Adaptation method for 5G lightweight terminal and power gap operating system

Abstract

The invention provides an adaptation method for a 5G lightweight terminal and a power gap operating system, and relates to the technical field of lightweight 5G terminals, the method comprises the following steps: obtaining equipment related information of all 5G lightweight terminals in the power gap operating system; obtaining a computing resource allocation result by using an equipment enumeration algorithm and an allocation algorithm based on adaptive weight; analyzing the computing resource allocation result by using a long-short-term memory model and a resource scheduling strategy to obtain a spectrum resource allocation result; performing channel optimization and signal enhancement by adjusting the spectrum resource allocation result to obtain a spectrum resource optimization result; and on the basis of the spectrum resource optimization result, the 5G lightweight terminal is utilized to carry out adaptive optimization processing and fault prediction on the transmission data to obtain a system adaptive result, and the adaptation of the 5G lightweight terminal and the power gap operating system is completed. According to the invention, the problems of high communication overhead and low multi-device access efficiency of the lightweight 5G terminal are solved.

Description

Technical Field

[0001] This specification relates to the field of lightweight 5G terminal technology, and in particular to a method for adapting a 5G lightweight terminal to the power Hongmeng operating system. Background Art

[0002] Existing protocol stacks are usually based on general 5G standards, such as the 5G protocol stack defined by 3GPP, but are not specially optimized for the proprietary scenarios of Power Hongmeng. The layers of the protocol stack are relatively complex, and support for lightweight devices such as RedCap is limited. Advantages: Supports standardized communication protocols and has high compatibility. Provides high security, especially in data encryption and authentication. Disadvantages: Not optimized for low-power devices, and the overall energy consumption is high. The communication overhead is large, and it may not be suitable for low-latency access of large-scale devices.

[0003] Traditional device enumeration and mounting processes rely on manual configuration or semi-automated processes. The operating system identifies the device through its unique identifier (such as MAC address, IMEI, etc.) and allocates its resources to the corresponding communication channel. As the number of connected devices increases, manual mounting becomes inefficient and prone to configuration errors. Advantages: Suitable for the access and management of small-scale devices. Simple operation in a single or fixed scenario, and low deployment cost. Disadvantages: Manual configuration is prone to errors in large-scale, multi-device access scenarios. The system responds slowly, cannot adjust the mounting strategy in time, and cannot cope with high concurrency scenarios.

[0004] In existing 5G communications, resource allocation is usually managed by a static resource pool preset by the network operator or the system. After the device is connected, the system allocates resources based on the device's bandwidth requirements and communication priority, but this method is difficult to adjust in real time. Advantages: It can guarantee resource allocation for high-priority tasks. For standardized scenarios, it has strong stability. Disadvantages: Static allocation is difficult to flexibly respond to the real-time needs of the device, and resource utilization is low. The configuration of the communication channel is complex and cannot effectively support high concurrency requirements in dynamic scenarios.

[0005] Most current adaptation technologies rely on the traditional manual configuration of device mounting methods, and static resource allocation cannot cope with complex multi-terminal dynamic access scenarios. In addition, the existing communication protocol stack is not optimized for low-power devices, resulting in high energy consumption of RedCap terminals, large communication overhead, and severe signal interference, making it difficult to meet the access needs of large-scale devices. RedCap terminals have high storage requirements, while the Hongmeng system has low storage requirements, which may cause storage mismatch or unreasonable resource allocation when docking the system. Summary of the invention

[0006] In view of the above-mentioned deficiencies in the prior art, the present invention provides an adaptation method for a 5G lightweight terminal and the power Hongmeng operating system, which solves the problems of high communication overhead of lightweight 5G terminals and low access efficiency of multiple devices.

