Task allocation method and device, electronic equipment and storage medium

Abstract

The invention discloses a task allocation method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: acquiring a plurality of to-be-allocated tasks, and based on the plurality of to-be-allocated tasks, determining processing time delay when the plurality of to-be-allocated tasks are executed through a task processing network; based on the to-be-allocated tasks, total energy consumption when the to-be-allocated tasks are executed through the task processing network is determined; based on the total energy consumption and the processing time delay, task allocation is carried out on the to-be-allocated tasks, and task groups corresponding to the task processing networks are obtained; the number of the to-be-allocated tasks in the task group is at least zero, and when the task processing network executes task processing for the to-be-allocated tasks according to the task group, the total task cost determined by the total energy consumption and the processing time delay is minimum.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a task allocation method, device, electronic device and storage medium. Background Art

[0002] The Internet of Everything is the development trend of the information age. With a large number of different devices connected to the cloud computing network, the processing of massive data has brought new challenges to the core computing module. The traditional one-center cloud computing architecture is insufficient in the face of new distributed computing scenarios. For some large-structured distributed computing networks, it will take a lot of time to upload all data to the central processor in the cloud. Considering the network congestion problem, it will eventually cause a large processing delay.

[0003] In the related art, for task allocation, usually only the transmission delay of the task is considered, which leads to low accuracy of task allocation and high task operation costs. Summary of the invention

[0004] In order to solve the technical problems existing in the related art, the embodiments of the present application provide a task allocation method, device, electronic device and computer-readable storage medium.

[0005] To achieve the above purpose, the technical solution of the embodiment of the present application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a task allocation method, which is applied to a task allocation node of a cloud edge computing network, wherein the cloud edge computing network includes a plurality of task processing networks and the task allocation node, and the method includes:

[0007] Acquire a plurality of tasks to be assigned, and determine, based on the plurality of tasks to be assigned, processing delays when the plurality of tasks to be assigned are executed through the task processing network;

[0008] Based on the multiple tasks to be assigned, determining the total energy consumption when executing the multiple tasks to be assigned through the task processing network;

[0009] Based on the total energy consumption and the processing delay, the plurality of tasks to be assigned are assigned to obtain task groups corresponding to the task processing networks;

[0010] The number of the tasks to be assigned in the task group is at least zero, and when the task processing network performs task processing for the tasks to be assigned according to the task group, the overall task cost determined by the total energy consumption and the processing delay is minimized.

[0011] In a second aspect, an embodiment of the present application provides a task allocation device, which is applied to a task allocation node of a cloud edge computing network, wherein the cloud edge computing network includes a plurality of task processing networks and the task allocation node, including:

[0012] an acquisition module, configured to acquire a plurality of tasks to be assigned, and determine, based on the plurality of tasks to be assigned, a processing delay when the plurality of tasks to be assigned are executed through the task processing network;

[0013] An energy consumption module, used for determining, based on the multiple tasks to be assigned, the total energy consumption when the multiple tasks to be assigned are executed through the task processing network;

[0014] A task allocation module is used to allocate tasks to the multiple tasks to be allocated based on the total energy consumption and the processing delay to obtain task groups corresponding to each of the task processing networks; the number of the tasks to be allocated in the task group is at least zero, and when the task processing network performs task processing for the tasks to be allocated according to the task group, the overall task cost determined by the total energy consumption and the processing delay is minimized.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a first memory for storing a computer program that can be run on the processor;

[0016] Wherein, when the processor is used to run the computer program, it executes the steps of the task allocation method on the electronic device side described in the embodiment of the present application.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the task allocation method provided by the embodiment of the present application is implemented.

[0018] The task allocation method, device, electronic device and computer-readable storage medium provided by the embodiment of the present application, by determining the processing delay when executing multiple tasks to be allocated through a task processing network based on multiple tasks to be allocated, determining the total energy consumption when executing multiple tasks to be allocated through a task processing network based on multiple tasks to be allocated, and performing task allocation for multiple tasks to be allocated based on total energy consumption and processing delay, and obtaining the task groups corresponding to each task processing network. In this way, by recording the processing result of each task, the network performance can be monitored, and adjusted and optimized according to the actual effect, by comprehensively considering the total energy consumption and processing delay, the task allocation can minimize the overall task cost, and the tasks are allocated to the network that can complete them at the lowest cost (including energy consumption and processing time). This helps to reduce operating costs and improve resource utilization efficiency. By comprehensively considering the total energy consumption and processing delay, the efficiency and reliability of task processing can be effectively improved, thereby effectively improving the accuracy of task allocation and effectively reducing task operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The following is a flow chart of the task allocation method according to an embodiment of the present application. Figure 1 ;

[0020] Figure 2 The following is a flow chart of the task allocation method according to an embodiment of the present application. Figure 2 ;

[0021] Figure 3 The principle of the task allocation method of the embodiment of the present application is shown as follows Figure 1 ;

[0022] Figure 4 The principle of the task allocation method of the embodiment of the present application is shown as follows Figure 2 ;

[0023] Figure 5 The principle of the task allocation method of the embodiment of the present application is shown as follows Figure 3 ;

[0024] Figure 6 It is a trend diagram of the number of evaluations provided in the embodiment of the present application;

[0025] Figure 7 This is a schematic diagram of the principle of the task allocation method provided in the embodiment of the present application. Figure 4 ;

[0026] Figure 8 A schematic diagram of the structure of a task allocation device according to an embodiment of the present application;

[0027] Fig. 9 A schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0030] The Internet of Everything is the development trend of the information age. With a large number of different devices connected to the cloud computing network, the processing requirements of massive data have brought new challenges to the core computing modules. The traditional single-center cloud computing architecture is insufficient in the face of new distributed computing scenarios. For some large-scale distributed computing networks, it will take a lot of time to upload all data to the central processor in the cloud. Considering the network congestion problem, it will eventually cause a large processing delay.

[0031] For some data information with high real-time requirements, such as real-time monitoring data information, such delay will seriously affect the overall performance of the system. At the same time, for some sensitive commercial data, since in the traditional cloud computing-based control architecture, data needs to be uploaded to the cloud in a centralized manner, the risk of data leakage and theft is high. It cannot meet the requirements of privacy and information security.

[0032] Disadvantages of existing technology:

[0033] Since the cloud computing server is far away from the terminal device, the time delay of data transmission and the consumption of communication resources are large. When a large number of terminal devices access the central cloud computing server, the cloud server is overloaded, the overall anti-interference ability of the cloud computing network is poor, and the network failure rate is high. As a high-energy-consuming industry, the cloud computing industry requires a lot of calculations at the terminal nodes, edge computing networks, and cloud computing layers, which consume a lot of power resources. This proposal transforms the original architecture and introduces small photovoltaic power stations on the edge side to participate in energy supply, which can achieve the goals of reducing energy consumption, saving energy and reducing emissions, and reducing costs. When solving related problems, the existing algorithms cannot achieve good results because the problem itself is a constrained optimization scheduling problem. When solving the problem, the swarm intelligence algorithm is prone to fall into the local optimum and convergence problems slowly. This proposal combines the fireworks algorithm, which has a very powerful performance in the swarm intelligence algorithm, and optimizes it so that the optimized algorithm can be applied to the cloud edge computing resource scheduling problem, with faster solution speed and higher accuracy. The cloud edge computing network consists of a cloud computing layer and an edge computing layer. Cloud computing servers are generally composed of high-performance computer terminals with powerful data processing and storage capabilities. The collected data is concentrated in the cloud computing layer, and decisions are made through data processing and mining. The edge computing layer uses the fog computing network formed by the connection between computing nodes to plan and divide the tasks that need to be processed under the requirement of load balancing with the purpose of minimizing time consumption. The devices in the terminal device layer transmit information data wirelessly or wiredly and access the perception network.

[0034] In the actual application process, when the terminal device layer uploads real-time data, for some data that needs to be processed in real time, the system uses the computing power of the computing nodes at the edge computing layer to process these data. This not only reduces the computing pressure on the cloud server, but also avoids the time delay caused by network congestion and transmission to the distant cloud. At the same time, sensitive data is calculated on the edge side to avoid network attacks and information leakage during data transmission, thereby improving data security.

[0035] Based on this, an embodiment of the present application provides a task allocation method, which is applied to an electronic device. Figure 1 The following is a flow chart of the task allocation method according to an embodiment of the present application. Figure 1 , applied to a task allocation node of a cloud edge computing network, the cloud edge computing network includes a plurality of task processing networks and the task allocation node, such as Figure 1 As shown, the task allocation method provided in the embodiment of the present application can be Figure 1 Steps 101 to 103 are shown to be implemented.

[0036] In step 101, a plurality of tasks to be assigned are obtained, and based on the plurality of tasks to be assigned, processing delays when the plurality of tasks to be assigned are executed through the task processing network are determined.

[0037] In some embodiments, the task processing network includes an edge task processing network, a cloud task processing network, and a terminal task processing network.

[0038] In some embodiments, taking multiple tasks to be assigned and determining the processing delay of these tasks when they are executed is a complex optimization problem. The processing delay depends on many factors, including the characteristics of the task, the status of the network, the distribution of computing resources, etc. The task allocation system first needs to obtain multiple tasks to be assigned from the task queue. These tasks may have different priorities, resource requirements, execution time and other characteristics. The network edge nodes close to the data source handle tasks with high real-time and low latency requirements. The server cluster located in the central data center handles computing-intensive and high-bandwidth demand tasks. Including user devices, such as smartphones or IoT devices, are usually used to process lightweight, delay-insensitive tasks.

[0039] As an example, see Figure 3 , Figure 3 This is a schematic diagram of the principle of the task allocation method provided in the embodiment of the present application. Figure 1 , Figure 3 The task processing network shown includes an edge task processing network (edge ​​computing node layer), a cloud task processing network (cloud computing layer) and a terminal task processing network (terminal device layer).

[0040] In some embodiments, based on the multiple tasks to be assigned, determining the processing delay when executing the multiple tasks to be assigned through the task processing network can be achieved in the following ways: based on the multiple tasks to be assigned, determining the first processing delay when executing the multiple tasks to be assigned through the edge task processing network; based on the multiple tasks to be assigned, determining the second processing delay when executing the multiple tasks to be assigned through the cloud task processing network; based on the multiple tasks to be assigned, determining the third processing delay when executing the multiple tasks to be assigned through the terminal task processing network; according to the first weight variables corresponding to the edge task processing network, the cloud task processing network and the terminal task processing network respectively, performing weighted summation on the first processing delay, the second processing delay and the third processing delay to obtain the processing delay.

