Energy-saving control method of equipment, storage medium, electronic device and program product

Abstract

The embodiment of the invention provides an energy-saving control method of equipment, a storage medium, an electronic device and a program product, and the method comprises the steps that an FTTR main gateway constructs an equipment state database according to collected equipment data, and the FTTR main gateway comprises an artificial intelligence AI model; and the FTTR main gateway analyzes the equipment data in the equipment state database by using an AI model to determine an energy-saving control instruction, and sends the energy-saving control instruction to the corresponding equipment. According to the embodiment of the invention, the problems that a complex and changeable network environment cannot be accurately adapted and the energy-saving efficiency is low due to the fact that only a fixed energy-saving control instruction can be issued in the related technology are solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communications, and in particular, to an energy-saving control method for a device, a storage medium, an electronic device, and a program product. Background Art

[0002] With the continuous development of optical networks, fiber to the room (Fiber to the Rome, FTTR) has been fully rolled out. FTTR technology connects FTTR slave devices (Sub FTTR Unit, SFU) in different rooms or locations in scenarios such as homes or small and medium-sized enterprises through optical fibers, thereby providing high-bandwidth and high-reliability connections between multiple SFUs. The point-to-multipoint optical distribution network can be used to achieve the connection between the FTTR main device (Main FTTR Unit, MFU) and SFU. The wired backhaul provided by FTTR technology allows MFU and SFU to exchange information through wired transmission, avoiding frequent information exchange occupying a large amount of wireless time and frequency resources.

[0003] With the widespread application of FTTR technology, the energy consumption of network equipment has become increasingly prominent. Traditional energy-saving methods are often based on fixed rules or simple threshold judgments, and cannot accurately adapt to complex and changing network environments and user needs. In the FTTR system, the different working states of devices such as the master gateway and slave gateway, as well as the diverse needs of various services, make achieving efficient energy saving a difficult problem that needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide an energy-saving control method, storage medium, electronic device and program product for a device, so as to at least solve the problem in the related art that only fixed energy-saving control instructions can be issued, resulting in the inability to accurately adapt to complex and changeable network environments and low energy-saving efficiency.

[0005] According to one embodiment of the present application, a method for energy-saving control of a device is provided, including: a fiber-to-the-room FTTR main gateway builds a device status database based on collected device data, wherein the FTTR main gateway includes an artificial intelligence AI model; the FTTR main gateway analyzes the device data in the device status database by using the AI ​​model to determine energy-saving control instructions, and sends the energy-saving control instructions to the corresponding device.

[0006] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps in the above method embodiment when running.

[0007] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in the above method embodiment.

[0008] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0009] Through the above embodiments of the present application, the intelligent analysis of the AI ​​model can more accurately match the device status and reduce unnecessary energy consumption, thereby significantly improving energy utilization efficiency and reducing operating costs. Since the AI ​​model can automatically identify energy-saving opportunities based on the status of the device, generate refined energy-saving control instructions, and realize dynamic energy-saving management of the device, it avoids the limitations of traditional energy-saving methods based on fixed rules when dealing with network changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a hardware structure block diagram of a computer terminal according to the energy-saving control method of the device of the embodiment of the present application;

[0011] Figure 2 is a flow chart of an energy-saving control method for a device according to an embodiment of the present application;

[0012] Figure 3 is a schematic diagram of a FTTR system scenario according to an embodiment of the present application;

[0013] Figure 4 is a structural block diagram of an energy-saving control device for a device according to an embodiment of the present application;

[0014] Figure 5 is a schematic diagram of the AI ​​model architecture according to an embodiment of the present application;

[0015] Figure 6 It is a schematic diagram of an energy-saving state machine according to an embodiment of the present application. DETAILED DESCRIPTION

[0016] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0017] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0018] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a computer terminal as an example, Figure 1is a hardware structure block diagram of the computer terminal running the method embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned computer terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0019] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the energy-saving control method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0020] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0021] In this embodiment, a method for energy saving control running on the above-mentioned computer terminal is provided. Figure 2 is a flow chart of an energy-saving control method according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0022] Step S202, the fiber to the room FTTR main gateway builds a device status database according to the collected device data, wherein the FTTR main gateway includes an artificial intelligence (AI) model;

[0023] In an exemplary embodiment of the present application, the device data includes at least one of the following: Passive Optical Network (PON) port traffic data, Wireless Fidelity (WIFI) traffic data, Local Area Network (LAN) port traffic, device status data, power consumption information and alarm information.

