area where an atmospheric ducting event occurred in a historical time period.

[0006] The technical solution provided by this application at least brings the following beneficial effects: The atmospheric duct interference prediction method provided by this application can determine the prediction result of the atmospheric duct event in the target setting area within the preset time period based on the weather parameters and the atmospheric duct prediction model of the target setting area. Moreover, when the prediction result of the atmospheric duct event indicates that an atmospheric duct event will occur in the target setting area within the preset time period, it can determine the cells in the target setting area where an atmospheric duct event will occur within the preset time period. This not only improves the accuracy of the atmospheric duct interference prediction result, but also can accurately predict the atmospheric duct interference down to the base station level, which helps operators or relevant staff to take preventive measures before the occurrence of the atmospheric duct effect, so as to reduce signal interruption and fading phenomena and enhance network performance and user experience.

[0007] A possible implementation method is that the cells in the target setting area where an atmospheric duct event occurred during the historical time period are determined based on the following parameters: the background noise data of at least one cell in the target setting area during the historical time period, and the time-frequency domain characteristics of at least one cell in the target setting area.

[0008] Another possible implementation method is that the cells in the target setting area where an atmospheric duct event occurred during the historical time period are determined based on the following steps: Based on the background noise data of at least one cell in the target setting area during the historical time period, determine the interfering cells in the target setting area during the historical time period; where the interfering cell is a cell whose average background noise data is greater than a preset threshold; when the proportion of the interfering cells in the target setting area during the historical time period is greater than or equal to a preset proportion, determine that an atmospheric duct interference event occurred in the target setting area during the historical time period; based on the time-frequency domain characteristics of the interfering cells in the target setting area during the historical time period and the time-frequency domain characteristics of the atmospheric duct interference, determine the cells in the target setting area where an atmospheric duct event occurred during the historical time period.

[0009] Another possible implementation method is that the atmospheric duct prediction model is trained by using the weather parameters of the setting area during the historical time period and the atmospheric duct event parameters of the setting area during the historical time period as training samples; where the atmospheric duct event parameters are used to indicate whether an atmospheric duct event occurred.

[0010] Another possible implementation method is that obtaining the weather parameters of the target setting area to be predicted within the preset time period includes at least one of the following: determining the weather parameters of the target setting area to be predicted within the preset time period based on the weather forecast data; determining the weather parameters of the target setting area to be predicted within the preset time period based on the historical weather parameters of the target setting area during the historical time period.

[0011] Another possible implementation method is to determine the weather parameters of the target setting area to be predicted in a preset time period based on the historical weather parameters of the target setting area to be predicted in a historical time period, including: determining the weather parameters of the target setting area to be predicted in a preset time period through a weather prediction model based on the historical weather parameters of the target setting area to be predicted in a historical time period.

[0012] Another possible implementation method is that the weather prediction model is constructed based on the exponential smoothing prediction method or the extreme gradient boosting (XGBoost) algorithm.

[0013] In a second aspect, the present application provides an atmospheric duct interference prediction device, including: an acquisition module and a determination module. The acquisition module is configured to acquire the weather parameters of the target setting area to be predicted in a preset time period; the determination module is configured to determine the prediction result of the atmospheric duct event in the target setting area in the preset time period based on the weather parameters and the atmospheric duct prediction model; in the case where the prediction result of the atmospheric duct event indicates that an atmospheric duct event will occur in the target setting area in the preset time period, determine the cells in the target setting area where an atmospheric duct event will occur in the preset time period based on the cells in the target setting area where an atmospheric duct event occurred in the historical time period.

[0014] A possible implementation method is that the cells in the target setting area where an atmospheric duct event occurred in the historical time period are determined based on the following parameters: the background noise data of at least one cell in the target setting area in the historical time period, and the time-frequency domain characteristics of at least one cell in the target setting area.

[0015] Another possible implementation method is that the cells in the target setting area where an atmospheric duct event occurred in the historical time period are determined based on the following steps: determining the interfering cells in the target setting area in the historical time period based on the background noise data of at least one cell in the target setting area in the historical time period; where the interfering cell is a cell whose average background noise data is greater than a preset threshold; in the case where the proportion of the interfering cells in the target setting area in the historical time period is greater than or equal to a preset proportion, determining that an atmospheric duct interference event occurred in the target setting area in the historical time period; determining the cells in the target setting area where an atmospheric duct event occurred in the historical time period based on the time-frequency domain characteristics of the interfering cells in the target setting area in the historical time period and the time-frequency domain characteristics of the atmospheric duct interference.

[0016] Another possible implementation method is that the atmospheric duct prediction model is trained by using the weather parameters of the setting area in the historical time period and the atmospheric duct event parameters of the setting area in the historical time period as training samples; where the atmospheric duct event parameters are used to indicate whether an atmospheric duct event occurs.