[0041] In some embodiments, determining the processing delay when different task processing networks execute multiple tasks to be assigned and performing weighted summation is a complex process that comprehensively considers network characteristics, task requirements and resource allocation, and the estimated processing delay when multiple tasks to be assigned are executed through edge task processing networks. Edge networks are usually located near data sources, have low latency, and are suitable for processing tasks with high real-time requirements. Expected processing delay when multiple tasks to be assigned are executed through cloud task processing networks. Cloud networks have powerful computing and storage capabilities and are suitable for processing computing-intensive tasks, but may cause higher latency due to network transmission distance and bandwidth limitations. Expected processing delay when multiple tasks to be assigned are executed through terminal task processing networks. Terminal networks are usually on user devices and have limited processing capabilities, but can handle some lightweight tasks and may have lower latency. Each task processing network has a corresponding weight variable, which reflects the relative importance of each network in task processing. The determination of weight variables can be based on factors such as network performance, task requirements, and cost-effectiveness. According to the weight variables of each task processing network, the first processing delay, the second processing delay and the third processing delay are weighted and summed. The total processing delay obtained by weighted summation can be used as an indicator to evaluate the efficiency of different task processing networks. The task allocation strategy can be optimized according to the total processing delay, such as adjusting the weight variables or reallocating tasks to different networks.

[0042] As an example, a processing scenario containing three tasks will process these tasks through three different networks: edge, cloud, and terminal, and calculate the weighted total processing delay. The first processing delay (edge ​​network): Assume that there are three tasks A, B, and C, and their processing delays through the edge network are 10ms, 20ms, and 15ms, respectively. The second processing delay (cloud network): Similarly, the delays for tasks A, B, and C to be processed through the cloud network are 50ms, 60ms, and 55ms, respectively. The third processing delay (terminal network): The delays for tasks A, B, and C to be processed through the terminal network are 5ms, 10ms, and 7ms, respectively. Assume that the weight variables set for the edge, cloud, and terminal networks are: (w_1=0.4), (w_2=0.3), (w_3=0.3), which means that the processing delay of the edge network accounts for 40% of the total processing delay, and the cloud network and the terminal network each account for 30%. The above weight variables can be used to calculate the weighted total processing delay, which is 73.1ms. This value reflects the relative importance of different networks in processing delay. Developers can evaluate and optimize task allocation strategies based on this total processing delay.

[0043] In this way, by analyzing the execution delays of multiple tasks to be assigned on the edge, cloud, and terminal task processing networks, and performing weighted summation according to their respective weight variables, precise control of task processing delays can be effectively achieved. Task allocation can be dynamically adjusted according to different network characteristics, task requirements, and environmental conditions, thereby optimizing the performance of the entire system. Through weighted summation, the relative importance of each network can be comprehensively considered to ensure that the task processing delay matches the network performance and task requirements, thereby improving resource utilization and task execution efficiency. At the same time, this method can also be dynamically adjusted according to the real-time network status and task execution status to adapt to the ever-changing environment and needs, thereby providing a more flexible and scalable system design.

[0044] In some embodiments, based on the multiple tasks to be assigned, determining the first processing delay when executing the multiple tasks to be assigned through the edge task processing network can be achieved in the following way: determining the first task processing delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the edge task processing network; determining the first task transmission delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the edge task processing network and the terminal task processing network; adding the first task processing delay of the edge task processing network and the first task transmission delay of the edge task processing network to obtain the first processing delay.

[0045] In some embodiments, determining the total processing delay of a task on the edge task processing network requires considering two main factors: the processing delay of the task and the transmission delay of the task. Based on the task volume of multiple tasks to be assigned, it is necessary to analyze the task execution performance of the edge task processing network. This includes the processing power of the network node, the current workload, the computational complexity of the task, etc. The processing delay of each task can be estimated by analyzing the processing power of the network. In a distributed system, tasks need to be transmitted in the network. The task transmission delay depends on the network bandwidth, transmission distance, network congestion, etc. The task transmission speed between the edge task processing network and the terminal task processing network needs to be considered to determine the transmission delay of the task from the terminal to the edge network. The first processing delay is the total processing delay of the task on the edge network, which is equal to the sum of the task processing delay and the task transmission delay. By adding these two delays, the total processing time of the task on the edge network is obtained. Influencing factors, task processing performance, the computing power of the edge network, the current workload, and the computational complexity of the task will affect the processing delay. Network bandwidth, the higher the bandwidth, the lower the transmission delay is usually. Transmission distance, the shorter the transmission distance, the lower the signal propagation delay. Network congestion: Network congestion will increase transmission delay.

[0046] As an example, assume that there are three tasks A, B, and C to be assigned to the edge task processing network, and the execution performance and task transmission speed of the edge network are known. The first processing delay will be calculated by the following steps: Task processing delay: Assume that the computing power of the edge network can process 100 task units per second. Task A needs to process 10 task units, task B needs to process 20 task units, and task C needs to process 30 task units. The processing delay of task A = 10 task units / 100 task units / second = 0.1 seconds = 100ms. - The processing delay of task B = 20 task units / 100 task units / second = 0.2 seconds = 200ms. The processing delay of task C = 30 task units / 100 task units / second = 0.3 seconds = 300ms. Task transmission delay: Assume that the transmission speed between the edge network and the terminal network is 200MB of data per second. The data volume of task A is 2MB, the data volume of task B is 4MB, and the data volume of task C is 6MB. The transmission delay of task A = 2MB / 200MB / sec = 0.01sec = 10ms. The transmission delay of task B = 4MB / 200MB / sec = 0.02sec = 20ms. The transmission delay of task C = 6MB / 200MB / sec = 0.03sec = 30ms. Total processing delay: The total processing delay of task A = the processing delay of task A + the transmission delay of task A = 100ms + 10ms = 110ms. The total processing delay of task B = the processing delay of task B + the transmission delay of task B = 200ms + 20ms = 220ms. The total processing delay of task C = the processing delay of task C + the transmission delay of task C = 300ms + 30ms = 330ms.

[0047] In this way, by analyzing the task volume of multiple tasks to be assigned, the task execution performance of the edge task processing network, and the task transmission speed, the first task processing delay and the first task transmission delay of the edge task processing network can be accurately determined. Such analysis helps to optimize the task allocation strategy and ensure that tasks can be executed and transmitted efficiently. By adding the processing delay and the transmission delay, the first processing delay on the edge network is obtained, which provides a key performance indicator. It can help identify and deal with possible performance bottlenecks, thereby improving the efficiency and responsiveness of the entire system. At the same time, it can also help to better understand the execution of different tasks on the network, provide data support for task allocation and resource optimization, and ensure that the edge task processing network can provide high-quality services, meet user needs, and improve user experience.

[0048] In some embodiments, the above-mentioned determination of the second processing delay when executing the multiple tasks to be assigned through the cloud task processing network based on the multiple tasks to be assigned can be achieved in the following way: determining the second task processing delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the cloud task processing network; determining the second task transmission delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the cloud task processing network and the terminal task processing network; adding the second task processing delay of the cloud task processing network and the second task transmission delay of the cloud task processing network to obtain the second processing delay.

[0049] In some embodiments, in a distributed computing environment, in order to determine the second task processing delay and the second task transmission delay of the cloud task processing network, and perform weighted summation to obtain the second processing delay, it is necessary to analyze the task execution performance of the cloud task processing network according to the task amount of multiple tasks to be assigned. This includes the processing power of the cloud server cluster, the current workload, the computational complexity of the task, etc. The processing delay of each task can be estimated by analyzing the computing resources of the cloud network. In a distributed system, tasks need to be transmitted in the network. The task transmission delay depends on the network bandwidth, transmission distance, network congestion, etc. The task transmission speed between the cloud task processing network and the terminal task processing network needs to be considered to determine the transmission delay of the task from the terminal to the cloud network. The second processing delay is the total processing delay of the task on the cloud task processing network, which is equal to the sum of the task processing delay and the task transmission delay. By adding these two delays, the total processing time of the task on the cloud network is obtained.

[0050] As an example, assume that there are three tasks A, B, and C to be assigned to the cloud task processing network, and the execution performance and task transmission speed of the cloud network are known. The second processing delay will be calculated by the following steps: Task processing delay: Assume that the computing power of the cloud network can process 1000 task units per second. Task A needs to process 50 task units, task B needs to process 150 task units, and task C needs to process 250 task units. The processing delay of task A = 50 task units / 1000 task units / second = 0.05 seconds = 50ms. The processing delay of task B = 150 task units / 1000 task units / second = 0.15 seconds = 150ms. The processing delay of task C = 250 task units / 1000 task units / second = 0.25 seconds = 250ms. Task transmission delay: Assume that the transmission speed between the cloud network and the terminal network is 500MB of data per second. The data volume of task A is 5MB, the data volume of task B is 15MB, and the data volume of task C is 25MB. The transmission delay of task A = 5MB / 500MB / second = 0.01 second = 10ms. The transmission delay of task B = 15MB / 500MB / second = 0.03 second = 30ms. The transmission delay of task C = 25MB / 500MB / second = 0.05 second = 50ms. Total processing delay: The total processing delay of task A = the processing delay of task A + the transmission delay of task A = 50ms + 10ms = 60ms. The total processing delay of task B = the processing delay of task B + the transmission delay of task B = 150ms + 30ms = 180ms. The total processing delay of task C = the processing delay of task C + the transmission delay of task C = 250ms + 50ms = 300ms. In this example, the processing delay and transmission delay of each task on the cloud network are calculated separately, and then they are added together to obtain the total processing delay of each task.

[0051] In this way, by analyzing the task volume of multiple tasks to be assigned and the task execution performance of the cloud task processing network, as well as the task transmission speed, the second task processing delay and the second task transmission delay of the cloud task processing network can be accurately determined. Such analysis helps to optimize the task allocation strategy and ensure that tasks can be executed and transmitted efficiently. By adding the processing delay and the transmission delay, the second processing delay on the cloud network is obtained, which provides a key performance indicator. It can help identify and deal with possible performance bottlenecks, thereby improving the efficiency and responsiveness of the entire system. At the same time, it can also help to better understand the execution of different tasks on the network and provide data support for task allocation and resource optimization. It can ensure that the cloud task processing network can provide high-quality services, meet user needs, and improve user experience.

[0052] In some embodiments, based on the multiple tasks to be assigned, determining the third processing delay when executing the multiple tasks to be assigned through the terminal task processing network can be achieved in the following way: based on the task amount of the multiple tasks to be assigned and the task execution performance of the terminal task processing network, determining the third processing delay when executing the multiple tasks to be assigned through the terminal task processing network.

