Method and system for optimizing cloud edge collaborative unloading strategy

Abstract

The invention relates to a method and a system for optimizing a cloud edge collaborative unloading strategy. The method comprises the following steps of: decomposing a data transmission carrier into a plurality of orthogonal subcarriers; establishing an information transmission channel model according to the orthogonal subcarriers under the condition that the OoS requirement and the transmitting power limiting condition are met, and maximizing a target function of the information transmission channel model; generating a power distribution strategy and a transmission distribution method of data transmission subcarriers through the optimized information transmission signal model; after the capacity of a data transmission signal is maximized, an unloading strategy of a cloud-side collaborative unloading system is optimized, a cloud-side collaborative computing unloading model is established under the condition that the OoS requirement and the transmitting power limiting condition are met, the objective function of the cloud-side collaborative computing unloading model is minimized, and the cloud-side collaborative computing unloading system is optimized. And performing joint optimization on the edge server unloading strategy, the cloud server unloading strategy and the transmission power strategy to generate a final cloud edge collaborative unloading strategy. The overall time delay of the system is reduced, and the overall system cost of the cloud edge cooperative system is ensured.

Description

Technical Field

[0001] The present invention relates to an optimization method and system for a cloud-edge collaborative unloading strategy based on wireless energy and information transmission, and belongs to the technical field of wireless energy and information synchronous transmission. Background Art

[0002] With the continuous advancement of digital construction of oil fields, in order to ensure the normal operation and production safety of oil and gas field equipment, a large number of unmanned inspection equipment need to be deployed to conduct regular inspections and maintenance of oil field sites. Given the vast area and complex and changeable environment of oil fields, stable energy supply and information transmission have become key requirements. Wireless energy and information synchronous transmission technology can complete information transmission while transmitting electrical energy. It has significant advantages such as improving energy utilization efficiency, simplifying system structure and enhancing communication security, and has therefore become a hot topic of current research.

[0003] Traditional cloud computing and edge computing are no longer sufficient to meet the needs of multi-scenario businesses. Cloud-edge collaboration can meet the needs of multi-scenario businesses by realizing the coordinated linkage of edge computing and cloud computing to jointly process data, especially in the field of intelligent inspection equipment. Given that inspection robots need to perform tasks for a long time in oilfield environments, wireless charging devices are used to achieve data transmission from the edge to the cloud based on energy and information synchronous transmission technology. Therefore, how to effectively improve the data transmission channel capacity of wireless energy and information transmission, and how to optimize the unloading strategy, are of great significance to ensuring system costs and reducing overall system latency and energy consumption.

[0004] In the prior art, the data channel capacity can be effectively increased and the data transmission rate can be guaranteed by reasonably designing the circuit structure to reduce the interference of energy transmission on the data transmission channel. Invention patent CN115626282A "Non-contact modular multi-rotor UAV system" proposes a non-contact energy information transmission system for realizing power energy transfer and information interaction management between the UAV platform and the mission payload. This solution does not conduct an in-depth discussion on the communication model or specific circuit design. Invention patent CN108512315A "Injection-type wireless energy and information synchronous transmission circuit based on bilateral LCC structure" proposes an injection-type wireless energy and information synchronous transmission circuit, which uses a blocking circuit to isolate energy signals from each other, while increasing the design cost and complexity of the system. Summary of the invention

[0005] In response to the above problems, the purpose of the present invention is to provide an optimization method and system for a cloud-edge collaborative unloading strategy based on wireless energy and information transmission, which reduces the overall system delay and ensures the overall system cost of the cloud-edge collaborative system. Edge computing can provide computing power near the inspection equipment, thereby providing better quality computing services with shorter transmission delays.

