Intelligent electric meter dual-mode converged communication method and device, intelligent electric meter and medium

Abstract

The invention discloses an intelligent electric meter dual-mode converged communication method and device, an intelligent electric meter and a medium, and relates to the technical field of communication. According to the scheme, two different communication modules, namely the WiFi module and the GPRS module, are arranged for the intelligent electric meter; when the intelligent electric meter and the server have communication requirements, the time period information and the WiFi communication performance parameters of the current moment are collected, and the WiFi connection success probability of this time is predicted by using the pre-constructed WiFi connection success rate prediction model, so that WiFi communication or GPRS communication is selected to be started according to the WiFi connection success probability, the economical efficiency of WiFi communication and the reliability of GPRS communication are both considered, and the user experience is improved. Unified optimization of meter reading success rate maximization and communication cost minimization is realized.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a dual-mode fusion communication method, device, smart meter, and medium for smart meters. Background Technology

[0002] Smart meters, through their built-in communication modules, collect and transmit electricity consumption data (such as voltage, current, power, and energy) and meter status information to a server in real time, thereby enabling efficient remote meter reading. Simultaneously, the communication module can also receive commands from the server for parameter settings, remote control, and firmware upgrades, significantly improving the intelligent management level of the power system.

[0003] In terms of communication technology, smart meters primarily employ Wireless Fidelity (WiFi) or General Packet Radio Service (GPRS). While WiFi networks are less expensive, they are susceptible to external network conditions and malfunctions, leading to insufficient communication stability. In contrast, GPRS networks offer more flexible communication options, enhancing network reliability and environmental adaptability, thereby improving the success rate of meter information collection. However, GPRS requires a Subscriber Identity Module (SIM) card, which increases data charges and operating costs.

[0004] Given the above, how to effectively control data traffic costs to reduce operating costs while ensuring the reliability of smart meter communication is a problem that technical personnel in this field urgently need to solve. Summary of the Invention

[0005] The purpose of this application is to provide a dual-mode converged communication method, device, smart meter, and medium for smart meters, so as to effectively control traffic charges and reduce operating costs while ensuring the reliability of smart meter communication.

[0006] To address the aforementioned technical problems, this application provides a dual-mode fusion communication method for smart meters, applied to smart meters equipped with both WiFi and GPRS modules; the method includes:

[0007] When there is a need to communicate with the server, determine the current time period and collect the WiFi communication performance parameters at the current time.

[0008] The time period information and WiFi communication performance parameters are input into a pre-built WiFi connection success rate prediction model to output the WiFi connection success probability at the current moment. The construction process of the WiFi connection success rate prediction model includes: collecting historical WiFi communication feature vectors in multiple historical time periods and determining the weight vectors corresponding to each historical time period; based on each historical time period and its corresponding historical WiFi communication feature vectors and weight vectors, a WiFi connection success rate prediction model is constructed to predict the WiFi connection success probability in each time period.

[0009] Determine whether to enable WiFi communication based on the probability of successful WiFi connection;

[0010] If so, a communication connection with the server is established via the WiFi module;

[0011] If not, a communication connection with the server is established via the GPRS module.

[0012] On the one hand, historical WiFi communication feature vectors are collected from multiple historical time periods, including:

[0013] The daily cycle is divided into multiple historical time periods based on the meter reading cycle;

[0014] Based on each historical period, the average WiFi signal strength, WiFi response failure rate, WiFi connection failure rate, WiFi communication percentage, and WiFi communication re-reading rate were collected respectively.

[0015] On the other hand, based on each historical period, the corresponding average WiFi signal strength, WiFi response failure rate, WiFi connection failure rate, WiFi communication percentage, and WiFi communication re-reading rate were collected, including:

[0016] Determine the average value of the received signal strength indication for each WiFi communication within a historical period to determine the average WiFi signal strength;

[0017] Determine the quotient of the number of failed WiFi communication responses to the number of successful WiFi communication responses within a historical period to determine the WiFi response failure rate;

[0018] Determine the ratio of the number of failed WiFi connections to the number of successful WiFi connections within a historical time period to determine the WiFi connection failure rate;

[0019] Determine the quotient of the number of WiFi communication data exchanges and the total number of communication data exchanges within a historical period to determine the proportion of WiFi communication.