[0024] In one embodiment, the device data is transmitted to the AI ​​model in the FTTR main gateway in real time or at a fixed time through a specific transmission protocol. For example, the FTTR main gateway chip obtains the real-time traffic data of each device port and sends it to the AI ​​model via wired or wireless means.

[0025] In an exemplary embodiment of the present application, the AI ​​model is an AI model that has undergone feature dimensionality reduction and model compression.

[0026] In one embodiment, feature dimension reduction (such as principal component analysis (PCA)) and model compression technology are used to reduce the AI ​​model's dependence on hardware resources, generate a lightweight AI model, and support efficient operation in the FTTR main gateway.

[0027] In an exemplary embodiment of the present application, a fiber-to-the-room FTTR main gateway builds a device status database based on collected device data, including: the FTTR main gateway uses data feature extraction and preprocessing algorithms to perform data cleaning and data normalization on the collected device data to obtain preprocessed device data; the FTTR main gateway correlates and integrates the preprocessed device data based on the network behavior characteristics of the device and the correlation of network resources to build a device status database.

[0028] In one embodiment, data such as PON / WIFI / LAN traffic, device power consumption, and user connection time are integrated to build a real-time network status profile as a device status database. The operating parameters of different devices are integrated to provide a comprehensive data basis for subsequent analysis and decision-making. For example, information such as the device's CPU usage, memory occupancy, and the number of connected devices and traffic distribution in each WIFI frequency band are collected.

[0029] In an exemplary embodiment of the present application, before the fiber-to-the-room FTTR main gateway builds a device status database based on the collected device data, it also includes: the FTTR main gateway collects the device data uploaded by the terminal device connected to the FTTR main gateway according to a preset period, and the device data uploaded by the FTTR slave gateway device connected to the FTTR main gateway.

[0030] In one embodiment, the FTTR system scenario diagram is as follows: Figure 3 As shown in the figure, the FTTR master gateway is internally deployed with an AI model and an energy-saving data collection module. As the core of the entire FTTR system, the FTTR master gateway is not only connected to the FTTR slave gateway, but also to various terminal devices (such as personal computers, smart phones, and smart home devices). The energy-saving data collection module collects device data uploaded by terminal devices and FTTR slave gateways. The FTTR slave gateway is deployed with a data collection module to collect device data from terminal devices connected to the FTTR slave gateway.

[0031] Step S204, the FTTR main gateway analyzes the device data in the device status database by using the AI ​​model to determine the energy-saving control instruction, and sends the energy-saving control instruction to the corresponding device;

[0032] In an exemplary embodiment of the present application, the FTTR main gateway determines energy-saving control instructions by analyzing the device data in the device status database using an AI model, including: the FTTR main gateway uses the AI ​​model to analyze the network status of the device in the device status database to determine whether the network status of the device meets the energy-saving conditions, wherein the AI ​​model includes at least one of the following: decision tree, naive Bayes, and long short-term memory network LSTM; when the judgment result is yes, the FTTR main gateway determines the energy-saving strategy of the device according to the device type and service priority, and generates energy-saving control instructions according to the energy-saving strategy.

[0033] In one embodiment, the AI ​​model determines whether the network status of the device meets the energy-saving conditions. For example, if the traffic mean is lower than the threshold and the device load is light, it triggers power reduction or shuts down non-essential modules. The model differentiates execution strategies based on device type and service priority (such as retaining only key service modules).

[0034] In one embodiment, when the transmission power of the WIFI module of a device needs to be reduced, the AI ​​model sends an instruction containing power adjustment parameters to the device. After receiving the instruction, the device adjusts the transmission power of the WIFI module as required to achieve energy saving.

[0035] In an exemplary embodiment of the present application, after sending the energy-saving control instruction to the corresponding device, it also includes: updating the parameters of the AI ​​model according to the operating data of the device.