[0053] In some embodiments, the processing capability of the terminal device needs to be evaluated based on the task volume of multiple tasks to be assigned. This includes the hardware resources of the terminal device such as CPU, memory, storage, and the efficiency of the operating system and application programs. The processing delay of each task can be estimated by analyzing the performance of the terminal device. The complexity, data volume, and real-time requirements of each task will affect the processing delay. For example, a lightweight image processing task may only take a few milliseconds, while a complex video editing task may take several seconds. If the task needs to interact with an external network, such as downloading or uploading data, the network conditions will also affect the processing delay. Network bandwidth, signal strength, latency, etc. will affect the execution time of the task. The terminal device may run multiple tasks at the same time, which may lead to resource competition and performance degradation. The priority and scheduling strategy of the task need to be considered to ensure that critical tasks can get enough resources. By optimizing the task, such as using multi-threading, asynchronous processing, data caching and other technologies, the processing efficiency of the terminal device can be improved and the processing delay can be reduced.

[0054] In step 102, based on the plurality of tasks to be assigned, the total energy consumption when the plurality of tasks to be assigned are executed through the task processing network is determined.

[0055] In some embodiments, the task processing network includes an edge task processing network, a cloud task processing network, and a terminal task processing network.

[0056] In some embodiments, the above step 102 can be implemented in the following ways: based on the multiple tasks to be assigned, determining a first energy consumption when executing the multiple tasks to be assigned through the edge task processing network; based on the multiple tasks to be assigned, determining a second energy consumption when executing the multiple tasks to be assigned through the cloud task processing network; based on the multiple tasks to be assigned, determining a third energy consumption when executing the multiple tasks to be assigned through the terminal task processing network; and according to the second weight variables corresponding to the edge task processing network, the cloud task processing network and the terminal task processing network respectively, performing weighted summation on the first energy consumption, the second energy consumption and the third energy consumption to obtain the total energy consumption.

[0057] In some embodiments, in a distributed computing environment, the energy consumption of the task processing network is an important consideration. In order to determine the energy consumption when executing multiple tasks to be assigned through different networks, it is necessary to evaluate the energy consumption of the edge task processing network, the cloud task processing network, and the terminal task processing network, and perform weighted summation according to their respective weight variables. The energy consumption of the edge network depends on the power consumption of the network nodes, the processing delay of the task, and the efficiency of the network architecture. The energy consumption can be estimated by monitoring the power consumption of the nodes and using energy consumption simulation tools. The energy consumption of the cloud network is affected by factors such as the scale of the data center, the number of servers, the cooling system, and the power infrastructure. The energy consumption can be estimated by the power efficiency ratio (PUE) of the data center and the power consumption of IT equipment. The energy consumption of the terminal network is related to the type of equipment, the processing time of the task, and the energy efficiency ratio of the equipment. The energy consumption can be estimated by the power consumption of the equipment and the use of energy consumption simulation tools. The energy consumption weight variable of each task processing network reflects the relative importance of the network in the total energy consumption. The weight variable can be determined based on factors such as the frequency of use of the network, the importance of the task, and the energy cost. According to their respective weight variables, the first energy consumption, the second energy consumption and the third energy consumption are weighted and summed to obtain the total energy consumption. By analyzing the total energy consumption, optimization measures can be taken to reduce the total energy consumption, such as using more efficient equipment, improving task scheduling algorithms, optimizing data processing processes, etc.

[0058] In some embodiments, when the plurality of tasks to be assigned are executed through the edge task processing network, the first energy consumption is the energy consumption of the terminal task processing network when the plurality of tasks to be assigned are executed through the edge task processing network.

[0059] In some embodiments, the above-mentioned determination of the first energy consumption when executing the multiple tasks to be assigned through the edge task processing network based on the multiple tasks to be assigned can be achieved in the following ways: determining the first task transmission delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the edge task processing network and the terminal task processing network; determining the first task processing delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the edge task processing network; determining the first transmission energy consumption of the terminal task processing network based on the first task transmission delay and the unit consumption of the terminal task processing network when transmitting tasks between the edge task processing network and the terminal task processing network; determining the first processing energy consumption of the terminal task processing network based on the first task processing delay and the unit energy consumption of the terminal task processing network when performing task processing in the edge task processing network; adding the first transmission energy consumption and the first processing energy consumption to obtain the first energy consumption.

[0060] In some embodiments, the first energy consumption refers to the energy consumption of the terminal task processing network when multiple tasks to be assigned are executed through the edge task processing network. This energy consumption is generated during the transmission of the task from the terminal to the edge network. The first task transmission delay refers to the time it takes for the task to be transmitted from the terminal to the edge network. It depends on the data volume of the task, the network bandwidth, the transmission protocol, and the network congestion. The first task processing delay refers to the time required for the edge network to process the task. It depends on the computing power of the edge network, the current workload, and the complexity of the task. The first transmission energy consumption refers to the energy consumption of the terminal task processing network during the transmission of the task from the terminal to the edge network. This energy consumption can be estimated by the power consumption, transmission time, transmission distance, and transmission protocol of the terminal device. The first processing energy consumption refers to the energy consumption when the edge network processes the task. This energy consumption can be estimated by the power consumption, processing time, and complexity of the processing task of the edge network. The calculation of the first energy consumption, the first transmission energy consumption and the first processing energy consumption are added to obtain the first energy consumption. Assume that the data volume of the task is D MB, the network bandwidth is B MB / s, and the transmission speed between the edge network and the terminal network is V MB / s. The first task transmission delay = D / V. Assume that the computing power of the edge network is C task units / second, and the computing amount of each task is T task units. The first task processing delay = T / C. Assume that the power consumption of the terminal device is PW, and the transmission time is the transmission delay. The first transmission energy consumption = P*the first task transmission delay. Assume that the power consumption of the edge network is EW, and the processing time is the processing delay. The first processing energy consumption = E*the first task processing delay.

[0061] As an example, assume that there is a task A to be assigned to the edge task processing network, and the performance parameters of the edge network and the terminal network are known. The first energy consumption will be calculated by the following steps: Task transmission delay: Assume that the data volume of task A is 10MB, and the transmission speed between the edge network and the terminal network is 100MB / s. First task transmission delay = 10MB / 100MB / s = 0.1 seconds = 100 milliseconds. Task processing delay: Assume that the computing power of the edge network can process 100 task units per second, and task A needs to process 20 task units. The first task processing delay = 20 task units / 100 task units / second = 0.2 seconds = 200 milliseconds. Transmission energy consumption: Assume that the power consumption of the terminal device is 5W and the transmission time is 100 milliseconds. The first transmission energy consumption = 5W*100 milliseconds = 500 milliwatt-hours. Processing energy consumption: Assume that the power consumption of the edge network is 20W and the processing time is 200 milliseconds. -First processing energy consumption = 20W*200 milliseconds = 4000 milliwatt-hours. Calculate the first energy consumption: first energy consumption = first transmission energy consumption + first processing energy consumption = 500 mWh + 4000 mWh = 4500 mWh.

[0062] In this way, it helps to identify the energy consumption of tasks in the terminal network and optimize the task allocation strategy to ensure that tasks can be executed and transmitted efficiently. At the same time, it can also help to better understand the energy consumption of different tasks on the network, and provide data support for energy consumption optimization and resource management. In this way, it can ensure that the edge task processing network can provide high-quality services, meet user needs, and improve user experience. In addition, this analysis can also help identify and deal with possible energy consumption bottlenecks, thereby improving the efficiency and responsiveness of the entire system. By reducing energy consumption, the impact on the environment can be reduced, and operating costs may be reduced, improving the sustainability of the system. Through the analysis of task energy consumption, the task allocation strategy can be optimized, system performance can be improved, and the impact on the environment can be reduced.

[0063] In some embodiments, when the plurality of tasks to be assigned are executed through the cloud task processing network, the first energy consumption is the energy consumption of the terminal task processing network when the plurality of tasks to be assigned are executed through the cloud task processing network.

[0064] In some embodiments, the above-mentioned determination of the second energy consumption when executing the multiple tasks to be assigned through the cloud task processing network based on the multiple tasks to be assigned can be achieved in the following manner: determining the second task processing delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the cloud task processing network; determining the second task transmission delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the cloud task processing network and the terminal task processing network; determining the second transmission energy consumption of the terminal task processing network based on the second task transmission delay and the unit consumption of the terminal task processing network when transmitting tasks between the cloud task processing network and the terminal task processing network; determining the second processing energy consumption of the terminal task processing network based on the second task processing delay and the unit energy consumption of the terminal task processing network when the cloud task processing network performs task processing; adding the second transmission energy consumption and the second processing energy consumption to obtain the second energy consumption.

[0065] In some embodiments, when multiple tasks to be assigned are executed through a cloud task processing network, the energy consumption of the tasks during transmission and processing can be analyzed. The first energy consumption refers to the energy consumption of the terminal task processing network when transmitting the task to the cloud task processing network. This energy consumption can be estimated by the power consumption, transmission time, transmission distance and transmission protocol of the terminal device. Second task processing delay: This refers to the time required for the cloud task processing network to process the task. It depends on the computing power of the cloud network, the current workload and the complexity of the task. Second task transmission delay: This refers to the time it takes for the task to be transmitted from the terminal to the cloud network. It depends on the data volume of the task, the network bandwidth, the transmission protocol and the network congestion. Second transmission energy consumption: This refers to the energy consumption of the terminal task processing network during the transmission of the task from the terminal to the cloud network. This energy consumption can be estimated by the power consumption, transmission time, transmission distance and transmission protocol of the terminal device. Second processing energy consumption: This refers to the energy consumption of the cloud network when processing the task. This energy consumption can be estimated by the power consumption, processing time and complexity of the processing task of the cloud network. Calculation of the second energy consumption: Add the second transmission energy consumption and the second processing energy consumption to obtain the second energy consumption.

[0066] As an example, there is a task B to be assigned to the cloud task processing network, and the performance parameters of the cloud network and the terminal network are known. The first energy consumption = the energy consumption of the terminal device when transmitting the task to the cloud network. Assume that the computing power of the cloud network can process 200 task units per second, and task B needs to process 40 task units. The second task processing delay = 40 task units / 200 task units / second = 0.2 seconds = 200 milliseconds. Assume that the data volume of task B is 15MB and the network bandwidth is 100MB / s. The second task transmission delay = 15MB / 100MB / s = 0.15 seconds = 150 milliseconds. Assume that the power consumption of the terminal device is 4W and the transmission time is 150 milliseconds. The second transmission energy consumption = 4W*150 milliseconds = 600 milliwatt-hours. Assume that the power consumption of the cloud network is 25W and the processing time is 200 milliseconds. The second processing energy consumption = 25W*200 milliseconds = 5000 milliwatt-hours. Second energy consumption = second transmission energy consumption + second processing energy consumption = 600 mWh + 5000 mWh = 5600 mWh. The energy consumption of task B during transmission to the cloud network and processing is calculated. The second energy consumption reflects the total energy consumption of the terminal device during task transmission and processing. This analysis helps to understand the energy consumption of tasks in the cloud network, thereby providing a basis for energy consumption optimization and resource management. At the same time, it can also help identify and deal with possible energy consumption bottlenecks, thereby improving the efficiency and responsiveness of the entire system. By reducing energy consumption, the impact on the environment can be reduced, and operating costs may be reduced.