[0020] Determine the quotient between the number of WiFi data transfer communications and the total number of WiFi communications within a historical period to determine the WiFi data transfer rate.

[0021] On the other hand, determining whether to enable WiFi communication based on the probability of a successful WiFi connection includes:

[0022] Determine the decision threshold corresponding to the time period in which the current moment occurs;

[0023] The threshold function value is determined based on the WiFi connection success probability, the decision threshold, and the threshold function.

[0024] Determine whether the threshold function value is greater than the preset threshold value;

[0025] If so, then confirm that WiFi communication is enabled;

[0026] If not, then confirm that WiFi communication is not enabled.

[0027] On the other hand, it also includes:

[0028] WiFi communication results are collected at preset intervals for each time period, and WiFi communication loss items are set.

[0029] Generate a loss function based on the WiFi communication results, the WiFi communication loss term, and the threshold function value;

[0030] The weight vector and decision threshold for each time period are updated based on the loss function.

[0031] On the other hand, WiFi communication loss items are set, including:

[0032] Set a cost item to represent the execution of GPRS communication after WiFi communication failure;

[0033] Configure a penalty for actively switching to GPRS communication.

[0034] On the other hand, the weight vectors and decision thresholds for each time period are updated based on the loss function, including:

[0035] Based on the weight vector, learning rate, and loss function, a new weight vector is determined using the gradient descent algorithm.

[0036] A new decision threshold is determined using the gradient descent algorithm based on the decision threshold, learning rate, and loss function.

[0037] To address the aforementioned technical problems, this application also provides a dual-mode fusion communication device for smart meters, applicable to smart meters equipped with both WiFi and GPRS modules; the device includes:

[0038] The data acquisition and determination module is used to determine the current time period and collect the WiFi communication performance parameters at the current time when there is a communication requirement with the server.

[0039] The prediction module is used to input time period information and WiFi communication performance parameters into a pre-built WiFi connection success rate prediction model to output the WiFi connection success probability at the current moment. The construction process of the WiFi connection success rate prediction model includes: collecting historical WiFi communication feature vectors in multiple historical time periods and determining the weight vector corresponding to each historical time period; based on each historical time period and its corresponding historical WiFi communication feature vector and weight vector, constructing a WiFi connection success rate prediction model to predict the WiFi connection success probability in each time period.

[0040] The judgment module is used to determine whether to enable WiFi communication based on the probability of a successful WiFi connection; if yes, the first communication module is triggered; if no, the second communication module is triggered.

[0041] The first communication module is used to establish a communication connection with the server via the WiFi module;

[0042] The second communication module is used to establish a communication connection with the server via the GPRS module.

[0043] To address the aforementioned technical problems, this application also provides a smart meter, comprising:

[0044] Memory, used to store computer programs;

[0045] The processor is used to implement the steps of the above-described dual-mode fusion communication method for smart meters when executing computer programs.

[0046] To address the aforementioned technical problems, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the aforementioned dual-mode fusion communication method for smart meters.

[0047] The beneficial effect of this application is that it sets up two different communication modules for the smart meter: a WiFi module and a GPRS module. When the smart meter needs to communicate with the server, it collects the current time period information and WiFi communication performance parameters, and uses a pre-built WiFi connection success rate prediction model to predict the probability of WiFi connection success. This allows the smart meter to choose between WiFi communication and GPRS communication based on the WiFi connection success rate, thus balancing the economy of WiFi communication and the reliability of GPRS communication. This achieves a unified optimization that maximizes the meter reading success rate and minimizes communication costs.