[0006] To achieve the above-mentioned objectives, the present invention proposes the following technical solutions: a method for optimizing a cloud-edge collaborative offloading strategy, comprising the following steps: a cloud-edge collaborative offloading system comprises: a user terminal, an MEC edge server and an MCC cloud server; the signal transmitter of the user terminal transmits a data transmission carrier to a receiving terminal, the MEC edge server and the MCC cloud server; the data transmission carrier is decomposed into a number of orthogonal subcarriers; under the conditions of meeting the OoS requirements and the transmission power limit, an information transmission channel model is established according to the orthogonal subcarriers to maximize the objective function of the information transmission channel model; through the optimized information transmission signal model, a power allocation strategy and a transmission allocation method of the data transmission subcarrier are generated; after maximizing the data transmission signal capacity, the offloading strategy of the cloud-edge collaborative offloading system is optimized, and under the conditions of meeting the OoS requirements and the transmission power limit, a cloud-edge collaborative computing offloading model is established to minimize the objective function of the cloud-edge collaborative computing offloading model, and the edge server offloading strategy, the cloud server offloading strategy and the transmission power strategy are jointly optimized to generate the final cloud-edge collaborative offloading strategy.

[0007] Furthermore, the transmission state of the data transmission carrier is determined by whether the subcarrier is performing data transmission and the transmission power value allocated when the subcarrier is performing power transmission; the total number of bits of information received at the wireless energy and information synchronous transmission receiving end is:

[0008]

[0009] Among them, U(P,S) is the total number of bits, i is the i-th subcarrier, s i Indicates whether subcarrier i is transmitting data; G dp (ω) is the transmission gain of data transmission; G pf is the energy noise gain; W is the channel bandwidth; is the power allocation strategy for data transmission, p i is the power of the ith subcarrier; p f is the power of the fth subcarrier; n F is the number of subcarriers.

[0010] Furthermore, the i =1, the subcarrier i performs data transmission, when s i =0, the subcarrier i is not used for data transmission.

[0011] Furthermore, the OoS requirement is:

[0012]

[0013] Among them, C i is the channel capacity, R minis the minimum transmission rate value of data transmission, P min It is the minimum power value that the data transmission channel can successfully transmit the signal, P max It is the battery capacity limit when wireless energy and information are transmitted simultaneously.

[0014] Furthermore, the power allocation strategy and transmission allocation method of the data transmission subcarrier are generated as follows: a power allocation strategy is given, thereby converting the optimization problem into a subcarrier allocation strategy problem, thereby allocating subcarriers; using the subcarrier allocation result, the dual method is used to obtain the optimal solution of the power allocation subproblem; the optimization results of subcarrier allocation and power allocation are alternately iteratively optimized by the alternating iterative method, and if the difference between the current optimization result and the previous optimization result is less than a preset threshold or the number of iterations is greater than the preset maximum number of iterations, the iteration is stopped, thereby obtaining the optimal solution of the objective function.

[0015] Furthermore, the cloud-edge collaborative computing offloading model is a cloud-edge collaborative offloading system cost minimization model, and the cloud-edge collaborative offloading system cost is the weighted sum of the energy consumption and delay generated by task processing. The energy consumption and delay are added through the weight factor, where the weight factor belongs to (0,1).

[0016] Furthermore, the execution methods of the cloud-edge collaborative offloading system include: local execution on the user side, offloading to the MEC edge server, and offloading to the MCC cloud server.

[0017] Furthermore, when the task is executed locally on the user side, its computational latency and energy consumption are determined by the local computing capacity and computing power. When the task is executed on the local i-th device, the execution latency is and execution energy consumption It is expressed as:

[0018]

[0019] Among them, c i The CPU cycles required for task processing, is the CPU calculation frequency of the device, is the local computing power; when the task is offloaded to the MEC edge server, several devices that are being charged are used as edge servers, and each device selects an edge server within its communication range to offload the task. Assuming that all devices are equipped with a single antenna, the device can only offload tasks to one edge server at a time; Assuming that the i-th device offloads part of the task to be processed to the edge server, the execution delay and execution energy consumption Execution delay caused by task transmission and calculation and execution energy consumption It is expressed as:

[0020]

[0021] Among them, s i Indicates the size of the task data, u M is the CPU frequency of the edge server, r i is the uplink transmission rate, is the transmission power of the ith device, p M is the computing power of the MEC server; when the task is offloaded to the cloud server MCC, the device being charged is used as the edge server, and the task is transmitted from the edge server to the cloud server through the data transmission channel of the SWTPI system. Assuming that the i-th device partially unloads the MCC when unloading the task to the MEC, the execution delay is and execution energy consumption The execution delay is caused by the transmission delay from device to MEC and from MEC to MEC and the computing delay of cloud server. and execution energy consumption It is expressed as:

[0022]

[0023] Among them, C i is the maximum data transfer rate of SWTPI, u c is the CPU frequency of the cloud server, p trm is the transmission power of the edge server, p C is the computing power of the cloud server.