[0067] In some embodiments, based on the multiple tasks to be assigned, determining the third energy consumption when executing the multiple tasks to be assigned through the terminal task processing network can be achieved in the following way: determining the reference energy consumption of the terminal task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the terminal task processing network; multiplying the reference energy consumption of the terminal task processing network by the energy consumption parameter of the terminal task processing network to obtain the third energy consumption.

[0068] In some embodiments, it is necessary to evaluate the processing capacity of the terminal device based on the task volume of multiple tasks to be assigned. This includes the hardware resources of the terminal device such as CPU, memory, storage, and the efficiency of the operating system and application programs. The processing energy consumption of each task can be estimated by analyzing the performance of the terminal device. Assuming that the average processing energy consumption of each task on the terminal device is E_r (unit: watt-hour / task), the reference energy consumption = E_r*, the number of tasks to be assigned. The energy consumption parameters may include factors such as the power consumption of the terminal device, the task execution time, and the task complexity. The energy consumption parameter can be a fixed multiple or a dynamically changing coefficient, depending on the usage and workload of the terminal device. The third energy consumption = reference energy consumption * energy consumption parameter. The energy consumption parameter here may be a global parameter, or it may have different parameters for different types of tasks. The third energy consumption when executing multiple tasks to be assigned through the terminal task processing network can be obtained. This process helps developers and administrators optimize the energy consumption of terminal devices, improve user application experience, and ensure system stability and response speed.

[0069] In step 103, task allocation is performed on the plurality of tasks to be allocated based on the total energy consumption and the processing delay to obtain task groups corresponding to the task processing networks.

[0070] In some embodiments, see Figure 2 , Figure 2 The following is a flow chart of the task allocation method according to an embodiment of the present application. Figure 2 , Figure 1 The illustrated step 103 may be performed by Figure 2 Steps 1031 to 1033 are shown to be implemented.

[0071] In step 1031, based on the total energy consumption and the processing delay, the allocation weight of each of the task processing networks is predicted to obtain the predicted allocation weight of each of the task processing networks.

[0072] In some embodiments, energy consumption weight: based on the total energy consumption, an energy consumption weight index can be defined, for example, the lower the energy consumption, the greater the weight. Delay weight: based on the processing delay, a delay weight index can be defined, for example, the shorter the processing delay, the greater the weight. Collect the total energy consumption and processing delay data of each task processing network under different workloads. In order to compare the performance of each network, the energy consumption and processing delay data need to be normalized. This can be achieved by dividing the energy consumption and processing delay of each network by the maximum energy consumption and maximum processing delay of all networks. For the energy consumption weight, the weight index can be defined as 1 / normalized energy consumption. For the delay weight, the weight index can be defined as 1 / normalized processing delay. According to business requirements and network performance, different weight factors (α and β) can be set for the energy consumption weight and delay weight, where α+β=1. Comprehensive weight = α*energy consumption weight index + β*delay weight index.

[0073] In some embodiments, by calculating the comprehensive weight of each network, the predicted allocation weight of each network relative to other networks can be obtained: Predicted allocation weight = comprehensive weight / sum of comprehensive weights of all networks.

[0074] In step 1032, the number of the plurality of tasks to be assigned is multiplied by the predicted assignment weight of each of the task processing networks to obtain the number of tasks assigned by each of the task processing networks.

[0075] In some embodiments, multiplication is an intuitive method to calculate the number of tasks assigned to each task processing network, but it depends on whether the predicted allocation weights are accurate. The predicted allocation weights of each task processing network are calculated based on the total energy consumption, processing delay and other relevant factors. These weights represent the relative efficiency of each network in performing tasks. To ensure that the allocation of all tasks is fair, the predicted allocation weights need to be normalized so that their sum is equal to 1. In this way, the weight of each network can be expressed as their proportion in the entire task processing. The normalized predicted allocation weight of each network is multiplied by the total number of tasks to obtain the number of tasks that should be allocated to each network, ensuring that the allocation of the number of tasks matches the predicted efficiency of the network. In practical applications, the number of tasks assigned may need to be adjusted according to actual conditions. For example, if a network cannot handle the number of tasks it predicts to be assigned due to some reasons (such as maintenance or failure), then other networks need to take on additional tasks. After the tasks are assigned, the performance and energy consumption of the network need to be evaluated, and the predicted allocation weights need to be adjusted and optimized according to the actual results. This helps to improve the accuracy and efficiency of task allocation.

[0076] As an example, suppose there are 3 tasks to be assigned, 3 task processing networks, and the predicted assignment weights are 0.5, 0.3, and 0.2 (normalized). The total number of tasks = 3. The number of tasks assigned to network A = 0.5*3=1.5, which is rounded to 1 or 2. The number of tasks assigned to network B = 0.3*3=0.9, which is rounded to 1. The number of tasks assigned to network C = 0.2*3=0.6, which is rounded to 1. Network A may be assigned 1 or 2 tasks, network B may be assigned 1 task, and network C may be assigned 1 task. The actual assignment of the number of tasks may need to be adjusted according to the specific situation (such as whether the processing capacity of network A allows the assignment of 2 tasks).

[0077] In step 1033, for each of the task processing networks, the to-be-allocated tasks having the same number of tasks allocated by the task processing network are determined as a task group corresponding to the task processing network.

[0078] In some embodiments, the above-mentioned prediction of the allocation weights of each of the task processing networks based on the total energy consumption and the processing delay to obtain the predicted allocation weights of each of the task processing networks can be achieved as follows: traverse i to perform the following processing: according to the i-th explosion radius, based on the total energy consumption and the processing delay, the allocation weights of each of the task processing networks are predicted for the i-th time to obtain the i-th candidate allocation weights of each of the task processing networks; according to the differential mutation rule, the i-th candidate allocation weights of each of the task processing networks are mutated to obtain the i-th predicted allocation weight; the N-th predicted allocation weight is determined as the predicted allocation weight.

[0079] In some embodiments, i is not less than 1 and not greater than N, N is used to indicate the maximum predicted number of times the weight is assigned, and the i-th explosion radius is smaller than the i+1-th explosion radius.

[0080] In some embodiments, the differential evolution algorithm (DE) is a population-based random search. The explosion radius refers to the range of the search space, that is, the possible value range of the allocation weight. In the differential evolution algorithm, each individual in the population (in this case, the allocation weight of the task processing network) is updated according to the information of other individuals in the current population. This process is repeated many times, each time called a generation or an iteration. The differential evolution algorithm uses differential mutation operations to generate new individuals. This operation usually involves three steps: selection, crossover, and mutation. The selection operation randomly selects individuals from the current population; the crossover operation mixes these selected individuals to generate new individuals; the mutation operation increases the diversity of the population by introducing randomness. After the i-th iteration, the allocation weight of each task processing network is updated according to the differential mutation rule to form the i-th candidate allocation weight. After N iterations, the algorithm stops, and the result of the last iteration (the N-th predicted allocation weight) will be determined as the final predicted allocation weight. In each iteration, the algorithm evaluates the performance of each candidate allocation weight according to a fitness function. This fitness function is usually related to total energy consumption and processing delay. According to the fitness function, the algorithm selects the best performing candidate allocation weights as part of the next generation, and introduces new candidate allocation weights through mutation operations. The differential evolution algorithm can gradually optimize the allocation weights in multiple rounds of iterations, and finally obtain a predicted allocation weight with good performance.

[0081] As an example, there is a task processing network allocation problem with three task processing networks (A, B, C) and three tasks to be assigned. The differential evolution algorithm will be used to predict the allocation weights for each network. Initialize the population: Randomly initialize a population containing multiple candidate allocation weight vectors. For example, each vector can be the allocation weights of three task processing networks A, B, and C. The i-th iteration: The i-th candidate allocation weight: Evaluate each allocation weight vector in the current population based on total energy consumption and processing latency. Select the best performing individual in the population as the reference individual. For each individual, select three different individuals for differential operation to generate a differential vector. Cross the differential vector with the reference individual to generate a new candidate allocation weight vector. Differential mutation: Perform mutation operations on the candidate allocation weight vector, for example, by adding a small random vector to increase diversity. Evaluation and selection: Evaluate the fitness of the newly generated candidate allocation weight vectors. Select the vector with the best fitness as part of the next generation population. Determine the final allocation weight: After multiple iterations, the algorithm stops. The best performing individual in the last generation of the population (the Nth predicted allocation weight) will be determined as the final predicted allocation weight. For example, if 5 iterations are performed, the final allocation weight may be: Network A weight: 0.45 - Network B weight: 0.35, Network C weight: 0.20 These weights represent the relative efficiency of each network in processing tasks, and tasks can be allocated based on these weights to ensure the overall performance optimization.

[0082] In some embodiments, based on the total energy consumption and the processing delay, the multiple tasks to be assigned are assigned, and after the task groups corresponding to each of the task processing networks are obtained, the following processing can also be performed: The following processing is performed for each of the task processing networks: When the tasks to be assigned exist in the task group corresponding to the task processing network, the tasks to be assigned in the task group corresponding to the task processing network are processed through the task processing network to obtain the task processing results corresponding to the task group.

[0083] In some embodiments, each task processing network is evaluated for performance, including its processing capacity and energy efficiency, and the processing cost (including energy consumption and processing time) of each network is determined based on the data of total energy consumption and processing delay. A distribution strategy is formulated to distribute tasks based on the processing cost of each network. The strategy can be a simple round-robin method or a more complex dynamic distribution strategy based on cost or performance. According to the distribution strategy, the tasks to be distributed are distributed to the corresponding task processing networks. This may involve grouping tasks and assigning each group of tasks to a network. For each task processing network, the following processing is performed: When the network receives the task group assigned to it, it starts processing these tasks. Use the processing resources of the network to perform task processing according to the priority and order of the tasks. Record the processing results of each task, including success or failure status, processing time, energy consumption, etc. Summarize the results of each network processing to evaluate the performance and efficiency of the entire system. Analyze the processing results to identify potential problems and optimization space, for example, some networks may require more resources or more efficient algorithms. It can ensure that tasks are processed efficiently while optimizing total energy consumption and processing latency, helping to improve the overall performance and responsiveness of the system while reducing operating costs.