[0017] Another possible implementation, an acquisition module, specifically configured to determine weather parameters of a target setting area to be predicted in a preset time period based on weather forecast data; and determine weather parameters of the target setting area to be predicted in the preset time period based on historical weather parameters of the target setting area to be predicted in a historical time period.

[0018] Another possible implementation, an acquisition module, specifically configured to determine, through a weather prediction model, weather parameters of a target setting area to be predicted in a preset time period based on historical weather parameters of the target setting area to be predicted in a historical time period.

[0019] Another possible implementation, the weather prediction model is constructed based on the exponential smoothing prediction method or the XGBoost algorithm.

[0020] In a third aspect, the present application provides an electronic device, which includes: a processor and a memory; the memory stores instructions executable by the processor; when the processor is configured to execute the instructions, the electronic device implements the method of the first aspect above.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which includes: computer software instructions; when the computer software instructions run on an electronic device, the electronic device implements the method of the first aspect above.

[0022] In a fifth aspect, the present application provides a computer program product, which includes a computer program; when the computer program runs on an electronic device, the electronic device implements the method of the first aspect above.

[0023] For the beneficial effects of the second to fifth aspects above, refer to the corresponding descriptions of the first aspect and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic diagram of an atmospheric duct interference prediction system provided by the present application;

[0025] Figure 2 It is a schematic flowchart of an atmospheric duct interference prediction method provided by the present application;

[0026] Figure 3 It is a schematic flowchart of another atmospheric duct interference prediction method provided by the present application;

[0027] Figure 4 It is a schematic flowchart of an atmospheric duct interference prediction model training method provided by the present application;

[0028] Figure 5 It is a schematic diagram of the composition of an atmospheric duct interference prediction device provided by the present application;

[0029] Figure 6 A structural schematic diagram of an electronic device provided for this application. Specific implementation manners

[0030] The atmospheric duct interference prediction method provided by this application will be described in detail below in conjunction with the accompanying drawings.

[0031] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone.

[0032] The terms "first" and "second" in the specification and drawings of this application are used to distinguish different objects or different treatments of the same object, rather than to describe the specific order of the objects.

[0033] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may alternatively include other unlisted steps or units, or may alternatively include other steps or units inherent to these processes, methods, products, or devices.

[0034] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0035] To facilitate a clear description of the technical solutions of the embodiments of this application, in the embodiments of this application, words such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and roles. Those skilled in the art can understand that the words such as "first" and "second" are not limiting the quantity and execution order.

[0036] In the description of this application, unless otherwise specified, the meaning of "a plurality" refers to two or more.

[0037] Atmospheric duct interference phenomena are mainly caused by specific meteorological conditions. When there are some special changes in the temperature and humidity in the atmosphere, such as the presence of a temperature inversion layer where the air temperature increases with the increase in the height of the atmosphere, or when the humidity distribution in the atmosphere also participates in forming a special refractive index profile, the electromagnetic waves propagating in the atmosphere will be confined to a thin layer in the atmosphere and propagate like in a metal waveguide, rather than being scattered into space along a straight or curved path. This phenomenon can cause electromagnetic waves to propagate farther along the ground, beyond the normal line of sight, thus interfering with signal receiving points that should not receive electromagnetic waves in the distance.

[0038] The meteorological conditions for the formation of atmospheric ducts include but are not limited to calm nights, temperature inversion layers, low humidity, and specific terrain configurations. Atmospheric duct interference can have an adverse impact on modern wireless communication systems, especially mobile communication networks. The atmospheric duct effect can cause co-channel interference over long distances, resulting in signal crosstalk between base stations. This not only reduces the quality of network communication and increases the call drop rate, but also makes the signal coverage of the cell uneven. Some areas may have overly strong signals, while other areas may have weakened signals, affecting the user experience.

[0039] Currently, the prediction methods for atmospheric duct interference cannot be accurate to the base station level. Operators or relevant staff cannot take precise countermeasures against atmospheric duct interference, resulting in some base stations in the communication network being possibly affected by long-distance co-channel interference generated by atmospheric ducts, causing signal crosstalk between base stations, reducing the network service quality, and also affecting the data transmission rate.

[0040] To address the above technical problems, this application provides a method for predicting atmospheric duct interference. The idea is: it can determine the prediction result of the atmospheric duct event in the target set area within a preset time period based on the weather parameters and the atmospheric duct prediction model of the target set area, and can also determine the cells in the target set area that will experience an atmospheric duct event when the prediction result of the atmospheric duct event indicates that an atmospheric duct event will occur in the target set area within the preset time period. This can not only improve the accuracy of the prediction result of atmospheric duct interference, but also accurately predict the result of atmospheric duct interference to the base station level, helping operators or relevant staff to take preventive measures before the occurrence of the atmospheric duct effect to reduce signal interruption and fading phenomena, and enhance network performance and user experience.

