Internet of Things equipment computing power resource scheduling method and related equipment

Abstract

The invention provides an Internet of Things equipment computing power resource scheduling method and related equipment. The method comprises the steps that when a data processing request is detected, computing power task information of the data processing request is acquired, and the computing power task information comprises a task type and a computing power demand; determining a candidate scheduling strategy corresponding to the data processing request according to the task type, the computing power demand and an Internet of Things equipment resource global table; determining a target scheduling strategy from the candidate scheduling strategies according to the energy state table of the Internet of Things equipment; and according to the target scheduling strategy, performing computing power resource scheduling of the Internet of Things equipment for the data processing request. Compared with the prior art, a more intelligent and high-efficiency computing power resource scheduling scheme is realized by comprehensively considering various key factors such as task types, required computing power, availability of equipment resources and energy states, and the scheme can not only remarkably improve the utilization efficiency of resources, but also optimize energy management, so that the resource utilization rate is improved. Therefore, the energy consumption is reduced.

Description

Technical Field

[0001] This application relates to the field of Internet of Things communication, and in particular to a method for scheduling computing power resources of Internet of Things devices and related devices. Background Art

[0002] The Internet of Things refers to connecting any object to a network through information sensing devices according to an agreed protocol. The object exchanges and communicates information through an information dissemination medium to achieve functions such as intelligent identification, positioning, tracking, and supervision. With the rapid development of modern electronic technology and Internet technology, the Internet of Things has gradually penetrated into all aspects of life and production and has become an important part of people's daily life and production.

[0003] In an Internet of Things system, various devices and sensors will generate a large amount of data. This data needs to be processed and analyzed to be converted into valuable information to provide intelligent services for users. However, data processing consumes a large amount of computing resources, that is, the so-called computing power. Therefore, how to efficiently schedule the computing power resources of Internet of Things devices has become a key issue in the design of Internet of Things systems.

[0004] Currently, the scheduling of computing power resources of Internet of Things devices is mainly based on the load conditions of each device and follows the principle of load balancing. Although this scheduling method is simple and direct, it has some obvious limitations: it does not consider the special computing power requirements of different types of tasks, which may lead to some tasks being assigned to unsuitable devices, affecting the processing efficiency and resulting in low scheduling rationality.

[0005] Therefore, the current technology has the technical problem of low scheduling rationality and needs to be improved. Summary of the Invention

[0006] The embodiments of this application provide a method for scheduling computing power resources of Internet of Things devices and related devices, which has the advantages of improving resource utilization efficiency, optimizing energy management, extending the service life of devices, and enhancing scheduling flexibility.

[0007] To solve the above technical problems, the embodiments of this application provide the following technical solutions:

[0008] This application provides a method for scheduling computing power resources of Internet of Things devices, which is applied to a computing power scheduling device in an Internet of Things system. The Internet of Things system includes multiple Internet of Things devices. The method includes:

[0009] When detecting a data processing request, obtain the computing power task information of the data processing request. The computing power task information includes the task type and the computing power requirement.

[0010] Determine a candidate scheduling policy corresponding to the data processing request according to the task type, the computing power requirement, and the global table of Internet of Things device resources;

[0011] Determine a target scheduling policy from the candidate scheduling policies according to the energy state table of Internet of Things devices;

[0012] Perform computing power resource scheduling for Internet of Things devices for the data processing request according to the target scheduling policy.

[0013] In one embodiment, the foregoing method further includes:

[0014] Obtain the mains power supply parameters and new energy power supply parameters of each Internet of Things device;

[0015] Obtain the energy consumption parameters of each Internet of Things device when processing data processing requests of different task types;

[0016] Process the mains power supply parameters and new energy power supply parameters according to the trained prediction neural network to obtain an energy supply table of Internet of Things devices for a preset time period;

[0017] Associate the energy consumption parameters and the energy supply table of Internet of Things devices to generate the energy state table of Internet of Things devices.

[0018] In one embodiment, the foregoing determining a target scheduling policy from the candidate scheduling policies according to the energy state table of Internet of Things devices includes:

[0019] Determine the task time parameters of each candidate scheduling policy according to the data processing parameters and communication parameters of Internet of Things devices;

[0020] Determine the energy consumption parameters of each candidate scheduling policy according to the energy state table of Internet of Things devices; the energy consumption parameter is the difference between the mains consumption and the new energy consumption;

[0021] Determine a target scheduling policy from the candidate scheduling policies based on the task time parameters and the energy consumption parameters.