[0036] In one embodiment, the operation data of the equipment is continuously collected to train and optimize the energy-saving AI model. The AI ​​model parameters are continuously updated with new data to improve the accuracy and adaptability of the AI ​​model. For example, if a certain energy-saving operation causes a network anomaly, the model will automatically correct the strategy to avoid similar problems from happening again, forming a closed-loop optimization process of "perception-decision-execution-feedback".

[0037] In an exemplary embodiment of the present application, an energy-saving control instruction is sent to a corresponding device, including: classifying and encapsulating the energy-saving control instruction according to the device type and the communication protocol, and sending it to the corresponding device through a fiber multimedia control interface (Fiber Multimedia Control Interface, FMCI) protocol, a wireless multimedia control interface (Wireless Multimedia Control Interface, WMCI) protocol, a fiber physical layer operations management and maintenance (Fiber Physical Layer Operations Administration and Maintenance, F-PLOAM) protocol or a custom control protocol.

[0038] In one embodiment, the AI ​​model generates energy-saving control instructions, classifies and encapsulates the energy-saving control instructions according to the device type and communication protocol, and sends them to the corresponding devices through FMCI, WMCI, F-PLOAM or custom control protocols. For example, when it is decided to reduce the transmit power of the WIFI module of a slave gateway, an instruction containing power adjustment parameters is sent to the slave gateway, and the slave gateway adjusts as required after receiving the instruction to achieve energy saving.

[0039] In one embodiment, for some complex energy-saving decisions and scenario analysis, the energy-saving agent of the FTTR main gateway works together with the complex AI model in the cloud. The energy-saving agent uploads the local data to the cloud after preliminary processing. The complex AI model in the cloud uses its powerful computing power and richer data sets for in-depth analysis. The cloud model is based on deep learning algorithms, such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), etc., to accurately predict and analyze network traffic trends, user behavior patterns, etc. The cloud model generates detailed energy-saving suggestions and strategies based on the analysis results, and the energy-saving agent receives and executes these instructions to achieve more efficient energy-saving control.

[0040] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0041] In this embodiment, an energy-saving control device for a device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0042] Figure 4 is a structural block diagram of an energy-saving control device for a device according to an embodiment of the present application, such as Figure 4 As shown, the device includes: a building module 10 and a sending module 20.

[0043] A construction module 10 is used to construct a device status database based on the collected device data, wherein the construction module 10 includes an artificial intelligence AI model;

[0044] The sending module 20 is used to analyze the device data in the device status database by using the AI ​​model to determine the energy-saving control instruction, and send the energy-saving control instruction to the corresponding device.

[0045] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0046] In order to facilitate the understanding of the technical solutions provided by the application embodiments, the embodiments are described below in combination with specific scenarios.

[0047] Scenario Example 1

[0048] The process of the device energy saving control method according to another embodiment of the present application includes the following steps:

[0049] Step S501, in the FTTR system, collect relevant data of the master and slave devices, including optical port traffic, WIFI traffic, LAN port traffic, power consumption information, alarm information, etc. These data are transmitted to the AI ​​model in the master gateway in real time or regularly through a specific transmission protocol. For example, the master and slave device chips obtain the real-time traffic data of each device port and send it to the AI ​​model via wired or wireless means.

[0050] Specifically, for optical port traffic, optical power sensors and traffic monitoring chips are used to accurately measure the traffic data of the optical link between the master gateway and the slave gateway, and between the slave gateway and the terminal device, and the data is collected at a certain time interval (such as every second). When collecting WIFI traffic, the statistical function of the WIFI chip is used to obtain upload and download traffic data under different frequency bands (2.4G and 5G) and different service set identifiers (SSID), as well as the media access control address (MAC address) of the connected device, signal strength and other information. LAN port traffic collection uses the network interface controller to monitor the data transmission volume of devices (such as computers, smart home appliances, etc.) connected to the LAN port. In terms of power consumption information collection, power consumption sensors are installed on the master gateway, slave gateway and key terminal devices (such as high-power smart TVs) to monitor the power consumption of the equipment in real time and convert it into energy consumption data. Alarm information is generated through the built-in fault detection program of the device. Once the device is abnormal (such as port failure, signal loss), the alarm information is immediately generated and transmitted to the data acquisition module.