[0007] In order to achieve the above-mentioned invention object, the technical solution adopted by the present invention is: a method for adapting a 5G lightweight terminal to the power Hongmeng operating system, comprising:

[0008] S1: Obtain device-related information of all 5G lightweight terminals in the Hongmeng operating system;

[0009] S2: using a device enumeration algorithm and an allocation algorithm based on adaptive weights to process the device-related information and obtain a computing resource allocation result;

[0010] S3: Analyze the computing resource allocation result by using the long short-term memory model and the resource scheduling strategy to obtain a spectrum resource allocation result;

[0011] S4: adjusting the spectrum-resource allocation result, performing channel optimization and signal enhancement, and obtaining a spectrum resource optimization result;

[0012] S5: Based on the spectrum resource optimization results, the 5G lightweight terminal is used to perform adaptation optimization processing and fault prediction on the transmission data to obtain the system adaptation results, and complete the adaptation of the 5G lightweight terminal and the power Hongmeng operating system.

[0013] The beneficial effects of the present invention are: through the simplification of the protocol stack, automatic device mounting and enumeration, dynamic resource scheduling, channel optimization, and edge computing processing, the adaptation method of 5G lightweight terminals and the power Hongmeng operating system is realized. In view of the needs of low-power devices, the protocol stack design is optimized to reduce communication overhead; at the same time, through the automated device mounting and resource allocation mechanism, the efficiency of concurrent access of multiple devices is improved.

[0014] Furthermore, the S1 includes:

[0015] Use the lightweight protocol stack in the 5G lightweight terminal to obtain the heartbeat signaling;

[0016] Based on the heartbeat signaling, obtain device-related information of all 5G lightweight terminals in the Hongmeng operating system.

[0017] Further, the S2 includes:

[0018] S210: Process the device-related information using a device enumeration algorithm to obtain an enumeration allocation result; wherein the device number is used as a hash key and the device information is used as a hash value to initialize a hash mapping to obtain a mapping result;

[0019] Based on the mapping result, the devices are arranged using corresponding device characteristics to obtain a device processing queue;

[0020] Based on the device processing queue, corresponding computing resources and communication channels are allocated based on device characteristics to obtain an enumeration allocation result; wherein the device number, the device information and the device characteristics belong to the device related information;

[0021] S220: Based on the enumerated allocation result, using an allocation algorithm based on adaptive weights, the allocation strategy is adjusted in real time according to the needs of the device and the network load to obtain a computing resource allocation result.

[0022] Furthermore, the expression of the computing resource allocation result is:

[0023]

[0024] in, Indicates the result of computing resource allocation. represents the computing resource requirement weight of device i, represents the computing resource requirement weight of device j, T r1 represents the total computing resources available to the system, α 1 Indicates the weight coefficient of CPU resources, C i represents the CPU resources required by device i, β 1 Represents the weight coefficient of memory resources, M i represents the memory resources required by device i, γ 1 Represents the weight coefficient of network bandwidth demand, N i Represents the network bandwidth requirement of device i, i represents the i-th device, and j represents the j-th device.

[0025] Further, the S3 includes:

[0026] The calculation resource allocation result is analyzed using the long short-term memory model to obtain the spectrum resource prediction result:

[0027]

[0028] D i =d i1 , d i2 , d i3 ,…,d in ;

[0029] in, represents the spectrum resource prediction result, f represents the prediction function of the LSTM network, and D i represents the historical resource usage data of device i, t represents time t, and d i1represents the first historical resource usage data of device i, d i2 represents the second historical resource usage data of device i, d i3 represents the third historical resource usage data of device i, d in Indicates the nth historical resource usage data of device i;

[0030] Based on the spectrum resource prediction result, a resource scheduling strategy is used to allocate resources, and a spectrum resource allocation result is obtained:

[0031]

[0032] in, Indicates the spectrum resource allocation result, represents the spectrum resource allocation weight of device i, represents the spectrum resource allocation weight of device j, T R1 represents the total resources of the system, i represents the i-th device, j represents the j-th device, n represents the number of devices, and γ 1 The coefficient representing the bandwidth demand adjustment weight, N i represents the network bandwidth requirement of device i, β 2 The coefficient representing the CPU resource adjustment weight, C i represents the CPU resources required by device i, α 2 The coefficient representing the signal quality adjustment weight, S i Indicates the signal quality of device i.