[0022] In one embodiment, the foregoing determining a target scheduling policy from the candidate scheduling policies based on the task time parameters and the energy consumption parameters includes:

[0023] Obtain a screening function;

[0024] Determine the sorting parameters of each candidate scheduling policy according to the screening function, the task time parameters, and the energy consumption parameters;

[0025] Determine the target scheduling policy according to the sorting parameters.

[0026] In one embodiment, determining a target scheduling policy from the candidate scheduling policies according to the energy state table of the Internet of Things devices includes:

[0027] Obtain the working environment parameters of each Internet of Things device;

[0028] Determine the life loss parameters corresponding to each candidate scheduling policy according to the working environment parameters, the data processing parameters, and the computing power task information;

[0029] Determine a target scheduling policy from the candidate scheduling policies based on the task time parameters, the energy consumption parameters, and the life loss parameters.

[0030] In one embodiment, determining a target scheduling policy from the candidate scheduling policies based on the task time parameters, the energy consumption parameters, and the life loss parameters includes:

[0031] Obtain a screening function;

[0032] Determine the sorting parameters of each candidate scheduling policy according to the screening function, the life loss parameters, the task time parameters, and the energy consumption parameters;

[0033] Determine the target scheduling policy according to the sorting parameters.

[0034] In one embodiment, the foregoing method further includes:

[0035] Obtain the computing power resource data of each Internet of Things device;

[0036] Determine the computing power type and computing power capacity of the minimum computing power unit under each Internet of Things device according to the computing power resource data;

[0037] Determine the global Internet of Things device resource table for a preset time according to the computing power type and computing power capacity.

[0038] In one embodiment, determining the candidate scheduling policy corresponding to the data processing request according to the task type, the computing power requirement, and the global Internet of Things device resource table includes:

[0039] Based on the global Internet of Things device resource table, determine the optional Internet of Things devices according to the correspondence between the task type and the computing power type;

[0040] Determine the candidate Internet of Things devices from the optional Internet of Things devices according to the matching relationship between the computing power requirement and the computing power capacity;

[0041] Determine the candidate scheduling policy according to the task type, the computing power requirement, and the candidate Internet of Things devices.

[0042] Meanwhile, this application also provides an Internet of Things device computing power resource scheduling device, which is arranged in the computing power scheduling device in the Internet of Things system, and the Internet of Things system includes multiple Internet of Things devices; the device includes:

[0043] An acquisition module, configured to acquire the computing power task information of the data processing request when detecting a data processing request, where the computing power task information includes a task type and a computing power requirement;

[0044] A matching module, configured to determine a candidate scheduling strategy corresponding to the data processing request according to the task type, the computing power requirement, and the global Internet of Things device resource table;

[0045] A determination module, configured to determine a target scheduling strategy from the candidate scheduling strategies according to the Internet of Things device energy status table;

[0046] A scheduling module, configured to perform Internet of Things device computing power resource scheduling for the data processing request according to the target scheduling strategy.

[0047] Meanwhile, this application provides a computer device, which includes a processor and a memory, and the memory stores multiple instructions, and the instructions are suitable for being loaded by the processor to execute the steps in the above method.

[0048] Meanwhile, this application provides a computer-readable storage medium, and the computer-readable storage medium stores multiple instructions, and the instructions are suitable for being loaded by the processor to execute the steps in the above method.

[0049] Meanwhile, this application provides a computer program product or a computer program, and the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium; the processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in the above method.

[0050] Beneficial effects: The present application provides an Internet of Things device computing power resource scheduling method and related devices; the method includes: when detecting a data processing request, obtaining the computing power task information of the data processing request, where the computing power task information includes the task type and the computing power requirement; determining a candidate scheduling strategy corresponding to the data processing request according to the task type, the computing power requirement, and the Internet of Things device resource global table; determining a target scheduling strategy from the candidate scheduling strategies according to the Internet of Things device energy status table; and performing Internet of Things device computing power resource scheduling for the data processing request according to the target scheduling strategy. Compared with the current technology, the present application realizes a more intelligent and efficient computing power resource scheduling scheme by comprehensively considering many key factors such as the type of task, the required computing power, the availability of device resources, and the energy status. This scheme can not only significantly improve the utilization efficiency of resources, but also optimize energy management, thereby reducing energy consumption; further, the present application helps to extend the service life of the device, and through flexible scheduling strategies, enhances the scheduling flexibility of the entire system, ensuring the optimization of resource allocation. In addition, the scheduling technology also has an adaptive learning ability, and can continuously adjust and optimize the scheduling strategy according to historical data and real-time feedback. It can monitor the system load and resource usage in real time, so as to dynamically adjust resource allocation to cope with changing workloads. This dynamic adjustment mechanism ensures that the system can maintain the best performance and response speed in the face of different working scenarios. Brief Description of the Drawings

[0051] The following will clearly show the technical solutions and their beneficial effects of the present application by describing the specific embodiments of the present application in detail with reference to the accompanying drawings.

