Satellite edge computing-based resource allocation strategy generation method, device and equipment

Abstract

The application discloses a resource allocation strategy generation method, device and equipment based on satellite edge computing, which is applied to a satellite-ground hybrid edge computing system and comprises the following steps: calculating the signal-to-noise ratio, decoding rate, transmission data volume and data transmission energy consumption of signal transmission between a satellite and a user terminal according to unloading decision parameters, and calculating the time slot calculation task volume and time slot calculation energy consumption; calculating the total time slot energy consumption based on the data transmission energy consumption and the time slot calculation energy consumption, and constructing an average energy consumption objective function; constructing a target optimization model by using the Lyapunov algorithm in combination with the average energy consumption objective function and decision constraints; and obtaining a target resource allocation strategy by performing hierarchical decision solving on the target optimization model based on a Markov decision and an SCA algorithm. The application can solve the technical problem that the existing technology does not comprehensively consider factors such as task scheduling, resource allocation, communication link state, user heterogeneous characteristics and system multiple index performances, so that the actual resource allocation lacks accuracy, reliability and applicability.

Description

Technical Field

[0001] The present application relates to the field of distributed computing technology, and in particular to a method, device and equipment for generating a resource allocation strategy based on satellite edge computing. Background Art

[0002] Although some connected devices are equipped with powerful central processing units (CPUs), they still cannot handle the demands of computationally intensive tasks. Therefore, efficiently utilizing computing resources has become a major challenge in today's network technology. Cloud computing, as a centralized computing model, provides crucial support for connected devices through its powerful computing capabilities and on-demand resource provisioning. However, this model also suffers from drawbacks such as high latency, high energy consumption, data security risks, and a poor user experience. This has led to the development of an extended computing model for cloud computing: edge computing (EC).

[0003] Edge computing significantly reduces transmission latency and energy consumption, improving service quality by bringing computing resources to the edge of the network, closer to the user. Because ground-based edge computing has limited coverage and is susceptible to disasters, Low Earth Orbit (LEO) satellites and spaceborne edge computing offer advantages. They can seamlessly cover a large area of ​​users, and distributed data processing on satellite edge servers further disperses information, making attacks more difficult. Furthermore, they enable collaborative satellite-ground collaboration and dynamic task allocation.

[0004] However, current edge computing on low-orbit satellites (LEOs) still has shortcomings. For example, it independently handles task scheduling and resource allocation, and fails to consider the coupling effect between the two, resulting in low overall system performance and insufficient resource utilization. It also fails to consider heterogeneous characteristics such as communication conditions between user terminals, resulting in resource allocation that is not objective and reliable enough. In addition, most existing technologies optimize a single goal, which is bound to ignore other system performance, resulting in a lack of accuracy in the overall resource allocation of the system. Furthermore, current technologies cannot adapt to complex scenarios where both communication link status and resource allocation change, so their applications are limited and it is difficult to meet actual application needs. Summary of the Invention

[0005] This application provides a resource allocation strategy generation method, device and equipment based on satellite edge computing, which is used to solve the technical problem that the existing technology does not comprehensively consider factors such as task scheduling, resource allocation, communication link status, user heterogeneity characteristics and multiple system performance indicators, resulting in the lack of accuracy, reliability and applicability of actual resource allocation.

[0006] In view of this, the first aspect of this application provides a resource allocation strategy generation method based on satellite edge computing, which is applied to a satellite-ground hybrid edge computing system, including:

[0007] Determine the decision of the user terminal computing task based on the communication resource allocation strategy and the task offloading strategy, and obtain the offloading decision parameter;

[0008] Calculating the signal-to-noise ratio, decoding rate, transmission data volume, and data transmission energy consumption of satellite and user terminal signal transmission based on the offloading decision parameters;

[0009] Calculating the time slot computing task amount and time slot computing energy consumption of the user terminal and the satellite respectively according to the offloading decision parameter and the actual computing capacity, wherein the actual computing capacity includes the user computing capacity and the satellite computing capacity;

[0010] Calculating the total energy consumption of a time slot based on the data transmission energy consumption and the time slot calculation energy consumption, and constructing an average energy consumption objective function according to the total energy consumption of the time slot;

[0011] Constructing multiple decision constraints based on the offloading decision parameters, the actual computing capacity, the dynamic evolution state of the queue, the amount of queue task discards, the data transmission power, and the decoding sorting variable;

[0012] After constructing an initial queue energy consumption optimization model by combining the average energy consumption objective function and the decision constraints, the initial queue energy consumption optimization model is simplified using the Lyapunov algorithm to obtain a target optimization model;

[0013] The target optimization model is solved by hierarchical decision making based on Markov decision making and SCA algorithms to obtain a target resource allocation strategy.

[0014] Preferably, the process of determining the decision of the user terminal computing task based on the communication resource allocation strategy and the task offloading strategy to obtain the offloading decision parameter further includes:

[0015] Dynamic communication resource allocation strategy, task offloading strategy and computing resource allocation strategy are formulated according to the mobility of user terminals, task requirements and link status.

[0016] Preferably, the calculating of the signal-to-noise ratio, decoding rate, transmission data volume, and data transmission energy consumption of the satellite and user terminal signal transmission based on the offloading decision parameters includes:

[0017] Calculating the signal-to-noise ratio of each signal sent from the user terminal to the satellite based on the offloading decision parameter, the channel model, and the data transmission power;

[0018] Calculating a decoding rate of the information stream based on the signal-to-noise ratio and the total system bandwidth;

[0019] Calculating the transmission data volume of the information flow according to the decoding rate and the task transmission time;

[0020] The time slot transmission energy consumption of the user terminal is calculated in combination with the offloading decision parameter and the data transmission power to obtain the data transmission energy consumption.

[0021] Preferably, the calculating of the signal-to-noise ratio, decoding rate, transmission data volume and data transmission energy consumption of the satellite and user terminal signal transmission based on the offloading decision parameters further includes:

[0022] The RSMA technology is used to send the information flow of the user terminal to the satellite for calculation according to the transmission data volume and the data transmission energy consumption;

[0023] The satellite decodes the received information stream and allocates computing resources based on SIC technology and computing resource allocation strategy.

[0024] Preferably, the calculating the time slot computing task amount and time slot computing energy consumption of the user terminal and the satellite respectively based on the offloading decision parameter and the actual computing capacity includes:

[0025] Calculating the computing task amount of the user terminal according to the offloading decision parameter and the user computing capability to obtain the user computing task amount;

[0026] Calculating the computing energy consumption of the user terminal according to the offloading decision parameter, the user computing capability and the transmission computing time to obtain the user computing energy consumption;

[0027] Calculating a satellite computing task volume according to the satellite computing capability and the satellite processing density to obtain the satellite computing task volume;

[0028] Calculating the satellite computing energy consumption according to the satellite computing capability and the satellite computing time to obtain the satellite computing energy consumption;

[0029] The user computing task amount and the satellite computing task amount constitute a time slot computing task amount;

[0030] The user computing energy consumption and the satellite computing energy consumption constitute the time slot computing energy consumption.