[0041] The following specifically introduces the embodiments provided in this application in conjunction with the accompanying drawings of the specification.

[0042] The technical solutions provided in the embodiments of this application can be applied to various mobile communication networks. For example, they can be applied to a new radio (NR) mobile communication network using 5G, a time division duplex long term evolution (TD-LTE) mobile communication network, a frequency division duplex long term evolution (FDD-LTE) mobile communication network, a future mobile communication network, or a multi-communication fusion system, etc. The embodiments of this application do not limit this.

[0043] The atmospheric duct interference prediction method provided in this application can be applied to an atmospheric duct interference prediction system as Figure 1 shown. As Figure 1 shown, the atmospheric duct interference prediction system includes: a front-end device 110 and a back-end server 120. Among them, the front-end device 110 and the back-end server 120 are connected to each other, and a trained atmospheric duct prediction model 121 is deployed in the back-end server 120.

[0044] In some embodiments, the front-end device 110 can be a device for human-computer interaction with users, such as a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc. The embodiments of this application do not limit the specific device form of the front-end device 110.

[0045] In some embodiments, the back-end server 120 can be a server cluster composed of multiple servers, or a single server, or a computer, or a cloud server, or a processor or processing chip in a server or computer, etc. The embodiments of this application do not limit the specific device form of the back-end server 120. Figure 1 The case where the back-end server 120 is a single server is illustrated hereinafter.

[0046] In some embodiments, the atmospheric duct prediction model 121 can determine the prediction result of the atmospheric duct event in the target set area to be predicted within a preset time period based on the weather parameters of the target set area to be predicted within a preset time period input. Exemplarily, the atmospheric duct prediction model 121 can be trained using the weather parameters of the set area in the historical time period and the atmospheric duct event parameters of the set area in the historical time period as training samples.

[0047] In some embodiments, the atmospheric duct prediction model 121 may be an XGBoost algorithm model.

[0048] In some embodiments, the front-end device 110 is configured to obtain weather parameters of a target set area to be predicted in a preset time period, and send the weather parameters of the target set area to be predicted in the preset time period to the back-end server 120, so that the back-end server 120 can determine a prediction result of an atmospheric duct event in the target set area in the preset time period based on the weather parameters and the atmospheric duct prediction model 121.

[0049] The back-end server 120 is configured to determine a prediction result of an atmospheric duct event in the target set area in a preset time period based on the weather parameters and the atmospheric duct prediction model 121; and in the case that the prediction result of the atmospheric duct event indicates that an atmospheric duct event will occur in the target set area in the preset time period, determine a cell in the target set area where an atmospheric duct event will occur in the preset time period based on cells in the historical time period where atmospheric duct events occurred in the target set area.

[0050] It should be noted that the system architecture described in the embodiments of the present application is for more clearly explaining the technical solutions of the embodiments of the present application, and does not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art know that with the evolution of the system architecture, the technical solutions provided in the embodiments of the present application are equally applicable to similar technical problems.

[0051] See Figure 2 , which is a schematic flowchart of a method for predicting atmospheric duct interference provided by an embodiment of the present application. As Figure 2 shown, the method for predicting atmospheric duct interference provided by the present application can be implemented by the back-end server in the above-mentioned atmospheric duct interference prediction system, and specifically includes the following steps S201 to S203.

[0052] S201. Obtain weather parameters of a target set area to be predicted in a preset time period.

[0053] In some embodiments, the weather parameters of the target set area to be predicted in the preset time period may be manually input into the atmospheric duct interference prediction system by a person, or an application programming interface (API) may be called to pre-define a data structure of the weather parameters, so that the atmospheric duct interference prediction system can obtain the weather parameters of the target set area in the preset time period from a software component or system with weather parameter prediction capabilities or weather forecast services through the API.

[0054] In some embodiments, the weather parameters of the target setting area to be predicted in a preset time period can be determined by at least one of the following steps A1 and A2.

[0055] A1. Determine the weather parameters of the target setting area to be predicted in the preset time period based on the weather forecast data.

[0056] A2. Determine the weather parameters of the target setting area to be predicted in the preset time period based on the historical weather parameters of the target setting area to be predicted in the historical time period.

[0057] Exemplarily, when the weather forecast can provide the weather parameters of the target setting area to be predicted in the preset time period, the weather parameters of the target setting area to be predicted provided by the weather forecast can be directly obtained.

[0058] When the weather forecast cannot provide the weather parameters of the target setting area to be predicted in the preset time period, the weather parameters of the target setting area to be predicted in the preset time period can be determined based on the historical weather parameters of the target setting area to be predicted in the historical time period.