[0052] Figure 1 is a schematic flowchart of the Internet of Things device computing power resource scheduling method provided by an embodiment of the present application;

[0053] Figure 2 is a schematic structural diagram of the Internet of Things device computing power resource scheduling device provided by an embodiment of the present application;

[0054] Figure 3 is a schematic structural diagram of a computer device provided by an embodiment of the present application. Detailed Embodiments

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0056] In the description of the embodiments of the present application, it should be understood that terms such as "first" and "second" in the specification, claims and drawings are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than that shown in the drawings or described content. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0057] In the current field of Internet of Things technology, the scheduling of computing power resources of devices mainly depends on the load conditions of each device, and the principle of load balancing is usually adopted for resource allocation. Although this load-based scheduling method is simple and direct and easy to implement, its limitations are also obvious. First, it does not fully consider the special requirements of different types of tasks for computing power resources, which may lead to some tasks being wrongly allocated to unsuitable devices, thus affecting the processing efficiency of the tasks. Second, this method ignores the energy consumption problem of Internet of Things devices during the scheduling process. In many application scenarios, Internet of Things devices may rely on battery power or use renewable energy. If only pursuing load balancing, it may lead to low energy utilization efficiency and thus cause unnecessary energy waste. Moreover, the existing scheduling methods do not consider factors such as the working environment and life loss of devices, which may cause some devices to be overused, thus shortening their service life.

[0058] This single scheduling method has led to a reduction in scheduling rationality. Specifically, it is manifested in the following aspects:

[0059] 1. Low resource utilization efficiency: Due to the lack of full consideration of the matching between task types and device characteristics, it may cause waste of resources or low processing efficiency.

[0060] 2. Poor management: The energy status of Internet of Things devices is ignored during the scheduling process, which may cause some devices to run out of energy, thus affecting the stable operation of the entire system.

[0061] 3. Insufficient life management: The working environment and service life of devices are not taken into account, which may cause some devices to be damaged prematurely, thus increasing the maintenance cost and replacement frequency.

[0062] 4. Flexibility: The existing scheduling strategies cannot be dynamically adjusted according to the real-time changing network conditions and task requirements, which limits the adaptability and flexibility of the scheduling strategies.

[0063] In view of the above problems, there is an urgent need for improvement in the prior art to enhance the rationality and efficiency of computing power resource scheduling for Internet of Things (IoT) devices. This may involve developing more intelligent scheduling algorithms that can comprehensively consider multiple factors such as task characteristics, device capabilities, energy status, and working environment to achieve more efficient and sustainable resource management.

[0064] To solve the above problems, this application proposes an IoT device computing power resource scheduling method for a computing power scheduling device applied to an IoT system. As Figure 1 shown, the method includes:

[0065] 101: When a data processing request is detected, obtain the computing power task information of the data processing request, where the computing power task information includes the task type and the computing power requirement;

[0066] 102: Determine the candidate scheduling strategies corresponding to the data processing request according to the task type, the computing power requirement, and the global IoT device resource table;

[0067] 103: Determine the target scheduling strategy from the candidate scheduling strategies according to the IoT device energy status table;

[0068] 104: Perform IoT device computing power resource scheduling for the data processing request according to the target scheduling strategy.

[0069] In some embodiments, in the IoT system, the computing power task information of the data processing request will include in detail the type of the task and the required computing power resources. Based on these detailed information and the global IoT device resource table, we can identify multiple candidate scheduling strategies corresponding to the data processing request. Subsequently, by referring to the IoT device energy status table, we can select an optimal target scheduling strategy from these candidate scheduling strategies. Finally, based on this target scheduling strategy, we can perform the scheduling work of the IoT device computing power resources for the data processing request.

[0070] The global IoT device resource table is determined by comprehensively integrating the computing power resource data of each IoT device, and it details the computing power type and computing power capacity of the smallest computing power unit under each IoT device. In this way, we can comprehensively understand the computing power resource situation of the IoT devices and perform reasonable scheduling based on this information.