[0084] In some embodiments, the number of the tasks to be assigned in the task group is at least zero, and when the task processing network performs task processing for the tasks to be assigned according to the task group, the overall task cost determined by the total energy consumption and the processing delay is minimized.

[0085] This helps improve the efficiency of task processing, because tasks are assigned to the networks that are most suitable for executing them, thereby reducing the total processing time and energy consumption. It helps optimize resource usage, because the task allocation strategy can be customized according to the processing capacity and energy efficiency of each network, thus avoiding waste of resources. By recording the processing results of each task, the performance of the system can be monitored, and problems can be quickly identified and solved, thereby improving the stability and reliability of the system. Finally, this performance- and cost-based allocation method can also reduce operating costs, because by reducing energy consumption and processing time, energy consumption and maintenance costs can be reduced.

[0086] In this way, by determining the processing delay when executing multiple tasks to be assigned through the task processing network based on multiple tasks to be assigned, determining the total energy consumption when executing multiple tasks to be assigned through the task processing network based on multiple tasks to be assigned, and assigning multiple tasks to be assigned based on the total energy consumption and processing delay, a task group corresponding to each task processing network is obtained. In this way, by recording the processing results of each task, the network performance can be monitored, and adjustments and optimizations can be made according to the actual effect. By comprehensively considering the total energy consumption and processing delay, task allocation can minimize the overall task cost, and tasks are assigned to the network that can complete them at the lowest cost (including energy consumption and processing time). This helps to reduce operating costs and improve resource utilization efficiency. By comprehensively considering the total energy consumption and processing delay, the efficiency and reliability of task processing can be effectively improved, thereby effectively improving the accuracy of task allocation and effectively reducing task operating costs.

[0087] The present application is described below in conjunction with application examples.

[0088] The cloud-edge computing network consists of a cloud computing layer and an edge computing layer. Cloud computing servers are generally composed of high-performance computer terminals with powerful data processing and storage capabilities. The collected data is concentrated in the cloud computing layer, and decisions are made through data processing and mining. The edge computing layer uses the fog computing network formed by the connection between computing nodes to plan and divide the tasks that need to be processed under the requirement of load balancing with the purpose of minimizing time consumption. The devices in the terminal device layer transmit information data wirelessly or wiredly and access the perception network.

[0089] In the actual application process, when the terminal device layer uploads real-time data, for some data that needs to be processed in real time, the system uses the computing power of the computing nodes at the edge computing layer to process these data. This not only reduces the computing pressure on the cloud server, but also avoids the time delay caused by network congestion and transmission to the distant cloud. At the same time, sensitive data is calculated on the edge side to avoid network attacks and information leakage during data transmission, thereby improving data security.

[0090] In some embodiments, see Figure 3 , the total delay of data in the network is the sum of transmission delay, processing delay and queuing delay. V = {A1, A2, A3, A4, A5, ..., A n} is a set of n computing nodes. i Represents a single computing node. Any two computing nodes communicate with each other via wired or wireless means. Each computing node A i The computing power is C i . Set T = {Y 1,2 D 1,2,...Y i,j D i,j ,...} Each element in represents the transmission delay between two computing nodes. Y represents the communication relationship between two computing nodes. When the value is 1, there is a data transmission relationship between the two computing nodes. If it is 0, there is no data transmission relationship between the two computing nodes. D represents the communication delay between two computing nodes. D i,j It is composed of the data transmission delay and some other fixed delays. i,j =d i,j +L / R i,j ,L represents the frame length of the data, R i,j Indicates the network bandwidth between two computing nodes. i,j Represents some fixed delays including storage and propagation delays.

[0091] The network consumes energy when performing calculations. Since both the edge computing network and the cloud computing server can be connected to the external power grid, and the terminal edge devices are often powered by independent power supplies and batteries, their energy consumption costs need to be considered. The following is an analysis and list of different computing demand scenarios. Task delay model. For the multi-edge node model proposed in this paper, there are many ways to process tasks in the terminal device. For a single task i, it can be calculated in the terminal device, the edge server, and the cloud computing server.

[0092] In some embodiments, when calculating in the local terminal device, the computing capability of the terminal device i is m i , the size of computing task i is l i ,c i is the amount of computing resources required for computing task i, and its delay T i for:

[0093]

[0094] In some embodiments, when computing in the edge computing node where the terminal device is located, the total time overhead is composed of computing delay and transmission delay. The computing delay at this time can be expressed as:

[0095]

[0096]

[0097]

[0098] Among them, T c is the latency from the terminal device to the edge computing node, l i is the size of the task file, is the speed at which device i uploads to the corresponding edge computing node, T i c To calculate the delay, n i The computing power allocated to the edge server for the corresponding task.

[0099] In some embodiments, when computing in a cloud server, the computing task is first transmitted to a local edge computing node and then to a cloud computing server. Generally, tasks with a large amount of computing are transmitted to the cloud computing server for computing. The delay formula can be expressed as follows:

[0100]

[0101]

[0102]

[0103] Among them, T i c is the computing task latency of the cloud computing server, T i t→c is the total delay of transmitting computing tasks from terminal devices to cloud computing servers. The computing resources allocated to each task by the cloud computing server, T i t→e is the latency of task transmission from the device to the edge server, T i e→c The latency from edge computing node to cloud computing server; is the transmission speed from edge server to cloud server.

[0104] In some embodiments, the energy consumption model of the task can be basically ignored because the edge computing node devices and cloud servers are connected to the power grid and run, and the energy consumption of the terminal devices during the processing of computing tasks is mainly considered. i It can be analyzed in three situations.

[0105] When computing tasks are performed at the terminal node, the energy consumption of the terminal node device can be expressed as:

[0106]

[0107] Among them, k is the energy consumption parameter of the edge computing node, m i represents the computing power of the edge node, c i is the computing resources required for task i.

[0108] In some embodiments, when a computing task is transmitted to an edge server for computing, the total energy consumption of the terminal node is composed of the computing task uploading consumption and the waiting energy consumption. The total energy consumption can be expressed as:

[0109]

[0110]

[0111] In the formula, Indicates the unit energy consumption of the terminal edge node during the computing task upload process, represents the transmit power of the terminal edge node, is the device energy consumption when the terminal node is idle, T i w It is the waiting time after the edge node upload is completed. Indicates the power consumption of the terminal device in idle state.

[0112] In some embodiments, when the computing task is calculated at the cloud service layer, similarly, the energy consumption of the edge node is composed of the transmission energy consumption during uploading and the total energy consumption when waiting for the processing result to be returned, which can be expressed as:

[0113]

[0114]

[0115] In the formula, is the power consumption of the edge node in standby mode, is the power consumption of edge node i while waiting for the computing task to be completed, T i w is the waiting time of the edge node, T i e→c T is the time it takes to transfer the computing task from the edge server to the cloud server. i c,c is the computing time of the task in the cloud server. is the transmission speed from edge server to cloud server, The computing resources allocated to each task on a cloud computing server.

[0116] In some embodiments, see Figure 4 , Figure 4 The principle of the task allocation method of the embodiment of the present application is shown as follows Figure 2 Photovoltaic power stations use solar energy as their energy source to generate electricity to supply edge-side computing needs. Excess electricity can be stored in energy storage batteries. When electricity demand is insufficient, demand can be met by purchasing electricity from the grid.

[0117] Energy storage power stations use energy-type battery packs as energy storage elements, storing electricity during the "valley" period of electricity and discharging it during the "peak" period of electricity, thereby achieving peak shaving and valley filling and regulating user-side demand response. This can not only reduce the peak load of the power grid, which is beneficial to the safe operation of the power grid, but also generate huge economic benefits.

[0118] The output power of the photovoltaic unit P pv Calculated according to the following formula:

[0119] P pv =P STC G AC [1+k3(T C -T r )] / G STC (13)

[0120] T c =T amt +30G AC / 1000 (14)

[0121] Among them, P STC G is the maximum test power under standard test conditions; AC is the light intensity; k3 is the power temperature coefficient T r is the reference temperature, G STC is the light intensity under standard test conditions; T c It indicates the operating temperature of the solar panel.

[0122] The state of charge (SOC) of the energy storage battery represents the ratio of the remaining energy of the battery to the rated energy. The charging and discharging process can be expressed by the formula:

[0123] SOC(t)=(1-δ)SOC(t-1)-P c Δtη c / E c (15)

[0124] SOC(t)=(1-δ)SOC(t-1)-P d Δt / E c η d (16)

[0125] Among them, P c is the charging power, P d is the discharge power, η c is the charging efficiency, η d is the discharge efficiency. c It represents the overall capacity of the battery within the Δt time period, and δ is the self-discharge coefficient of the battery.

[0126] On this basis, the total cost model can be expressed as the weighted sum of the delay cost and the energy consumption cost. At the same time, the coefficient parameter size can be dynamically set according to the sensitivity of different tasks to delay and energy consumption. For time-sensitive computing tasks, the delay coefficient can be set larger, and for energy-sensitive tasks, the energy consumption coefficient can be set larger. The total cost model can be expressed as:

[0127]

[0128] stα i ,β i ,x i ∈{0,1}(18)

[0129] Among them, α i , β i , χ i It is a number between 0 and 1. When it is 1, it means that task i is calculated on the edge node, edge server and cloud server. Indicates the unit price of the electricity cost of the energy storage battery, Indicates the amount of electricity consumed by the energy storage battery on the edge side. represents the unit price of solar energy cost, represents the solar power consumed at the edge side, represents the unit price of electricity cost in the edge grid, Represents the electrical energy consumed from the grid.

[0130] The problem of optimizing computing tasks in cloud-edge networks can be converted into a problem of minimizing the total cost.

[0131]

[0132]

[0133] In the formula, is a binary variable, which takes 1 when offloading to edge servers at the edge of other service areas. i ,β i ,x i It is a binary variable that equals 1, indicating that the task must be calculated in one of the places.

[0134] Since this problem is a complex, multi-variable, multi-constrained optimization problem, it is difficult to solve, and the traditional optimization solution is not effective. Therefore, a swarm intelligence optimization algorithm is adopted to solve it. After comparison, the fireworks algorithm is selected for solution, and the fireworks algorithm is improved in many aspects, such as the introduction of unequal displacement spark generation strategy and differential-Levi flight strategy variation to improve its search performance.