[0051] Specifically, the collected data is encapsulated in a custom data packet format through Ethernet, Wi-Fi and other network transmission methods, and transmitted to the AI ​​model in the main gateway. During the transmission process, a checksum and error correction algorithm is used to ensure the accuracy and integrity of the data. After the AI ​​model receives the data, it first cleans the data to remove abnormal data caused by interference or equipment failure. For sudden changes in traffic data, smoothing is performed using a sliding window algorithm; for power consumption data, a reasonable threshold range is set to remove abnormal values ​​that exceed the range. Then, data normalization is performed to unify data of different types and magnitudes into the same numerical range to facilitate subsequent analysis and processing.

[0052] In step S502, after receiving data such as network / device status and power consumption, the AI ​​model builds a real-time portrait of the system's operating status. It integrates the operating parameters of different devices to provide a comprehensive data basis for subsequent analysis and decision-making. For example, the AI ​​model collects information such as the CPU usage rate and memory occupancy rate of the master and slave devices, as well as the number of connected devices and traffic distribution in each WIFI frequency band.

[0053] Specifically, the AI ​​model continuously receives pre-processed data and builds a real-time network device status database. It associates and integrates data from different acquisition sources, such as associating the WiFi traffic data of a slave gateway with the MAC address of the device connected to the slave gateway, the device type, and the corresponding LAN port traffic data to form a complete network usage record. At the same time, it records the power consumption information and alarm information of the device in order to comprehensively analyze the operating status and energy consumption of the network.

[0054] Step S503: AI models (such as decision trees, naive Bayes, LSTM, etc.) analyze data in real time to determine energy-saving conditions. For example, if the traffic mean is lower than the threshold and the device load is light, it triggers power reduction or shuts down non-essential modules. The model differentiates execution strategies based on device type and business priority (such as retaining only key business modules).

[0055] Specifically, feature dimension reduction (PCA) and model compression technology are used to reduce the AI ​​model's dependence on hardware resources, allowing it to run efficiently in FTTR main equipment. For example, 5-dimensional data is reduced to 3 dimensions to reduce computational complexity; the minimum-maximum normalization is used to unify the data magnitude and improve the model reasoning speed (delay is controlled within 150ms). This optimization ensures the feasibility of the AI ​​model on resource-constrained devices.

[0056] Specifically, the AI ​​model performs power reduction actions differently according to the service type (such as video streaming, (VoIP)) and device grouping (such as high power consumption group). For example: the chip CPU core is turned off and the chip frequency is reduced; the WIFI is turned off, the WIFI transmission power is reduced, and the Multiple-Input Multiple-Output (MIMO) is downgraded; the PON energy-saving state machine enters doze mode and sleep mode; the network port reduces the negotiation rate, Gigabit Ethernet (GE) switches (Fast Ethernet, FE), and closes the idle network port; the Universal Serial Bus (USB) low-power mode, long-term idle, Physical Layer Medium Access Control (PHY MAC) sleeps, and all functions are suspended.

[0057] Specifically, the AI ​​model is started, which is built based on the decision tree algorithm. First, the network traffic data is analyzed, and the statistical characteristics such as the mean and variance of the traffic are calculated to determine the stability and change trend of the traffic. Combined with the device load (such as CPU usage and memory occupancy), if the traffic mean is lower than a preset threshold for a continuous period of time (such as 10 minutes) and the device load is at a low level, the decision tree model determines that the current network state is suitable for energy-saving operations. The model further infers specific energy-saving measures based on the device type and business priority. For slave gateways with fewer connected devices and extremely low traffic, the decision tree model outputs the decision to turn off some of its WIFI bands (such as retaining only the 2.4G band) or reduce the transmission power of the WIFI module; for some LAN ports connected to non-critical terminal devices, the decision tree model decides to reduce the negotiation rate of the port to reduce energy consumption.

[0058] Step S504: For some complex energy-saving decisions and scenario analysis, the energy-saving agent works in collaboration with the complex AI model in the cloud. The energy-saving agent preliminarily processes the local data and uploads it to the cloud. The complex AI model in the cloud uses its powerful computing power and richer data sets for in-depth analysis. The cloud model is based on deep learning algorithms, such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), to accurately predict and analyze network traffic trends, user behavior patterns, etc. The cloud model generates detailed energy-saving suggestions and strategies based on the analysis results, and the energy-saving agent receives and executes these instructions to achieve more efficient energy-saving control.

