A control method, apparatus, device, and storage medium for an embedded device.

By dynamically determining the optimal transmission time of messages to be sent in the embedded device and merging them into a single wake-up batch transmission, the problem of existing technologies being unable to accommodate the latency requirements of different services is solved, thus achieving optimization of low-power communication.

CN123124064APending Publication Date: 2026-11-17GREE ELECTRIC APPLIANCE INC OF ZHUHAI +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611611308.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-10-19
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing low-power communication solutions cannot take into account the different latency requirements of different services and changes in network conditions, resulting in a high number of wake-up calls for wireless communication modules and high communication power consumption.

Method used

By obtaining service registration information, the communication address, maximum tolerable latency, and predicted line latency of the message to be sent are determined. The earliest and latest sending times are dynamically determined and merged into a single wake-up batch transmission, thus optimizing the number of wake-up calls and the duration of the wireless communication module.

Benefits of technology

While ensuring that each service does not exceed the maximum tolerable latency, the number of wake-up calls and wake-up duration of the wireless communication module are minimized to reduce the communication power consumption of the embedded device and improve the low-power communication effect.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123124064A_ABST
    Figure CN123124064A_ABST
Patent Text Reader

Abstract

This application discloses a control method, apparatus, device, and storage medium for an embedded device, belonging to the Internet of Things (IoT) technology field of the next-generation information technology industry. It acquires service registration information for multiple services, including communication addresses and maximum tolerable latency. For each message to be sent, its communication address is determined, and the maximum tolerable latency and predicted line latency are determined accordingly. Combining the time the message enters the transmission buffer, the earliest and latest transmission times for each message are determined. Based on the earliest and latest transmission times of all messages, an optimal transmission time is determined, and the wireless communication module is woken up to send all messages in batches. This achieves dynamic determination of the optimal transmission time for messages based on service type and network conditions, enabling batch transmission with a single wake-up, reducing the number of wake-ups and the wake-up duration of the wireless communication module, lowering the communication power consumption of the embedded device, and improving the low-power communication effect in the IoT technology field.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] In the field of Internet of Things (IoT) technology within the next-generation information technology industry, this specifically relates to a control method, device, equipment, and storage medium for embedded devices. Background Technology

[0002] With the rapid development of IoT technology, embedded wireless communication terminals are widely used in smart homes, industrial monitoring, smart agriculture, and other scenarios. These terminals are typically battery-powered and are extremely sensitive to power consumption. How to minimize communication power consumption without affecting business functions has long been a core challenge in this field.

[0003] Current low-power communication solutions mainly employ two strategies: one is a fixed-period wake-up and sleep mechanism, where the terminal wakes up periodically at preset time intervals, sends and receives data, and then goes back to sleep; the other is a strategy based on data caching and batch reporting, where the terminal caches multiple data packets and sends them in batches. However, both of these solutions have significant limitations. The fixed-period strategy cannot distinguish the differentiated communication latency requirements of different services. For example, video streaming services require low latency and frequent wake-ups, while temperature and humidity sensor data can tolerate higher latency and can remain in sleep mode for extended periods. The batch reporting strategy, on the other hand, uses a one-size-fits-all approach to process all data, lacking fine-grained identification and adaptation to different service types. Summary of the Invention

[0004] The purpose of this application is to provide a control method, apparatus, device, and storage medium for embedded devices, which can solve the problem that existing low-power communication solutions cannot take into account the differentiated latency requirements of different services and changes in network conditions, resulting in a high number of wake-up calls and high communication power consumption of the wireless communication module.

[0005] To solve the above-mentioned technical problems, this application is implemented as follows: In a first aspect, embodiments of this application provide a control method for an embedded device, the embedded device including a transmit buffer and a wireless communication module, the method comprising: Obtain service registration information for multiple services, wherein the service registration information includes the communication addresses and maximum tolerable latency corresponding to the multiple services; For each message to be sent in the sending buffer, determine the communication address of the message to be sent, and determine the maximum tolerable delay and the predicted line delay of the message to be sent based on the communication address of the message to be sent. Based on the time when the message to be sent enters the sending buffer, the maximum tolerable delay of the message to be sent, and the predicted line delay, the earliest and latest sending times of the message to be sent are determined. Based on the earliest and latest transmission times of all pending messages in the transmission buffer, the optimal transmission time for all pending messages is determined, and the wireless communication module is woken up based on the optimal transmission time to transmit all pending messages through the wireless communication module.

[0006] Optionally, after obtaining the business registration information for multiple services, the following may also be included: Obtain the historical round-trip time for each of the communication addresses, and determine statistical feature information based on the historical round-trip time, wherein the statistical feature information includes the latest delay value; Historical predicted line delays are obtained, and based on the historical predicted line delays, the latest delay value, and a preset dynamic adjustment coefficient, the predicted line delay corresponding to each communication address is determined.

[0007] Optionally, the statistical characteristic information further includes the standard deviation, and also includes: If the standard deviation is greater than the preset fluctuation threshold, the preset dynamic adjustment coefficient is adjusted.

[0008] Optionally, determining the earliest and latest transmission times of the message to be transmitted based on the time the message enters the transmission buffer, the maximum tolerable delay of the message to be transmitted, and the predicted line delay includes: The earliest transmission time of the message to be sent is obtained by summing the time when the message to be sent enters the transmission buffer with the predicted line delay of the message to be sent. The latest transmission time of the message to be sent is obtained by subtracting the predicted line delay of the message to be sent from the sum of the time when the message to be sent enters the transmission buffer and the maximum tolerable delay of the message to be sent.

[0009] Optionally, determining the optimal transmission time for all pending messages based on the earliest and latest transmission times of all pending messages in the transmission buffer includes: For each message to be sent, the interval between the earliest and latest sending times of the message to be sent is determined as the sending time window of the message to be sent. Based on the sending time window of all the messages to be sent, determine the common overlap interval of all the messages to be sent; Based on the common overlapping interval, the optimal transmission time for all messages to be sent is determined.