[0048] In addition, this application also provides a dual-mode fusion communication device for smart meters, a smart meter and a medium, with the same effect as above. Attached Figure Description

[0049] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a topology diagram of a dual-communication module access system provided in an embodiment of this application;

[0051] Figure 2 A flowchart illustrating a dual-mode fusion communication method for smart meters provided in this application embodiment;

[0052] Figure 3 This is a schematic diagram of the dual-mode converged communication architecture for smart meters provided in an embodiment of this application;

[0053] Figure 4 This is a schematic diagram of a dual-mode fusion communication device for a smart meter provided in an embodiment of this application;

[0054] Figure 5 This is a structural diagram of a smart meter provided in an embodiment of this application. Detailed Implementation

[0055] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0056] The core of this application is to provide a dual-mode fusion communication method, device, smart meter, and medium for smart meters, so as to effectively control traffic charges and reduce operating costs while ensuring the reliability of smart meter communication.

[0057] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0058] Currently, in terms of communication technology, smart meters mainly use WiFi or GPRS technology. While WiFi networks are lower in cost, they are susceptible to external network conditions and malfunctions, leading to insufficient communication stability. In contrast, GPRS networks offer more flexible communication options, enhancing network reliability and environmental adaptability, thereby improving the success rate of meter information collection. However, GPRS requires a SIM card, which increases data charges and operating costs. Therefore, to balance communication reliability and economy, this application provides a dual-mode fusion communication method for smart meters.

[0059] Figure 1 This is a topology diagram of a dual-communication module access system provided in an embodiment of this application. Figure 1 As shown, in this embodiment, the smart meter is equipped with a WiFi module and a GPRS module. The smart meter can establish a communication connection with the server and transmit data through the WiFi module and GPRS module respectively.

[0060] Figure 2 This is a flowchart illustrating a dual-mode fusion communication method for smart meters provided in an embodiment of this application. Figure 2 As shown, the method includes:

[0061] S10: When there is a communication requirement with the server, determine the current time period information and collect the WiFi communication performance parameters at the current time.

[0062] Specifically, when the smart meter needs to communicate with the server, such as during meter reading, the current time period is determined. In this embodiment, multiple time periods t are pre-divided, for example, one hour per period. Simultaneously, WiFi communication performance parameters at the current time are collected. This embodiment does not limit the specific type of WiFi communication performance parameters; for example, they can be Received Signal Strength Indicator (RSSI), signal-to-noise ratio, data rate, packet loss rate, latency, and connection stability, depending on the specific implementation.

[0063] S11: Input the time period information and WiFi communication performance parameters into the pre-built WiFi connection success rate prediction model to output the WiFi connection success probability at the current moment.

[0064] Subsequently, the time period information and WiFi communication performance parameters are input into a pre-built WiFi connection success rate prediction model, thereby outputting the WiFi connection success probability corresponding to the current moment.

[0065] It should be noted that the WiFi connection success rate prediction model is a logistic regression model used to predict the probability of WiFi connection success in different time periods. Its construction process includes: collecting historical WiFi communication feature vectors from multiple historical time periods and determining the weight vector corresponding to each historical time period; and constructing the model based on each historical time period and its corresponding historical WiFi communication feature vector and weight vector. The specific formula is as follows:

[0066] ;

[0067] in, This represents the probability of a successful WiFi connection. This is the weight vector corresponding to time period t. ; Let i be the WiFi communication feature vector in time period t. T stands for transpose.

[0068] It should be noted that this embodiment does not restrict the specific content of the historical WiFi communication feature vector, nor does it restrict the weight vector corresponding to each historical period; it depends on the specific implementation.

[0069] S12: Determine whether to enable WiFi communication based on the WiFi connection success probability; if yes, proceed to step S13; if no, proceed to step S14.

[0070] S13: Establish a communication connection with the server via the WiFi module.

[0071] S14: Establish a communication connection with the server via the GPRS module.

[0072] Finally, the system determines whether to enable WiFi communication based on the WiFi connection success probability. If WiFi communication is confirmed to be enabled, a communication connection with the server is established via the WiFi module. If WiFi communication is confirmed to be disabled, a communication connection with the server is established via the GPRS module. This embodiment does not limit the specific process of determining whether to enable WiFi communication based on the WiFi connection success probability. For example, the WiFi connection success probability can be directly compared with a threshold, and the decision to enable WiFi communication can be made based on the different magnitudes. Alternatively, a threshold function can be used for soft switching of the communication mode, depending on the specific implementation.