[0031] Preferably, the multiple decision constraints are constructed based on the offloading decision parameters, the actual computing capacity, the dynamic evolution state of the queue, the amount of queue task discards, the data transmission power, and the decoding sorting variable, and the above also includes:

[0032] Calculating a user dynamic evolution state of a user terminal queue according to the amount of transmitted data, the amount of time slot calculation tasks, and the amount of time slot task arrivals;

[0033] Calculating the user task discard quantity of the user terminal queue according to the user dynamic evolution state, the time slot task arrival quantity and the user queue upper limit value;

[0034] Calculating a satellite dynamic evolution state of a satellite queue according to the amount of transmitted data and the amount of time slot calculation tasks;

[0035] Calculating the satellite mission discard amount of the satellite queue according to the satellite dynamic evolution state, the transmission data amount and the satellite queue upper limit;

[0036] The user dynamic evolution state and the satellite dynamic evolution state are queue dynamic evolution states;

[0037] The user task discard amount and the satellite task discard amount are queue task discard amounts.

[0038] Preferably, after constructing the initial queue energy consumption optimization model by combining the average energy consumption objective function and the decision constraint condition, the initial queue energy consumption optimization model is simplified using the Lyapunov algorithm to obtain a target optimization model, including:

[0039] Constructing an initial queue energy consumption optimization model in combination with the average energy consumption objective function and the decision constraints;

[0040] Defining a virtual packet loss queue according to the queue task discard amount;

[0041] A Lyapunov function is defined according to the virtual packet loss queue and the dynamic evolution state of the queue using a Lyapunov algorithm;

[0042] Defining a drift penalty term according to the Lyapunov function, the total energy consumption of the time slot and an energy consumption weight parameter;

[0043] The drift penalty term is minimized and optimized through a defined queue stability cost function, and the initial queue energy consumption optimization model is simplified into a target optimization model.

[0044] Preferably, the target optimization model is subjected to hierarchical decision solving based on Markov decision and SCA algorithms to obtain a target resource allocation strategy, including:

[0045] Dividing the target optimization model into an upper-layer optimization model and a lower-layer optimization model according to the hierarchical reinforcement learning method guided by the Lyapunov algorithm;

[0046] Based on the Markov decision making and the upper-level optimization model, a global queue state space, a global queue action space and a global queue reward function are defined to obtain an upper-level queue stable decision model;

[0047] An extended SCA algorithm is used to optimize and solve the upper-layer queue stability decision model to obtain an offloading strategy, a transmit power allocation strategy, and a decoding strategy;

[0048] Based on the Markov decision making and the lower-level optimization model, a local queue state space, a local queue action space, and a local queue reward function are defined to obtain a lower-level queue stable decision model;

[0049] A standard SCA algorithm is used to optimize and solve the lower-layer queue stability decision model to obtain a computing resource allocation strategy, wherein the computing resource allocation strategy includes a user computing resource allocation strategy and a satellite computing resource allocation strategy;

[0050] The target resource allocation strategy includes the offloading strategy, the transmit power allocation strategy, the decoding strategy and the computing resource allocation strategy.

[0051] The second aspect of the present application provides a resource allocation strategy generation device based on satellite edge computing, which is applied to a satellite-ground hybrid edge computing system, including:

[0052] An offloading decision determination unit, configured to determine a decision on a computing task of a user terminal based on a communication resource allocation strategy and a task offloading strategy, and obtain an offloading decision parameter;

[0053] a transmission parameter calculation unit, configured to calculate the signal-to-noise ratio, decoding rate, transmission data volume, and data transmission energy consumption of signal transmission between the satellite and the user terminal according to the offloading decision parameters;

[0054] a task processing analysis unit, configured to calculate the time slot computing task amount and time slot computing energy consumption of the user terminal and the satellite respectively according to the offloading decision parameter and the actual computing capacity, wherein the actual computing capacity includes the user computing capacity and the satellite computing capacity;

[0055] an energy consumption target construction unit, configured to calculate the total energy consumption of a time slot based on the data transmission energy consumption and the time slot calculation energy consumption, and to construct an average energy consumption target function according to the total energy consumption of the time slot;

[0056] A constraint condition construction unit, configured to construct a plurality of decision constraint conditions based on the offloading decision parameter, the actual computing capacity, the dynamic evolution state of the queue, the amount of queue task discards, the data transmission power, and the decoding sorting variable;

[0057] a model optimization construction unit, configured to construct an initial queue energy consumption optimization model by combining the average energy consumption objective function and the decision constraint condition, and then simplify the initial queue energy consumption optimization model using a Lyapunov algorithm to obtain a target optimization model;

[0058] The model optimization solving unit is used to perform hierarchical decision solving on the target optimization model based on Markov decision and SCA algorithm to obtain the target resource allocation strategy.

[0059] The third aspect of the application provides a satellite edge computing-based resource allocation strategy generation device, the device comprising a processor and a memory;

[0060] The memory is configured to store program code and transmit the program code to the processor;

[0061] The processor is configured to execute the satellite edge computing-based resource allocation strategy generation method according to the instructions in the program code.

[0062] From the above technical solutions, it can be seen that the embodiments of the application have the following advantages:

[0063] In the application, a satellite edge computing-based resource allocation strategy generation method is provided, which is applied to a star-ground hybrid edge computing system, and comprises the following steps: determining a decision of a user terminal computing task based on a communication resource allocation strategy and a task offloading strategy, to obtain offloading decision parameters; calculating a signal-to-noise ratio, a decoding rate, a transmission data volume and a data transmission energy consumption of signal transmission between a satellite and a user terminal according to the offloading decision parameters; calculating a time slot computing task volume and a time slot computing energy consumption of the user terminal and the satellite respectively according to the offloading decision parameters and actual computing capabilities, wherein the actual computing capabilities comprise user computing capabilities and satellite computing capabilities; calculating a total time slot energy consumption based on the data transmission energy consumption and the time slot computing energy consumption, and constructing an average energy consumption target function according to the total time slot energy consumption; constructing a plurality of decision constraint conditions according to the offloading decision parameters, the actual computing capabilities, a queue dynamic evolution state, a queue task discard volume, a data transmission power and a decoding order variable; after constructing an initial queue energy consumption optimization model by combining the average energy consumption target function and the decision constraint conditions, simplifying the initial queue energy consumption optimization model by using a Lyapunov algorithm to obtain a target optimization model; and performing hierarchical decision solving on the target optimization model based on a Markov decision and an SCA algorithm, to obtain a target resource allocation strategy.