[0135] In some embodiments, see Figure 5 , Figure 5 The principle of the task allocation method of the embodiment of the present application is shown as follows Figure 3 The fireworks algorithm is a swarm intelligence algorithm with the characteristics of fast operation speed and strong search ability. It has a wide range of applications in solving complex problems. In the fireworks algorithm, each spark is regarded as a potential solution. As the explosion proceeds, the nearby domain is searched. The fireworks algorithm mainly includes three steps: (1) fireworks initialization; (2) calculation of the fitness value of the fireworks, and obtaining the explosion radius and the number of sparks, and performing "explosion" search; (3) analysis of search results, and judgment of whether to enter the next iteration or terminate the search and output.

[0136] There are four key factors involved in the fireworks algorithm: explosion operator, mutation operator, mapping condition and result selection strategy.

[0137] The explosion operator consists of explosion intensity and explosion radius. The explosion intensity indicates the number of sparks generated by each explosion. For sparks with higher fitness values, the explosion intensity is high, thus generating more offspring sparks in the nearby domain. Conversely, the explosion intensity is low. The explosion radius indicates the displacement of a specified spark, and the calculation formula is shown in (21):

[0138]

[0139]

[0140] Among them, S i represents the number of explosion sparks generated after the explosion of firework i, m is a constant value for boundary control; Y max Refers to the spark with the worst fitness value; f(x i ) is the fitness value of firework i; θ is used to avoid the denominator being 0, and pop represents the population size. i represents the explosion radius of firework i, is a constant value, indicating the upper limit of the explosion radius, Y min is the fitness value of the spark with the highest quality in the current population.

[0141] Here, a spark generation strategy with unequal position offsets is introduced, which can significantly enhance the diversity of the spark population and enhance the search capability. ik , introduce random quantity to calculate the position offset ΔX ik =A i ×U(-1,1);, get the position x after displacement ik =x ik +ΔX ikIn each iteration of the fireworks algorithm, the explosion radius and explosion intensity of each firework spark are adjusted according to the fitness value of the firework. However, for the individual with the lowest fitness value in the fireworks population, i.e., the optimal solution, the explosion radius value obtained will be very small, which will result in the explosion radius being too small to play a mining role in the actual optimization search process, which will greatly weaken the search performance of the fireworks algorithm.

[0142] To avoid this problem, the minimum explosion radius detection strategy (MEACS) is introduced. min,k is the detection value with the lowest explosion radius in the kth dimension, that is:

[0143]

[0144] Among them, A ik represents the explosion radius of firework i in dimension k.

[0145] In some embodiments, regarding A min,k , see Figure 6 , Figure 6 It is a trend diagram of the evaluation times provided in the embodiment of the present application, which adopts a nonlinear decreasing explosion radius detection strategy, and the expression is as follows:

[0146]

[0147] In some embodiments, the mutation link is an important step in the fireworks algorithm. By mutating individuals, the algorithm can be optimized in a larger range. The mutation method used by the fireworks algorithm is Gaussian mutation. Since the differential operation can make full use of the difference information between populations, the diversity of the population can be enhanced. The Levy flight function is a flight function with strong randomness. It combines short-distance search and a small amount of long-distance search. Its step size obeys the Levy distribution and the direction obeys the uniform distribution. The Levy flight function is introduced to make the mutation have better jumping ability, thereby avoiding early local optimality and enhancing search capabilities. A differential-Levi flight mutation method is proposed here to replace the Gaussian distribution. On the one hand, it strengthens the information exchange between individuals in the population, and on the other hand, it strengthens the randomness of the algorithm and avoids the algorithm from falling into the local optimality.

[0148] In some embodiments, the Gaussian variation and the differential variation are compared. Figure 7 As shown, Figure 7 This is a schematic diagram of the principle of the task allocation method provided in the embodiment of the present application. Figure 4 , the calculation process of the improved fireworks algorithm is as follows:

[0149] The fireworks algorithm is initialized to generate the first generation population, denoted as POP1. The first generation population POP1 is exploded to generate sparks. The explosion intensity and explosion radius are shown in the above calculation formula. The newly generated population is denoted as POP2. The individuals in populations POP1 and POP2 are formed into a set and sorted from high to low according to the fitness value to generate a new population, namely population POP3. The individuals in POP3 are mutated using the differential method, and the individual fitness values ​​before and after the differential mutation are compared. The high ones are kept and the low ones are removed to generate a new generation of population. The algorithm performs multiple rounds of iterations, and when the preset number of iterations is met or the output conditions are met, the calculation results are output. The expression for differential mutation introduced by spark mutation is:

[0150]

[0151] in, is the position of the target individual in the kth dimension; is the position of the best individual in the current population in the kth dimension; F is the scaling factor, which is used to scale the difference, and its value range is generally 0 to 2; and are the positions of two different individuals in the kth dimension.

[0152] The Levy distribution can be described as:

[0153] L(s)~|s| -1-β ,0<β≤2 (26)

[0154] Among them, s is the random step length of Levy flight, and the random step length can be defined as:

[0155]

[0156]

[0157]

[0158]

[0159] Among them, v obeys the normal distribution, and β is generally 1.5. Therefore, the spark mutation formula introduced by Levy flight can be expressed as:

[0160]

[0161] In some embodiments, mainly for the task allocation problem in the cloud edge computing network, in order to utilize computing resources and reduce network delay, the time delay and energy consumption of all terminals executing tasks are weighted and calculated respectively, and the original unloading decision and resource allocation problem are transformed into a cost optimization problem that comprehensively considers the minimum delay and energy consumption, and the task allocation scheme is calculated using the improved fireworks algorithm. The cloud edge computing network form in which small photovoltaic power stations participate in the peak and valley regulation of power grid electricity by using photovoltaic solar energy to reduce energy consumption, and the cost optimization of minimum delay and energy consumption is performed by combining the power and cost of photovoltaic power stations. Since this optimization problem is a non-convex optimization problem, the fireworks algorithm is used to solve it, and the difference-Levi flight strategy and other methods are introduced to improve it, enhance the information exchange and individual randomness between individuals during the algorithm iteration process, and enable the algorithm to obtain a better solution in a shorter time. When the computing task arrives, the nature of the task can be classified. If it needs to be calculated on the edge side, the task is assigned to the edge computing node for calculation. When the task can be collaboratively calculated in the cloud edge network, the task allocation method proposed in this proposal is used to allocate the task to achieve the highest computing efficiency. The cloud-edge computing network model that adds a small photovoltaic power station to the edge side can participate in the peak-valley regulation of power grid electricity by using photovoltaic solar energy, reduce energy consumption, and achieve energy saving and cost reduction. It has good application prospects for scenarios with heavy computing tasks on the edge side. The energy consumption index and the delay index are comprehensively considered to form a total cost model, and the adaptation of different types of computing tasks is achieved through dynamic adjustment of coefficients. Compared with a single delay model, a more reasonable task allocation optimization solution is achieved by incorporating energy consumption into the cost model. When using the swarm intelligence algorithm to solve the problem, because the problem has many constraints and variables, the algorithm is prone to premature convergence and cannot achieve a good optimization effect. By improving the fireworks algorithm and introducing the differential-Levi flight strategy, the algorithm accuracy can be significantly improved and the convergence speed can be accelerated.

[0162] In order to implement the task allocation method on the electronic device side of the embodiment of the present application, the embodiment of the present application also provides a task allocation device, Figure 8 Schematic diagram of the composition structure of the task allocation device according to an embodiment of the present application. Figure 8As shown, a task allocation node is applied to a cloud edge computing network, and the cloud edge computing network includes multiple task processing networks and the task allocation node. The task allocation device includes: an acquisition module 61, used to acquire multiple tasks to be assigned, and based on the multiple tasks to be assigned, determine the processing delay when the multiple tasks to be assigned are executed through the task processing network; an energy consumption module 62, used to determine the total energy consumption when the multiple tasks to be assigned are executed through the task processing network based on the multiple tasks to be assigned; a task allocation module 63, used to assign tasks to the multiple tasks to be assigned based on the total energy consumption and the processing delay, and obtain task groups corresponding to each of the task processing networks; the number of the tasks to be assigned in the task group is at least zero, and when the task processing network performs task processing for the tasks to be assigned according to the task group, the overall task cost determined by the total energy consumption and the processing delay is minimized.

[0163] In some embodiments, the task processing network includes an edge task processing network, a cloud task processing network and a terminal task processing network; the above-mentioned acquisition module 61 is also used to determine, based on the multiple tasks to be assigned, a first processing delay when the multiple tasks to be assigned are executed through the edge task processing network; based on the multiple tasks to be assigned, determine a second processing delay when the multiple tasks to be assigned are executed through the cloud task processing network; based on the multiple tasks to be assigned, determine a third processing delay when the multiple tasks to be assigned are executed through the terminal task processing network; according to the first weight variables corresponding to the edge task processing network, the cloud task processing network and the terminal task processing network respectively, the first processing delay, the second processing delay and the third processing delay are weightedly summed to obtain the processing delay.

[0164] In some embodiments, the above-mentioned acquisition module 61 is also used to determine the first task processing delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the edge task processing network; determine the first task transmission delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the edge task processing network and the terminal task processing network; add the first task processing delay of the edge task processing network and the first task transmission delay of the edge task processing network to obtain the first processing delay.

[0165] In some embodiments, the above-mentioned acquisition module 61 is also used to determine the second task processing delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the cloud task processing network; determine the second task transmission delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the cloud task processing network and the terminal task processing network; add the second task processing delay of the cloud task processing network and the second task transmission delay of the cloud task processing network to obtain the second processing delay.

[0166] In some embodiments, the acquisition module 61 is further used to determine a third processing delay when executing the multiple tasks to be assigned through the terminal task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the terminal task processing network.

[0167] In some embodiments, the task processing network includes an edge task processing network, a cloud task processing network and a terminal task processing network; the above-mentioned energy consumption module 62 is also used to determine, based on the multiple tasks to be assigned, a first energy consumption when executing the multiple tasks to be assigned through the edge task processing network; based on the multiple tasks to be assigned, determine a second energy consumption when executing the multiple tasks to be assigned through the cloud task processing network; based on the multiple tasks to be assigned, determine a third energy consumption when executing the multiple tasks to be assigned through the terminal task processing network; according to the second weight variables corresponding to the edge task processing network, the cloud task processing network and the terminal task processing network respectively, the first energy consumption, the second energy consumption and the third energy consumption are weightedly summed to obtain the total energy consumption.