[0073] In this embodiment, two different communication modules, WiFi and GPRS, are provided for the smart meter. When the smart meter needs to communicate with the server, the current time period information and WiFi communication performance parameters are collected, and a pre-built WiFi connection success rate prediction model is used to predict the probability of a successful WiFi connection. This allows the smart meter to choose between WiFi or GPRS communication based on the WiFi connection success rate, balancing the economics of WiFi communication with the reliability of GPRS communication, and achieving a unified optimization that maximizes the meter reading success rate and minimizes communication costs.

[0074] Based on the above embodiments, in some embodiments, historical WiFi communication feature vectors within multiple historical time periods are collected, including:

[0075] S101: Divide the daily cycle into multiple historical time periods according to the meter reading cycle.

[0076] S102: Based on each historical time period, collect the corresponding average WiFi signal strength, WiFi response failure rate, WiFi connection failure rate, WiFi communication ratio, and WiFi communication re-reading rate.

[0077] Given that the actual meter reading cycle of smart meters is generally one hour, in order to achieve accurate model construction, this embodiment specifically divides the daily cycle into multiple historical time periods based on the meter reading cycle. That is, the 24 hours of a day are divided into 24 time periods, each corresponding to one hour. Therefore, when collecting parameters, it is necessary to collect WiFi communication feature vectors from multiple historical time periods. Specifically, based on each historical time period, the corresponding average WiFi signal strength, WiFi response failure rate, WiFi connection failure rate, WiFi communication proportion, and WiFi communication re-reading rate are collected. It can be understood that the average WiFi signal strength is used to evaluate the stability and coverage of the WiFi signal; the WiFi response failure rate reflects the reliability of WiFi communication; the WiFi connection failure rate measures the access performance of the WiFi network; the WiFi communication proportion evaluates the importance of WiFi in overall communication; and the WiFi communication re-reading rate reflects the integrity and reliability of WiFi data transmission.

[0078] Table 1 Model Training Data Table

[0079]

[0080] As shown in Table 1, approximately 4KB of feature vector data was collected over one month. To collect this information, the following steps were taken in the implementation: First, the average received signal strength of each WiFi communication within a historical period was determined to establish the average WiFi signal strength. Second, the quotient of the number of failed WiFi communication responses to the number of successful WiFi communication responses within a historical period was determined to establish the WiFi response failure rate. Third, the quotient of the number of failed WiFi communication connections to the number of successful WiFi communication connections within a historical period was determined to establish the WiFi connection failure rate. Fourth, the quotient of the number of WiFi data exchanges to the total number of data exchanges within a historical period was determined to establish the WiFi communication percentage. Finally, the quotient of the number of WiFi data transfer communications to the total number of WiFi communication communications within a historical period was determined to establish the WiFi data transfer rate.

[0081] This approach enables the complete acquisition of historical WiFi communication feature vectors over a given period. These feature vectors assess signal stability, communication response efficiency, network connection success rate, the role of WiFi in overall communication, and the accuracy and integrity of data transmission. Models built upon these feature vectors can more accurately predict the probability of successful WiFi communication.

[0082] Based on the above embodiments, in some embodiments, determining whether to enable WiFi communication is based on the WiFi connection success probability includes:

[0083] S111: Determine the decision threshold corresponding to the time period in which the current moment is located.

[0084] S112: Determine the threshold function value based on the WiFi connection success probability, decision threshold, and threshold function.

[0085] S113: Determine whether the threshold function value is greater than the preset threshold value; if yes, confirm that WiFi communication is enabled; if no, confirm that WiFi communication is disabled.