[0059] When the weather forecast can provide the weather parameters of the target setting area to be predicted in a certain time period within the preset time period, for the weather parameters of the target setting area to be predicted in the time period that the weather forecast cannot provide, the weather parameters of the target setting area to be predicted in the time period that the weather forecast cannot provide can be determined based on the historical weather parameters of the target setting area to be predicted in the historical time period.

[0060] In some embodiments, the weather parameters of the target setting area to be predicted in the preset time period can be determined by a weather prediction model. Exemplarily, the above step A2 can be specifically implemented as: determining the weather parameters of the target setting area to be predicted in the preset time period through the weather prediction model based on the historical weather parameters of the target setting area to be predicted in the historical time period.

[0061] In some embodiments, the weather parameters may include at least one of the following: temperature data, humidity data, wind speed data, air pressure data, weather type data.

[0062] Among them, the unit of temperature data can be degrees Celsius (°C) or degrees Fahrenheit (°F); the humidity data is used to represent the content of water vapor in the air, and the unit of humidity data can be relative humidity (%RH); the wind speed data is used to represent the distance that air moves within a unit time, and the unit of wind speed data can be meters per second (m / s) or kilometers per hour (km / h); the air pressure data is used to represent the pressure of the atmosphere on a unit area, and the unit of air pressure data can be hectopascals (hPa) or millimeters of mercury (mmHg); the weather type data is used to represent the weather type of the target set area, and the weather type can include at least one of sunny, cloudy, overcast, rainy, thunderstorm, ice and snow, and fog.

[0063] It should be noted that the historical weather parameters of the target set area in the historical time period and the weather parameters of the target set area in the preset time period can be discrete parameters with the date as the time unit. That is, in the case where the weather parameters include temperature data, the temperature data included in the historical weather parameters of the target set area in the historical time period can be the daily average temperature of the target set area every day in the historical time period; the temperature data included in the weather parameters of the target set area in the preset time period can be the daily average temperature of the target set area every day in the preset time period.

[0064] In some embodiments, in order to facilitate obtaining the weather parameters of the target set area in the preset time period, the target set area can be an administrative area, such as a prefecture-level administrative region or a county and township-level administrative region.

[0065] S202. Based on the weather parameters and the atmospheric duct prediction model, determine the prediction result of the atmospheric duct event in the target set area in the preset time period.

[0066] In some embodiments, input the weather parameters of the target set area to be predicted in the preset time period into the atmospheric duct prediction model, and the atmospheric duct prediction model can output the prediction result of the atmospheric duct event in the target set area in the preset time period. Among them, the prediction result of the atmospheric duct event in the target set area in the preset time period can include the prediction result of the atmospheric duct event every day in the target set area in the preset time period; the prediction result of the atmospheric duct event is used to indicate whether an atmospheric duct event will occur in the target set area.

[0067] In some embodiments, the atmospheric duct prediction model can be trained based on the weather parameters of the set area in the historical time period and the atmospheric duct event parameters of the set area in the historical time period as training samples; among them, the atmospheric duct event parameters are used to indicate whether an atmospheric duct event occurs.

[0068] Exemplarily, the atmospheric duct event parameters can include 1 and -1. 1 is used to indicate that an atmospheric duct event occurs in the set area, and -1 is used to indicate that no atmospheric duct event occurs in the set area.

[0069] It should be noted that the atmospheric duct event parameters can indicate whether an atmospheric duct event occurs daily in a set area within a historical time period. Based on this, when training the atmospheric duct prediction model, the weather parameters and atmospheric duct event parameters of the set area every day within the historical time period can be corresponded one by one according to the date.

[0070] In some embodiments, when the atmospheric duct prediction model is trained with the weather parameters of the set area within the historical time period and the atmospheric duct event parameters of the set area within the historical time period as training samples, the prediction result of the atmospheric duct event in the target set area within the preset time period can be the atmospheric duct event parameters of the target set area output by the atmospheric duct prediction model, where the atmospheric duct event parameters are used to indicate whether an atmospheric duct event occurs.

[0071] S203. When the prediction result of the atmospheric duct event indicates that the atmospheric duct event will occur in the target set area within the preset time period, based on the cells where the atmospheric duct event occurred in the target set area within the historical time period, determine the cells where the atmospheric duct event will occur in the target set area within the preset time period.

[0072] It can be understood that the generation of the atmospheric duct is mainly affected by the atmospheric inversion layer. Therefore, the occurrence of the atmospheric duct event is closely related to specific atmospheric conditions and geographical locations. Based on this, when the atmospheric duct event will occur in the target set area, the cells where the atmospheric duct event occurred in the target set area within the historical time period may send the atmospheric duct event again. Herein, the cell refers to the geographical range covered by a base station within the target set area.