[0168] In some embodiments, when the multiple tasks to be assigned are executed through the edge task processing network, the first energy consumption is the energy consumption of the terminal task processing network when the multiple tasks to be assigned are executed through the edge task processing network; the above-mentioned energy consumption module 62 is also used to determine the first task transmission delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the edge task processing network and the terminal task processing network; determine the first task processing delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the edge task processing network; determine the first transmission energy consumption of the terminal task processing network based on the first task transmission delay and the unit consumption of the terminal task processing network when transmitting tasks between the edge task processing network and the terminal task processing network; determine the first processing energy consumption of the terminal task processing network based on the first task processing delay and the unit energy consumption of the terminal task processing network when the edge task processing network performs task processing; add the first transmission energy consumption and the first processing energy consumption to obtain the first energy consumption.

[0169] In some embodiments, when the multiple tasks to be assigned are executed through the cloud task processing network, the first energy consumption is the energy consumption of the terminal task processing network when the multiple tasks to be assigned are executed through the cloud task processing network; the above-mentioned energy consumption module 62 is also used to determine the second task processing delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the cloud task processing network; determine the second task transmission delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the cloud task processing network and the terminal task processing network; determine the second transmission energy consumption of the terminal task processing network based on the second task transmission delay and the unit consumption of the terminal task processing network when transmitting tasks between the cloud task processing network and the terminal task processing network; determine the second processing energy consumption of the terminal task processing network based on the second task processing delay and the unit energy consumption of the terminal task processing network when the cloud task processing network performs task processing; add the second transmission energy consumption and the second processing energy consumption to obtain the second energy consumption.

[0170] In some embodiments, the energy consumption module 62 is also used to determine the reference energy consumption of the terminal task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the terminal task processing network; multiply the reference energy consumption of the terminal task processing network by the energy consumption parameter of the terminal task processing network to obtain the third energy consumption.

[0171] In some embodiments, the above-mentioned task allocation module 63 is also used to predict the allocation weight of each of the task processing networks based on the total energy consumption and the processing delay to obtain the predicted allocation weight of each of the task processing networks; multiply the number of the multiple tasks to be allocated by the predicted allocation weight of each of the task processing networks to obtain the number of tasks allocated to each of the task processing networks; for each of the task processing networks, determine the number of tasks to be allocated assigned to the task processing network as the task group corresponding to the task processing network.

[0172] In some embodiments, the above-mentioned task allocation module 63 is also used to traverse i and perform the following processing: according to the i-th explosion radius, based on the total energy consumption and the processing delay, the allocation weights of each of the task processing networks are predicted for the i-th time to obtain the i-th candidate allocation weights of each of the task processing networks; according to the differential mutation rule, the i-th candidate allocation weights of each of the task processing networks are mutated to obtain the i-th predicted allocation weight; i is not less than 1 and not greater than N, N is used to indicate the maximum prediction number of the allocation weight, and the i-th explosion radius is less than the i+1-th explosion radius; the N-th predicted allocation weight is determined as the predicted allocation weight.

[0173] In some embodiments, the above-mentioned task assignment module 63 is also used to perform the following processing for each of the task processing networks: when the task to be assigned exists in the task group corresponding to the task processing network, the task to be assigned in the task group corresponding to the task processing network is processed through the task processing network to obtain the task processing result corresponding to the task group.

[0174] It should be noted that: the task allocation device provided in the above embodiment only uses the division of the above program modules as an example when performing task allocation. In actual applications, the above processing allocation can be completed by different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the task allocation device provided in the above embodiment and the task allocation method embodiment on the electronic device side belong to the same concept. The specific implementation process is detailed in the task allocation method embodiment on the electronic device side, which will not be repeated here.

[0175] Based on the hardware implementation of the above program modules, and in order to implement the task allocation method on the electronic device side of the embodiment of the present application, the embodiment of the present application also provides an electronic device, Fig. 9 FIG. 1 is a schematic diagram of the hardware structure of the electronic device according to an embodiment of the present application. Fig. 9 As shown, the electronic device 80 includes:

[0176] The first communication interface 81 is capable of exchanging information with other devices (such as the second client);

[0177] The processor 82 is connected to the first communication interface 81 to implement information interaction with other devices (such as the second client) and is used to execute the task allocation method on the electronic device side provided above when running a computer program, and the computer program is stored in the first memory 83.

[0178] Specifically, the processor 82 is used to obtain a plurality of tasks to be assigned, and based on the plurality of tasks to be assigned, determine a processing delay when the plurality of tasks to be assigned are executed through the task processing network;

[0179] The first communication interface 81 is used to determine the total energy consumption when executing the multiple tasks to be assigned through the task processing network based on the multiple tasks to be assigned;

[0180] The processor 82 is also used to perform task allocation for the multiple tasks to be allocated based on the total energy consumption and the processing delay, so as to obtain task groups corresponding to each of the task processing networks; the number of the tasks to be allocated in the task group is at least zero, and when the task processing network performs task processing for the tasks to be allocated according to the task group, the overall task cost determined by the total energy consumption and the processing delay is minimized.

[0181] In one embodiment, the processor 82 is also used to determine, based on the multiple tasks to be assigned, a first processing delay when executing the multiple tasks to be assigned through the edge task processing network; based on the multiple tasks to be assigned, determine a second processing delay when executing the multiple tasks to be assigned through the cloud task processing network; based on the multiple tasks to be assigned, determine a third processing delay when executing the multiple tasks to be assigned through the terminal task processing network; and perform weighted summation of the first processing delay, the second processing delay and the third processing delay according to the first weight variables corresponding to the edge task processing network, the cloud task processing network and the terminal task processing network respectively, to obtain the processing delay.

[0182] In one embodiment, the processor 82 is further used to determine the first task processing delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the edge task processing network; determine the first task transmission delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the edge task processing network and the terminal task processing network; add the first task processing delay of the edge task processing network and the first task transmission delay of the edge task processing network to obtain the first processing delay.

[0183] In one embodiment, the processor 82 is further used to determine the second task processing delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the cloud task processing network; determine the second task transmission delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the cloud task processing network and the terminal task processing network; add the second task processing delay of the cloud task processing network and the second task transmission delay of the cloud task processing network to obtain the second processing delay.

[0184] In one embodiment, the processor 82 is further configured to determine a third processing delay when executing the plurality of tasks to be assigned through the terminal task processing network based on the task amounts of the plurality of tasks to be assigned and the task execution performance of the terminal task processing network.

[0185] In one embodiment, the first communication interface 81 is specifically used to: determine a first energy consumption when executing the multiple tasks to be assigned through the edge task processing network based on the multiple tasks to be assigned; determine a second energy consumption when executing the multiple tasks to be assigned through the cloud task processing network based on the multiple tasks to be assigned; determine a third energy consumption when executing the multiple tasks to be assigned through the terminal task processing network based on the multiple tasks to be assigned; and perform weighted summation of the first energy consumption, the second energy consumption and the third energy consumption according to the second weight variables corresponding to the edge task processing network, the cloud task processing network and the terminal task processing network respectively, to obtain the total energy consumption.

[0186] In one embodiment, the first communication interface 81 is further specifically used to: determine a first task transmission delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the edge task processing network and the terminal task processing network; determine a first task processing delay of the edge task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the edge task processing network; determine a first transmission energy consumption of the terminal task processing network based on the first task transmission delay and the unit consumption of the terminal task processing network when transmitting tasks between the edge task processing network and the terminal task processing network; determine a first processing energy consumption of the terminal task processing network based on the first task processing delay and the unit energy consumption of the terminal task processing network when the edge task processing network performs task processing; and add the first transmission energy consumption and the first processing energy consumption to obtain the first energy consumption.

[0187] In one embodiment, the first communication interface 81 is further specifically used to: determine the second task processing delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the cloud task processing network; determine the second task transmission delay of the cloud task processing network based on the task amount of the multiple tasks to be assigned and the task transmission speed between the cloud task processing network and the terminal task processing network; determine the second transmission energy consumption of the terminal task processing network based on the second task transmission delay and the unit consumption of the terminal task processing network when transmitting tasks between the cloud task processing network and the terminal task processing network; determine the second processing energy consumption of the terminal task processing network based on the second task processing delay and the unit energy consumption of the terminal task processing network when the cloud task processing network performs task processing; add the second transmission energy consumption and the second processing energy consumption to obtain the second energy consumption.

[0188] In one embodiment, the first communication interface 81 is further specifically used to: determine the reference energy consumption of the terminal task processing network based on the task amount of the multiple tasks to be assigned and the task execution performance of the terminal task processing network; multiply the reference energy consumption of the terminal task processing network by the energy consumption parameter of the terminal task processing network to obtain the third energy consumption.

[0189] In one embodiment, the processor 82 is further specifically used to: predict the allocation weights of each of the task processing networks based on the total energy consumption and the processing delay to obtain the predicted allocation weights of each of the task processing networks; multiply the number of the multiple tasks to be assigned by the predicted allocation weights of each of the task processing networks to obtain the number of tasks assigned to each of the task processing networks; and for each of the task processing networks, determine the number of tasks to be assigned assigned to the task processing network as the task group corresponding to the task processing network.

[0190] In one embodiment, the processor 82 is further specifically used to: traverse i to perform the following processing: according to the i-th explosion radius, based on the total energy consumption and the processing delay, perform the i-th prediction on the allocation weights of each of the task processing networks to obtain the i-th candidate allocation weights of each of the task processing networks; according to the differential mutation rule, mutate the i-th candidate allocation weights of each of the task processing networks to obtain the i-th predicted allocation weight; i is not less than 1 and not greater than N, N is used to indicate the maximum number of predictions of the allocation weight, and the i-th explosion radius is less than the i+1-th explosion radius; the N-th predicted allocation weight is determined as the predicted allocation weight.

[0191] In one embodiment, the processor 82 is further specifically used to: perform the following processing for each of the task processing networks respectively: when the task to be assigned exists in the task group corresponding to the task processing network, perform task processing on the task to be assigned in the task group corresponding to the task processing network through the task processing network to obtain the task processing result corresponding to the task group.

[0192] It should be noted that the specific processing process of the first communication interface 81 and the processor 82 can be understood by referring to the task allocation method on the electronic device side.

[0193] Of course, in actual application, the various components in the electronic device 80 are coupled together through the first bus system 84. It is understandable that the first bus system 84 is used to realize the connection and communication between these components. In addition to the data bus, the first bus system 84 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Fig. 9 In the figure, various buses are labeled as a first bus system 84 .

[0194] The first memory 83 in the embodiment of the present application is used to store various types of data to support the operation of the electronic device 80. Examples of such data include: any computer program used to operate on the electronic device 80.

[0195] The task allocation method on the electronic device side disclosed in the above embodiment of the present application can be applied to the processor 82, or implemented by the processor 82. The processor 82 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the task allocation method on the electronic device side can be completed by the hardware integrated logic circuit or software instructions in the processor 82. The above-mentioned processor 82 may be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 82 can implement or execute the task allocation method, steps and logic block diagrams on each electronic device side disclosed in the embodiment of the present application. A general-purpose processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the task allocation method on the electronic device side disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the first memory 83. The processor 82 reads the information in the first memory 83 and completes the steps of the task allocation method on the electronic device side in combination with its hardware.