[0059] Step S505, the AI ​​model generates an energy-saving decision, generates an energy-saving control instruction based on the decision, encapsulates it according to the device type and communication protocol, and sends it to the corresponding device through FMCI, WMCI, F-PLOAM or a custom control protocol. For example, when it is decided to reduce the transmit power of a WIFI module from a gateway, an instruction containing power adjustment parameters is sent to the gateway, and the gateway adjusts as required after receiving the instruction to achieve energy saving. If it is detected that the traffic of the LAN port connected to a terminal device is extremely low and lasts for a long time, the AI ​​model sends an instruction to reduce the negotiation rate of the LAN port, and the device makes corresponding adjustments after receiving the instruction.

[0060] Step S506: Continuously collect the operating data of the FTTR system to train and optimize the AI ​​model. Use new data to continuously update the model parameters to improve the accuracy and adaptability of the model. For example, if a certain energy-saving operation causes a network anomaly, the model will automatically correct the strategy to avoid similar problems from happening again, forming a closed-loop optimization process of "perception-decision-execution-feedback".

[0061] Scenario Example 2

[0062] The data collection module in the FTTR master gateway collects the number of WIFI connected devices, device types (such as mobile phones, computers, smart home appliances), WIFI traffic, device working modes (normal, energy-saving, sleep) and corresponding power consumption data of each slave gateway every minute. (For example, at 10 o'clock in the evening, a room is connected to 3 mobile phones and 1 computer from the gateway, the WIFI traffic is 20Mbps, the working mode is normal, and the power consumption is 10W.) These data are integrated and stored in the database of the AI ​​model.

[0063] Extract features from the integrated data, encode the device type, and calculate the average number of WIFI connected devices and the average WIFI traffic per hour. After analysis, select the average number of WIFI connected devices, device type encoding, and average WIFI traffic as key features. (For example, the average number of WIFI connected devices at 9-10 pm for the slave gateway is 3.5, and the average WIFI traffic is 22Mbps).

[0064] The Naive Bayes model is selected to formulate energy-saving strategies. The historical data of the past month is used for training, and the average number of WIFI connected devices, device type code and WIFI traffic average are used as input features, and the corresponding device working mode (normal, energy saving, sleep) is used as output. (For example, when the number of connected devices is small (such as less than 2), the device type is mainly mobile phones and the WIFI traffic is less than 15Mbps, the corresponding working mode is sleep.) The probability distribution of each feature in different working modes is calculated through the training algorithm, and the Naive Bayes model is constructed.

[0065] The AI ​​model obtains the latest status data of the network and devices in real time. These real-time data are input into the trained Naive Bayes model for inference. (For example, at 2 a.m., the real-time data of a slave gateway shows that the number of WIFI connected devices is 1 (mobile phone) and the WIFI traffic is 8Mbps. The model calculates the probability of different working modes based on the input features, and by comparing the probability sizes, it concludes that the slave gateway is most suitable for entering sleep mode).

[0066] According to the reasoning result of the Naive Bayes model, the preset energy-saving rules are matched and the specific energy-saving strategy is determined to switch the slave gateway to the sleep mode.

[0067] The AI ​​model generates control instructions, which contain the operation information of switching to sleep mode and the device identification of the target slave gateway. The SFU's WIFI energy-saving decision is sent through the WMCI message "SFU Energy Saving Decision Configuration", which mainly includes frequency band, number of streams, bandwidth, MCS, transmission power, energy-saving cycle, etc. After receiving the instruction from the gateway, it is adjusted according to the instruction to achieve energy saving. The main gateway can also send energy-saving decisions to the SFU through other messages (such as F-PLOAM messages, FMCI messages, etc.). For example, the PON energy-saving state adjustment decision can be sent to the SFU through the F-PLOAM message. The SFU enters sleep mode by shutting down unnecessary functional modules.

[0068] After executing the sleep mode strategy for two hours, evaluate the energy-saving effect. (For example, by comparing the power consumption data before and after execution, it is found that the power consumption of the slave gateway has been reduced from 8W to 4W, indicating a significant energy-saving effect.) Feedback the evaluation results to the naive Bayes model. If the energy-saving effect is good and there is no network anomaly, the model maintains the current probability distribution parameters; if users report problems such as slow network connection recovery, data will be collected again and the probability distribution of the model will be updated to improve the accuracy and adaptability of the model.