[0073] Exemplarily, when the prediction result of the atmospheric duct event indicates that the atmospheric duct event will occur in the target set area within the preset time period, the cells where the atmospheric duct event occurred in the target set area within the historical time period can be determined as the cells where the atmospheric duct event will occur within the preset time period.

[0074] It can be understood that there is a lack of a comprehensive detection technology for the atmospheric duct phenomenon in the prior art. Therefore, it is impossible to directly determine the cells where the atmospheric duct event occurred in the target set area within the historical time period. Therefore, the cells in the target set area that were interfered within the historical time period can be determined by observing the background noise data of the cells, and then the cells where the atmospheric duct event occurred in the target set area within the historical time period can be determined.

[0075] As a possible implementation manner, the cells where the atmospheric duct event occurred in the target set area within the historical time period are determined based on the following parameters: the background noise data of at least one cell in the target set area within the historical time period, and the time-frequency domain characteristics of at least one cell in the target set area.

[0076] Exemplarily, as Figure 3 shown, for the cells in the target setting area where atmospheric duct events occurred during the historical time period, they can be determined based on the following steps S301 - S303.

[0077] S301. Determine the interfering cells in the target setting area during the historical time period based on the background noise data of at least one cell in the target setting area during the historical time period; wherein, the interfering cell is a cell whose average background noise data is greater than a preset threshold.

[0078] It can be understood that the background noise data of the cell can reflect the inherent noise level in the environment of the cell during the historical time period. Therefore, by monitoring the background noise of the cell, it can be identified whether the cell is interfered by an external interference source. In the case where the cell is interfered by an external interference source, it can be determined whether an atmospheric duct event occurs in the cell.

[0079] Exemplarily, the background noise data of the cell during the historical time period can include the average background noise data of the cell every day during the historical time period. In the case where the average background noise data of the cell is greater than the preset threshold, it can be considered that the cell is interfered by an external interference source, that is, the cell is an interfering cell.

[0080] In some embodiments, measurement devices for obtaining the background noise data of the cell can be arranged in the cell, such as a spectrum analyzer, a noise meter, a wireless network analyzer, etc. The background noise of the cell is measured by the measurement device to obtain the background noise data of the cell during the historical time period.

[0081] In some embodiments, in the case where the base station or the management and control unit of the base station can obtain the background noise data of the cells within the coverage area of the base station, the background noise data of the cell during the historical time period can be obtained through the base station or the management and control unit of the base station. Among them, the management and control unit of the base station can be a network management system (NMS), a distributed unit (DU), a centralized unit (CU), an operation and maintenance center (OMC), etc.

[0082] S302. In the case where the proportion of the interfering cells in the target setting area during the historical time period is greater than or equal to a preset proportion, determine that an atmospheric duct interference event occurred in the target setting area during the historical time period.

[0083] In some embodiments, when the atmospheric duct phenomenon occurs, the area affected by the atmospheric duct interference may be relatively large. Therefore, when the proportion of interfering cells in the target set area in the historical time period is greater than or equal to the preset proportion, it can be considered that an atmospheric duct interference event has occurred in the target set area in the historical time period.

[0084] In some embodiments, when the background noise data of a cell in the historical time period includes the average background noise data of the cell every day in the historical time period, obtain the proportion of interfering cells in the target set area every day in the historical time period. If the number of consecutive days when the proportion of interfering cells in the target set area in the historical time period is greater than or equal to the preset proportion exceeds the preset number of days, determine that an atmospheric duct interference event has occurred in the target set area in the historical time period.

[0085] S303. Based on the time-frequency domain characteristics of the interfering cells in the target set area in the historical time period and the time-frequency domain characteristics of the atmospheric duct interference, determine the cells in the target set area where the atmospheric duct event has occurred in the historical time period.

[0086] It should be noted that when a cell is affected by the atmospheric duct interference, due to the atmospheric duct effect, signals from distant base stations that should not originally reach may be received by the cell base station. Therefore, the signal of the cell will suddenly increase, and there may be multiple ducts in a short period of time. Since the atmospheric duct causes electromagnetic waves to propagate through different paths, resulting in additional delay spread, multiple signal copies with time delays may appear at the receiving end of the cell. Due to the refraction effect caused by the atmospheric duct, the frequency of the signal may shift slightly, resulting in the signal frequency detected at the receiving end of the cell not being exactly the same as that at the transmitting end. Moreover, the atmospheric duct effect may cause the signal spectrum to expand, making the bandwidth occupied by the signal wider.

[0087] As can be seen from the above, when affected by the atmospheric duct interference, the time-domain characteristics of a cell may include signal intensity duct, delay spread, etc., and the frequency-domain characteristics of the cell may include spectrum expansion, frequency shift, etc.