[0196] In an exemplary embodiment, the electronic device 80 can be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), field programmable gate array (FPGA), general processor, controller, microcontroller (MCU), microprocessor, or other electronic components to execute the task allocation method on the aforementioned electronic device side.

[0197] It can be understood that the memory (including the first memory 83) of the embodiment of the present application can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAMbus random access memory (DRRAM, Direct Rambus Random Access Memory).The memories (including the first memory 83) described in the embodiments of the present application are intended to include but are not limited to these and any other suitable types of memories.

[0198] In an exemplary embodiment, the present application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, for example, including a first memory 83 storing a computer program, and the above-mentioned computer program can be executed by a processor 82 in an electronic device 80 to complete the steps of the task allocation method on the electronic device side described in the above-mentioned embodiment of the present application. Among them, the computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, FlashMemory, magnetic surface storage, optical disk, or CD-ROM.

[0199] It should be noted that: "first", "second", "third", etc. are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0200] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0201] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A task allocation method, characterized in that: A task allocation node applied to a cloud edge computing network, wherein the cloud edge computing network includes a plurality of task processing networks and the task allocation node, and the method includes: Acquire a plurality of tasks to be assigned, and determine, based on the plurality of tasks to be assigned, processing delays when the plurality of tasks to be assigned are executed through the task processing network; Based on the multiple tasks to be assigned, determining the total energy consumption when executing the multiple tasks to be assigned through the task processing network; Based on the total energy consumption and the processing delay, the plurality of tasks to be assigned are assigned to obtain task groups corresponding to the task processing networks respectively; The number of the tasks to be assigned in the task group is at least zero, and when the task processing network performs task processing for the tasks to be assigned according to the task group, the overall task cost determined by the total energy consumption and the processing delay is minimized.

2. The method according to claim 1, characterized in that The task processing network includes an edge task processing network, a cloud task processing network and a terminal task processing network; The determining, based on the plurality of tasks to be assigned, processing delays when executing the plurality of tasks to be assigned through the task processing network comprises: Based on the multiple tasks to be assigned, determining a first processing delay when executing the multiple tasks to be assigned through the edge task processing network; Based on the multiple tasks to be assigned, determining a second processing delay when executing the multiple tasks to be assigned through the cloud task processing network; Based on the plurality of tasks to be assigned, determining a third processing delay when executing the plurality of tasks to be assigned through the terminal task processing network; According to the first weight variables respectively corresponding to the edge task processing network, the cloud task processing network and the terminal task processing network, the first processing delay, the second processing delay and the third processing delay are weightedly summed to obtain the processing delay.

3. The method according to claim 2, characterized in that The determining, based on the plurality of tasks to be assigned, a first processing delay when executing the plurality of tasks to be assigned through the edge task processing network comprises: Determining a first task processing delay of the edge task processing network based on the task amounts of the multiple tasks to be assigned and the task execution performance of the edge task processing network; Determine a first task transmission delay of the edge task processing network based on the task amounts of the multiple tasks to be assigned and the task transmission speed between the edge task processing network and the terminal task processing network; The first task processing delay of the edge task processing network and the first task transmission delay of the edge task processing network are added to obtain the first processing delay.

4. The method according to claim 2, characterized in that: The determining, based on the plurality of tasks to be assigned, a second processing delay when executing the plurality of tasks to be assigned through the cloud task processing network comprises: Determining a second task processing delay of the cloud task processing network based on the task amounts of the multiple tasks to be assigned and the task execution performance of the cloud task processing network; Determining a second task transmission delay of the cloud task processing network based on the task amounts of the multiple tasks to be assigned and the task transmission speed between the cloud task processing network and the terminal task processing network; The second task processing delay of the cloud task processing network and the second task transmission delay of the cloud task processing network are added to obtain the second processing delay.

5. The method according to claim 2, characterized in that: The determining, based on the plurality of tasks to be assigned, a third processing delay when executing the plurality of tasks to be assigned through the terminal task processing network comprises: Based on the task amounts of the plurality of tasks to be assigned and the task execution performance of the terminal task processing network, a third processing delay when the plurality of tasks to be assigned are executed through the terminal task processing network is determined.

6. The method according to claim 1, characterized in that The task processing network includes an edge task processing network, a cloud task processing network and a terminal task processing network; The determining, based on the plurality of tasks to be assigned, the total energy consumption when executing the plurality of tasks to be assigned through the task processing network comprises: Based on the multiple tasks to be assigned, determining a first energy consumption when executing the multiple tasks to be assigned through the edge task processing network; Based on the multiple tasks to be assigned, determining a second energy consumption when executing the multiple tasks to be assigned through the cloud task processing network; Based on the multiple tasks to be assigned, determining a third energy consumption when executing the multiple tasks to be assigned through the terminal task processing network; According to the second weight variables corresponding to the edge task processing network, the cloud task processing network and the terminal task processing network respectively, the first energy consumption, the second energy consumption and the third energy consumption are weightedly summed to obtain the total energy consumption.

7. The method according to claim 6, characterized in that When the plurality of tasks to be assigned are executed through the edge task processing network, the first energy consumption is the energy consumption of the terminal task processing network when the plurality of tasks to be assigned are executed through the edge task processing network; The determining, based on the plurality of tasks to be assigned, a first energy consumption when executing the plurality of tasks to be assigned through the edge task processing network comprises: Determine a first task transmission delay of the edge task processing network based on the task amounts of the multiple tasks to be assigned and the task transmission speed between the edge task processing network and the terminal task processing network; Determining a first task processing delay of the edge task processing network based on the task amounts of the multiple tasks to be assigned and the task execution performance of the edge task processing network; Determine a first transmission energy consumption of the terminal task processing network based on the first task transmission delay and the unit consumption of the terminal task processing network when the task is transmitted between the edge task processing network and the terminal task processing network; Determining a first processing energy consumption of the terminal task processing network based on the first task processing delay and the unit energy consumption of the terminal task processing network when the edge task processing network performs task processing; The first transmission energy consumption and the first processing energy consumption are added to obtain the first energy consumption.

8. The method according to claim 6, characterized in that When the plurality of tasks to be assigned are executed through the cloud task processing network, the first energy consumption is the energy consumption of the terminal task processing network when the plurality of tasks to be assigned are executed through the cloud task processing network; The determining, based on the plurality of tasks to be assigned, a second energy consumption when executing the plurality of tasks to be assigned through the cloud task processing network comprises: Determining a second task processing delay of the cloud task processing network based on the task amounts of the multiple tasks to be assigned and the task execution performance of the cloud task processing network; Determining a second task transmission delay of the cloud task processing network based on the task amounts of the multiple tasks to be assigned and the task transmission speed between the cloud task processing network and the terminal task processing network; Determining a second transmission energy consumption of the terminal task processing network based on the second task transmission delay and the unit consumption of the terminal task processing network when the task is transmitted between the cloud task processing network and the terminal task processing network; Determining a second processing energy consumption of the terminal task processing network based on the second task processing delay and the unit energy consumption of the terminal task processing network when the cloud task processing network performs task processing; The second transmission energy consumption and the second processing energy consumption are added to obtain the second energy consumption.

9. The method according to claim 6, characterized in that The determining, based on the plurality of tasks to be assigned, a third energy consumption when executing the plurality of tasks to be assigned through the terminal task processing network comprises: Determining a reference energy consumption of the terminal task processing network based on the task amounts of the plurality of tasks to be assigned and the task execution performance of the terminal task processing network; The reference energy consumption of the terminal task processing network and the energy consumption parameter of the terminal task processing network are multiplied to obtain the third energy consumption.

10. The method according to claim 1, characterized in that The step of performing task allocation on the plurality of tasks to be allocated based on the total energy consumption and the processing delay to obtain task groups corresponding to the task processing networks respectively includes: Based on the total energy consumption and the processing delay, the allocation weight of each of the task processing networks is predicted to obtain the predicted allocation weight of each of the task processing networks; Multiplying the number of the plurality of tasks to be assigned by the predicted assignment weight of each of the task processing networks to obtain the number of tasks assigned by each of the task processing networks; For each of the task processing networks, the to-be-allocated tasks having the same number of tasks allocated by the task processing network are determined as a task group corresponding to the task processing network.

11. The method according to claim 10, characterized in that The step of predicting the allocation weight of each of the task processing networks based on the total energy consumption and the processing delay to obtain the predicted allocation weight of each of the task processing networks includes: Traversing i, the following processing is performed: according to the i-th explosion radius, based on the total energy consumption and the processing delay, the allocation weights of each of the task processing networks are predicted for the i-th time to obtain the i-th candidate allocation weights of each of the task processing networks; according to the differential mutation rule, the i-th candidate allocation weights of each of the task processing networks are mutated to obtain the i-th predicted allocation weights; i is not less than 1 and not greater than N, N is used to indicate the maximum number of predictions of the assigned weight, and the i-th explosion radius is less than the i+1-th explosion radius; The Nth prediction allocation weight is determined as the prediction allocation weight.

12. The method according to claim 1, characterized in that After allocating the multiple tasks to be allocated based on the total energy consumption and the processing delay to obtain task groups corresponding to the task processing networks, the method further includes: The following processing is performed for each of the task processing networks: When the task group corresponding to the task processing network contains the task to be assigned, the task processing network is used to perform task processing on the task group corresponding to the task processing network to obtain a task processing result corresponding to the task group.

13. A task allocation device, applied to a task allocation node of a cloud edge computing network, wherein the cloud edge computing network includes a plurality of task processing networks and the task allocation node, characterized in that: include: an acquisition module, used for acquiring a plurality of tasks to be assigned, and determining, based on the plurality of tasks to be assigned, a processing delay when the plurality of tasks to be assigned are executed through the task processing network; An energy consumption module, used for determining, based on the multiple tasks to be assigned, a total energy consumption when the multiple tasks to be assigned are executed through the task processing network; A task allocation module is used to allocate tasks to the multiple tasks to be allocated based on the total energy consumption and the processing delay to obtain task groups corresponding to each of the task processing networks; the number of the tasks to be allocated in the task group is at least zero, and when the task processing network performs task processing for the tasks to be allocated according to the task group, the overall task cost determined by the total energy consumption and the processing delay is minimized.

14. An electronic device, characterized in that: include: a processor and a first memory for storing a computer program executable on said processor; Wherein, when the processor is used to run the computer program, it executes the steps of the method described in any one of claims 1 to 12.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images