[0064] The satellite edge computing-based resource allocation strategy generation method provided by the application can not only determine whether the computing task is left in local computing or offloaded to the satellite for edge computing according to the offloading decision parameter, but also calculate some transmission parameters of the user terminal signal, such as signal-to-noise ratio; this process fully considers the heterogeneous characteristics of the user terminal, so that the computing resource allocation operation based thereon is more in line with the actual situation. Moreover, the total time slot energy consumption caused by the task scheduling is calculated by considering various performance parameters of the user terminal and the satellite, and the average energy consumption objective function is constructed based thereon, which considers the energy consumption optimization problem of the system; the queue stability optimization problem is fully considered by configuring the decision constraint condition according to the queue dynamic evolution state and the task discard amount; the communication link dynamic change and time-varying characteristics of resource allocation are considered by configuring the decision constraint condition according to the actual computing capacity, data transmission power and decoding order variable; in addition, the process of optimizing the model by using the Lyapunov algorithm and then solving can balance multiple optimization objectives to achieve the optimal solution, and can also adapt to the calculation of multiple formats of data in the target optimization model; the multi-stage optimization problem of dynamic link state and resource allocation can also be optimized and solved, which is suitable for complex scene changes. The entire process comprehensively considers the influence among various situations, multiple parameters and multiple optimization objectives of the edge computing system, and can obtain an accurate and reliable resource allocation strategy, which has strong applicability. Therefore, the application can solve the technical problem that the prior art does not comprehensively consider factors such as task scheduling, resource allocation, communication link state, user heterogeneous characteristics and system performance indicators, resulting in lack of accuracy, reliability and applicability of actual resource allocation. BRIEF DESCRIPTION OF DRAWINGS

[0065] Figure 1 A flowchart of the satellite edge computing-based resource allocation strategy generation method provided by the embodiment of the application is shown;

[0066] Figure 2 A structure diagram of the satellite edge computing-based resource allocation strategy generation device provided by the embodiment of the application is shown;

[0067] Figure 3 A structure diagram of the satellite edge computing-based resource allocation strategy generation device provided by the embodiment of the application is shown;

[0068] Figure 4 A diagram of the satellite edge computing-based resource allocation strategy generation device provided by the embodiment of the application is shown;

[0069] Figure 5 A diagram of the satellite edge computing-based resource allocation strategy generation device provided by the embodiment of the application is shown; DETAILED DESCRIPTION

[0070] In order to enable personnel in the technical field to better understand the scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0071] For the convenience of understanding, please refer to Figure 1 The embodiments of the resource allocation strategy generation method based on satellite edge computing provided by the present application are applied to a star-ground hybrid edge computing system, and include the following steps.

[0072] Step 101, determining the decision of the user terminal computing task based on the communication resource allocation strategy and the task offloading strategy, and obtaining the offloading decision parameter.

[0073] Further, step 101 further includes the following steps.

[0074] According to the mobility of the user terminal, the task demand and the link state, a dynamic communication resource allocation strategy, a task offloading strategy and a computing resource allocation strategy are formulated.

[0075] It should be noted that the resource allocation strategy generation method is applied to the star-ground hybrid edge computing system proposed in the present embodiment. The system combines the resources of low earth orbit satellites LEO and ground networks, and improves the resource utilization rate and service quality through collaborative work. Specifically, please refer to Figure 3 The system includes one low earth orbit satellite LEO and N ground user terminal groups GU. The low earth orbit satellite LEO serves as a satellite-borne edge computing node and deploys an edge computing MEC server for processing computing tasks and providing communication services. The ground user terminal groups orthogonally occupy N resource blocks NB, and all users in the group share the same resource block. Due to the heterogeneity of the user terminal, the mobility and the randomness of the task arrival amount, the system exhibits dynamic time-varying characteristics in communication link state and resource allocation.

[0076] The system provided in the present embodiment works in a time slot mode, and the time is expressed as The time slot is The working process of the system can be divided into four stages. In the first stage , the system dynamically formulates a communication resource allocation strategy, a task offloading strategy and a computing resource allocation strategy according to the mobility of the user terminal, the task demand and the link state. In the second stage , the user terminal can transmit and process the computing task according to the communication resource allocation strategy and the task offloading strategy formulated by the system, and can choose to transmit to the low earth orbit satellite LEO or remain on the local device for direct computing. The selection can generate an offloading decision parameter The third stage The satellite LEO and the user terminal allocate computing resources for each user according to the computing resource allocation strategy. The fourth stage The satellite LEO returns the computing result to the device of the user terminal. Since the volume of the computing result is much smaller than the original task data, the time of this stage can be ignored. Moreover, since , are much smaller than and , the case of can be ignored. The above offloading decision parameters represent the parameters of the nth ground user terminal group i user terminal. The number of ground user terminal groups is expressed as Each ground user terminal group includes multiple user terminals, and the number is expressed as The user's computing task message can be divided into information streams, and then transmitted. The offloading decision parameters are expressed as:

[0077]

[0078] Step 102, according to the offloading decision parameters, the signal-to-noise ratio, decoding rate, transmission data volume and data transmission energy of the satellite and user terminal signal transmission are calculated.

[0079] Further, step 102 includes:

[0080] According to the offloading decision parameters, the channel model and the data transmission power, the signal-to-noise ratio of each signal transmitted by the user terminal to the satellite is calculated.

[0081] According to the signal-to-noise ratio and the total bandwidth of the system, the decoding rate of the information stream is calculated.

[0082] According to the decoding rate and the task transmission time, the transmission data volume of the information stream is calculated.

[0083] The time slot transmission energy of the user terminal is calculated in combination with the offloading decision parameters and the data transmission power, and the data transmission energy is obtained.

[0084] Further, step 102 further includes:

[0085] According to the transmission data volume and the data transmission energy, the information stream of the user terminal is sent to the satellite for calculation by using the RSMA technology;

[0086] The received information stream is decoded and computing resources are allocated by the satellite based on the SIC technology and the computing resource allocation strategy.

[0087] It should be noted that in order to alleviate the transmission interference between multiple different user terminals and improve the frequency utilization and system capacity, the embodiment selects the rate splitting multiple access (RSMA) technology to realize the information transmission of the user to the satellite, and the user terminal is configured with a single antenna. The RSMA technology is used to realize the splitting and decoding of the information stream at the physical layer, the information transmission is carried out by sharing the same frequency spectrum resource, so as to alleviate the transmission interference between users and improve the frequency utilization.

[0088] Please refer to Figure 4 , if the transmission signal of the i-th user terminal of the n ground user terminal groups is:

[0089]

[0090] wherein, indicates the data transmission power of the user terminal assigned to the information stream j, is the transmission signal corresponding to the information stream. If the signal received by the satellite LEO is expressed as:

[0091]

[0092] wherein, is an additive white Gaussian noise, is a channel model, which can be expressed as:

[0093]

[0094] wherein, , are the antenna gains of the satellite LEO and the user terminal respectively, is the Rayleigh fading of the complex Gaussian variable, is the shadow fading of the lognormal distribution, is a unit path loss constant, is the path attenuation, is the path loss exponent, is the distance from the user terminal to the satellite LEO in each time slot.