[0033] Further, the S4 includes:

[0034] Based on the spectrum resource allocation result, the channel status is monitored and collected to obtain spectrum demand data and channel status data;

[0035] Based on the spectrum demand data, obtaining predicted spectrum demand data through calculation;

[0036] The predicted spectrum demand data and the channel status data are calculated using a weighted allocation algorithm to obtain a spectrum resource optimization result:

[0037]

[0038] in, Indicates the spectrum resource optimization result. represents the spectrum resource weight optimized by device i, represents the spectrum resource weight optimized by device j, T R2 represents the total available spectrum resources of the system, i represents the i-th device, j represents the j-th device, n represents the number of devices, and α 3 The coefficient representing the channel quality adjustment weight, CQIi represents the channel quality of device i, β 3 The coefficient representing the signal-to-noise ratio adjustment weight, SNR i represents the signal-to-noise ratio of device i, γ 3 The coefficient representing the interference intensity adjustment weight, I i Indicates the interference strength of device i.

[0039] Further, the S5 includes:

[0040] Based on the spectrum resource optimization result, the transmission data is cleaned, filtered and compressed using a 5G lightweight terminal to obtain a preprocessing result;

[0041] Using a linear regression algorithm, the preprocessing result is calculated to obtain a fault prediction result;

[0042] Based on the preprocessing results and the fault prediction results, a data flow and coordination mechanism between the 5G lightweight terminal and the electric power Hongmeng operating system is constructed, and the transmission data is summarized and analyzed on a large scale and stored for a long time to obtain the system adaptation results, thereby completing the adaptation of the 5G lightweight terminal and the electric power Hongmeng operating system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0044] Figure 1 It is an exemplary flowchart of a method for adapting a 5G lightweight terminal to the power Hongmeng operating system according to some embodiments of this specification. DETAILED DESCRIPTION

[0045] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0046] Example

[0047] Figure 1 This is an exemplary flow chart of a method for adapting a 5G lightweight terminal to the power Hongmeng operating system according to some embodiments of this specification. Figure 1 As shown, the process includes the following steps. In some embodiments, the process can be executed by a processor.

[0048] S1: Get device-related information of all 5G lightweight terminals in Hongmeng operating system.

[0049] 5G lightweight terminal (5G RedCap terminal) is a terminal device used to realize the interconnection between people, machines and things.

[0050] Device-related information refers to different device information of 5G lightweight terminals. For example, device-related information may include device number, device information, and device characteristics.

[0051] The device number is the number of the 5G lightweight terminal device.

[0052] Device information refers to the hardware capability information of 5G lightweight terminal devices.

[0053] Device characteristics are the processing characteristics of 5G lightweight terminals. For example, device characteristics may include 5G lightweight terminal device type and processing capabilities.

[0054] In some embodiments, the processor can implement S1 based on the following steps: using the lightweight protocol stack in the 5G lightweight terminal to obtain heartbeat signaling; based on the heartbeat signaling, obtaining device-related information of all 5G lightweight terminals in the Hongmeng operating system.

[0055] The lightweight protocol stack is a protocol stack that sends heartbeat signaling once per second.

[0056] In some embodiments, the processor may streamline the structure of the protocol stack, remove redundant communication layers, reduce communication overhead, and obtain a lightweight protocol stack.

[0057] Heartbeat signaling is the signaling used to achieve communication between 5G lightweight terminals and the Hongmeng operating system.

[0058] S2: Process the device-related information using a device enumeration algorithm and an allocation algorithm based on adaptive weights to obtain a computing resource allocation result.

[0059] The device enumeration algorithm is an algorithm used to determine the order in which devices are processed.

[0060] The adaptive weight-based allocation algorithm is an algorithm for adjusting resource allocation weights.

[0061] The computing resource allocation result is the result of the computing resources allocated to each device. For example, the computing resource allocation result may include the device CPU resource allocation result, the device memory resource allocation result, and the device network bandwidth allocation result.

[0062] In some embodiments, the processor may implement S2 based on the following steps.

[0063] S210: Process the device-related information using a device enumeration algorithm to obtain an enumeration allocation result.

[0064] The enumeration allocation result is a result of allocating computing resources to the device based on the device attributes.