[0010] Optionally, determining the common overlap interval of all messages to be sent based on the transmission time window of all messages to be sent includes: Determine the maximum value among the earliest transmission times of all the messages to be sent, and use it as the start time of the interval; Determine the minimum value among the latest transmission times of all the messages to be sent, and use it as the interval cutoff time; If the start time of the interval is less than or equal to the end time of the interval, the interval between the start time and the end time of the interval is defined as the common overlapping interval.

[0011] Optionally, it also includes: If the start time of the interval is greater than the end time of the interval, the message with the smallest latest sending time among all the messages to be sent is determined as the message to be sent first. The priority sending time of the priority sending message is determined based on the earliest and latest sending times of the priority sending message, and after the priority sending message is sent, the common overlap interval of other messages to be sent among all messages to be sent is re-determined.

[0012] Optionally, after waking up the wireless communication module based on the optimal transmission time to transmit all the messages to be transmitted through the wireless communication module, the method further includes: For each communication address, the actual line delay of the communication address is obtained, and the historical round-trip delay of the communication address is updated according to the actual line delay to redetermine the predicted line delay corresponding to the communication address.

[0013] Optionally, before waking up the wireless communication module based on the optimal transmission time to transmit all the messages to be transmitted through the wireless communication module, the method further includes: Obtain the current time, and for each message to be sent, determine the remaining time between the latest sending time of the message and the current time; If the remaining time is less than the predicted line delay corresponding to the message to be sent, the wireless communication module is woken up to send the message to be sent through the wireless communication module.

[0014] Secondly, embodiments of this application provide a control device for an embedded device, the embedded device including a transmit buffer and a wireless communication module, the device comprising: The information acquisition module is used to acquire service registration information for multiple services, including the communication addresses and maximum tolerable latency corresponding to the multiple services. The latency prediction module determines the communication address of each message to be sent in the transmission buffer, and determines the maximum tolerable latency and predicted line latency of the message to be sent based on the communication address of the message to be sent. The interval determination module determines the earliest and latest transmission times of the message to be sent based on the time when the message to be sent enters the transmission buffer, the maximum tolerable delay of the message to be sent, and the predicted line delay. The transmission control module determines the optimal transmission time for all pending messages based on the earliest and latest transmission times of all pending messages in the transmission buffer, and wakes up the wireless communication module based on the optimal transmission time to transmit all pending messages through the wireless communication module.

[0015] Thirdly, embodiments of this application provide an embedded device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0016] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0017] In this embodiment, by acquiring service registration information for multiple services, including the communication addresses and maximum tolerable delays corresponding to the multiple services, for each message to be sent in the sending buffer, the communication address of the message to be sent is determined, and based on the communication address of the message to be sent, the maximum tolerable delay and predicted line delay of the message to be sent are determined. Based on the time when the message to be sent enters the sending buffer, the maximum tolerable delay and predicted line delay of the message to be sent, the earliest sending time and the latest sending time of the message to be sent are determined, based on all messages to be sent in the sending buffer. The earliest and latest transmission times of the messages are used to determine the optimal transmission time for all messages to be sent. Based on the optimal transmission time, the wireless communication module is woken up to send all messages to be sent. This achieves dynamic determination of the optimal transmission time of messages according to service type and network conditions, and merges all messages to be sent into a single wake-up for batch transmission. This minimizes the number of wake-ups and the wake-up duration of the wireless communication module while ensuring that each service does not exceed its maximum tolerable latency, thereby reducing the communication power consumption of embedded devices and improving the low-power communication effect in the field of IoT technology. Attached Figure Description

[0018] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of the steps of a control method for an embedded device provided in some embodiments of the present invention; Figure 2 This is a schematic diagram of the overall process of embedded device control provided by some embodiments of the present invention; Figure 3 This is a structural block diagram of a control device for an embedded device provided in some embodiments of the present invention; Figure 4 This is a schematic diagram of the hardware structure of an embedded device provided in some embodiments of the present invention. Detailed Implementation

[0020] 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, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0022] The following description, in conjunction with the accompanying drawings, details a control method for an embedded device provided in this application through specific embodiments and application scenarios.

[0023] Reference Figure 1 The diagram illustrates a flowchart of the steps of a control method for an embedded device according to some embodiments of the present invention. The embedded device includes a transmit buffer and a wireless communication module, and may specifically include the following steps: Step 101: Obtain service registration information for multiple services, including the communication address and maximum tolerable latency corresponding to the multiple services.

[0024] In one example, the embedded device can be a system that may include a transmit buffer, a wireless communication module, a service management module, a rule register, an intelligent delay analysis module, a transmit message scheduling module, and a power management unit.

[0025] The business management module is used to receive business registration information when the application starts, and encapsulate the business registration information into rule entries and store them in the rule register.

[0026] The rule register is used to store rule entries indexed by the communication address. The rule entries include the maximum tolerable delay, data priority, and predicted line delay corresponding to the communication address.

[0027] The intelligent delay analysis module tracks and learns the historical round-trip delay for each communication address in the rule register, determines the predicted line delay for that communication address, and updates the rule register accordingly. The transmit buffer stores messages to be sent submitted by the application layer.

[0028] The message sending scheduling module is used to extract messages to be sent from the sending buffer, query the rule register according to the communication address of the message to be sent, determine the earliest and latest sending times of the message to be sent, and determine the optimal sending time based on the earliest and latest sending times of all messages to be sent, and update the wake-up schedule.

[0029] The power management unit monitors the wake-up schedule, controlling the wireless communication module to enter sleep mode before the wake-up time arrives, and waking up the wireless communication module when the wake-up time arrives. The wireless communication module, after waking up, merges the messages to be sent that have reached the transmission time window into data frames and sends them, then enters sleep mode after transmission is complete.