[0095] ​​The satellite LEO uses the serial interference cancellation (SIC) technology to decode the received signal, and then can allocate computing resources to the received computing tasks according to the computing resource allocation strategy. Specifically, the satellite LEO prioritizes a certain information stream for decoding according to the specific decoding strategy, and regards other information streams to be decoded as interference; then removes the influence of the current information stream that has been decoded from the received signal to reduce the interference to subsequent decoding; and then decodes the remaining information streams in turn. This decoding strategy can effectively improve the communication efficiency and decoding accuracy in multi-user terminal scenarios. The decoding strategy is determined by the decoding sorting variable, which is the decoding order, expressed as ,if , represents the signal flow wall Decode first, and on this basis, the signal-to-noise ratio of each signal stream is expressed as :

[0096]

[0097] in, is the variance of Gaussian additive white noise, that is, the noise power, is the offloading decision parameter, indicating that the user chooses to leave the computing task to local computing or offload it to the satellite LEO. , it is left to local calculation, then the signal-to-noise ratio caused by communication is 0, that is, , at this time, the user will not interfere with the transmission operation of other user terminals, that is, the interference is 0, which can be expressed as:

[0098]

[0099] if , which offloads the computational tasks to the satellite LEO computation, then the signal-to-noise ratio of the signal needs to meet the following conditions for correct decoding:

[0100]

[0101] in, The decoding threshold is the minimum signal-to-noise ratio (SINR) required for the system to successfully decode a signal. When the received SINR is greater than or equal to this threshold, the system considers the signal to be correctly decoded.

[0102] Based on the above, the user terminal can be calculated based on the signal-to-noise ratio and the total system bandwidth Information flow Decoding rate:

[0103]

[0104] in, Total bandwidth available for the system, i.e. total bandwidth of the system, Number of ground user terminals, also number of orthogonal shared resource blocks, when the offloading decision parameter Then The decoding rate .

[0105] The total data decoding rate of the user terminal The total data decoding rate of the user terminal

[0106]

[0107] The total data decoding rate of the user terminal

[0108]

[0109] Wherein, The time for the user terminal to send the information stream to the satellite LEO, i.e. mission transmission time. At this time, the user terminal The time slot transmission energy consumption of the time slot The data transmission energy consumption can be expressed as:

[0110]

[0111] Step 103, according to the offloading decision parameter and the actual calculation capacity, respectively calculating the time slot calculation task amount and the time slot calculation energy consumption of the user terminal and the satellite, the actual calculation capacity including the user calculation capacity and the satellite calculation capacity.

[0112] Further, step 103, comprising:

[0113] According to the offloading decision parameter and the user calculation capacity, calculating the calculation task amount of the user terminal, obtaining the user calculation task amount;

[0114] According to the offloading decision parameter, the user calculation capacity and the transmission calculation time, calculating the calculation energy consumption of the user terminal, obtaining the user calculation energy consumption;

[0115] According to the satellite calculation capacity and the satellite processing density, calculating the calculation task amount of the satellite, obtaining the satellite calculation task amount;

[0116] According to the satellite calculation capacity and the satellite calculation time, calculating the calculation energy consumption of the satellite, obtaining the satellite calculation energy consumption;

[0117] The user calculation task amount and the satellite calculation task amount constitute the time slot calculation task amount;

[0118] The user calculation energy consumption and the satellite calculation energy consumption constitute the time slot calculation energy consumption.

[0119] It should be noted that this embodiment takes into account both local computing and satellite edge computing, so the local computing mode and satellite edge computing mode should be divided into analysis during the calculation and analysis process. , then the user terminal The computing tasks are calculated locally, and the actual computing power allocated by the user is the user computing power. The computing power of the user in a time slot is expressed as , the unit is cycles / s, the maximum value of the user's computing power is expressed as Then the user terminal In the time slot The amount of user computing tasks can be expressed as:

[0120]

[0121] in, The processing density of the user's CPU is in cycles / bit. The decision transmission time of information, The sum of the two represents the local processing transmission calculation time. In the time slot The user computing energy consumption is expressed as:

[0122]

[0123] in, For user terminals The CPU effective energy coefficient.

[0124] like , then the user terminal The calculation task is calculated in the satellite LEO, then the satellite LEO is in the time slot The amount of satellite computing tasks processed is expressed as:

[0125]

[0126] in, Assigned to user terminals for satellite LEO The actual computing power of the satellite, that is, the computing power of the satellite, can be expressed as , is the CPU processing density of satellite LEO, that is, satellite processing density. The satellite computing energy consumption is expressed as:

[0127]

[0128] in, CPU effective energy coefficient of the satellite LEO.

[0129] Step 104, calculate the total energy consumption of the time slot based on the data transmission energy consumption and the time slot calculation energy consumption, and construct an average energy consumption objective function according to the total energy consumption of the time slot.

[0130] The time slot calculation energy consumption includes user calculation energy consumption and satellite calculation energy consumption , and the data transmission energy consumption is expressed as Therefore, the user terminal in the time slot The system time slot energy consumption is expressed as:

[0131]

[0132] Therefore, the system in the time slot The total energy consumption of the time slot of the ground user terminal group n is expressed as:

[0133]

[0134] Therefore, the total energy consumption of the time slot of the system in the time slot can be expressed as:

[0135]

[0136] In order to be able to carry out joint optimization based on energy consumption optimization subsequently, the embodiment takes the minimization of the long-term average total energy consumption of the system as the optimization target, and further constructs an average energy consumption objective function:

[0137]

[0138] Step 105, construct multiple decision constraints according to the offloading decision parameters, actual calculation capacity, queue dynamic evolution state, queue task discard amount, data transmission power, and decoding order variable.

[0139] Further, step 105 further includes:

[0140] Calculate the user dynamic evolution state of the user terminal queue according to the transmission data amount, time slot calculation task amount and time slot task arrival amount;

[0141] Calculate the user task discard amount of the user terminal queue according to the user dynamic evolution state, time slot task arrival amount and user queue upper limit value;

[0142] Calculate the satellite dynamic evolution state of the satellite queue according to the transmission data amount and time slot calculation task amount;

[0143] Calculate the satellite task discard amount of the satellite queue according to the satellite dynamic evolution state, transmission data amount and satellite queue upper limit value;

[0144] The user dynamic evolution state and the satellite dynamic evolution state are the queue dynamic evolution state;

[0145] The user task discard amount and the satellite task discard amount are the queue task discard amount.