[0069] Scenario Example 3

[0070] AI model training data sources include:

[0071] (1) Traffic data, including optical link traffic: PON port upstream and downstream traffic between MFU and SFU (granularity: 100ms level); WIFI traffic: classified by SSID / frequency band (2.4G / 5G) / terminal type (mobile phone / PC / IoT device); LAN port traffic: classified by port number, device MAC address, and protocol type (HTTP / VoIP / video stream).

[0072] (2) Device status data, including hardware parameters: CPU / GPU utilization (sampling rate 10Hz), memory usage, temperature sensor value; network parameters: SFU optical module optical power (accuracy ±0.1dBm), bit error rate (BER), SFUPON / LAN uplink registration status.

[0073] (3) User behavior data, including terminal connection period characteristics (such as the sleep period from 0:00 to 6:00 on weekdays and weekends); service type labels (real-time interaction type / background transmission type / high-priority service); and terminal movement trajectory (based on RSSI fingerprint positioning algorithm).

[0074] The AI ​​model training and optimization process includes training data sets: 7×24-hour historical data of 1,000 FTTR systems; model architecture: two-layer bidirectional LSTM (256 units per layer) + attention mechanism; training strategy: using a hybrid loss function (MAE×0.6+RMSE×0.4). The sample data is shown in Table 1.

[0075] Table 1 Example data table

[0076]

[0077] The expected energy-saving effects are: the traffic prediction error rate is significantly reduced (a significant improvement compared to the traditional ARIMA model), and the model inference delay is controlled within the threshold that meets real-time decision-making needs.

[0078] Scenario Example 4

[0079] After receiving the device data, the AI ​​model first uses the data feature extraction and preprocessing algorithm. Taking the principal component analysis (PCA) algorithm as an example, for multi-dimensional data such as optical port traffic, WIFI traffic, LAN port traffic, power consumption information, etc., the PCA algorithm decomposes the eigenvalues ​​of the data covariance matrix to find the main components in the data and achieve data dimensionality reduction. In actual operation, assuming that network data of 10 different dimensions are collected, the PCA algorithm calculates the covariance matrix of these data, and then solves the eigenvalues ​​and eigenvectors. According to the size of the eigenvalue, the first few main eigenvectors are selected, and the original 10-dimensional data is projected into the low-dimensional space spanned by these eigenvectors, for example, reducing it to 3 dimensions. This not only retains the main information of the data, but also reduces the data dimension and reduces the complexity of subsequent processing. At the same time, a normalization algorithm is used to process the data, such as minimum-maximum normalization. For traffic data, assuming that its value range is between 0-1000Mbps, the minimum-maximum normalization formula is used. , X is the data to be normalized, X min is the minimum value in the data set used for normalization, X max is the maximum value in the data set, Xnorm For normalized data, the data is mapped to the range of 0-1, making data of different magnitudes comparable and improving the performance of subsequent machine learning algorithms.

[0080] Scenario Example 5

[0081] The AI ​​model uses a decision tree algorithm to determine whether the current network status meets the energy-saving conditions. The decision tree algorithm makes decisions by building a tree structure. First, taking network traffic data as an example, the traffic mean is selected as the root node judgment condition of the decision tree. Set a traffic mean threshold, such as 50Mbps. If the current network traffic mean is greater than 50Mbps, the decision tree continues to judge other conditions along one branch, such as the device load; if it is less than 50Mbps, it judges other related conditions along another branch. At each node, the algorithm selects the optimal feature for splitting based on indicators such as information gain or Gini coefficient. Suppose that when judging the device load, the CPU usage rate is used as the next judgment condition, and the CPU usage rate threshold is set to 50%. If the traffic mean is less than 50Mbps and the CPU usage rate is less than 50%, the decision tree continues to judge other conditions until it reaches the leaf node. The leaf node corresponds to different decision results, such as meeting the energy-saving conditions or not meeting the energy-saving conditions. If it is finally judged that the energy-saving conditions are met, the decision tree model further infers specific energy-saving measures based on the device type and business priority. For slave gateways with fewer connected devices and extremely low traffic, the decision tree model outputs a decision to shut down some of its WIFI bands (such as keeping only the 2.4G band) or reduce the transmission power of the WIFI module.