[0071] The IoT device energy status table is obtained by processing the mains power supply parameters and new energy supply parameters of each IoT device, as well as the energy consumption parameters of each IoT device when processing data processing requests of different task types, through a trained prediction neural network. When determining the target scheduling strategy, we can select the optimal scheduling strategy based on the IoT device energy status table, combined with the task time parameters and energy consumption parameters.

[0072] Through the above method, we can effectively improve the rationality of the computing power resource scheduling of Internet of Things devices and solve the problem of low scheduling rationality existing in the prior art.

[0073] Specifically, when a data processing request is detected, we first need to obtain the computing power task information of the data processing request, which includes the type of the task and the required computing power resources. Then, based on the task type, computing power requirements, and the global table of Internet of Things device resources, we can determine the candidate scheduling strategies corresponding to the data processing request. Next, according to the energy status table of Internet of Things devices, we screen out the target scheduling strategy from the candidate scheduling strategies. Finally, based on this target scheduling strategy, we perform the scheduling of the computing power resources of Internet of Things devices for the data processing request.

[0074] In the whole process, the accuracy and timeliness of the global table of Internet of Things device resources and the energy status table of Internet of Things devices are crucial. The global table of Internet of Things device resources is determined by integrating the computing power resource data of each Internet of Things device, and it details the computing power type and computing power capacity of the minimum computing power unit under each Internet of Things device. The energy status table of Internet of Things devices is obtained by processing the mains power supply parameters and new energy supply parameters of each Internet of Things device, as well as the energy consumption parameters when each Internet of Things device processes data processing requests of different task types through a trained prediction neural network.

[0075] In this way, we can comprehensively understand the computing power resources and energy status of Internet of Things devices and perform reasonable scheduling based on this information, so as to effectively improve the rationality of the computing power resource scheduling of Internet of Things devices and solve the problem of low scheduling rationality existing in the prior art.

[0076] To further optimize the computing power resource scheduling of Internet of Things devices, system designers can adopt advanced prediction algorithms to predict future resource requirements. These algorithms can predict the computing power requirements of Internet of Things devices in different time periods based on historical data and real-time data, so as to make preparations for resource allocation and scheduling in advance. In addition, through machine learning technology, the system can continuously learn and adapt to the usage patterns of Internet of Things devices and dynamically adjust the scheduling strategy to adapt to the changing workload.

[0077] In practical applications, the computing power resource scheduling system of Internet of Things devices needs to have high scalability and flexibility. With the increase in the number of Internet of Things devices and the diversification of application scenarios, the system must be able to quickly adapt to new devices and new task types. For this reason, system designers can adopt a modular design method to decompose the scheduling system into multiple modules that can be independently updated and expanded to support the continuous evolution of the system.

[0078] In addition, to ensure the efficiency and reliability of the computing power resource scheduling of IoT devices, the system also needs to integrate advanced monitoring and fault diagnosis mechanisms. By monitoring the operating status and resource usage of IoT devices in real time, the system can timely detect potential problems and take preventive measures or respond quickly. The fault diagnosis mechanism can help quickly locate the source of problems, reduce system downtime, and improve the overall system stability.

[0079] In summary, by adopting prediction algorithms, machine learning technologies, modular design, and monitoring and fault diagnosis mechanisms, the computing power resource scheduling system of IoT devices can manage resources more intelligently and efficiently, meeting the growing demands of IoT applications. This not only improves the usage efficiency of IoT devices but also provides users with a more stable and reliable service experience.

[0080] Furthermore, Figure 1 The method shown further includes: obtaining the mains power supply parameters and new energy power supply parameters of each IoT device; obtaining the energy consumption parameters of each IoT device when processing data processing requests of different task types; processing the mains power supply parameters and new energy power supply parameters according to the trained prediction neural network to obtain the energy supply table of IoT devices for a preset time period; and associating the energy consumption parameters with the energy supply table of IoT devices to generate the energy status table of IoT devices.

[0081] The method proposed in this application involves a comprehensive process aimed at deeply understanding and mastering the energy supply and consumption status of each IoT device by collecting and analyzing the mains power supply parameters and new energy power supply parameters of each IoT device, and at the same time obtaining the energy consumption parameters of these devices when processing data processing requests of different task types. By using the trained prediction neural network to process these power supply parameters, this application can accurately predict the energy supply of IoT devices for a preset time period. Further, by combining the energy consumption parameters with the predicted energy supply situation, a detailed energy status table of IoT devices can be generated, which will provide strong data support for subsequent computing power resource scheduling.