[0030] In step 101, when the application starts, it can register with the system's business management module according to its own business characteristics. Registration information includes a business type identifier (such as video, sensor, heartbeat, alarm, etc.), communication address (i.e., target IP address and port number), maximum tolerable latency, data priority, and predicted data volume. The business management module encapsulates the above information into rule entries and stores them in the system's rule register. Rule entries are stored using "communication address + port number" as an index. For example, video streaming services can be set to a maximum tolerable latency of 50ms and a high priority; temperature and humidity sensor data can be set to a maximum tolerable latency of 5s and a low priority; and emergency alarm services can be set to a maximum tolerable latency of 20ms and an extremely high priority.

[0031] In some embodiments of this application, after obtaining the business registration information of multiple services, the method further includes: Sub-step 11: Obtain the historical round-trip time for each of the communication addresses, and determine statistical feature information based on the historical round-trip time, wherein the statistical feature information includes the latest time delay value.

[0032] In sub-step 11, the system's intelligent latency analysis module can perform independent latency tracking and learning on each set of "communication address + port number" recorded in the rule register. Specifically, the intelligent latency analysis module can statistically analyze the historical round-trip time (RTT) data of the communication address according to a preset period, and calculate its statistical characteristics, including the average latency μ, standard deviation σ, and latest latency value L_new. As an example, the preset period can be every 100 data packets or every 10 minutes.

[0033] Sub-step 12: Obtain historical predicted line delay, and determine the predicted line delay corresponding to each communication address based on the historical predicted line delay, the latest delay value, and the preset dynamic adjustment coefficient.

[0034] In sub-step 12, after obtaining the statistical feature information, the historical predicted line delay can be obtained. Then, based on the historical predicted line delay, the latest delay value in the statistical feature information, and the preset dynamic adjustment coefficient, the predicted line delay corresponding to each communication address is determined. Specifically, the intelligent delay analysis module can use a weighted moving average algorithm to predict the predicted line delay D_pred for the next communication. Formula (1) is as follows: D_pred = α × L_new + (1-α) × D_prev (1) Where D_prev represents the historical predicted line delay, i.e., the previously determined predicted line delay, and α is the preset dynamic adjustment coefficient. The prediction result can be updated in real time to the "Prediction Delay" field of the corresponding entry in the register. In one example, the preset dynamic adjustment coefficient can be set to 0.3 by default. In some embodiments of this application, the statistical characteristic information further includes standard deviation, and also includes: If the standard deviation is greater than the preset fluctuation threshold, the preset dynamic adjustment coefficient is adjusted.

[0035] Specifically, when increased latency fluctuations are detected, i.e., when the standard deviation σ exceeds a preset fluctuation threshold, the dynamic adjustment coefficient α is automatically increased to improve the response speed to the latest changes. When the network environment undergoes drastic changes, i.e., when the standard deviation σ exceeds a preset threshold, the system automatically triggers a complete line latency relearning to quickly converge to the new network state.

[0036] It should be noted that the preset fluctuation threshold can be set according to the actual network environment and business needs, and this application embodiment does not impose specific limitations on it.

[0037] As can be seen, by taking service type as the primary dimension of power management, a paradigm shift from device-centric to service-centric power management is achieved. Different service types correspond to different maximum tolerable latency and data priorities, thus providing a basis for subsequent differentiated scheduling.

[0038] Step 102: For each message to be sent in the transmission buffer, determine the communication address of the message to be sent, and determine the maximum tolerable delay and the predicted line delay of the message to be sent based on the communication address of the message to be sent.

[0039] In step 102, when the application layer initiates a network request and submits a data packet to the network layer, the network layer first stores the packet in the USB (Universal Serial Bus) transmit buffer. The transmit packet scheduling module then retrieves the packet from the transmit buffer, parses its communication address (i.e., the target IP address and port number), and queries the rule register to obtain the maximum tolerable latency and the current predicted line latency corresponding to the service.

[0040] This enables the terminal to automatically optimize its transmission strategy when network quality fluctuates, avoiding invalid wake-ups and retransmissions caused by network congestion, further reducing unnecessary power consumption, and improving communication success rate.

[0041] Step 103: Determine the earliest and latest transmission times of the message to be sent based on the time when the message to be sent enters the transmission buffer, the maximum tolerable delay of the message to be sent, and the predicted line delay.

[0042] In step 103, the message scheduling module can calculate the earliest possible transmission time TS_earliest (i.e., the earliest transmission time) and the latest required transmission time TS_deadline (i.e., the latest transmission time) of the current message based on the time when the message enters the transmission buffer, the maximum tolerable delay, and the predicted line delay.

[0043] In some embodiments of this application, determining the earliest and latest transmission times of the message to be transmitted based on the time the message enters the transmission buffer, the maximum tolerable delay of the message to be transmitted, and the predicted line delay includes: Sub-step 21: The earliest transmission time of the message to be sent is obtained by summing the time when the message to be sent enters the transmission buffer with the predicted line delay of the message to be sent.

[0044] In sub-step 21, the earliest transmission time can be obtained using the formula TS_earliest = current time + D_pred. This formula ensures that the actual arrival time of all packets is greater than the predicted delay, providing a deterministic upper bound for the receiver's processing of non-real-time services and batch aggregation. This is a key policy constraint for achieving intelligent low power consumption. If the packet is sent immediately at the current time, it will arrive after the current time plus the predicted line delay D_pred, which is exactly equal to the predicted value. However, in the presence of network jitter, the actual delay may be less than the predicted line delay D_pred (i.e., the packet arrives too early), which may result in the receiver not being ready (e.g., outside of a shallow sleep listening gap). Therefore, adding the predicted line delay D_pred to the current time is not to ensure that the packet arrives at the receiver exactly at the predicted time, but rather to allow the sender to wait for a line delay, using this time window to aggregate more pending data packets, thereby achieving large-scale merging at the subsequent actual transmission time and minimizing the number of wake-ups.