[0065] In some embodiments, the processor can implement S210 based on the following steps: use the device number as the hash key and the device information as the hash value to initialize the hash mapping and obtain a mapping result; based on the mapping result, arrange the devices using the corresponding device characteristics to obtain a device processing queue; based on the device processing queue, allocate corresponding computing resources and communication channels based on the device characteristics to obtain an enumeration allocation result.

[0066] The mapping result is used to find and verify the device using the hash value.

[0067] The device processing queue is a queue arranged according to device processing priority.

[0068] In some embodiments, the processor may use the mapping result to arrange the devices based on the device characteristics to obtain a device processing queue.

[0069] In some embodiments, the processor may search through a hash map to find out whether the device already exists, and insert the currently non-existent device into the queue according to priority to obtain a device processing queue.

[0070] In this way, key devices can be accessed and mounted first.

[0071] Computing resources are the resources required by a device to participate in computing. For example, computing resources may include CPU resources and memory resources.

[0072] A communication channel is the network bandwidth over which devices communicate.

[0073] S220: Based on the enumerated allocation result, using an allocation algorithm based on adaptive weights, the allocation strategy is adjusted in real time according to the needs of the device and the network load to obtain a computing resource allocation result.

[0074] In some embodiments, the expression for calculating the resource allocation result may be:

[0075]

[0076] in, Indicates the result of computing resource allocation. represents the computing resource requirement weight of device i, represents the computing resource requirement weight of device j, T r1 represents the total computing resources available to the system, α 1Indicates the weight coefficient of CPU resources, C i represents the CPU resources required by device i, β 1 Represents the weight coefficient of memory resources, M i represents the memory resources required by device i, γ 1 Represents the weight coefficient of network bandwidth demand, N i Represents the network bandwidth requirement of device i, i represents the i-th device, and j represents the j-th device.

[0077] S3: Analyze the computing resource allocation result using the long short-term memory model and resource scheduling strategy to obtain a spectrum resource allocation result.

[0078] In some embodiments, the processor may analyze the computing resource allocation result using a long short-term memory model to obtain a spectrum resource prediction result; based on the spectrum resource prediction result, use a resource scheduling strategy to perform resource allocation to obtain a spectrum resource allocation result.

[0079] The long short-term memory model is an LSTM neural network model.

[0080] The spectrum resource prediction result is the spectrum resource result required by each device in the future.

[0081] In some embodiments, the processor may input the computing resource allocation result into the long short-term memory model, and obtain the spectrum resource prediction result by analyzing the computing resource allocation result.

[0082] In some embodiments, the spectrum resource prediction result may be expressed as:

[0083]

[0084] D i =d i1 , d i2 , d i3 ,…,d in ;

[0085] in, represents the spectrum resource prediction result, f represents the prediction function of the LSTM network, and D i represents the historical resource usage data of device i, t represents time t, and d i1 represents the first historical resource usage data of device i, d i2 represents the second historical resource usage data of device i, d i3 represents the third historical resource usage data of device i, d in represents the nth historical resource usage data of device i; where d i1The first historical resource usage data of device i may be the network bandwidth requirement of device i, d i2 The second historical resource usage data of device i may be the CPU resources required by device i, d i3 The third historical resource usage data of device i may be the signal quality of device i.

[0086] The spectrum resource allocation result is the result of allocating resources based on different weights of spectrum resources.

[0087] In some embodiments, the processor may adjust the allocation of spectrum resources and computing resources in real time according to the prediction results, and use a weighted allocation algorithm to allocate limited resources according to the priority and needs of each terminal to obtain a spectrum resource allocation result.

[0088] In some embodiments, the spectrum resource allocation result may be expressed as:

[0089]

[0090] in, Indicates the spectrum resource allocation result, represents the spectrum resource allocation weight of device i, represents the spectrum resource allocation weight of device j, T R1 represents the total resources of the system, i represents the i-th device, j represents the j-th device, n represents the number of devices, and γ 1 The coefficient representing the bandwidth demand adjustment weight, N i represents the network bandwidth requirement of device i, β 2 The coefficient representing the CPU resource adjustment weight, C i represents the CPU resources required by device i, α 2 The coefficient representing the signal quality adjustment weight, S i Indicates the signal quality of device i.

[0091] S4: adjusting the spectrum resource allocation result, performing channel optimization and signal enhancement, and obtaining a spectrum resource optimization result.