[0146] It should be noted that, in order to construct the optimization model, the corresponding decision constraint condition also needs to be configured for the average energy consumption target function, so as to meet the joint optimization demand. The joint optimization needs to consider the factors such as offloading decision, decoding strategy, transmission power allocation and computing resource, and therefore, in order to guarantee the stability of the long-term task queue, improve the computing efficiency and reduce the system energy consumption, the decision constraint condition needs to be constructed according to the offloading decision parameter, the actual computing capacity, the queue dynamic evolution state, the queue task discard amount, the data transmission power, the decoding order variable and other parameters.

[0147] Among the above factors, the queue dynamic evolution state and the queue task discard amount can reflect the state of the system queue, and the decision constraint condition configured according to the queue parameters can make the system optimization model consider the queue stability problem and the system energy consumption problem at the same time, and through the solution scheme, the two can be optimized and balanced well, so as to achieve the optimal state.

[0148] The user terminal and the satellite LEO are both provided with a task queue for storing the arrived computing tasks and tracking the dynamic state. The user side task queue is mainly used for storing the random computing tasks generated in each time slot, and the computing tasks generated by the user at the beginning of each time slot need to meet the independent and identically distributed (i.i.d) and the second-order distance bound, and the distribution needs to meet:

[0149]

[0150] The user task queue is represented as , wherein the user terminal The user dynamic evolution state is expressed as:

[0151]

[0152] , wherein is the time slot task arrival amount of each time slot, represents the output task amount of the user terminal queue, mainly includes two parts, i.e. the local user computing task amount and the transmission data amount offloaded to the satellite LEO ; therefore, the following can be obtained:

[0153]

[0154] User terminal User queue upper limit value is recorded as Tasks exceeding the queue upper limit will be discarded, so the user task discard amount is expressed as:

[0155]

[0156] Wherein, The maximum task discard tolerance of the user terminal .

[0157] The satellite side allocates a management task queue for each user terminal, which can also be called a satellite task queue, which is specifically expressed as The satellite LEO manages the user terminal The satellite queue evolution state, that is, the satellite dynamic evolution state, is expressed as:

[0158]

[0159] Wherein, The amount of information sent by the user terminal , that is, the transmission data amount, the output task amount is the satellite computing task amount of the satellite task queue So we know The satellite queue upper limit value managed by the satellite LEO is Tasks exceeding the upper limit value will be discarded, so the satellite task discard amount is expressed as:

[0160]

[0161] Wherein, The maximum task discard tolerance of the satellite LEO.

[0162] After the above calculation, the decision constraint conditions can be constructed according to the unloading decision parameters, actual computing capacity, queue dynamic evolution state, queue task discard amount, data transmission power, decoding order variable and other parameters. Specifically, the unloading decision parameters need to be limited to 0 / 1 binary variables; the actual computing capacity allocated by the user side and the satellite side needs to be not greater than the maximum computing capacity; the allocated data transmission power cannot exceed the maximum power; the decoding order variable needs to be in discrete form.

[0163] The constraint condition constructed according to the queue dynamic evolution state and the queue task discard amount is mainly to ensure that the queue is strongly stable and the number of discarded packets is not too large. Specifically, according to the queue dynamic evolution state of the user and the satellite, the queue length can be limited to not grow indefinitely. Under this constraint, each received data packet will be processed within a limited queuing delay, thereby realizing the long-term stability of the data queue. This queue stability not only ensures that the backlog of each task queue always remains within a limited range, avoiding exceeding its specified capacity, but also ensures that tasks can be processed within a limited time, meeting the system quality of service (QoS) requirements. According to the queue task discard amount, the number of discarded packets can be limited to not exceed a specified threshold.

[0164] Step 106, after constructing the initial queue energy consumption optimization model combining the average energy consumption objective function and the decision constraint condition, a Lyapunov algorithm is used to simplify the initial queue energy consumption optimization model to obtain a target optimization model.

[0165] Further, step 106 includes:

[0166] combining the average energy consumption objective function and the decision constraint condition to construct an initial queue energy consumption optimization model;

[0167] defining a virtual packet discard queue according to the queue task discard amount;

[0168] defining a Lyapunov function according to the virtual packet discard queue and the queue dynamic evolution state using a Lyapunov algorithm;

[0169] defining a drift penalty term according to the Lyapunov function, the total energy consumption of the time slot, and the energy consumption weight parameter;

[0170] minimizing and optimizing the drift penalty term through the defined queue stability cost function, and simplifying the initial queue energy consumption optimization model to a target optimization model.

[0171] By combining the above average energy consumption objective function and the configuration of the decision constraint condition, the initial queue energy consumption optimization model can be expressed as:

[0172]

[0173] wherein, is the maximum data transmission power that can be allocated.

[0174] Since the initial queue energy consumption optimization model contains binary variables and continuous variables, it is a long-term stochastic mixed integer nonlinear programming problem, and the model problem will only be more complex and difficult to solve due to the dynamic and stochastic nature of the environment. Therefore, the embodiment proposes to use Lyapunov algorithm to simplify the initial queue energy consumption optimization model, or in other words, to transform the solution problem of the model into a series of deterministic optimization problems for each time slot, thereby reducing the solution complexity and making it adaptable to the dynamically changing environment.

[0175] Still divided into local computing of user terminals and satellite edge computing, virtual packet loss queues can be defined according to the respective queue task discard amount, and then the user terminals The user virtual packet loss queue at time slot t is expressed as:

[0176]

[0177] The satellite virtual packet loss queue at time slot t of the satellite LEO is expressed as:

[0178]

[0179] The two virtual packet loss queues can be used to forcibly guarantee the packet loss limits on the user side and the satellite side.

[0180] The total queue can be expressed as:

[0181]

[0182] And the queue within each group of ground user terminals is expressed as:

[0183]

[0184] Among them, the user side queue is expressed as:

[0185]

[0186] The satellite side queue is expressed as:

[0187]

[0188] Lyapunov function can be defined as:

[0189]

[0190] The conditional Lyapunov drift can be written as:

[0191]

[0192] Assuming that the current system queue state in the time slot is The drift is then the expected change of the function over a time slot, so the Lyapunov drift The weighted drift penalty term is then given by:

[0193]

[0194] wherein is a weight parameter that emphasizes the importance of system energy consumption, denoted as energy weight parameter, which can be used to control the balance between system energy consumption and queue stability.

[0195] The upper bound of the right side of the drift penalty term can be optimized:

[0196]

[0197] wherein is a constant, expressed as:

[0198]

[0199] wherein For the nth group of user terminals, the user-side queue constant is:

[0200]

[0201] The satellite-side queue constant is:

[0202]

[0203] The queue stability cost function is defined as:

[0204]

[0205] wherein

[0206]

[0207] The user-side queue stability cost function is:

[0208]

[0209] The satellite-side queue stability cost function is:

[0210]

[0211] By minimizing the drift penalty term, the system congestion can be effectively controlled and the queue state can be stabilized, thereby reducing the amount of tasks waiting in the buffer, helping to maintain a low level of task backlog, and minimizing task delay. Through the above optimization, the solution problem of the initial queue energy consumption optimization model is converted to the solution of the following objective optimization model:

[0212]

[0213] To achieve a closer optimal solution to the initial queue energy consumption optimization model, the model requires more time to meet the average energy consumption constraint. Furthermore, a larger V value increases the system's ability to achieve lower average energy consumption. The target optimization model is suitable for dynamic optimization of each time slot and does not require prior knowledge of the environment or rely on the probability distribution of random events.