[0024] Further, the method for jointly optimizing the edge server offloading strategy, the cloud server offloading strategy and the transmission power strategy is as follows: obtain the task offloading power P, the strategy X for offloading to the edge server and the strategy Y for offloading to the cloud server; given Y and P, convert the optimization problem into a linear programming subproblem to obtain the optimized offloading strategy; given X and P, convert the optimization problem into a linear programming subproblem to obtain the optimized offloading strategy; given X and Y, obtain the optimal transmission power allocation by the dual method and the subgradient method, and perform alternate iterative optimization on these three subproblems by the alternating iterative method. If the difference between the optimization result of this time and the optimization result of the previous time is less than a preset threshold or the number of iterations is greater than the preset maximum number of iterations, stop the iteration to obtain the optimal solution of the objective function; wherein, the initialization channel capacity O(X,Y,P) of the subcarrier is:

[0025]

[0026] Where N is the task workload, α and (1-α) are the weight coefficients of energy consumption and delay respectively, and x i is the strategy for offloading to the i-th edge server, y iis the strategy for offloading to the i-th cloud server.

[0027] The present invention also discloses an optimization system for a cloud-edge collaborative offloading strategy, the cloud-edge collaborative offloading system comprising: a user end, an MEC edge server and an MCC cloud server; a sending module, used to transmit a data transmission carrier from a signal transmitting end of the user end to a receiving end, the MEC edge server and the MCC cloud server; a carrier decomposition module, used to decompose the data transmission carrier into a plurality of orthogonal subcarriers; a channel maximization module, used to establish an information transmission channel model according to the orthogonal subcarriers under the conditions of meeting OoS requirements and transmission power restrictions, so as to maximize the objective function of the information transmission channel model; through the optimized information transmission signal model, a power allocation strategy and a transmission allocation method for the data transmission subcarriers are generated; a cloud-edge collaborative offloading strategy generation module, used to optimize the offloading strategy of the cloud-edge collaborative offloading system after maximizing the data transmission signal capacity, establish a cloud-edge collaborative computing offloading model under the conditions of meeting OoS requirements and transmission power restrictions, so as to minimize the objective function of the cloud-edge collaborative computing offloading model, jointly optimize the edge server offloading strategy, the cloud server offloading strategy and the transmission power strategy, and generate the final cloud-edge collaborative offloading strategy.

[0028] The technical solution of the present invention has at least the following technical effects or advantages:

[0029] 1. The solution in the present invention reduces the overall system latency and ensures the overall system cost of the cloud-edge collaborative system. Edge computing can provide computing power near the inspection equipment, thereby providing better computing services with shorter transmission delays.

[0030] 2. The present invention improves resource utilization. The present invention uses the patrol equipment in charging as the edge server and considers the strategy of maximizing the capacity of the synchronous wireless transmission of energy and information (SWTPI) channel to reduce system delay. Taking the device resources and maximum delay of the available servers as constraints, a computational offloading architecture that minimizes the weighted sum of system delay and energy consumption is constructed. The problem is formalized as a multivariable non-convex optimization problem, and the problem is solved based on an iterative algorithm of continuous convex approximation and alternating iteration. Compared with using only the mobile edge computing (MEC) system, the system cost is reduced by about 30%, which significantly improves the system performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a schematic structural diagram of a wireless energy and information transmission device in one embodiment of the present invention;

[0032] Figure 2 It is a schematic diagram of the execution method of the cloud-edge collaborative unloading system in one embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is described in detail through specific embodiments. However, it should be understood that the provision of specific embodiments is only for a better understanding of the present invention, and they should not be understood as limitations of the present invention. In the description of the present invention, it should be understood that the terms used are only for the purpose of description and cannot be understood as indicating or implying relative importance.