[0088] In some embodiments, it is possible to observe whether the time-frequency domain diagram of the interfering cells in the target set area in the historical time period, such as the short-time Fourier transform (STFT) diagram, conforms to the time-frequency domain characteristics of the atmospheric duct interference. When the time-frequency domain diagram of the interfering cells in the target set area in the historical time period conforms to the time-frequency domain characteristics of the atmospheric duct interference, determine the corresponding interfering cells as the cells where the atmospheric duct event has occurred in the target set area in the historical time period.

[0089] As can be seen from the above steps S201 - S203, the atmospheric duct interference prediction method provided by the embodiments of the present application can determine the prediction result of the atmospheric duct event in the target set area within the preset time period based on the weather parameters and the atmospheric duct prediction model of the target set area. Moreover, when the prediction result of the atmospheric duct event indicates that an atmospheric duct event will occur in the target set area within the preset time period, it can determine the cells in the target set area where an atmospheric duct event will occur within the preset time period. This can not only improve the accuracy of the atmospheric duct interference prediction result, but also accurately locate the prediction result of the atmospheric duct interference to the base station level, which helps operators or relevant staff take preventive measures before the occurrence of the atmospheric duct effect to reduce signal interruption and fading phenomena and enhance network performance and user experience.

[0090] In some embodiments, the weather prediction model in the above step S201 can be constructed based on the exponential smoothing prediction method or the XGBoost algorithm.

[0091] Exemplarily, when constructing the weather prediction model in the present application using the exponential smoothing prediction method, the historical weather parameters of the target set area in the historical time period can be used as training data to train the weather prediction model.

[0092] The exponential smoothing prediction method includes the single exponential smoothing method, the double exponential smoothing method, and the triple exponential smoothing method, etc. When the historical weather parameters of the target set area in the historical time period used as training data include the daily weather parameters of the target set area in the historical time period, the single exponential smoothing method can be used to construct the weather prediction model. Among them, the prediction result of the weather parameters of the target set area in the preset time period satisfies the following formula:

[0093] y t+1 ′=ay t +(1 - a)y t ′

[0094] Where y′ t+1 represents the prediction result of the weather parameters of the target set area at the t + 1 moment, y t represents the actual weather parameters of the target set area at the t moment, y t ′ represents the prediction result of the weather parameters of the target set area at the t moment, a represents the smoothing coefficient, and the t + 1 moment is used to represent the next moment after the t moment. When the historical weather parameters of the target set area in the historical time period include the daily weather parameters of the target set area in the historical time period, the t + 1 moment and the t moment can represent two adjacent dates.

[0095] It should be noted that the smoothing coefficient in the weather prediction model determines how the model weights historical data points to generate predictions. The value range of the smoothing coefficient in the weather prediction model provided in this application can be: greater than or equal to 0.1 and less than or equal to 0.3.

[0096] In the case of using the XGBoost algorithm to construct the weather prediction model in this application, the historical weather parameters of the target setting area to be predicted in the historical time period can be classified according to the weather type data included in the weather parameters. The weather parameters corresponding to different weather types are used as training data to perform classification training on the weather prediction model, and the trained weather prediction model is obtained.

[0097] In some embodiments, an atmospheric duct prediction model is deployed in the backend server of the atmospheric duct interference prediction system. Before performing atmospheric duct interference prediction on the target setting area based on the atmospheric duct interference prediction model, it is necessary to construct and train the atmospheric duct prediction model in the backend server of the atmospheric duct interference prediction system or other devices and equipment with model construction and training capabilities.

[0098] Exemplarily, the devices and equipment with model construction and training capabilities may include computers, supercomputers, server clusters, cloud computing platforms, embedded devices, etc.

[0099] In some embodiments, the atmospheric duct prediction model may be a model constructed and trained based on a classification algorithm, such as the XGBoost algorithm.

[0100] Exemplarily, as Figure 4 shown, the training of the atmospheric duct prediction model can be specifically implemented as the following steps S401 - S405.

[0101] S401: Corresponding the weather parameters of the setting area in the historical time period and the atmospheric duct event parameters of the setting area in the historical time period one by one according to the date, and dividing them into a training set and a test set.

[0102] In some embodiments, it is also necessary to preprocess the weather parameters of the setting area in the historical time period and the atmospheric duct event parameters of the setting area in the historical time period, such as missing value processing, feature scaling, etc.

[0103] S402: Set the parameters of the XGBoost algorithm, including the number of trees, depth, learning rate, etc. of the XGBoost algorithm tree.

[0104] It should be noted that the parameters of the XGBoost algorithm will affect the performance and training speed of the atmospheric duct prediction model. Based on this, appropriate parameters can be selected based on the coverage range of the target setting area to be predicted and the length of the preset time period.

[0105] S403. Use the weather parameters of the set area in the historical time period and the atmospheric duct event parameters of the set area in the historical time period included in the training set to train the atmospheric duct prediction model.