[0214] Step 107: Perform hierarchical decision solving on the target optimization model based on Markov decision and SCA algorithms to obtain a target resource allocation strategy.

[0215] Furthermore, step 107 includes:

[0216] Based on the hierarchical reinforcement learning method guided by the Lyapunov algorithm, the target optimization model is divided into an upper-level optimization model and a lower-level optimization model;

[0217] Based on the Markov decision and the upper optimization model, the global queue state space, global queue action space and global queue reward function are defined to obtain the upper queue stable decision model;

[0218] The extended SCA algorithm is used to optimize and solve the upper-layer queue stability decision model, and the offloading strategy, transmit power allocation strategy, and decoding strategy are obtained.

[0219] Based on the Markov decision making and the lower-level optimization model, the local queue state space, local queue action space and local queue reward function are defined to obtain the lower-level queue stable decision model;

[0220] The standard SCA algorithm is used to optimize and solve the lower-level queue stability decision model to obtain the computing resource allocation strategy, which includes user computing resource allocation strategy and satellite computing resource allocation strategy.

[0221] The target resource allocation strategy includes offloading strategy, transmit power allocation strategy, decoding strategy and computing resource allocation strategy.

[0222] It should be noted that since the target optimization model belongs to the complex convex optimization and numerical optimization, it cannot be solved directly, so this embodiment chooses to use Markov decision modeling. Before modeling, in order to consider the coupling between variables and the characteristics of staged optimization, this embodiment combines the hierarchical reinforcement learning method guided by Lyapunov to hierarchically process the target optimization model. Figure 5 ,The upper optimization model is responsible for the optimization of offloading ,decision, transmission power allocation and decoding decision, while the lower optimization ,model is responsible for the optimization of computing resource allocation on the user ,side and satellite side.

[0223] Markov decision can be used to optimize the upper and lower layers respectively. Although Markov decision modeling includes four basic elements: state, action, state transition probability and reward, the solution model of this embodiment does not require prior knowledge of the environment state and does not rely on the probability distribution of random events, so the state transition probability is unknown.

[0224] The upper-level decision modeling requires obtaining global queue information, optimizing global queue stability by controlling the amount of data sent from the user-side queue to the satellite-side queue, and adjusting the stability values ​​of the queues on both sides. Therefore, the global queue state space can be defined as:

[0225]

[0226] That is, the global real-time queue status , User task arrival volume and channel status The global queue action space can be expressed as:

[0227]

[0228] That is, the uninstall decision parameter , decoding sort variables and data transmission power The global queue reward function can be expressed as:

[0229]

[0230] in, is the penalty for exceeding and violating the constraint, 、 、 、 is the weight coefficient used to balance the order of magnitude.

[0231] Because the upper-layer action space contains binary data, discrete variables, and continuous variables, this embodiment uses an extended SCA algorithm to solve the constructed Markov model. The algorithm uses a Bernoulli distribution to model and sample binary data to ensure that the gradient does not vanish. The Gumbel-Softmax technique is used to process discrete variables so that their output action gradients can be backpropagated. Continuous variables are processed using a reparameterization method to ensure gradient continuity during the sampling process. Finally, the optimal solution for the upper-layer queue stabilization decision model is obtained, specifically including the offloading strategy, transmit power allocation strategy, and decoding strategy.

[0232] Since the lower-layer queue stability decision model optimizes the allocation of computing resources on the user side and the satellite side, the modeling process of the lower-layer queue stability decision model needs to be divided into user-side modeling and satellite-side modeling. For user-side modeling, the main focus is to obtain user queue information and adjust the computing output of the user queue to optimize the queue stability and energy consumption on the user side. The user-side local queue state space is defined as:

[0233]

[0234] That is, the real-time queue status from the user side and user task arrival volume constitute.

[0235] The user-side local queue action space is defined as:

[0236]

[0237] Calculate resource allocation for the user side.

[0238] The user-side local queue reward function is defined as:

[0239]

[0240] Since the action space on the user side only contains continuous variables, this embodiment directly uses the standard SCA algorithm to perform optimization and solve to obtain the user computing resource allocation strategy.

[0241] For satellite-side modeling, the main goal is to obtain satellite fleet information and adjust the computational output of the satellite fleet to optimize the fleet stability and energy consumption on the satellite side. Therefore, the local fleet state space on the satellite side is defined as:

[0242]

[0243] That is, the real-time queue status from the satellite side and data arrival at the satellite constitute.

[0244] The satellite-side local queue action space is defined as:

[0245]

[0246] Calculate resource allocation for satellites.

[0247] The satellite-side local queue reward function is defined as:

[0248]

[0249] Similarly, the action space on the satellite side only contains continuous variables, so the standard SCA algorithm is directly sampled for optimization and solution to obtain the satellite computing resource allocation strategy.

[0250] The solution provided in this embodiment dynamically adjusts computing resource allocation based on real-time information to achieve stability and energy efficiency for both user-side and satellite-side queues. The system makes dynamic decisions based on real-time information. The lower-layer network optimizes the computational output and energy consumption of the queues, achieving queue stability and energy optimization on both the user and satellite sides, respectively. The upper-layer network dynamically balances the queue states on both sides by adjusting the transmission rate from the user-side queue to the satellite-side queue. Through the coordinated iterative optimization of the upper and lower-layer networks, the system gradually converges to the global optimal strategy, achieving efficient operation in complex and dynamic environments.

[0251] The satellite edge computing-based resource allocation strategy generation method provided in the present application not only determines whether computing tasks should be retained locally or offloaded to the satellite for edge computing based on offloading decision parameters, but also calculates some transmission parameters of the user terminal's transmitted signal, such as the signal-to-noise ratio. This process fully considers the heterogeneous characteristics of user terminals, making the computing resource allocation operation based on this more realistic. Furthermore, the total time slot energy consumption caused by task scheduling is calculated while considering various performance parameters of the user terminal and the satellite, and an average energy consumption objective function is constructed based on this, taking into account the system's energy consumption optimization problem. Decision constraints are configured based on parameters such as the dynamic evolution state of the queue and the amount of task discarded, fully considering the queue stability optimization problem. Decision constraints are configured based on actual computing power, data transmission power, and decoding order variables, taking into account the dynamic changes in the communication link and the time-varying characteristics of resource allocation. Furthermore, the Lyapunov algorithm is used to optimize and solve the model, balancing multiple optimization objectives to achieve the optimal solution while also accommodating the calculation of data in various formats within the target optimization model. It can also optimize and solve multi-stage optimization problems such as dynamically changing link states and resource allocation, adapting to complex scenarios. The entire process comprehensively considers the impact of multiple situations, multiple types of parameters, and multiple optimization objectives of the edge computing system, and can obtain an accurate and reliable resource allocation strategy with strong applicability. Therefore, the embodiments of the present application can solve the technical problem that the existing technology does not comprehensively consider factors such as task scheduling, resource allocation, communication link status, user heterogeneity, and multiple system performance indicators, resulting in the lack of accuracy, reliability, and applicability of actual resource allocation.