[0034] In order to solve the problems of low energy utilization efficiency and complex system structure in the prior art. The present invention proposes an optimization method and system for cloud-edge collaborative offloading strategy based on wireless energy and information transmission, including a strategy of maximizing energy and synchronous wireless transmission of information (SWTPI) channel capacity to reduce system delay, and constructs a computational offloading architecture with the device resources and maximum delay of available servers as constraints, minimizes the weighted sum of system delay and energy consumption, formalizes the problem as a multivariable non-convex optimization problem, and solves the problem based on an iterative algorithm of continuous convex approximation and alternating iteration, thereby improving resource utilization. The present invention uses the patrol equipment in charging as the edge server and considers the strategy of maximizing energy and SWTPI channel capacity to reduce system delay. With the device resources and maximum delay of available servers as constraints, a computational offloading architecture that minimizes the weighted sum of system delay and energy consumption is constructed, and the problem is formalized as a multivariable non-convex optimization problem, and the problem is solved based on an iterative algorithm of continuous convex approximation and alternating iteration. Compared with the mobile edge computing (MEC) system alone, the system cost is reduced by about 30%, and the system performance is significantly improved. The present invention will be described in detail below through embodiments in conjunction with the accompanying drawings.

[0035] Embodiment 1

[0036] This embodiment discloses an optimization method for a cloud-edge collaborative unloading strategy, comprising the following steps: a cloud-edge collaborative unloading system, comprising: a user end, an MEC edge server and an MCC cloud server; the user end comprises a wireless energy and information transmission device, such as Figure 1 As shown, the device includes: a high-frequency inverter circuit, an LCC compensation unit, a main coupling coil, a rectifier circuit, and a signal loading and extraction circuit. One end of the high-frequency inverter circuit is connected to the power supply, and the other end of the high-frequency inverter circuit is connected to the LCC compensation unit on the inverter side. The LCC compensation unit on the inverter side is connected to the rectifier circuit through the main coupling coil and the LCC compensation unit on the rectifier side, and the rectifier circuit is connected to the extraction circuit. Information is transmitted between the LCC compensation unit on the inverter side and the LCC compensation unit on the rectifier side. By maximizing the channel capacity of wireless energy and information synchronous transmission, a theoretical model for maximizing the data transmission channel capacity is established, so that all subcarriers The total channel capacity is maximized and based on the alternating iteration and dual method Iterative algorithm framework for power allocationThe strategy and transmission strategy allocation scheme are jointly optimized.

[0037] S1. The signal transmitter at the user end transmits the data transmission carrier to the receiving end, MEC edge server and MCC cloud server; the data transmission carrier is decomposed into several orthogonal subcarriers.

[0038] The transmission status of the data transmission carrier is determined by whether the subcarrier is performing data transmission and the transmission power value allocated when the subcarrier is performing power transmission; the total number of bits of information received at the wireless energy and information synchronous transmission receiving end is:

[0039]

[0040] Where u(P,S) is the total number of bits, i is the i-th subcarrier, s i Indicates whether subcarrier i is transmitting data. i = 1, subcarrier i performs data transmission, when s i = 0, subcarrier i is not used for data transmission; G dp (ω) is the transmission gain of data transmission; G pf is the energy noise gain; W is the channel bandwidth; is the power allocation strategy for data transmission, p i is the power of the ith subcarrier; p f is the power of the fth subcarrier; n F is the number of subcarriers.

[0041] S2. Under the conditions of meeting OoS requirements and transmission power constraints, an information transmission channel model is established based on orthogonal subcarriers to maximize the objective function of the information transmission channel model. Through the optimized information transmission signal model, a power allocation strategy and transmission allocation method for data transmission subcarriers are generated.

[0042] In order to ensure that both the receiving end and the sending end can successfully transmit data, both the sending end and the receiving end in this embodiment should meet the OoS requirements, which are specifically:

[0043]

[0044] Among them, C i is the channel capacity, R min is the minimum transmission rate value of data transmission, P min It is the minimum power value that the data transmission channel can successfully transmit the signal, P max It is the battery capacity limit when wireless energy and information are transmitted simultaneously.