[0106] In some embodiments, during the training of the atmospheric duct prediction model, the atmospheric duct prediction model is gradually optimized in an iterative manner, and a new decision tree is added in each iteration to correct the errors of the previous model.

[0107] S404. Use the weather parameters of the set area in the historical time period included in the test set to test the trained atmospheric duct prediction model, and determine the performance index of the atmospheric duct prediction model based on the test output result of the atmospheric duct prediction model.

[0108] In some embodiments, the weather parameters of the set area in the historical time period included in the test set can be input into the atmospheric duct prediction model to obtain the test output result of the atmospheric duct prediction model, and compare it with the atmospheric duct event parameters of the set area in the historical time period included in the test set to calculate the performance index of the atmospheric duct prediction model, such as accuracy rate, mean square error, etc.

[0109] S405. Adjust the parameters of the atmospheric duct prediction model based on the performance index of the atmospheric duct prediction model.

[0110] Exemplarily, the parameter optimization result of the atmospheric duct prediction model can be determined based on the cross-validation method, and the parameter optimization result of the atmospheric duct prediction model is used to improve the model performance.

[0111] It can be seen that the above mainly introduces the solution provided by the embodiments of the present application from the perspective of the method. To implement the above functions, the embodiments of the present application provide the corresponding hardware structure and / or software module for each function. Those skilled in the art should easily realize that, combined with the modules and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0112] The embodiments of the present application can divide the atmospheric duct interference prediction device into functional modules according to the above method examples. For example, each functional module can be corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. Optionally, the division of modules in the embodiments of the present application is illustrative, and is only a logical function division. There can be other division methods in actual implementation.

[0113] In some embodiments, the present application further provides an atmospheric duct interference prediction device. The atmospheric duct interference prediction device may include one or more functional modules for implementing the atmospheric duct interference prediction method in the above method embodiments.

[0114] For example, Figure 5 is a schematic diagram of the composition of an atmospheric duct interference prediction device provided by an embodiment of the present application. As Figure 5 shown, the atmospheric duct interference prediction device 800 includes: an acquisition module 801 and a determination module 802.

[0115] The acquisition module 801 is used to acquire weather parameters of a target set area to be predicted in a preset time period; the determination module 802 is used to determine a prediction result of an atmospheric duct event in the target set area in the preset time period based on the weather parameters and an atmospheric duct prediction model; in the case where the prediction result of the atmospheric duct event indicates that an atmospheric duct event will occur in the target set area in the preset time period, based on the cells in the target set area where atmospheric duct events occurred in the historical time period, determine the cells in the target set area where atmospheric duct events will occur in the preset time period.

[0116] In some embodiments, the cells in the target set area where atmospheric duct events occurred in the historical time period are determined based on the following parameters: the background noise data of at least one cell in the target set area in the historical time period, and the time-frequency domain characteristics of at least one cell in the target set area.

[0117] In other embodiments, the cells in the target set area where atmospheric duct events occurred in the historical time period are determined based on the following steps: based on the background noise data of at least one cell in the target set area in the historical time period, determine the interfering cells in the target set area in the historical time period; where the interfering cell is a cell whose average background noise data is greater than a preset threshold; in the case where the proportion of the interfering cells in the target set area in the historical time period is greater than or equal to a preset proportion, determine that an atmospheric duct interference event occurred in the target set area in the historical time period; based on the time-frequency domain characteristics of the interfering cells in the target set area in the historical time period and the time-frequency domain characteristics of atmospheric duct interference, determine the cells in the target set area where atmospheric duct events occurred in the historical time period.

[0118] In some other embodiments, the atmospheric duct prediction model is trained by using weather parameters of a set area in a historical time period and atmospheric duct event parameters of the set area in the historical time period as training samples; wherein, the atmospheric duct event parameters are used to indicate whether an atmospheric duct event occurs.

[0119] In some other embodiments, the obtaining module 801 is specifically configured to determine weather parameters of a target set area to be predicted in a preset time period based on weather forecast data; and determine weather parameters of the target set area to be predicted in the preset time period based on historical weather parameters of the target set area to be predicted in a historical time period.

[0120] In some other embodiments, the obtaining module 801 is specifically configured to determine weather parameters of a target set area to be predicted in a preset time period through a weather prediction model based on historical weather parameters of the target set area to be predicted in a historical time period.

[0121] In some other embodiments, the weather prediction model is constructed based on the exponential smoothing prediction method or the XGBoost algorithm.

[0122] When the functions of the above integrated modules are implemented in the form of hardware, an exemplary structural diagram of the electronic device involved in the above embodiments is provided in an embodiment of the present invention. As Figure 6 shown, the electronic device 900 includes: a processor 902, a communication interface 903, and a bus 904. Optionally, the electronic device 900 may further include a memory 901.