[0082] Scenario Example 6

[0083] In one embodiment, the AI ​​model architecture includes:

[0084] Decision tree (CART algorithm): The traffic mean (threshold 50 Mbps), CPU usage (threshold 40%), and number of connected devices (threshold 3) are used as split nodes, and leaf nodes correspond to energy-saving actions (such as "reducing power" and "turning off modules").

[0085] K-means clustering: Group devices by power consumption (high / medium / low) and service type, and prioritize deep sleep strategies for high power consumption groups.

[0086] Real-time decision logic: For low-traffic scenarios, if the average traffic value for 10 consecutive minutes is <30Mbps and the CPU is <30%, the 5G band RF module will be turned off and the 2.4G band will be retained (power consumption is reduced from 12W to 6W). Device grouping strategy: For slave gateways clustered as "high power consumption-video streaming", the 4K video caching function will be turned off during non-peak hours (power consumption is reduced by 25%).

[0087] Figure 5 is a schematic diagram of the AI ​​model architecture according to an embodiment of the present application, Figure 5 The AI ​​model in includes input parameters, prediction system, decision optimization and execution energy saving.

[0088] The input parameters include network topology parameters, traffic related parameters, energy-saving state machine parameters, and business characteristic parameters.

[0089] The prediction system includes traffic prediction, business demand prediction, equipment load prediction, and user behavior prediction.

[0090] Decision optimization includes energy-saving strategy decisions, resource allocation decisions, state transition decisions, and parameter optimization decisions.

[0091] Energy saving includes equipment status adjustment, power consumption module management, resource dynamic configuration, status monitoring and feedback.

[0092] Scenario Example 7

[0093] In the FTTR system that supports AI models, the AI ​​model continuously analyzes the real-time data of the system. When it is detected that the number of WIFI connected devices of a slave gateway is continuously small (less than 2) for a period of time (such as 10 minutes), and the average WIFI traffic is less than 15Mbps, and the device load (such as CPU usage less than 30%, memory occupancy less than 40%) is low, the model determines that the current network state is suitable for energy-saving operation. For this slave gateway, the AI ​​model decides to turn off its 5G band and only retain the 2.4G band, and at the same time reduce the transmission power of the WIFI module, such as from 15dBm to 10dBm. If a sudden increase in network traffic is detected, such as at 2 a.m., the WIFI traffic of a slave gateway increases rapidly from 10Mbps to 50Mbps within 5 minutes, and continues to rise, the AI ​​model predicts that the traffic may continue to grow based on the learned traffic trend and device load, and immediately decides to restore the 5G band of the slave gateway and appropriately increase the transmission power, such as to 15dBm, to ensure network performance. At the same time, the AI ​​model will make decisions based on business priorities. For high-priority services (such as VoIP calls), their network resources will be prioritized even during low-traffic periods, and energy-saving operations that may affect business quality will not be easily performed.

[0094] In traditional FTTR system energy-saving solutions without AI models, fixed energy-saving rules are usually adopted. For example, 12 o'clock in the evening to 6 o'clock in the morning is set as a low-traffic period. During this period, the system uniformly reduces the transmission power of the WIFI modules of all slave devices (SFU) to a fixed value, such as from 20dBm to 10dBm, and closes the LAN port connections of some non-critical businesses. This method does not take into account the actual changes in network traffic and the load of the equipment. Suppose that on a certain night, due to a family member holding an online video conference, the network traffic has a short peak at 2 o'clock in the morning, but the system still runs according to the preset rules and will not adjust the energy-saving strategy due to changes in traffic. This may cause network performance to deteriorate and video conferences to freeze. At the same time, there is no flexible adjustment of energy consumption according to actual conditions, resulting in unnecessary energy waste. Because even if the traffic increases, the device will not return to normal power operation until the preset low-traffic period ends.

[0095] Compared with the traditional energy-saving method with fixed rules, the AI ​​model can monitor the changes in network status in real time, and make decisions and adjust the energy-saving status of the equipment immediately when energy-saving opportunities are found or network performance may be affected. In the above example, when the network traffic changes at 2 a.m., the AI ​​model can respond within seconds, while the traditional method will not adjust until the preset time is over. This real-time performance enables the FTTR system to achieve energy-saving optimization to the greatest extent while ensuring network performance, avoiding unnecessary energy consumption and improving energy efficiency.