[0092] The spectrum resource optimization result is the result of optimizing the spectrum resource allocation based on the score.

[0093] In some embodiments, the processor can implement S4 based on the following steps: based on the spectrum resource allocation result, monitor and collect the channel status to obtain spectrum demand data and channel status data; based on the spectrum demand data, obtain predicted spectrum demand data through calculation; use a weighted allocation algorithm to calculate the predicted spectrum demand data and the channel status data to obtain a spectrum resource optimization result.

[0094] The spectrum demand data is data reflecting the spectrum demand of each device at the current moment and over a period of time in the past.

[0095] Channel state data is data that reflects the communication quality of a device. For example, channel state data may include channel quality index scores, signal-to-noise ratios, and interference measurements, where the channel quality index scores range from 0 to 15.

[0096] The signal-to-noise ratio is the ratio of the signal strength to the noise level.

[0097] In some embodiments, the expression of the signal-to-noise ratio may be:

[0098]

[0099] Among them, SNR (dB) represents the signal-to-noise ratio, P signal Represents the signal power, P noise Represents the noise power.

[0100] The interference measurement is the strength of interference on adjacent frequency bands.

[0101] The predicted spectrum demand data is data that reflects the spectrum demand of various devices over a period of time in the future.

[0102] In some embodiments, the expression for predicting spectrum demand data may be:

[0103]

[0104] in, represents the predicted spectrum demand data, f represents the prediction function of the LSTM network, X t represents the current spectrum demand, c represents, φ represents the weight of historical spectrum demand data, X t-1 represents the historical spectrum demand data at time t-1, X t-2 It shows the historical spectrum demand data at time t-2. represents the error term.

[0105] In some embodiments, the processor may calculate the predicted spectrum demand data and the channel status data using a weighted allocation algorithm based on the channel quality and interference level of each terminal to obtain a spectrum resource optimization result.

[0106] In this way, spectrum resources can be allocated to terminal devices with better channel quality, thereby improving the overall signal-to-noise ratio.

[0107] In some embodiments, the spectrum resource optimization result may be expressed as:

[0108]

[0109] in, Indicates the spectrum resource optimization result. represents the spectrum resource weight optimized by device i, represents the spectrum resource weight optimized by device j, T R2 represents the total available spectrum resources of the system, i represents the i-th device, j represents the j-th device, n represents the number of devices, and α 3 The coefficient representing the channel quality adjustment weight, CQI i represents the channel quality of device i, β 3 The coefficient representing the signal-to-noise ratio adjustment weight, SNR i represents the signal-to-noise ratio of device i, γ 3 The coefficient representing the interference intensity adjustment weight, I i Indicates the interference strength of device i.

[0110] S5: Based on the spectrum resource optimization results, the 5G lightweight terminal is used to perform adaptation optimization processing and fault prediction on the transmission data to obtain the system adaptation results, and complete the adaptation of the 5G lightweight terminal and the power Hongmeng operating system.

[0111] The transmitted data is the communication data between the 5G lightweight terminal and the Hongmeng operating system.

[0112] The system adaptation result reflects the final allocation of computing resources and spectrum resources by the Hongmeng operating system to 5G lightweight terminals.

[0113] In some embodiments, the processor can implement S5 based on the following steps: based on the spectrum resource optimization results, use the 5G lightweight terminal to clean, filter and compress the transmission data to obtain a preprocessing result; use a linear regression algorithm to calculate the preprocessing result to obtain a fault prediction result; based on the preprocessing result and the fault prediction result, construct a data flow and coordination mechanism between the 5G lightweight terminal and the electric power Hongmeng operating system, perform large-scale aggregation analysis and long-term storage on the transmission data, obtain a system adaptation result, and complete the adaptation of the 5G lightweight terminal and the electric power Hongmeng operating system.

[0114] The preprocessing result is the result of the preliminary processing of the transmission data by the 5G lightweight terminal.

[0115] In some embodiments, the 5G lightweight terminal can perform basic processing such as cleaning, filtering, and compression of a portion of the transmitted data locally to obtain preprocessing results.