[0045] Sub-step 22: Subtract the predicted line delay of the message to be sent from the sum of the time when the message to be sent enters the sending buffer and the maximum tolerable delay of the message to be sent, to obtain the latest sending time of the message to be sent.

[0046] In sub-step 22, the latest transmission time can be obtained using the formula TS_deadline = current time + T_max - D_pred. Here, TS_deadline is the latest transmission time, T_max is the maximum tolerable delay, and D_pred is the predicted line delay. This formula ensures that the message is delivered within the tolerable period.

[0047] It is evident that a specific transmission time window is determined for each message to be sent. This window ensures that the message does not arrive at the receiving end too early and that the message does not exceed its maximum tolerable delay, thus providing a time constraint basis for the subsequent merging and transmission of multiple messages.

[0048] Step 104: Based on the earliest and latest transmission times of all messages to be transmitted in the transmission buffer, determine the optimal transmission time for all messages to be transmitted, and wake up the wireless communication module based on the optimal transmission time to transmit all messages to be transmitted through the wireless communication module.

[0049] In step 104, the message scheduling module determines the optimal sending time TS_send within the [TS_earliest, TS_deadline] time window by combining the priority, earliest sending time, and latest sending time of other messages to be sent in the buffer. For high-priority services (such as emergency alarms), TS_send is directly set to TS_earliest to ensure the shortest delay; for low-priority services, TS_send can be delayed as much as possible within the window to maximize merging with other messages to be sent and reduce the number of wake-ups of the wireless communication module.

[0050] The system can maintain a wake-up schedule to record the wake-up time of the next wireless communication module. Once the message scheduling module calculates TS_send, it adds it to the wake-up schedule. The power management unit (PMU) of the wireless communication module continuously monitors the wake-up schedule, keeping the wireless communication module in deep sleep mode (power consumption as low as microwatts) until the preset wake-up time is reached. When the wake-up time arrives, the PMU wakes up the wireless communication module, and the message scheduling module merges all messages in the buffer that have reached their transmission time window into a single data frame for unified transmission.

[0051] In some embodiments of this application, after waking up the wireless communication module based on the optimal transmission time to send all the messages to be sent through the wireless communication module, the method further includes: controlling the wireless communication module to enter a sleep state.

[0052] Specifically, after transmission is completed, the wireless communication module can be controlled to immediately re-enter a deep sleep state, with power consumption as low as microwatts.

[0053] It should be noted that it is the wireless communication module that is in hibernation, not the entire embedded device. The main processor or coprocessor of the embedded device remains running or operates in a low-power state during the hibernation period of the wireless communication module to acquire the historical round-trip time and determine the predicted line delay. Specifically, the delay learning module runs on the low-power coprocessor, the scheduling module can run on the main processor or coprocessor, and service registration is performed during system initialization or service changes. This method, through hardware and software co-design, minimizes the number of wake-ups and the wake-up duration of the wireless communication module while meeting the differentiated latency requirements of various services, thereby significantly reducing the overall communication power consumption of the embedded IoT terminal.

[0054] In some embodiments of this application, determining the optimal transmission time for all pending transmission messages based on the earliest and latest transmission times of all pending transmission messages in the transmission buffer includes: Sub-step 31: For each message to be sent, determine the interval between the earliest and latest sending times of the message to be sent as the sending time window of the message to be sent.

[0055] In sub-step 31, the interval between the earliest and latest sending times of each message to be sent can be used as the sending time window for that message. Sub-step 32: Based on the sending time window of all the messages to be sent, determine the common overlap interval of all the messages to be sent.

[0056] In sub-step 32, the message scheduling module can scan all messages to be sent, obtain their respective sending time windows, and find the maximum common overlap interval.

[0057] Sub-step 33: Based on the common overlapping interval, determine the optimal transmission time for all messages to be sent.

[0058] In sub-step 33, the message scheduling module selects the latest time point within the common overlap interval as the global wake-up time, in order to wait as much as possible, merge any new messages that may arrive later, and minimize the number of wake-ups.

[0059] In some embodiments of this application, determining the common overlap interval of all messages to be sent based on the transmission time window of all messages to be sent includes: Sub-step 41: Determine the maximum value among the earliest transmission times of all the messages to be sent, and use it as the start time of the interval.

[0060] In sub-step 41, the latest start time Max_Earliest of all windows can be calculated, which is the earliest time of the largest (i.e. latest) earliest transmission time of all messages to be sent, and used as the start time of the interval.

[0061] Sub-step 42: Determine the minimum value among the latest transmission times of all the messages to be sent, and use it as the interval cutoff time.

[0062] In substep 42, calculate the earliest deadline Min_Deadline for all windows, which is the latest (i.e., the earliest) latest sending time of all pending messages, and use it as the interval deadline.

[0063] Sub-step 43: If the start time of the interval is less than or equal to the end time of the interval, the interval between the start time and the end time of the interval is determined as the common overlapping interval.

[0064] In sub-step 43, if the interval start time Max_Earliest ≤ the interval end time Min_Deadline, it indicates that all messages to be sent have a common sendable time period, and this interval can be identified as a common overlapping interval.

[0065] As an example, assume the current time T=0, and there are three messages to be sent: Message A has a TS_earliest of 10ms and a TS_deadline of 100ms; Message B has a TS_earliest of 20ms and a TS_deadline of 120ms; and Message C has a TS_earliest of 30ms and a TS_deadline of 70ms. The common overlap interval has a start time Max_Earliest = max(10,20,30) = 30ms and an end time Min_Deadline = min(100,120,70) = 70ms, meaning the common overlap interval is [30ms, 70ms].

[0066] It should be added that if the wireless communication module is woken up at the earliest (i.e. 30ms), it can only send three messages to be sent: A, B, and C. After sending them, the wireless communication module will continue to enter the sleep state. Suppose that a new message to be sent, D, arrives at 35ms, the system has to wake up again after 35ms to send D, resulting in the wireless communication module being woken up twice.