[0045] Under the requirement of QoS, the data transmission channel capacity is maximized and the objective function of the information transmission channel model is maximized, which can be expressed by the following formula:

[0046]

[0047]

[0048] The optimization problem has both discrete and continuous variables, and the objective function and constraints are nonlinear, which is a mixed integer nonlinear programming problem. An iterative algorithm framework based on alternating iteration and dual method is proposed to jointly optimize the subcarrier allocation strategy and power allocation strategy of data transmission channel capacity.

[0049] The power allocation strategy and transmission allocation method for generating data transmission subcarriers are:

[0050] S2.1 Given a power allocation strategy, the optimization problem is transformed into a subcarrier allocation strategy problem. By analyzing the problem, it can be found that the subproblem is a linear programming subproblem. The optimization tools in MATLAB, such as the intlinprog function, can be used to solve the problem, thereby allocating subcarriers.

[0051] S2.2 uses the duality method through the subcarrier allocation results to obtain the optimal solution to the power allocation subproblem; then the optimization results of subcarrier allocation and power allocation are alternately iterated and optimized through the alternating iteration method. If the difference between the current optimization result and the previous optimization result is less than the preset threshold or the number of iterations is greater than the preset maximum number of iterations, the iteration is stopped to obtain the optimal solution of the objective function.

[0052] Specifically, the expression of the initialization channel capacity of the subcarrier in this embodiment is:

[0053]

[0054] Obtain the optimal result of the subcarrier allocation strategy subproblem O(S (t-1) ,S (t) );Calculate the final result S (t) =O(S (t) ,P (t) ), when S (t) The difference between the optimization result and the previous optimization result is less than the preset threshold |S (t) -S (t-1) |<δ or the number of iterations is greater than the preset maximum number of iterations t>t max , the algorithm terminates, otherwise it starts the next round of iteration. Finally, the optimal solution of subcarrier allocation strategy and power allocation strategy is obtained with lower complexity.

[0055] S3. After maximizing the data transmission signal capacity, the unloading strategy of the cloud-edge collaborative unloading system is optimized. Under the conditions of meeting the OoS requirements and transmission power constraints, a cloud-edge collaborative computing unloading model is established to minimize the objective function of the cloud-edge collaborative computing unloading model. The edge server unloading strategy, cloud server unloading strategy and transmission power strategy are jointly optimized to generate the final cloud-edge collaborative unloading strategy, thereby reducing the system's latency and energy consumption.

[0056] The cloud-edge collaborative computing offloading model is a cloud-edge collaborative offloading system cost minimization model. The cloud-edge collaborative offloading system cost is the weighted sum of the energy consumption and latency generated by task processing. The energy consumption and latency are added together through the weight factor, where the weight factor belongs to (0,1). When the energy consumption requirement is high, the weight factor takes a larger value, and when the latency requirement is high, the weight factor takes a smaller value.

[0057] The task is a task model that considers the divisibility of tasks, rather than binary offloading. Part of the task can be processed locally and part can be offloaded to the edge for processing. Therefore, the execution methods of the cloud-edge collaborative offloading system include: local execution on the user side, offloading to the MEC edge server, and offloading to the MCC cloud server, such as Figure 2 shown.

[0058] When the task is executed locally on the user side, it does not need to be offloaded to the MEC or MCC server. Its computing delay and energy consumption are determined by the local computing power and computing power. The entire delay and energy consumption of task processing are all generated locally. Its computing delay and energy consumption are determined by the local computing power and computing power. When the task is executed on the local i-th device, the execution delay and execution energy consumption It is expressed as:

[0059]

[0060] Among them, c i The CPU cycles required for task processing, is the CPU calculation frequency of the device, is the local computing power.

[0061] When the task is offloaded to the MEC server, this paper sets several devices being charged as edge servers. Each device can choose an edge server within its communication range to offload the task. It is assumed that all devices are equipped with a single antenna, so there is no interference in the communication system, and the device can only offload tasks to one edge server at a time.

[0062] Define the variable x i is the offloading strategy for tasks to MEC. i= 0, it means that all tasks are processed locally. i =1, it means that all tasks are offloaded to MEC. Then there are the following constraints: i ∈{0,1}; Assuming that the i-th device offloads part of the tasks to be processed to the edge server, the execution delay and execution energy consumption Execution delay caused by task transmission and calculation and execution energy consumption It is expressed as:

[0063]

[0064] Among them, s i Indicates the size of the task data, u M is the CPU frequency of the edge server, r i is the uplink transmission rate, is the transmission power of the ith device, p M is the computing power of the MEC server.