[0086] To determine whether to enable WiFi communication, this embodiment uses a threshold function. Specifically, it first determines the decision threshold corresponding to the time period t at the current moment. Understandably, each time period has a corresponding decision threshold. Subsequently, the threshold function value is determined based on the WiFi connection success probability, the decision threshold, and the threshold function itself. The specific formula is as follows:

[0087] ;

[0088] in, Here, k represents the threshold function value, and k is the steepness of the soft handover control. This represents the probability of a successful WiFi connection. This is the threshold for making a decision.

[0089] Finally, it is determined whether the threshold function value is greater than a preset threshold value. In this embodiment, the size of the preset threshold value is not limited and depends on the specific implementation. If the threshold function value is confirmed to be greater than the preset threshold value, WiFi communication is enabled; if the threshold function value is confirmed to be less than the preset threshold value, WiFi communication is disabled.

[0090] It should also be noted that when the smart meter's processor has limited computing power, the threshold can be directly set to 1 / 2. This allows the decision to enable WiFi communication to be made directly based on the relationship between the WiFi connection success probability and the decision threshold. Specifically, when the WiFi connection success probability is not less than the decision threshold, WiFi communication is enabled and an attempt is made to establish a WiFi connection. If the connection is successful, the WiFi communication is confirmed as successfully established; if the connection fails, it is retried. If the connection still fails after a preset number of retries, GPRS communication is used directly. When the WiFi connection success probability is less than the decision threshold, WiFi communication is not enabled, and GPRS communication is used directly to avoid wasting time and power. It should be noted that this embodiment does not limit the preset number of retries; it depends on the specific implementation. Thus, an accurate determination of whether to enable WiFi communication is achieved based on the threshold function.

[0091] Figure 3 This is a schematic diagram of a dual-mode converged communication architecture for a smart meter provided in an embodiment of this application. To ensure good performance of the WiFi connection success rate prediction model, based on the above embodiments, in some embodiments, such as… Figure 3 As shown, the method also includes:

[0092] S121: Collect WiFi communication results for each time period based on a preset period, and set WiFi communication loss items;

[0093] S122: Generate a loss function based on the WiFi communication results, the WiFi communication loss term, and the threshold function value.

[0094] S123: Update the weight vector and decision threshold for each time period based on the loss function.

[0095] Specifically, WiFi communication results for each time period are collected based on a preset period, and a WiFi communication loss term is set. It should be noted that this embodiment does not limit the preset period; for example, WiFi communication results for each time period can be collected monthly, meaning model iteration and optimization are performed on a monthly basis. Simultaneously, a WiFi communication loss term is set. It is understood that the purpose of setting the WiFi communication loss term is to control operating costs while ensuring meter reading success rate. The specific rules followed are as follows: ensure meter reading success and prioritize the use of WiFi communication; if WiFi communication fails, using GPRS communication incurs costs; if GPRS is actively used, an operational penalty is incurred. Based on the above rules, in some embodiments, the WiFi communication loss term can specifically be set as a cost term c representing the execution of GPRS communication after WiFi communication failure, and a penalty term λ representing the active switch to GPRS communication. In this embodiment, the specific size of the cost term and penalty term is not limited and depends on the specific implementation.

[0096] Therefore, based on the above rules, a loss function is generated according to the WiFi communication results, the WiFi communication loss term, and the threshold function value. The specific formula is as follows:

[0097] ;

[0098] in, Let N be the loss function. t This represents the number of WiFi communication feature vectors in time period t. For WiFi communication results, 1 indicates successful communication, and 0 indicates communication failure; λ represents the threshold function value; c represents the cost term; and λ represents the penalty term.

[0099] Finally, the weight vectors and decision thresholds for each time period are updated based on the loss function. Specifically, the new weight vectors are determined using gradient descent based on the weight vectors, learning rate, and loss function, as shown in the following formula:

[0100] ;

[0101] in, For the weight vector, For learning rate, This is the loss function.

[0102] Similarly, based on the decision threshold, learning rate, and loss function, a new decision threshold is determined using the gradient descent algorithm, as shown in the following formula:

[0103] ;

[0104] in, The threshold for judgment, For learning rate, This is the loss function.