[0067] If the latest wake-up time (70ms) is chosen for the wireless communication module: Although A, B, and C are ready at 30ms, the system forces the wireless communication module to sleep and not process them. When it wakes up at 70ms, not only are A, B, and C still in the transmission buffer and have not timed out, but even the message D, which arrived at 35ms, is already in the transmission buffer. Thus, the wireless communication module can be woken up only once to send all four messages (A, B, C, and D).

[0068] In some embodiments of this application, it also includes: Sub-step 51: If the start time of the interval is greater than the end time of the interval, the message with the smallest latest sending time among all the messages to be sent is determined as the message to be sent first.

[0069] In sub-step 51, if the interval start time Max_Earliest > the interval deadline Min_Deadline, it indicates that the transmission time windows of all pending messages do not have a common overlapping interval and cannot be merged into a single wake-up batch transmission. At this time, the EDF (Earliest Deadline First) preemption strategy can be activated, and the pending message with the smallest latest transmission time TS_deadline among all pending messages can be identified as the priority transmission message, and forced to be processed first, i.e., the most urgent and least waiting message.

[0070] Sub-step 52: Determine the priority sending time of the priority sending message based on the earliest and latest sending times of the priority sending message, and after the priority sending message is sent, re-determine the common overlapping interval of other messages to be sent among all messages to be sent.

[0071] In sub-step 52, the priority sending time can be determined within the sending time window of the priority sending message itself based on the earliest and latest sending times of the priority sending message. An early wake-up can be triggered separately for the priority sending message, and the priority sending message can be sent separately through the wireless communication module. Alternatively, the priority sending message can be sent in a small batch together with other messages whose sending time windows also meet the current wake-up time.

[0072] After the priority message is sent, the common overlap interval of the remaining messages to be sent is re-determined. That is, the steps of determining the start time of the interval, the end time of the interval, and determining whether there is a common overlap interval are re-executed for the remaining messages to be sent. In order to merge the remaining messages to be sent into a single wake-up batch, thereby minimizing the number of wake-ups of the wireless communication module while ensuring that the most urgent message does not exceed its maximum tolerable delay.

[0073] In some embodiments of this application, before waking up the wireless communication module based on the optimal transmission time to transmit all the messages to be transmitted through the wireless communication module, the method further includes: Sub-step 61: Obtain the current time, and for each message to be sent, determine the remaining time between the latest sending time of the message to be sent and the current time.

[0074] In sub-step 61, the message scheduling module has a real-time monitoring function, which can continuously detect and record the current time. For each message to be sent in the sending buffer, the message scheduling module can compare the latest sending time of the message to be sent with the current time to determine the remaining time between the latest sending time and the current time. This remaining time represents how long the message to be sent is until its latest sending time, that is, how long the message to be sent can continue to wait in the sending buffer without exceeding its maximum tolerable delay. Thus, by determining the remaining time of each message to be sent, a basis is provided for subsequent judgment on whether to trigger emergency sending.

[0075] Sub-step 62: If the remaining time is less than the predicted line delay corresponding to the message to be sent, wake up the wireless communication module to send the message to be sent through the wireless communication module.

[0076] In sub-step 62, if the remaining time of a message to be sent is less than the predicted line delay corresponding to that message, it means that even if the message is sent immediately, it will still need to pass through the predicted line delay to reach the receiving end. If it continues to wait for the next batch wake-up, the message to be sent will exceed its maximum tolerable delay. At this time, the message sending scheduling module can trigger emergency sending, wake up the wireless communication module in advance, and send the message to be sent separately through the wireless communication module to ensure that the message to be sent does not violate its service delay requirements.

[0077] It should be noted that the sending of the message to be sent is independent of the batch sending triggered based on the optimal sending time in step 104. That is, before the wake-up time of the batch sending arrives, the message to be sent with insufficient remaining time is woken up once in advance, so as to ensure that the urgent message does not time out, without affecting the batch sending of the remaining messages to be sent.

[0078] In some embodiments of this application, after waking up the wireless communication module based on the optimal transmission time to transmit all the messages to be transmitted through the wireless communication module, the method further includes: For each communication address, the actual line delay of the communication address is obtained, and the historical round-trip delay of the communication address is updated according to the actual line delay to redetermine the predicted line delay corresponding to the communication address.

[0079] Specifically, after each communication is completed, the actual line delay L_actual can be fed back to the intelligent delay analysis module to update the delay statistics database of the target, and then redetermine the predicted line delay corresponding to the communication address.

[0080] Furthermore, the system can evaluate the communication quality of each service according to a preset evaluation period (e.g., hourly). If the average actual line delay μ of a certain service is consistently much lower than its maximum tolerable delay T_max, indicating significant energy-saving potential, the system can automatically extend its maximum tolerable delay T_max appropriately, but not exceeding a preset upper limit, thereby further reducing the wake-up frequency. Conversely, if the actual line delay frequently approaches or exceeds T_max, the system can automatically shorten the maximum tolerable delay T_max of the service or increase its priority to ensure service quality. For example, the preset evaluation period is one hour, i.e., periodically every hour.

[0081] Based on the above, it is possible to ensure optimal power consumption for low-priority services while guaranteeing communication with minimal latency for urgent services, thus achieving a balance between power consumption optimization and service reliability.

[0082] In this embodiment, by acquiring service registration information for multiple services, including the communication addresses and maximum tolerable delays corresponding to the multiple services, for each message to be sent in the sending buffer, the communication address of the message to be sent is determined, and based on the communication address of the message to be sent, the maximum tolerable delay and predicted line delay of the message to be sent are determined. Based on the time when the message to be sent enters the sending buffer, the maximum tolerable delay and predicted line delay of the message to be sent, the earliest sending time and the latest sending time of the message to be sent are determined, based on all messages to be sent in the sending buffer. The earliest and latest transmission times of the messages are used to determine the optimal transmission time for all messages to be sent. Based on the optimal transmission time, the wireless communication module is woken up to send all messages to be sent. This achieves dynamic determination of the optimal transmission time of messages according to service type and network conditions, and merges all messages to be sent into a single wake-up for batch transmission. This minimizes the number of wake-ups and the wake-up duration of the wireless communication module while ensuring that each service does not exceed its maximum tolerable latency, thereby reducing the communication power consumption of embedded devices and improving the low-power communication effect in the field of IoT technology.