[0116] In some embodiments, the expression of the preprocessed data size may be:

[0117] D processed =α 4 ×Doriginal ;

[0118] Among them, D processed represents the size of the data after preprocessing, α 4 Indicates the compression ratio (the value ranges from 0.1 to 0.3), D original Indicates the original data size.

[0119] In this way, for tasks that require high real-time processing (such as transient data analysis or equipment status monitoring in the power grid), the system can distribute processing tasks to terminal devices or edge nodes close to the terminal through edge computing. This can reduce latency and ensure that critical data can be responded to quickly.

[0120] The fault prediction result is a result that reflects the probability of failure after the preprocessing result is transmitted.

[0121] In some embodiments, the processor may use a linear regression algorithm to find the best fitting straight line by minimizing the error between the predicted value and the true value of the preprocessing result to obtain a fault prediction result; wherein w is the data weight and b is the bias term.

[0122] In some embodiments, the expression of the fault prediction result may be:

[0123] Y=W T X+b;

[0124] Among them, Y represents the fault prediction result, W T represents the data weight, X represents the pre-processing result, and b represents the bias term.

[0125] In some embodiments, the processor can build a data flow and coordination mechanism between the 5G lightweight terminal and the power Hongmeng operating system based on the preprocessing results and the fault prediction results, and perform large-scale summary analysis and long-term storage of the transmitted data to obtain system adaptation results. For example, for tasks that require high real-time processing (such as transient data analysis or equipment status monitoring in the power grid), the processor distributes the processing tasks to the terminal device or the edge node close to the terminal through edge computing, and establishes a data flow and coordination mechanism between the terminal and the central server through the edge and center collaborative processing mechanism. The preprocessed data or analysis results can be transmitted in real time or in batches to the central server for large-scale summary analysis or long-term storage; among them, real-time data transmission includes the immediate transmission of key data on the terminal side to the central server, and batch data transmission includes the batch transmission of non-urgent data.

[0126] In this way, latency can be reduced and critical data can be responded to quickly, reducing frequent network communications.

[0127] In some embodiments of this specification, the adaptation method of 5G lightweight terminal and power Hongmeng operating system is realized through simplification of protocol stack, automatic mounting and enumeration of devices, dynamic resource scheduling, channel optimization, and edge computing processing. In view of the needs of low-power devices, the protocol stack design is optimized to reduce communication overhead; at the same time, the efficiency of concurrent access of multiple devices is improved through automated device mounting and resource allocation mechanism.

Claims

1. A method for adapting a 5G lightweight terminal to an electric Hongmeng operating system, characterized in that: include: S1: Obtain device-related information of all 5G lightweight terminals in the Hongmeng operating system; S2: using a device enumeration algorithm and an allocation algorithm based on adaptive weights to process the device-related information and obtain a computing resource allocation result; S3: Analyze the computing resource allocation result by using the long short-term memory model and the resource scheduling strategy to obtain a spectrum resource allocation result; S4: adjusting the spectrum resource allocation result, performing channel optimization and signal enhancement, and obtaining a spectrum resource optimization result; S5: Based on the spectrum resource optimization results, the 5G lightweight terminal is used to perform adaptation optimization processing and fault prediction on the transmission data to obtain the system adaptation results, and complete the adaptation of the 5G lightweight terminal and the power Hongmeng operating system.

2. The method for adapting the 5G lightweight terminal to the power Hongmeng operating system according to claim 1 is characterized in that: The S1 includes: Use the lightweight protocol stack in the 5G lightweight terminal to obtain the heartbeat signaling; Based on the heartbeat signaling, obtain device-related information of all 5G lightweight terminals in the Hongmeng operating system.

3. The method for adapting the 5G lightweight terminal to the power Hongmeng operating system according to claim 1 is characterized in that: The S2 includes: S210: Process the device-related information using a device enumeration algorithm to obtain an enumeration allocation result; wherein the device number is used as a hash key and the device information is used as a hash value to initialize a hash mapping to obtain a mapping result; Based on the mapping result, the devices are arranged using corresponding device characteristics to obtain a device processing queue; Based on the device processing queue, corresponding computing resources and communication channels are allocated based on device characteristics to obtain an enumeration allocation result; wherein the device number, the device information and the device characteristics belong to the device related information; S220: Based on the enumerated allocation result, using an allocation algorithm based on adaptive weights, the allocation strategy is adjusted in real time according to the needs of the device and the network load to obtain a computing resource allocation result.