[0123] The processor 902 may be used to implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present application. The processor 902 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present application. The processor 902 may also be a combination for implementing computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0124] The communication interface 903 is used to connect to other devices through a communication network. The communication network may be an Ethernet, a radio access network, a wireless local area network (WLAN), etc.

[0125] The memory 901 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or can also be an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0126] As a possible implementation, the memory 901 can exist independently of the processor 902. The memory 901 can be connected to the processor 902 through the bus 904 for storing instructions or program code. When the processor 902 calls and executes the instructions or program code stored in the memory 901, the atmospheric duct interference prediction method provided by the embodiments of the present invention can be implemented.

[0127] In another possible implementation, the memory 901 can also be integrated with the processor 902.

[0128] The bus 904 can be an extended industry standard architecture (EISA) bus, etc. The bus 904 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 6 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0129] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the service call device is divided into different functional modules to complete all or part of the functions described above.

[0130] The embodiments of the present application also provide a computer-readable storage medium. All or part of the processes in the above method embodiments can be completed by computer instructions instructing relevant hardware. The program can be stored in the above computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be the memory in any of the foregoing embodiments. The above computer-readable storage medium can also be an external storage device of the above service call device, such as a plug-in hard disk equipped on the above service call device, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the above computer-readable storage medium can also include both the internal storage unit of the above service call device and the external storage device. The above computer-readable storage medium is used to store the above computer program and other programs and data required by the above service call device. The above computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0131] The embodiments of the present application also provide a computer program product. The computer product includes a computer program. When the computer program product runs on a computer, it causes the computer to execute any one of the atmospheric duct interference prediction methods provided in the above embodiments.

[0132] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for predicting atmospheric duct interference, characterized in that: The method comprises: Obtaining weather parameters of the target set area to be predicted in a preset time period; Based on the weather parameters and the atmospheric duct prediction model, determining the prediction result of the atmospheric duct event of the target setting area in the preset time period; When the prediction result of the atmospheric waveguide event indicates that an atmospheric waveguide event will occur in the target setting area during the preset time period, the cells in which the atmospheric waveguide event will occur in the target setting area during the preset time period are determined based on the cells in which the atmospheric waveguide event occurred in the target setting area during the historical time period.

2. The method according to claim 1, characterized in that The target setting area is determined based on the following parameters: The background noise data of at least one cell in the target setting area in the historical time period and the time-frequency domain characteristics of at least one cell in the target setting area.

3. The method according to claim 2, characterized in that The target setting area is a cell where an atmospheric waveguide event occurred in a historical time period, and is determined based on the following steps: Based on the background noise data of at least one cell in the target setting area in the historical time period, determining the interference cell in the target setting area in the historical time period; wherein the interference cell is a cell whose average background noise data is greater than a preset threshold; When the proportion of interfering cells in the target setting area in the historical time period is greater than or equal to a preset proportion, determining that an atmospheric waveguide interference event occurs in the target setting area in the historical time period; Based on the time-frequency domain characteristics of the interfering cells in the target setting area in the historical time period and the time-frequency domain characteristics of the atmospheric waveguide interference, the cells in the target setting area where the atmospheric waveguide event occurred in the historical time period are determined.

4. The method according to claim 1, characterized in that The atmospheric waveguide prediction model is trained based on weather parameters of a set area in a historical time period and atmospheric waveguide event parameters of the set area in the historical time period as training samples; wherein the atmospheric waveguide event parameters are used to indicate whether an atmospheric waveguide event occurs.

5. The method according to claim 1, characterized in that The step of obtaining the weather parameters of the target setting area to be predicted in a preset time period includes at least one of the following: Determining weather parameters of the target setting area to be predicted in a preset time period based on weather forecast data; Based on the historical weather parameters of the target setting area to be predicted in the historical time period, the weather parameters of the target setting area to be predicted in the preset time period are determined.

6. The method according to claim 5, characterized in that The determining the weather parameters of the target setting area to be predicted in a preset time period based on the historical weather parameters of the target setting area to be predicted in the historical time period includes: Based on the historical weather parameters of the target setting area to be predicted in the historical time period, the weather parameters of the target setting area to be predicted in the preset time period are determined by a weather forecasting model.

7. The method according to claim 6, characterized in that The weather forecast model is constructed based on the exponential smoothing forecasting method or the extreme gradient boosting XGBoost algorithm.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor is coupled to the memory; the memory is used to store computer instructions, and the computer instructions are loaded and executed by the processor to enable a computer device to implement the atmospheric waveguide interference prediction method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes computer-executable instructions. When the computer-executable instructions are executed on a computer, the computer is enabled to execute the atmospheric waveguide interference prediction method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is run on an electronic device, the electronic device is enabled to perform the atmospheric waveguide interference prediction method according to any one of claims 1 to 7.

Images