[0082] To achieve the objectives of this application, obtaining the mains power supply parameters and new energy power supply parameters can be completed by installing special sensors on IoT devices, which can monitor the power input of the devices in real time and provide accurate data. As for the energy consumption parameters, they can be obtained through the built-in energy consumption monitoring modules of the devices, which can record in detail the actual energy consumption data of the devices when processing different types of tasks. The trained prediction neural network can be trained based on historical data and current power supply parameters, thus significantly improving the prediction accuracy. The generated energy status table can be stored using a database or other efficient data structures to ensure fast data query and real-time update.

[0083] By implementing the method described in this application, we can comprehensively consider the energy supply and consumption of each device when scheduling the computing power resources of Internet of Things devices, thereby significantly improving the rationality and efficiency of scheduling. Compared with existing technologies, this application not only considers load balancing but also comprehensively considers the energy supply and consumption, further optimizing the resource scheduling strategy and effectively solving the problem of low scheduling rationality in existing technologies. Therefore, this application has significant advantages in improving the rationality and efficiency of scheduling the computing power resources of Internet of Things devices, providing a new perspective and solution for the development and application of Internet of Things technology.

[0084] In addition, this application also involves the construction of an intelligent energy management system that can dynamically adjust the allocation of computing power resources according to the energy status table of Internet of Things devices. By monitoring and analyzing the energy usage of devices in real time, the system can automatically identify devices with low energy usage efficiency and take measures to optimize them. For example, the system can transfer tasks from devices with high energy consumption to devices with higher energy efficiency, or give priority to using new energy for power supply when the energy supply is sufficient, reducing the dependence on the main power supply.

[0085] To further improve the intelligence level of the system, this application also proposes an energy optimization algorithm based on machine learning. This algorithm can learn the energy usage patterns of devices and predict the energy demand in the next period of time. In this way, the system can make adjustments in advance, optimize the energy allocation, and reduce energy waste. In addition, the algorithm can also automatically adjust the parameters of the prediction model according to historical data and real-time data to adapt to changes in device usage patterns.

[0086] In practical applications, the methods and systems of this application can be widely used in many fields such as smart cities, smart factories, and smart homes. In a smart city, through the method of this application, efficient energy management of urban infrastructure can be achieved, improving energy usage efficiency and reducing carbon emissions. In a smart factory, this application can help the factory achieve intelligent energy management of devices, optimize the production process, and reduce downtime. In a smart home, this application can bring a more energy-saving lifestyle to household users, reducing household energy consumption through the energy optimization of smart devices.

[0087] In some embodiments, determining a target scheduling strategy from candidate scheduling strategies according to the energy status table of Internet of Things devices includes:

[0088] Based on the data processing parameters and communication parameters of the Internet of Things devices, determine the task time parameters of each candidate scheduling strategy. According to the energy status table of the Internet of Things devices, determine the energy consumption parameters of each candidate scheduling strategy; the energy consumption parameter is the difference between the mains power consumption and the new energy consumption. Based on the task time parameters and energy consumption parameters, determine the target scheduling strategy from the candidate scheduling strategies.

[0089] In this application, we propose an innovative technical solution that particularly focuses on the data processing parameters, communication parameters, and energy consumption parameters of Internet of Things devices. By deeply analyzing these key parameters, we can more accurately evaluate and determine the task time parameters and energy consumption parameters of each candidate scheduling strategy. This process helps us screen out the optimal target scheduling strategy from numerous candidate strategies, effectively solving the problem of low scheduling rationality in the existing technology.

[0090] Specifically, this application first obtains the data processing parameters and communication parameters of the Internet of Things devices. Based on these parameters, through a series of complex calculation processes, we can obtain the task time parameters of each candidate scheduling strategy. This step enables us to clearly understand the time cost required for each scheduling strategy in actual applications. In addition, we also use the energy status table of the Internet of Things devices to determine the energy consumption parameters of each candidate scheduling strategy, especially focusing on the difference between the mains power consumption and the new energy consumption. In this way, we can more reasonably balance the use of mains power and new energy, thereby achieving a more efficient and environmentally friendly resource scheduling.