[0065] When the task is offloaded to the cloud server MCC, the device being charged is used as the edge server, and the task is transmitted from the edge server to the cloud server through the data transmission channel of the SWTPI system. Define y i is the offloading strategy for tasks to MCC. i = 0, it means that all tasks are processed locally or in MEC. i =1, it means that all tasks are offloaded to MCC, then there is the following constraint y i ={0,1};

[0066] Assuming that the i-th device partially unloads the MCC when unloading tasks to the MEC, the execution delay is and execution energy consumption Execution delay caused by device-to-MEC and MEC-to-MEC transmission and cloud server computing delay and execution energy consumption It is expressed as:

[0067]

[0068] Among them, C i is the maximum data transfer rate of SWTPI, u c is the CPU frequency of the cloud server, p trm is the transmission power of the edge server, p C is the computing power of the cloud server.

[0069] The total time of the computation task and the total energy consumption of the mobile device are expressed as:

[0070]

[0071] α and (1-α) are the weight coefficients of task execution delay and energy consumption, respectively, which are determined according to the business requirements and device status of the mobile device. When the mobile device has a high latency requirement, α is set to a larger value; when the mobile device is low on power, α is set to a smaller value. On this basis, a computing strategy that satisfies the maximum latency constraint of the computing task and the server resource constraint is designed, so the optimization problem is expressed as:

[0072]

[0073] The method for jointly optimizing the edge server offloading strategy, cloud server offloading strategy and transmission power strategy is as follows:

[0074] Obtain task offloading power P, strategy X for offloading to edge servers, and strategy Y for offloading to cloud servers;

[0075] Given Y and P, the optimization problem is converted into a linear programming sub-problem, and the optimized unloading strategy is obtained through the optimization tool intlinprog function in MATLAB;

[0076] Given X and P, the optimization problem is converted into a linear programming sub-problem, and the optimized unloading strategy is obtained through the optimization tool intlinprog function in MATLAB;

[0077] Given X and Y, the optimal transmission power allocation is obtained by the dual method and the subgradient method. The three sub-problems are optimized by alternating iteration. If the difference between the current optimization result and the previous optimization result is less than the preset threshold or the number of iterations is greater than the preset maximum number of iterations, the iteration is stopped to obtain the optimal solution of the objective function; wherein, the initialization channel capacity of the subcarrier O(X,Y,P) is:

[0078]

[0079] Where N is the task workload, α and (1-α) are the weight coefficients of energy consumption and delay respectively, and x i is the strategy for offloading to the i-th edge server, y i is the strategy for offloading to the i-th cloud server.

[0080] Get the optimal result S of the strategy sub-problem offloaded to the edge server (t) =O(P (t-1) ,Y (t-1) ,X (t) );

[0081] Get the optimization result S of the strategy subproblem offloaded to the cloud server (t) =O(P(t-1) ,Y (t) ,X (t) );

[0082] Obtain the optimization result S of the task unloading power subproblem (t) =O(P (t) ,Y (t) ,X (t) ), calculate the final result S (t) , when S (t) The difference between the optimization result and the previous optimization result is less than the preset threshold |S (t) -S (t-1) |<δ or the number of iterations is greater than the preset maximum number of iterations t>t max , the algorithm terminates, otherwise it starts the next round of iteration. Finally, the optimal solution of the allocation strategy is obtained with lower complexity.

[0083] Embodiment 2

[0084] Based on the same inventive concept, this embodiment discloses an optimization system for a cloud-edge collaborative unloading strategy, including the following steps:

[0085] The cloud-edge collaborative offloading system includes: user end, MEC edge server and MCC cloud server;

[0086] A sending module is used to transmit a data transmission carrier from a signal transmitting end at a user end to a receiving end, an MEC edge server, and an MCC cloud server;

[0087] The carrier decomposition module is used to decompose the data transmission carrier into several orthogonal subcarriers; the channel maximization module is used to establish an information transmission channel model based on the orthogonal subcarriers under the conditions of meeting the OoS requirements and transmission power constraints, so as to maximize the objective function of the information transmission channel model; the power allocation strategy and transmission allocation method of the data transmission subcarriers are generated through the optimized information transmission signal model;