[0105] It should also be noted that the weight vector and decision threshold, updated periodically, are sent from the server to the smart meter via over-the-air (OTA) download, specifically to the communication equipment components that work with the smart meter. This communication equipment includes a Wi-Fi module and a GPRS module, along with related circuitry, on a separate circuit board embedded in the meter's pre-installed structural cavity via connectors. After the updated weight vector and decision threshold are sent to the smart meter, they are loaded and used to ensure good predictive performance of the Wi-Fi connection success rate prediction model.

[0106] The above embodiments provide a detailed description of the dual-mode fusion communication method for smart meters. This application also provides embodiments of the dual-mode fusion communication device for smart meters.

[0107] Figure 4 This is a schematic diagram of a dual-mode fusion communication device for a smart meter, provided as an embodiment of this application. The device is applied to a smart meter equipped with both a WiFi module and a GPRS module; such as... Figure 4 As shown, the device includes:

[0108] The data acquisition and determination module 10 is used to determine the time period information of the current moment and collect the WiFi communication performance parameters of the current moment when there is a communication requirement with the server.

[0109] The prediction module 11 is used to input time period information and WiFi communication performance parameters into a pre-built WiFi connection success rate prediction model to output the WiFi connection success probability at the current moment. The construction process of the WiFi connection success rate prediction model includes: collecting historical WiFi communication feature vectors in multiple historical time periods and determining the weight vectors corresponding to each historical time period; based on each historical time period and its corresponding historical WiFi communication feature vectors and weight vectors, constructing a WiFi connection success rate prediction model for predicting the WiFi connection success probability in each time period.

[0110] The judgment module 12 is used to determine whether to enable WiFi communication based on the probability of successful WiFi connection; if yes, the first communication module 13 is triggered; if no, the second communication module 14 is triggered.

[0111] The first communication module 13 is used to establish a communication connection with the server via the WiFi module.

[0112] The second communication module 14 is used to establish a communication connection with the server via the GPRS module.

[0113] In some embodiments, historical WiFi communication feature vectors are collected over multiple historical time periods, including: dividing the daily cycle into multiple historical time periods according to the meter reading cycle; and collecting the corresponding average WiFi signal strength, WiFi response failure rate, WiFi connection failure rate, WiFi communication proportion, and WiFi communication re-reading rate for each historical time period.

[0114] In some embodiments, based on each historical time period, the corresponding average WiFi signal strength, WiFi response failure rate, WiFi connection failure rate, WiFi communication proportion, and WiFi communication re-reading rate are collected, including: determining the average value of the received signal strength indication for each WiFi communication within the historical time period to determine the average WiFi signal strength; determining the quotient of the number of WiFi communication response failures and the number of WiFi communication responses within the historical time period to determine the WiFi response failure rate; determining the quotient of the number of WiFi communication connection failures and the number of WiFi communication connections within the historical time period to determine the WiFi connection failure rate; determining the quotient of the number of WiFi communication data interactions and the total number of communication data interactions within the historical time period to determine the WiFi communication proportion; and determining the quotient of the number of WiFi re-reading communications and the total number of WiFi communications within the historical time period to determine the WiFi communication re-reading rate.

[0115] In some embodiments, the determining module 12 includes:

[0116] The decision threshold determination module is used to determine the decision threshold corresponding to the time period in which the current time exists;

[0117] The threshold function value determination module is used to determine the threshold function value based on the WiFi connection success probability, the decision threshold, and the threshold function.

[0118] The first judgment submodule is used to determine whether the threshold function value is greater than the preset threshold value; if yes, then WiFi communication is enabled; if no, then WiFi communication is disabled.

[0119] In some embodiments, it also includes:

[0120] The data acquisition and setting module is used to collect WiFi communication results for each time period based on a preset period and to set WiFi communication loss items.

[0121] The generation module is used to generate a loss function based on the WiFi communication results, the WiFi communication loss term, and the threshold function value.

[0122] The update module is used to update the weight vector and decision threshold for each time period based on the loss function.