[0091] To further illustrate the implementation manner of this application, we can consider a specific example. In this example, we design a screening function that can sort according to the specific criteria of the candidate scheduling strategies. These criteria include task time parameters and energy consumption parameters. By applying this screening function, we can assign a sorting parameter to each candidate scheduling strategy. Finally, based on these sorting parameters, we can select the optimal target scheduling strategy. This method not only considers the time efficiency of task execution but also fully considers the economy and environmental friendliness of energy consumption, thus making the scheduling process more reasonable and efficient.

[0092] In summary, this application proposes a more scientific and reasonable computing power resource scheduling method for Internet of Things devices by comprehensively considering task time parameters and energy consumption parameters. Compared with the existing technology, this application not only ensures that tasks can be completed within the scheduled time but also pays more attention to the utilization of new energy, effectively reducing the dependence on and consumption of mains power. This not only improves the rationality and efficiency of scheduling but also promotes the sustainable utilization of resources, with significant social and environmental benefits.

[0093] When further optimizing the scheduling strategy of Internet of Things devices, this application also takes into account environmental factors and the real-time status of devices. By introducing environmental monitoring data such as temperature, humidity, etc., and the real-time load conditions of devices, we can further refine the scheduling strategy to ensure that the scheduling strategy can maintain optimal performance under different environmental conditions and device working states. This dynamic adjustment mechanism makes the scheduling strategy more flexible and adaptable.

[0094] In addition, this application also proposes a prediction model based on machine learning, which can predict future workload and energy consumption trends according to historical data and real-time data. Through this prediction, the scheduling strategy can make adjustments in advance to cope with possible load changes and energy supply fluctuations. This not only improves the foresight of the scheduling strategy but also enhances the stability and reliability of the entire Internet of Things system.

[0095] In terms of actual deployment, this application also considers the scalability and compatibility of the system. Through modular design, new devices and functions can be easily integrated into the existing scheduling system without causing large-scale system reconstruction. This design enables the scheduling strategy of Internet of Things devices to evolve continuously with the development of technology and the changes in business requirements.

[0096] In summary, this application proposes a comprehensive set of scheduling strategies for Internet of Things devices by comprehensively considering data processing parameters, communication parameters, energy consumption parameters, as well as environmental factors and device real-time status. These strategies not only improve the efficiency and rationality of scheduling but also enhance the adaptability and foresight of the system, providing solid technical support for the efficient operation of Internet of Things devices.

[0097] In some embodiments, determining the target scheduling strategy from candidate scheduling strategies based on task time parameters and energy consumption parameters includes: it is necessary to obtain a screening function; according to the screening function, task time parameters, and energy consumption parameters, determine the sorting parameters of each candidate scheduling strategy; then, according to the sorting parameters, determine the target scheduling strategy.

[0098] The setting of the screening function can be flexibly adjusted according to different application scenarios. For example, it can be specifically set to give priority to those strategies with the shortest task completion time or to preferentially select those strategies with the lowest energy consumption. The determination of task time parameters can be carried out through actual measurement or estimation, which represents the time length required to complete a specific task. The energy consumption parameter reflects the total amount of energy consumed during the execution of the task.

[0099] By adopting this method, we can comprehensively consider the two key factors of task time and energy consumption among numerous candidate scheduling strategies, and then select the optimal target scheduling strategy. This can not only improve the rationality and efficiency of scheduling, but also effectively solve the problem of insufficient scheduling rationality existing in the prior art.

[0100] Specifically, the implementation of this method can be completed through the following steps: 1. Obtain and configure a screening function, which can be customized according to actual needs, such as giving priority to the strategy with the shortest task time or the strategy with the lowest energy consumption. 2. Use the task time parameter and the energy consumption parameter to calculate the sorting parameter for each candidate scheduling strategy. This sorting parameter can be the weighted sum of task time and energy consumption, or a comprehensive score based on other criteria. 3. Sort all candidate scheduling strategies according to the calculated sorting parameter, and finally select the strategy with the highest ranking as the target scheduling strategy.

[0101] As a preferred implementation of this method, we can further consider other relevant factors, such as the importance of tasks and the current load of devices, to conduct a multi-dimensional comprehensive evaluation of candidate scheduling strategies. In this way, we can more comprehensively evaluate each scheduling strategy and thus select the truly optimal target scheduling strategy.

[0102] By applying the above method, we can minimize energy consumption as much as possible while ensuring the task completion efficiency, achieving the goal of equal emphasis on energy conservation and high efficiency. Compared with the prior art, the method proposed in this application has significantly improved in terms of scheduling rationality and flexibility, and can better adapt to the complex and changeable Internet of Things environment, providing strong support for the development of related technologies.