[0088] The cloud-edge collaborative offloading strategy generation module is used to optimize the offloading strategy of the cloud-edge collaborative offloading system after maximizing the data transmission signal capacity. Under the conditions of meeting the OoS requirements and transmission power constraints, a cloud-edge collaborative computing offloading model is established to minimize the objective function of the cloud-edge collaborative computing offloading model. The edge server offloading strategy, cloud server offloading strategy and transmission power strategy are jointly optimized to generate the final cloud-edge collaborative offloading strategy.

[0089] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not deviate from the spirit and scope of the present invention should be included in the protection scope of the claims of the present invention. The above content is only a specific implementation of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for optimizing cloud-edge collaborative offloading strategy, characterized in that: The following steps are included: The cloud-edge collaborative offloading system includes: a user end, a MEC edge server, and an MCC cloud server; The signal transmitting end of the user terminal transmits a data transmission carrier to the receiving end, the MEC edge server and the MCC cloud server; Decomposing the data transmission carrier into a plurality of orthogonal subcarriers; Under the condition of satisfying OoS requirements and transmission power limitation, establishing an information transmission channel model according to the orthogonal subcarriers to maximize the objective function of the information transmission channel model; Generate a power allocation strategy and a transmission allocation method for the data transmission subcarriers through the optimized information transmission signal model; After maximizing the data transmission signal capacity, the unloading strategy of the cloud-edge collaborative unloading system is optimized. Under the conditions of meeting the OoS requirements and transmission power constraints, a cloud-edge collaborative computing unloading model is established to minimize the objective function of the cloud-edge collaborative computing unloading model. The edge server unloading strategy, cloud server unloading strategy and transmission power strategy are jointly optimized to generate the final cloud-edge collaborative unloading strategy.

2. The method for optimizing the cloud-edge collaborative offloading strategy according to claim 1, characterized in that: The transmission state of the data transmission carrier is determined by whether the subcarrier is performing data transmission and the transmission power value allocated when the subcarrier is performing power transmission; the total number of bits of information received at the wireless energy and information synchronous transmission receiving end is: Among them, U(P,S) is the total number of bits, i is the i-th subcarrier, s i Indicates whether subcarrier i is transmitting data; G dp (ω) is the transmission gain of data transmission; G pf is the energy noise gain; W is the channel bandwidth; is the power allocation strategy for data transmission, p i is the power of the ith subcarrier; p f is the power of the fth subcarrier; n F is the number of subcarriers.

3. The method for optimizing the cloud-edge collaborative offloading strategy according to claim 2, characterized in that: The i =1, the subcarrier i performs data transmission, when s i =0, the subcarrier i is not used for data transmission.

4. The method for optimizing the cloud-edge collaborative offloading strategy according to claim 2, characterized in that: The OoS requirements are: Among them, C i is the channel capacity, R min is the minimum transmission rate value of data transmission, P min It is the minimum power value that the data transmission channel can successfully transmit the signal, P max It is the battery capacity limit when wireless energy and information are transmitted simultaneously.

5. The method for optimizing the cloud-edge collaborative offloading strategy according to claim 1, characterized in that: The power allocation strategy and transmission allocation method for generating the data transmission subcarrier are: Given a power allocation strategy, the optimization problem is transformed into a subcarrier allocation strategy problem, thereby allocating subcarriers; Based on the subcarrier allocation results, the optimal solution for the power allocation subproblem is obtained using the dual method. The optimization results of subcarrier allocation and power allocation are alternately iterated and optimized by the alternating iteration method. If the difference between the current optimization result and the previous optimization result is less than a preset threshold or the number of iterations is greater than the preset maximum number of iterations, the iteration is stopped to obtain the optimal solution of the objective function.

6. The method for optimizing the cloud-edge collaborative offloading strategy according to claim 1, characterized in that: The cloud-edge collaborative computing offloading model is a cloud-edge collaborative offloading system cost minimization model. The cloud-edge collaborative offloading system cost is the weighted sum of the energy consumption and delay generated by task processing. The energy consumption and delay are added through the weight factor, where the weight factor belongs to (0,1).