[0123] In some embodiments, the data acquisition and setting module includes:

[0124] The first setting module is used to set the cost item that represents the execution of GPRS communication after WiFi communication fails;

[0125] The second setting module is used to set penalty items that represent active switching to GPRS communication.

[0126] In some embodiments, the updating module includes:

[0127] The first update module is used to determine a new weight vector based on the weight vector, learning rate, and loss function using a gradient descent algorithm.

[0128] The second update module is used to determine a new decision threshold based on the decision threshold, learning rate, and loss function using a gradient descent algorithm.

[0129] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.

[0130] Figure 5 This is a structural diagram of a smart meter provided in an embodiment of this application. Figure 5 As shown, a smart meter includes:

[0131] Memory 20 is used to store computer programs;

[0132] The processor 21 is used to execute computer programs to implement the steps of the smart meter dual-mode fusion communication method mentioned in the above embodiments.

[0133] It should be noted that the WIFI module used in this application is the FCM360W. The FCM360W is a high-performance MCU Wi-Fi and Bluetooth module that supports IEEE 802.11b / g / n / ax and BLE 5.1 ​​protocols. It integrates a power management unit, power amplifier, low-noise amplifier, and RF transceiver switch. The module provides a rich set of peripheral interfaces, including UART, SPI, I2C*, I2S, SDIO*, ADC, and PWM, to meet the needs of various application scenarios. The FCM360W is a surface-mount module with a compact package, integrating the following features: a 240 MHz RISC processor, 48KB ROM and 512KB SRAM memory, 4 / 8MB Flash memory, and supports secondary development.

[0134] The memory of the WIFI module is used to store code and data, using common Flash memory, which is widely used in embedded systems. Application scenarios include: code storage, which is very suitable for storing the startup code and firmware of embedded systems due to its fast read speed and non-volatility; data storage, which can be used to store user data, configuration parameters, etc.; and industrial control equipment, whose wide operating temperature range and high durability make it suitable for use in industrial environments, such as data recording and parameter storage in industrial control equipment.

[0135] The processor of the WIFI module is used to process the loaded program, perform WIFI network management, control and manage the GPRS module through the communication interface, and interact with table data through the communication interface, etc.

[0136] A Reduced Instruction Set Computer (RISC) processor is a processor that uses a reduced instruction set architecture and is primarily used in embedded systems. RISC processors are widely used in embedded systems. Many microcontrollers (MCUs) adopt the RISC architecture. For example, the ARM (Advanced RISC Machine) series of processors is a very well-known RISC processor in the embedded field. They are widely used in smartphones, tablets, smart home appliances, and other devices. In smartphones, ARM processors can efficiently handle various tasks, such as running the operating system, executing applications, and processing sensor data. Its reduced instruction set and efficient pipeline architecture enable the processor to provide high performance with limited power consumption, which is crucial for mobile devices that have strict requirements for both power consumption and performance.

[0137] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above method embodiments.

[0138] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, embedded FLASH, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0139] The foregoing has provided a detailed description of a dual-mode fusion communication method, apparatus, smart meter, and medium for smart meters. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

[0140] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A smart meter dual-mode fusion communication method, characterized in that, The method is applied to a smart meter provided with a WiFi module and a GPRS module, and comprises the following steps: When there is a communication demand with a server, determining time period information in which a current time is located and collecting a WiFi communication performance parameter in the current time; inputting the time period information and the WiFi communication performance parameter into a WiFi connection success rate prediction model constructed in advance to output a WiFi connection success probability in the current time; wherein, the WiFi connection success rate prediction model is constructed by collecting historical WiFi communication feature vectors in multiple historical time periods and determining a weight vector corresponding to each historical time period; and based on each historical time period, the historical WiFi communication feature vector and the weight vector corresponding to the historical time period, the WiFi connection success rate prediction model for predicting the WiFi connection success probability in each time period is constructed; determining whether to enable WiFi communication according to the WiFi connection success probability; if yes, establishing a communication connection with the server through the WiFi module; if no, establishing a communication connection with the server through the GPRS module.