[0083] Reference Figure 2 The diagram illustrates an overall flow chart of embedded device control according to some embodiments of the present invention, which may specifically include the following steps: 1. Start: The starting point of the method flow. After the embedded device starts up, it will proceed to the subsequent steps.

[0084] 2. Service registration and parameter configuration (maximum tolerable latency T_max, etc.): When the application starts, it registers with the service management module. The registration information includes service type identifier, communication address (target IP address and port number), maximum tolerable latency T_max, data priority, etc. The service management module encapsulates these into rule entries and stores them in the rule register.

[0085] 3. System Operation: The system enters normal operation mode, and then executes the dynamic learning process of line delay on the left and the message sending scheduling process on the right in parallel.

[0086] 4. Dynamic learning of line delay: The intelligent delay analysis module independently tracks and learns the historical round-trip delay corresponding to each communication address in the rule register. This process is continuously executed in a loop.

[0087] 5. Statistical analysis of historical round-trip latency data: The intelligent latency analysis module can periodically collect historical round-trip latency data for this communication address and calculate statistical characteristic information, including average latency, standard deviation and latest latency value.

[0088] 6. Calculate the next communication line delay: Based on statistical feature information, a weighted moving average algorithm is used to determine the predicted line delay corresponding to the communication address.

[0089] 7. Update Predicted Delay: Update the calculated predicted line delay to the "Predicted Delay" field of the corresponding entry in the rule register.

[0090] 8. Wait for the next learning cycle: After the next learning cycle arrives, return to step (4) to continue the dynamic learning of line delay.

[0091] 9. Waiting for application layer data requests: The system waits for the application layer to initiate a network request and submit the data packet (i.e. the packet to be sent) to the sending buffer.

[0092] 10. Has data arrived?: Determine if there is a message to be sent in the send buffer. If not, return to step 9 and continue waiting. If yes, proceed to step 11.

[0093] 11. Resolve the target IP and port: The scheduling module extracts the message to be sent from the sending buffer and resolves its communication address, namely the target IP address and port number.

[0094] 12. Calculate the transmission time window: Query the rule register based on the communication address of the message to be transmitted to obtain the maximum tolerable delay and the predicted line delay corresponding to the message to be transmitted. Combined with the time when the message to be transmitted enters the transmission buffer, determine the earliest and latest transmission times of the message to be transmitted, and thus obtain the transmission time window of the message to be transmitted.

[0095] 13. Determine the optimal sending time: Based on the earliest and latest sending times of all messages to be sent in the sending buffer, determine the optimal sending time for all messages to be sent.

[0096] 14. Is it an urgent service / timeout: Determine whether the message to be sent is an urgent service message, or whether it is close to its maximum tolerable delay and is about to time out; if yes, proceed directly to step 15 to send; if no, proceed to step 16 to add to the time wake-up table.

[0097] 15. Sending: For urgent business or messages that are about to time out, wake up the wireless communication module in advance and send the message to be sent separately through the wireless communication module.

[0098] 16. Add to time wake-up table: For non-urgent messages, add the optimal sending time determined in step 13 to the wake-up time table, which is monitored by the power management unit.

[0099] 17. Wake-up time reached: The power management unit monitors the wake-up schedule and wakes up the wireless communication module when the wake-up time is reached. It then merges the messages in the transmission buffer that have reached the transmission time window into a data frame and sends it.

[0100] 18. Obtain actual delay: After each communication is completed, obtain the actual line delay for that communication address.

[0101] 19. System Evaluation: Feed back the actual line delay to the intelligent delay analysis module, update the delay statistics database for the communication address, and periodically evaluate the communication quality of each service.

[0102] 20. Latency much less than T_max: If the actual average latency of a certain service is consistently much lower than its maximum tolerable latency T_max, it indicates that there is a large energy-saving margin. Therefore, the maximum tolerable latency T_max of the service should be extended and the wake-up frequency reduced.

[0103] 21. Delay Approaching T_max: If the actual delay of a certain service frequently approaches or exceeds its maximum tolerable delay T_max, then the maximum tolerable delay T_max of the service will be shortened and its priority will be increased to ensure service quality.

[0104] 22. Network Severe Fluctuations: When a drastic change in the network environment is detected, such as when the standard deviation exceeds the preset fluctuation threshold, a complete line delay relearning can be triggered to quickly converge to the new network state.

[0105] In this embodiment, by acquiring service registration information for multiple services, including the communication addresses and maximum tolerable delays corresponding to the multiple services, for each message to be sent in the sending buffer, the communication address of the message to be sent is determined, and based on the communication address of the message to be sent, the maximum tolerable delay and predicted line delay of the message to be sent are determined. Based on the time when the message to be sent enters the sending buffer, the maximum tolerable delay and predicted line delay of the message to be sent, the earliest sending time and the latest sending time of the message to be sent are determined, based on all messages to be sent in the sending buffer. The earliest and latest transmission times of the messages are used to determine the optimal transmission time for all messages to be sent. Based on the optimal transmission time, the wireless communication module is woken up to send all messages to be sent. This achieves dynamic determination of the optimal transmission time of messages according to service type and network conditions, and merges all messages to be sent into a single wake-up for batch transmission. This minimizes the number of wake-ups and the wake-up duration of the wireless communication module while ensuring that each service does not exceed its maximum tolerable latency, thereby reducing the communication power consumption of embedded devices and improving the low-power communication effect in the field of IoT technology.