4. The method for adapting the 5G lightweight terminal to the power Hongmeng operating system according to claim 3 is characterized in that: The expression of the computing resource allocation result is: in, Indicates the result of computing resource allocation. represents the computing resource requirement weight of device i, represents the computing resource requirement weight of device j, T r1 represents the total computing resources available to the system, α1 represents the weight coefficient of CPU resources, and C i represents the CPU resources required by device i, β1 represents the weight coefficient of memory resources, M i represents the memory resources required by device i, γ1 represents the weight coefficient of network bandwidth requirement, N i Represents the network bandwidth requirement of device i, i represents the i-th device, and j represents the j-th device.

5. The method for adapting the 5G lightweight terminal to the power Hongmeng operating system according to claim 1 is characterized in that: The S3 includes: The calculation resource allocation result is analyzed using the long short-term memory model to obtain the spectrum resource prediction result: D i =d i1 ,d i2 ,d i3 ,…,d in ; in, represents the spectrum resource prediction result, f represents the prediction function of the LSTM network, and D i represents the historical resource usage data of device i, t represents time t, and d i1 represents the first historical resource usage data of device i, d i2 represents the second historical resource usage data of device i, d i3 represents the third historical resource usage data of device i, d in Indicates the nth historical resource usage data of device i; Based on the spectrum resource prediction result, a resource scheduling strategy is used to allocate resources, and a spectrum resource allocation result is obtained: IN i 2 =γ1×N i +β2×C i +α2×S i ; in, represents the spectrum resource allocation result, W 2 i represents the spectrum resource allocation weight of device i, represents the spectrum resource allocation weight of device j, T R1 represents the total resources of the system, i represents the i-th device, j represents the j-th device, n represents the number of devices, γ1 represents the coefficient of bandwidth demand adjustment weight, N i represents the network bandwidth requirement of device i, β2 represents the coefficient of CPU resource adjustment weight, C i represents the CPU resources required by device i, α2 represents the coefficient of signal quality adjustment weight, S i Indicates the signal quality of device i.

6. The method for adapting the 5G lightweight terminal to the power Hongmeng operating system according to claim 1 is characterized in that: The S4 includes: Based on the spectrum resource allocation result, the channel status is monitored and collected to obtain spectrum demand data and channel status data; Based on the spectrum demand data, obtaining predicted spectrum demand data through calculation; The predicted spectrum demand data and the channel status data are calculated using a weighted allocation algorithm to obtain a spectrum resource optimization result: IN i 3 =α3×CQI i +β3×SNR i -γ3I i ; in, represents the spectrum resource optimization result, W i 3 represents the spectrum resource weight optimized by device i, represents the spectrum resource weight optimized by device j, T R2 represents the total available spectrum resources of the system, i represents the i-th device, j represents the j-th device, n represents the number of devices, α3 represents the coefficient of the channel quality adjustment weight, CQI i represents the channel quality of device i, β3 represents the coefficient of signal-to-noise ratio adjustment weight, SNR i represents the signal-to-noise ratio of device i, γ3 represents the coefficient of interference intensity adjustment weight, I i Indicates the interference strength of device i.

7. The method for adapting the 5G lightweight terminal to the power Hongmeng operating system according to claim 1 is characterized in that: The S5 includes: Based on the spectrum resource optimization result, the transmission data is cleaned, filtered and compressed using a 5G lightweight terminal to obtain a preprocessing result; Using a linear regression algorithm, the preprocessing result is calculated to obtain a fault prediction result; Based on the preprocessing results and the fault prediction results, a data flow and coordination mechanism between the 5G lightweight terminal and the electric power Hongmeng operating system is constructed, and the transmission data is summarized and analyzed on a large scale and stored for a long time to obtain the system adaptation results, thereby completing the adaptation of the 5G lightweight terminal and the electric power Hongmeng operating system.

Images