[0252] For easier understanding, see Figure 2 The present application provides an embodiment of a resource allocation strategy generation device based on satellite edge computing. The resource allocation strategy generation device based on satellite edge computing is characterized in that it is applied to a satellite-ground hybrid edge computing system, including:

[0253] The unloading decision determination unit 201 is configured to determine a decision of a computing task of the user terminal based on the communication resource allocation strategy and the task unloading strategy, to obtain an unloading decision parameter;

[0254] The transmission parameter calculation unit 202 is configured to calculate a signal-to-noise ratio, a decoding rate, a transmission data volume and a data transmission energy consumption of the satellite and the user terminal signal transmission according to the unloading decision parameter;

[0255] The task processing analysis unit 203 is configured to calculate a time slot computing task volume and a time slot computing energy consumption of the user terminal and the satellite respectively according to the unloading decision parameter and an actual computing capability, the actual computing capability including a user computing capability and a satellite computing capability;

[0256] The energy consumption target construction unit 204 is configured to calculate a total time slot energy consumption based on the data transmission energy consumption and the time slot computing energy consumption, and to construct an average energy consumption target function according to the total time slot energy consumption;

[0257] The constraint condition construction unit 205 is configured to construct a plurality of decision constraint conditions according to the unloading decision parameter, the actual computing capability, a queue dynamic evolution state, a queue task discard volume, a data transmission power and a decoding order variable;

[0258] The model optimization construction unit 206 is configured to construct an initial queue energy consumption optimization model by combining the average energy consumption target function and the decision constraint conditions, to simplify the initial queue energy consumption optimization model by using a Lyapunov algorithm, and to obtain a target optimization model;

[0259] The model optimization solving unit 207 is configured to perform hierarchical decision solving on the target optimization model based on a Markov decision and an SCA algorithm, to obtain a target resource allocation strategy.

[0260] It can be understood that the specific operation process of the apparatus and the unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described herein.

[0261] The application further provides a resource allocation strategy generation device based on satellite edge computing, which comprises a processor and a memory;

[0262] The memory is configured to store program code and transmit the program code to the processor;

[0263] The processor is configured to execute the resource allocation strategy generation method based on satellite edge computing in the foregoing method embodiments according to the instructions in the program code.

[0264] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiments described above are merely illustrative, for example, the division of the units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or other forms.

[0265] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0266] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0267] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that makes a contribution or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for executing all or part of the steps of the method described in each embodiment of the present application by a computer device (which can be a personal computer, a server, or a network device, etc.). The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (English full name: Read-Only Memory, English abbreviation: ROM), a random access memory (English full name: Random Access Memory, English abbreviation: RAM), a magnetic disk or an optical disk, and various program code storage media.

[0268] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A resource allocation strategy generation method based on satellite edge computing, characterized in that: Applied to satellite-ground hybrid edge computing systems, including: Determine the decision of the user terminal computing task based on the communication resource allocation strategy and the task offloading strategy, and obtain the offloading decision parameter; Calculating the signal-to-noise ratio, decoding rate, transmission data volume, and data transmission energy consumption of satellite and user terminal signal transmission based on the offloading decision parameters; Calculating the time slot computing task amount and time slot computing energy consumption of the user terminal and the satellite respectively according to the offloading decision parameter and the actual computing capacity, wherein the actual computing capacity includes the user computing capacity and the satellite computing capacity; Calculating the total energy consumption of a time slot based on the data transmission energy consumption and the time slot calculation energy consumption, and constructing an average energy consumption objective function according to the total energy consumption of the time slot; Constructing multiple decision constraints based on the offloading decision parameters, the actual computing capacity, the dynamic evolution state of the queue, the amount of queue task discards, the data transmission power, and the decoding sorting variable; After constructing the initial queue energy consumption optimization model by combining the average energy consumption objective function and the decision constraints, the Lyapunov algorithm is used to simplify the initial queue energy consumption optimization model to obtain the target optimization model, which is expressed as: ； ； ； ； ； ； in, is a constant, represents the queue stability cost, is a weight parameter that emphasizes the importance of system energy consumption, Indicates that the system is in time slot The total energy consumption of the time slot is The i-th user terminal in the n-th ground user terminal group on the user side The amount of computing resources allocated, For user terminals The maximum amount of computing resources that can be allocated, Assign user terminals to satellites computing resources, is the maximum amount of computing resources that can be allocated at the satellite, Indicates user terminal The data transmission power allocated to information flow j is, is the maximum data transmission power that can be allocated, represents the offloading decision parameter of the i-th user terminal in the n-th ground user terminal group, represents the decoding order variable assigned to information stream j by the i-th user terminal, is the total number of ground user terminal groups, is the total number of user terminals, To allocate the total amount of information flow; The target optimization model is solved by hierarchical decision making based on Markov decision making and SCA algorithms to obtain a target resource allocation strategy.

2. The method for generating a resource allocation strategy based on satellite edge computing according to claim 1, characterized in that: The method of determining the decision of the user terminal computing task based on the communication resource allocation strategy and the task offloading strategy to obtain the offloading decision parameter also includes: Dynamic communication resource allocation strategy, task offloading strategy and computing resource allocation strategy are formulated according to the mobility of user terminals, task requirements and link status.

3. The method for generating a resource allocation strategy based on satellite edge computing according to claim 1, wherein: The calculating, based on the offloading decision parameters, the signal-to-noise ratio, decoding rate, transmission data volume, and data transmission energy consumption of the satellite and user terminal signal transmissions includes: Calculating the signal-to-noise ratio of each signal sent from the user terminal to the satellite based on the offloading decision parameter, the channel model, and the data transmission power; Calculating a decoding rate of the information stream based on the signal-to-noise ratio and the total system bandwidth; Calculating the transmission data volume of the information flow according to the decoding rate and the task transmission time; The time slot transmission energy consumption of the user terminal is calculated in combination with the offloading decision parameter and the data transmission power to obtain the data transmission energy consumption.