[0103] In practical applications, the setting and use of this screening function need to be combined with the specific working environment and task characteristics. For example, in an environment that requires quick response, the weight of task completion time may be set higher to ensure that tasks can be completed quickly. In an energy-sensitive application scenario, the weight of energy consumption may be increased to achieve long-term energy conservation.

[0104] In addition, to further optimize the scheduling strategy, a dynamic adjustment mechanism can be introduced. This means that during the task execution process, the weights of task time and energy consumption can be dynamically adjusted according to real-time data to cope with environmental changes and fluctuations in task requirements. This dynamic adjustment mechanism can make the scheduling strategy more flexible and adaptable.

[0105] During the implementation process, it is also necessary to consider the priority and urgency of tasks. Some tasks may need to be processed first due to their importance or urgency, even if they are not the optimal strategies in terms of time or energy consumption. Therefore, the screening function should also include an assessment of task priority to ensure that critical tasks can be processed in a timely manner.

[0106] To ensure the implementation effect of the scheduling strategy, a feedback mechanism can be established to evaluate and analyze the executed scheduling strategy. By collecting the actual data of task execution, the parameters of the screening function can be continuously adjusted to optimize future scheduling decisions. This continuous improvement process helps to enhance the overall performance of the scheduling system.

[0107] In summary, through a carefully designed screening function and comprehensive consideration of various factors, we can build an efficient and energy-saving scheduling system. This can not only meet the complex requirements in the current Internet of Things environment but also provide a solid foundation for the development of future technologies.

[0108] In some embodiments, according to the energy status table of Internet of Things devices, determining a target scheduling strategy from candidate scheduling strategies includes: obtaining the working environment parameters of each Internet of Things device; determining the life loss parameters corresponding to each candidate scheduling strategy according to the working environment parameters, data processing parameters, and computing power task information; and determining the target scheduling strategy from the candidate scheduling strategies based on the task time parameters, energy consumption parameters, and life loss parameters.

[0109] In the Internet of Things system, obtaining the working environment parameters of each Internet of Things device is to more accurately understand the operating conditions of Internet of Things devices in different environments. These working environment parameters may include factors such as temperature, humidity, and vibration, which will affect the operating efficiency and life of the devices. By obtaining these parameters, the status of Internet of Things devices can be more comprehensively evaluated, providing a scientific basis for device maintenance and management.

[0110] Then, according to the working environment parameters, data processing parameters, and computing power task information, determine the life loss parameters corresponding to each candidate scheduling strategy. The life loss parameter refers to the life value consumed by the device when executing a specific task. Different working environments and task types will have different impacts on the life of the device. Therefore, these factors need to be comprehensively considered to calculate the life loss parameters to ensure the scientificity and rationality of the scheduling strategy.

[0111] Based on the task time parameters, energy consumption parameters, and life loss parameters, determine the target scheduling strategy from the candidate scheduling strategies. The task time parameter refers to the time required to complete a specific task, and the energy consumption parameter refers to the energy consumption required to complete the task. By comprehensively considering these parameters, a scheduling strategy that achieves the best balance among task time, energy consumption, and device life loss can be selected to achieve the optimal allocation of resources.

[0112] For example, in a specific application scenario, if the working environment temperature of a certain Internet of Things device is relatively high and its life loss parameter may be relatively large, then when scheduling, other devices with better working environments may be preferentially selected to execute tasks, so as to extend the service life of the device and avoid premature aging caused by high-temperature environments.

[0113] Therefore, by comprehensively considering the working environment parameters, task time parameters, energy consumption parameters, and life loss parameters, the present application can more reasonably schedule the computing power resources of Internet of Things devices, thereby improving the rationality of scheduling and the service life of the devices. Compared with the prior art, the scheduling method of the present application is more comprehensive and intelligent, can extend the service life of the devices while ensuring the efficient completion of tasks, reduce the maintenance and replacement costs of the devices, and thus provide strong support for the stable operation and sustainable development of the Internet of Things system.

[0114] In the Internet of Things system, the monitoring of the health status of devices is crucial. By real-time monitoring of the working environment parameters of the devices, potential problems can be discovered in a timely manner and preventive measures can be taken. For example, when it is detected that the temperature or humidity of the device exceeds the normal range, the system can automatically adjust the working mode of the device or issue an alarm to prevent the device from being damaged due to environmental factors.