7. The method for optimizing the cloud-edge collaborative offloading strategy according to claim 6, characterized in that: The execution methods of the cloud-edge collaborative offloading system include: local execution on the user side, offloading to the MEC edge server, and offloading to the MCC cloud server.

8. The method for optimizing the cloud-edge collaborative offloading strategy according to claim 6, characterized in that: When the task is executed locally on the user side, its computing latency and energy consumption are determined by the local computing capacity and computing power. When the task is executed on the local i-th device, the execution latency is and execution energy consumption It is expressed as: Among them, c i The CPU cycles required for task processing, is the CPU calculation frequency of the device, is the local computing power; When the task is offloaded to the MEC edge server, several devices that are being charged are used as edge servers. Each device selects an edge server within its communication range to offload the task. Assuming that all devices are equipped with a single antenna, the device can only offload tasks to one edge server at a time. Assuming that the i-th device offloads part of the task to be processed to the edge server, the execution delay and execution energy consumption Execution delay caused by task transmission and calculation and execution energy consumption It is expressed as: Among them, s i Indicates the size of the task data, u M is the CPU frequency of the edge server, r i is the uplink transmission rate, is the transmission power of the ith device, p M is the computing power of the MEC server; When the task is unloaded to the cloud server MCC, the device being charged is used as the edge server, and the task is transmitted from the edge server to the cloud server through the data transmission channel of the SWTPI system. Assuming that the i-th device partially unloads the MCC when unloading the task to the MEC, the execution delay is and execution energy consumption The execution delay is caused by the transmission delay from device to MEC and from MEC to MEC and the computing delay of cloud server. and execution energy consumption It is expressed as: Among them, C i is the maximum data transfer rate of SWTPI, u c is the CPU frequency of the cloud server, p trm is the transmission power of the edge server, p C is the computing power of the cloud server.

9. The method for optimizing the cloud-edge collaborative offloading strategy according to claim 8, characterized in that: The method for jointly optimizing the edge server offloading strategy, cloud server offloading strategy and transmission power strategy is as follows: Obtain task offloading power P, strategy X for offloading to edge servers, and strategy Y for offloading to cloud servers; Given Y and P, the optimization problem is converted into a linear programming sub-problem to obtain the optimized unloading strategy; Given X and P, the optimization problem is converted into a linear programming sub-problem to obtain the optimized unloading strategy; Given X and Y, the optimal transmission power allocation is obtained by the dual method and the subgradient method. The three sub-problems are optimized by alternating iteration. If the difference between the current optimization result and the previous optimization result is less than the preset threshold or the number of iterations is greater than the preset maximum number of iterations, the iteration is stopped to obtain the optimal solution of the objective function; wherein, the initialization channel capacity of the subcarrier O(X,Y,P) is: Where N is the task workload, α and (1-α) are the weight coefficients of energy consumption and delay respectively, and x i is the strategy for offloading to the i-th edge server, y i is the strategy for offloading to the i-th cloud server.

10. An optimization system for cloud-edge collaborative offloading strategy, characterized in that: The cloud-edge collaborative offloading system includes: user end, MEC edge server and MCC cloud server; A sending module is used to transmit a data transmission carrier from a signal transmitting end of a user end to a receiving end, the MEC edge server and the MCC cloud server; A carrier decomposition module, used for decomposing the data transmission carrier into a plurality of orthogonal subcarriers; A channel maximization module is used to establish an information transmission channel model according to the orthogonal subcarriers under the condition of meeting the OoS requirements and transmission power limitation, so as to maximize the objective function of the information transmission channel model; and generate a power allocation strategy and a transmission allocation method for the data transmission subcarriers through the optimized information transmission signal model; The cloud-edge collaborative offloading strategy generation module is used to optimize the offloading strategy of the cloud-edge collaborative offloading system after maximizing the data transmission signal capacity, establish a cloud-edge collaborative computing offloading model under the conditions of meeting the OoS requirements and transmission power constraints, minimize the objective function of the cloud-edge collaborative computing offloading model, jointly optimize the edge server offloading strategy, cloud server offloading strategy and transmission power strategy, and generate the final cloud-edge collaborative offloading strategy.

Images