[0106] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0107] Reference Figure 3 The diagram illustrates a structural schematic of a control device for an embedded device according to some embodiments of the present invention. The embedded device includes a transmit buffer and a wireless communication module, and may specifically include the following modules: Information acquisition module 301 is used to acquire service registration information of multiple services, the service registration information including the communication address and maximum tolerable latency corresponding to the multiple services; The delay prediction module 302 determines the communication address of each message to be sent in the transmission buffer, and determines the maximum tolerable delay and the predicted line delay of the message to be sent based on the communication address of the message to be sent. The interval determination module 303 determines the earliest and latest transmission times of the message to be sent based on the time when the message to be sent enters the transmission buffer, the maximum tolerable delay of the message to be sent, and the predicted line delay. The transmission control module 304 determines the optimal transmission time for all pending messages based on the earliest and latest transmission times of all pending messages in the transmission buffer, and wakes up the wireless communication module based on the optimal transmission time to transmit all pending messages through the wireless communication module.

[0108] In one embodiment of this application, after obtaining the business registration information of multiple services, the method further includes: The feature information acquisition module is used to acquire the historical round-trip time delay corresponding to each of the communication addresses, and to determine statistical feature information based on the historical round-trip time delay, wherein the statistical feature information includes the latest delay value; The delay determination module is used to obtain historical predicted line delays and, based on the historical predicted line delays, the latest delay value, and a preset dynamic adjustment coefficient, determine the predicted line delay corresponding to each communication address.

[0109] In one embodiment of this application, the statistical characteristic information further includes the standard deviation, and also includes: The adjustment coefficient module is used to adjust the preset dynamic adjustment coefficient when the standard deviation is greater than the preset fluctuation threshold.

[0110] In one embodiment of this application, the interval determination module 303 includes: The earliest transmission time determination submodule is used to sum the time when the message to be sent enters the transmission buffer and the predicted line delay of the message to be sent to obtain the earliest transmission time of the message to be sent. The latest transmission time determination submodule is used to subtract the predicted line delay of the message to be transmitted from the sum of the time when the message to be transmitted enters the transmission buffer and the maximum tolerable delay of the message to be transmitted, in order to obtain the latest transmission time of the message to be transmitted.

[0111] In one embodiment of this application, the transmission control module 304 includes: The time window determination submodule is used to determine the interval between the earliest and latest sending times of each message to be sent as the sending time window of the message to be sent. The overlapping interval determination submodule is used to determine the common overlapping interval of all messages to be sent based on the sending time window of all messages to be sent. The optimal time determination submodule is used to determine the optimal transmission time for all messages to be sent based on the common overlap interval.

[0112] In one embodiment of this application, the overlapping interval determination submodule includes: The start time determination unit is used to determine the maximum value among the earliest transmission times of all the messages to be sent, as the start time of the interval. The deadline determination unit is used to determine the minimum value among the latest transmission times of all the messages to be sent, as the interval deadline. An interval determination unit is used to determine the interval between the interval start time and the interval end time as the common overlapping interval when the interval start time is less than or equal to the interval end time.

[0113] In one embodiment of this application, it further includes: The priority message detection module is used to determine the message with the smallest latest sending time among all the messages to be sent as the priority message when the start time of the interval is greater than the end time of the interval. The interval re-determination module is used to determine the priority sending time of the priority sending message based on the earliest and latest sending times of the priority sending message, and after the priority sending message is sent, to re-determine the common overlapping interval of other messages to be sent among all messages to be sent.

[0114] In one embodiment of this application, after waking up the wireless communication module based on the optimal transmission time to transmit all the messages to be transmitted through the wireless communication module, the method further includes: The delay update module is used to obtain the actual line delay of each communication address and update the historical round-trip delay of the communication address based on the actual line delay, so as to redetermine the predicted line delay corresponding to the communication address.

[0115] In one embodiment of this application, before waking up the wireless communication module based on the optimal transmission time to transmit all the messages to be transmitted through the wireless communication module, the method further includes: The remaining time determination module is used to obtain the current time and, for each message to be sent, determine the remaining time between the latest sending time of the message to be sent and the current time. A separate transmission module is used to wake up the wireless communication module when the remaining time is less than the predicted line delay corresponding to the message to be transmitted, so as to transmit the message to be transmitted through the wireless communication module.

[0116] The control device for an embedded device in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0117] The control device for an embedded device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit the specific operating system.

[0118] This application provides a control device for an embedded device that can achieve... Figure 1 The various processes implemented in the method embodiment of an embedded device control method are not described in detail here to avoid repetition.

[0119] In this embodiment, by acquiring service registration information for multiple services, including the communication addresses and maximum tolerable delays corresponding to the multiple services, for each message to be sent in the sending buffer, the communication address of the message to be sent is determined, and based on the communication address of the message to be sent, the maximum tolerable delay and predicted line delay of the message to be sent are determined. Based on the time when the message to be sent enters the sending buffer, the maximum tolerable delay and predicted line delay of the message to be sent, the earliest sending time and the latest sending time of the message to be sent are determined, based on all messages to be sent in the sending buffer. The earliest and latest transmission times of the messages are used to determine the optimal transmission time for all messages to be sent. Based on the optimal transmission time, the wireless communication module is woken up to send all messages to be sent. This achieves dynamic determination of the optimal transmission time of messages according to service type and network conditions, and merges all messages to be sent into a single wake-up for batch transmission. This minimizes the number of wake-ups and the wake-up duration of the wireless communication module while ensuring that each service does not exceed its maximum tolerable latency, thereby reducing the communication power consumption of embedded devices and improving the low-power communication effect in the field of IoT technology.