[0096] Scenario Example 8

[0097] During the operation of the FTTR system, the FTTR main gateway adjusts the energy-saving status parameters in real time based on the equipment data through the AI ​​model, and makes the most suitable energy-saving decision for the current working scenario according to the specific working scenario. Figure 6 is a schematic diagram of an energy-saving state machine according to an embodiment of the present application, Figure 6 In the process, different conditions are used to guide the state machine to switch between "normal mode", "energy-saving mode" and "deep sleep". These conditions include but are not limited to the ratio of traffic surge greater than A%, the duration of low load of the device for B seconds, whether it is currently in the night time period, and whether a wake-up command is received, etc., where A and B are both greater than zero. Table 2 is the initial energy-saving state parameter table, including parameters such as power consumption threshold and response time.

[0098] Table 2 Initial energy-saving state parameters

[0099]

[0100] The embodiment of this application integrates an AI model in the FTTR main gateway to achieve real-time, intelligent energy-saving control of the FTTR system, reduce system energy consumption while ensuring network performance and improving user experience. The AI ​​technology is deeply integrated with the FTTR scenario, and through localized real-time decision-making, multi-dimensional data fusion, dynamic priority perception and closed-loop optimization, the problems of poor adaptability and low energy efficiency of traditional energy-saving solutions are solved, providing an intelligent and high-precision energy-saving method for the FTTR system.

[0101] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0102] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0103] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0104] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0105] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0106] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0107] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for energy-saving control of equipment, characterized in that: include: The fiber-to-the-room FTTR main gateway builds a device status database based on the collected device data, wherein the FTTR main gateway includes an artificial intelligence AI model; The FTTR master gateway analyzes the device data in the device status database by using the AI ​​model to determine an energy-saving control instruction, and sends the energy-saving control instruction to the corresponding device.

2. The method according to claim 1, characterized in that in, The device data includes at least one of the following: passive optical network PON port traffic data, wireless fidelity WIFI traffic data, local area network LAN port traffic, device status data, power consumption information and alarm information.

3. The method according to claim 1, characterized in that in, The AI ​​model is an AI model that has undergone feature dimensionality reduction and model compression.

4. The method according to claim 1, characterized in that: The fiber-to-the-room FTTR master gateway builds a device status database based on the collected device data, including: The FTTR main gateway uses a data feature extraction and preprocessing algorithm to perform data cleaning and data normalization on the collected device data to obtain preprocessed device data; The FTTR main gateway associates and integrates the pre-processed device data according to the network behavior characteristics of the device and the relevance of network resources to build the device status database.

5. The method according to claim 1, characterized in that The FTTR master gateway analyzes the device data in the device status database by using the AI ​​model to determine the energy-saving control instruction, including: The FTTR master gateway uses the AI ​​model to analyze the network status of the device in the device status database to determine whether the network status of the device meets the energy-saving conditions, wherein the AI ​​model includes at least one of the following: decision tree, naive Bayes, and long short-term memory network LSTM; When the judgment result is yes, the FTTR master gateway determines the energy-saving strategy of the device according to the device type and the service priority, and generates the energy-saving control instruction according to the energy-saving strategy.

6. The method according to claim 1, characterized in that Before the fiber-to-the-room FTTR main gateway builds a device status database according to the collected device data, it also includes: The FTTR main gateway collects device data uploaded by terminal devices connected to the FTTR main gateway and device data uploaded by FTTR slave gateway devices connected to the FTTR main gateway according to a preset period.

7. The method according to claim 1, characterized in that After sending the energy-saving control instruction to the corresponding device, it also includes: updating the parameters of the AI ​​model according to the operating data of the device.

8. The method according to claim 1, characterized in that The sending the energy-saving control instruction to the corresponding device includes: The energy-saving control instructions are classified and encapsulated according to the device type and communication protocol, and sent to the corresponding device through the fiber multimedia control interface FMCI protocol, the wireless multimedia control interface WMCI protocol, the fiber physical layer operation management and maintenance F-PLOAM protocol or a custom control protocol.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 8 when executed by a processor.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 8 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

Images