2. The smart meter dual mode converged communication method of claim 1, wherein, The method for collecting historical WiFi communication feature vectors in multiple historical time periods comprises the following steps: splitting a daily cycle into multiple historical time periods according to a meter reading cycle; based on each historical time period, collecting a corresponding WiFi signal strength average, WiFi response failure rate, WiFi connection failure rate, WiFi communication proportion rate and WiFi communication re-reading rate, respectively.

3. The smart meter dual mode converged communication method of claim 2, wherein, based on each historical time period, collecting a corresponding WiFi signal strength average, WiFi response failure rate, WiFi connection failure rate, WiFi communication proportion rate and WiFi communication re-reading rate, respectively, comprises the following steps: determining an average value of received signal strength indication of each WiFi communication in the historical time period to determine the WiFi signal strength average; determining a quotient value of WiFi communication response failure times and WiFi communication response times in the historical time period to determine the WiFi response failure rate; determining a quotient value of WiFi communication connection failure times and WiFi communication connection times in the historical time period to determine the WiFi connection failure rate; determining a quotient value of WiFi communication data interaction times and total communication data interaction times in the historical time period to determine the WiFi communication proportion rate; determining a quotient value of WiFi re-reading communication times and total WiFi communication times in the historical time period to determine the WiFi communication re-reading rate.

4. The smart meter dual mode converged communication method of claim 1, wherein, determining whether to enable WiFi communication according to the WiFi connection success probability comprises the following steps: determining a decision threshold value corresponding to the time period in which the current time is located; determining a threshold function value based on the WiFi connection success probability, the decision threshold value and a threshold function; determining whether the threshold function value is greater than a preset threshold value; if yes, confirming to enable WiFi communication; if no, confirming not to enable WiFi communication.

5. The smart meter dual mode converged communication method of claim 4, wherein, The method further comprises the following steps: collecting WiFi communication results in each time period based on a preset period and setting a WiFi communication loss term; generate a loss function according to the WiFi communication result, the WiFi communication loss term and the threshold function value; update the weight vector and the decision threshold corresponding to each time period based on the loss function.

6. The smart meter dual mode converged communication method of claim 5, wherein, The WiFi communication loss term is set to include: The cost term representing the execution of GPRS communication after the failure of WiFi communication is set. The penalty term representing the active switching to GPRS communication is set.

7. The smart meter dual mode converged communication method of claim 5, wherein, The loss function is updated based on the weight vector and the decision threshold corresponding to each time period, including: Based on the weight vector, the learning rate and the loss function, a new weight vector is determined by a gradient descent algorithm. Based on the decision threshold, the learning rate and the loss function, a new decision threshold is determined by a gradient descent algorithm.

8. A smart meter dual-mode converged communication device, characterized in that, The device is applied to a smart meter provided with a WiFi module and a GPRS module; the device includes: The acquisition and determination module is configured to determine time period information of a current time and acquire WiFi communication performance parameters of the current time when there is a communication demand with a server; The prediction module is configured to input the time period information and the WiFi communication performance parameters into a pre-constructed WiFi connection success rate prediction model to output a WiFi connection success probability of the current time; the construction process of the WiFi connection success rate prediction model includes: acquiring historical WiFi communication feature vectors in a plurality of historical time periods and determining weight vectors corresponding to each historical time period; based on each historical time period, the historical WiFi communication feature vectors corresponding to each historical time period and the weight vectors, the WiFi connection success rate prediction model for predicting WiFi connection success probability in each time period is constructed; The judgment module is configured to determine whether to enable WiFi communication according to the WiFi connection success probability; if yes, the first communication module is triggered; if no, the second communication module is triggered; The first communication module is configured to establish a communication connection with the server through the WiFi module; The second communication module is configured to establish a communication connection with the server through the GPRS module.

9. A smart meter, characterized by The device includes: The memory is configured to store a computer program; The processor is configured to execute the computer program to implement the steps of the smart meter dual-mode fusion communication method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium, and the computer program is executed by the processor to implement the steps of the smart meter dual-mode fusion communication method according to any one of claims 1 to 7.

Images