4. The method for generating a resource allocation strategy based on satellite edge computing according to claim 1, wherein: The calculating of the signal-to-noise ratio, decoding rate, transmission data volume and data transmission energy consumption of the satellite and user terminal signal transmission according to the offloading decision parameters further includes: The RSMA technology is used to send the information flow of the user terminal to the satellite for calculation according to the transmission data volume and the data transmission energy consumption; The satellite decodes the received information stream and allocates computing resources based on SIC technology and computing resource allocation strategy.

5. The method for generating a resource allocation strategy based on satellite edge computing according to claim 1, wherein: The calculating of the time slot computing task amount and the time slot computing energy consumption of the user terminal and the satellite respectively according to the offloading decision parameter and the actual computing capacity includes: Calculating the computing task amount of the user terminal according to the offloading decision parameter and the user computing capability to obtain the user computing task amount; Calculating the computing energy consumption of the user terminal according to the offloading decision parameter, the user computing capability and the transmission computing time to obtain the user computing energy consumption; Calculating a satellite computing task volume according to the satellite computing capability and the satellite processing density to obtain the satellite computing task volume; Calculating the satellite computing energy consumption according to the satellite computing capability and the satellite computing time to obtain the satellite computing energy consumption; The user computing task amount and the satellite computing task amount constitute a time slot computing task amount; The user computing energy consumption and the satellite computing energy consumption constitute the time slot computing energy consumption.

6. The method for generating a resource allocation strategy based on satellite edge computing according to claim 1, wherein: The method of constructing multiple decision constraints based on the offloading decision parameters, the actual computing capacity, the dynamic evolution state of the queue, the amount of queue task discards, the data transmission power, and the decoding sorting variable also includes: Calculating a user dynamic evolution state of a user terminal queue according to the amount of transmitted data, the amount of time slot calculation tasks, and the amount of time slot task arrivals; Calculating the user task discard quantity of the user terminal queue according to the user dynamic evolution state, the time slot task arrival quantity and the user queue upper limit value; Calculating a satellite dynamic evolution state of a satellite queue according to the amount of transmitted data and the amount of time slot calculation tasks; Calculating the satellite mission discard amount of the satellite queue according to the satellite dynamic evolution state, the transmission data amount and the satellite queue upper limit; The user dynamic evolution state and the satellite dynamic evolution state are queue dynamic evolution states; The user task discard amount and the satellite task discard amount are queue task discard amounts.

7. The method for generating a resource allocation strategy based on satellite edge computing according to claim 1, wherein: After constructing the initial queue energy consumption optimization model by combining the average energy consumption objective function and the decision constraint condition, the initial queue energy consumption optimization model is simplified using the Lyapunov algorithm to obtain a target optimization model, including: Constructing an initial queue energy consumption optimization model in combination with the average energy consumption objective function and the decision constraints; Defining a virtual packet loss queue according to the queue task discard amount; A Lyapunov function is defined according to the virtual packet loss queue and the dynamic evolution state of the queue using a Lyapunov algorithm; Defining a drift penalty term according to the Lyapunov function, the total energy consumption of the time slot and an energy consumption weight parameter; The drift penalty term is minimized and optimized through a defined queue stability cost function, and the initial queue energy consumption optimization model is simplified into a target optimization model.

8. The method for generating a resource allocation strategy based on satellite edge computing according to claim 1, wherein: The target optimization model is subjected to hierarchical decision solving based on Markov decision and SCA algorithm to obtain the target resource allocation strategy, including: Dividing the target optimization model into an upper-layer optimization model and a lower-layer optimization model according to the hierarchical reinforcement learning method guided by the Lyapunov algorithm; Based on the Markov decision making and the upper-level optimization model, a global queue state space, a global queue action space and a global queue reward function are defined to obtain an upper-level queue stable decision model; An extended SCA algorithm is used to optimize and solve the upper-layer queue stability decision model to obtain an offloading strategy, a transmit power allocation strategy, and a decoding strategy; Based on the Markov decision making and the lower-level optimization model, a local queue state space, a local queue action space, and a local queue reward function are defined to obtain a lower-level queue stable decision model; A standard SCA algorithm is used to optimize and solve the lower-layer queue stability decision model to obtain a computing resource allocation strategy, wherein the computing resource allocation strategy includes a user computing resource allocation strategy and a satellite computing resource allocation strategy; The target resource allocation strategy includes the offloading strategy, the transmit power allocation strategy, the decoding strategy and the computing resource allocation strategy.

9. A resource allocation strategy generation device based on satellite edge computing, characterized in that: Applied to satellite-ground hybrid edge computing systems, including: An offloading decision determination unit, configured to determine a decision on a computing task of a user terminal based on a communication resource allocation strategy and a task offloading strategy, and obtain an offloading decision parameter; a transmission parameter calculation unit, configured to calculate the signal-to-noise ratio, decoding rate, transmission data volume, and data transmission energy consumption of signal transmission between the satellite and the user terminal according to the offloading decision parameters; a task processing analysis unit, configured to calculate the time slot computing task amount and time slot computing energy consumption of the user terminal and the satellite respectively according to the offloading decision parameter and the actual computing capacity, wherein the actual computing capacity includes the user computing capacity and the satellite computing capacity; an energy consumption target construction unit, configured to calculate the total energy consumption of a time slot based on the data transmission energy consumption and the time slot calculation energy consumption, and to construct an average energy consumption target function according to the total energy consumption of the time slot; A constraint condition construction unit, configured to construct a plurality of decision constraint conditions based on the offloading decision parameter, the actual computing capacity, the dynamic evolution state of the queue, the amount of queue task discards, the data transmission power, and the decoding sorting variable; The model optimization construction unit is configured to construct an initial queue energy consumption optimization model by combining the average energy consumption objective function and the decision constraint condition, and then simplify the initial queue energy consumption optimization model using the Lyapunov algorithm to obtain a target optimization model. The target optimization model is expressed as: ； ； ； ； ； ； in, is a constant, represents the queue stability cost, is a weight parameter that emphasizes the importance of system energy consumption, Indicates that the system is in time slot The total energy consumption of the time slot is The i-th user terminal in the n-th ground user terminal group on the user side The amount of computing resources allocated, For user terminals The maximum amount of computing resources that can be allocated, Assign user terminals to satellites computing resources, is the maximum amount of computing resources that can be allocated at the satellite, Indicates user terminal The data transmission power allocated to information flow j is, is the maximum data transmission power that can be allocated, represents the offloading decision parameter of the i-th user terminal in the n-th ground user terminal group, represents the decoding order variable assigned to information stream j by the i-th user terminal, is the total number of ground user terminal groups, is the total number of user terminals, To allocate the total amount of information flow; The model optimization solving unit is used to perform hierarchical decision solving on the target optimization model based on Markov decision and SCA algorithm to obtain the target resource allocation strategy.

10. A resource allocation strategy generation device based on satellite edge computing, characterized in that: The device includes a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the resource allocation strategy generation method based on satellite edge computing according to any one of claims 1-8 according to the instructions in the program code.

Images