[0120] Optionally, embodiments of this application also provide an embedded device. Figure 4 This is a schematic diagram of the hardware structure of an embedded device, including a processor 410, a memory 409, and a program or instructions stored in the memory 409 and executable on the processor 410. When the program or instructions are executed by the processor 410, they implement the various processes of the control method embodiment of the embedded device described above and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0121] It should be noted that the embedded devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0122] The embedded device 400 includes, but is not limited to, components such as: a radio frequency unit 401, a network module 402, an audio output unit 403, an input unit 404, a sensor 405, a display unit 406, a user input unit 407, an interface unit 408, a memory 409, and a processor 410. The user input unit 407 includes a touch panel 4071 and other input devices 4072; the display unit 406 includes a display panel 4061; and the input unit includes a graphics processor 4041 and a microphone 4042.

[0123] Those skilled in the art will understand that the embedded device 400 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 410 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 4 The embedded device structure shown does not constitute a limitation on the embedded device. An embedded device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0124] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embedded device control method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0125] The processor is the processor in the embedded device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0126] It should be noted that, in this document, 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 that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0127] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0128] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A control method of an embedded device, characterized by, The embedded device includes a transmit buffer and a wireless communication module, and the method includes: Obtain service registration information for multiple services, wherein the service registration information includes the communication addresses and maximum tolerable latency corresponding to the multiple services; For each message to be sent in the sending buffer, determine the communication address of the message to be sent, and determine the maximum tolerable delay and the predicted line delay of the message to be sent based on the communication address of the message to be sent. Based on the time when the message to be sent enters the sending buffer, the maximum tolerable delay of the message to be sent, and the predicted line delay, the earliest and latest sending times of the message to be sent are determined. Based on the earliest and latest transmission times of all pending messages in the transmission buffer, the optimal transmission time for all pending messages is determined, and the wireless communication module is woken up based on the optimal transmission time to transmit all pending messages through the wireless communication module.

2. The method according to claim 1, characterized in that, After obtaining the business registration information for multiple services, it also includes: Obtain the historical round-trip time for each of the communication addresses, and determine statistical feature information based on the historical round-trip time, wherein the statistical feature information includes the latest delay value; Historical predicted line delays are obtained, and based on the historical predicted line delays, the latest delay value, and a preset dynamic adjustment coefficient, the predicted line delay corresponding to each communication address is determined.

3. The method according to claim 2, characterized in that, The statistical characteristic information also includes standard deviation, and further includes: If the standard deviation is greater than the preset fluctuation threshold, the preset dynamic adjustment coefficient is adjusted.

4. The method according to claim 1, characterized in that, The step of determining the earliest and latest transmission times of the message to be transmitted based on the time when the message to be transmitted enters the transmission buffer, the maximum tolerable delay of the message to be transmitted, and the predicted line delay includes: The earliest transmission time of the message to be sent is obtained by summing the time when the message to be sent enters the transmission buffer with the predicted line delay of the message to be sent. The latest transmission time of the message to be sent is obtained by subtracting the predicted line delay of the message to be sent from the sum of the time when the message to be sent enters the transmission buffer and the maximum tolerable delay of the message to be sent.

5. The method according to claim 1, characterized in that, Determining the optimal transmission time for all pending messages based on the earliest and latest transmission times of all messages to be transmitted in the transmission buffer includes: For each message to be sent, the interval between the earliest and latest sending times of the message to be sent is determined as the sending time window of the message to be sent. Based on the sending time window of all the messages to be sent, determine the common overlap interval of all the messages to be sent; Based on the common overlapping interval, the optimal transmission time for all messages to be sent is determined.

6. The method according to claim 5, characterized in that, The step of determining the common overlap interval of all messages to be sent based on the sending time window of all messages to be sent includes: Determine the maximum value among the earliest transmission times of all the messages to be sent, and use it as the start time of the interval; Determine the minimum value among the latest transmission times of all the messages to be sent, and use it as the interval cutoff time; If the start time of the interval is less than or equal to the end time of the interval, the interval between the start time and the end time of the interval is defined as the common overlapping interval.

7. The method according to claim 6, characterized in that, Also includes: If the start time of the interval is greater than the end time of the interval, the message with the smallest latest sending time among all the messages to be sent is determined as the message to be sent first. The priority sending time of the priority sending message is determined based on the earliest and latest sending times of the priority sending message, and after the priority sending message is sent, the common overlap interval of other messages to be sent among all messages to be sent is re-determined.

8. The method according to any one of claims 1-7, characterized in that, After waking up the wireless communication module based on the optimal transmission time to transmit all the messages to be transmitted through the wireless communication module, the method further includes: For each communication address, the actual line delay of the communication address is obtained, and the historical round-trip delay of the communication address is updated according to the actual line delay to redetermine the predicted line delay corresponding to the communication address.

9. The method according to any one of claims 1-7, characterized in that, Before waking up the wireless communication module based on the optimal transmission time to transmit all the messages to be transmitted through the wireless communication module, the method further includes: Obtain the current time, and for each message to be sent, determine the remaining time between the latest sending time of the message and the current time; If the remaining time is less than the predicted line delay corresponding to the message to be sent, the wireless communication module is woken up to send the message to be sent through the wireless communication module.

10. A control device for an embedded device, characterized in that, The embedded device includes a transmit buffer and a wireless communication module; the apparatus includes: The information acquisition module is used to acquire service registration information for multiple services, including the communication addresses and maximum tolerable latency corresponding to the multiple services. The latency prediction module determines the communication address of each message to be sent in the transmission buffer, and determines the maximum tolerable latency and predicted line latency of the message to be sent based on the communication address of the message to be sent. The interval determination module determines the earliest and latest transmission times of the message to be sent based on the time when the message to be sent enters the transmission buffer, the maximum tolerable delay of the message to be sent, and the predicted line delay. The transmission control module determines the optimal transmission time for all pending messages based on the earliest and latest transmission times of all pending messages in the transmission buffer, and wakes up the wireless communication module based on the optimal transmission time to transmit all pending messages through the wireless communication module.

11. An embedded device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method as described in any one of claims 1 to 9.

12. A readable storage medium, characterized in that, A computer program is stored on the readable storage medium, which, when executed by a processor, implements the method as described in any one of claims 1 to 9.