[0115] In addition, the scheduling of the computing power resources of Internet of Things devices not only needs to consider the life loss of the devices, but also should consider the load balancing of the devices. By reasonably allocating tasks to avoid some devices working excessively while other devices are idle, the service life of the entire Internet of Things system can be effectively extended. The implementation of the load balancing strategy requires comprehensive consideration of the real-time working status and historical working data of the devices to achieve the optimal allocation of resources.

[0116] In practical applications, the scheduling strategy of Internet of Things devices should also have a certain adaptive ability. With the change of the environment and the fluctuation of task requirements, the scheduling strategy should be able to dynamically adjust to adapt to the new working conditions. For example, when the devices in a certain area need to be temporarily offline for maintenance, the scheduling system should be able to automatically re-allocate the tasks to other devices to ensure the continuity and stability of the entire system.

[0117] In summary, the scheduling of the computing power resources of Internet of Things devices is a complex and dynamic process that requires comprehensive consideration of various factors. Through intelligent scheduling algorithms, the efficient operation and maximum life of the devices can be achieved. This not only improves the performance of the Internet of Things system, but also brings a better service experience to users, while reducing the long-term operation costs.

[0118] In some embodiments, the present application further includes: determining a target scheduling policy from candidate scheduling policies based on task time parameters, energy consumption parameters, and life loss parameters, including obtaining a screening function, determining sorting parameters for each candidate scheduling policy according to the screening function, the life loss parameters, the task time parameters, and the energy consumption parameters, and determining the target scheduling policy according to the sorting parameters.

[0119] In the Internet of Things system, computing power resource scheduling is a complex and crucial process. To achieve more efficient resource utilization, the present application proposes a multi-parameter-based scheduling method. This method sorts candidate scheduling policies by obtaining a screening function and combining life loss parameters, task time parameters, and energy consumption parameters to determine the optimal target scheduling policy. Specifically, the screening function can be adjusted according to different application scenarios to adapt to different scheduling requirements. For example, in scenarios that require quick response, the screening function may attach more importance to task time parameters, while in energy-sensitive applications, it may focus more on energy consumption parameters.

[0120] The acquisition of the screening function can be achieved in various ways, such as through historical data analysis, machine learning model training, etc. Historical data analysis can reveal the performance of devices under different working conditions, while machine learning models can learn more accurate screening functions based on a large amount of data. The acquisition of life loss parameters requires considering the working environment parameters, data processing parameters, and computing power task information of Internet of Things devices. These parameters jointly determine the degree of life loss of the device. Therefore, when obtaining these parameters, factors such as the usage frequency, working temperature, and data processing volume of the device need to be comprehensively considered.

[0121] The acquisition of task time parameters and energy consumption parameters can be realized by the monitoring system collecting the running state information of each Internet of Things device in real time. The monitoring system can record the startup time, task execution time, idle time, etc. of the device, and the energy consumption parameters can be calculated from sensor data such as current and voltage. Through the above technical means, the scheduling method of the present application can comprehensively evaluate each candidate scheduling policy on the basis of considering task time, energy consumption, and device life, so as to select the optimal target scheduling policy. Compared with the prior art, this method not only improves the rationality of scheduling, but also effectively extends the service life of Internet of Things devices and reduces energy consumption. Thus, the present application provides a more efficient and intelligent solution to solve the problem of low scheduling rationality in the prior art. In addition, this method can also dynamically adjust the scheduling policy according to the actual running situation of the device, further improving the overall performance and reliability of the Internet of Things system.

[0122] In practical applications, the scheduling method of the present application also takes into account the heterogeneity of IoT devices. Since there are a wide variety of devices in the IoT system, and the computing power, energy consumption, and lifespan characteristics of each device are different, a scheduling strategy that can adapt to different device characteristics is required. By introducing device characteristic parameters, this method enables the scheduling strategy to make more personalized decisions according to the specific situation of the device. For example, for devices with low energy consumption but weak computing power, the scheduling strategy will tend to allocate tasks with smaller computational amounts to ensure the stable operation of the device and extend its lifespan.

[0123] In addition, the present application also proposes a dynamic adjustment mechanism to cope with the uncertainties and changes that may occur during the operation of the IoT system. In the IoT environment, the arrival of tasks is often random, and the urgency and resource requirements of tasks also vary. The dynamic adjustment mechanism can monitor the system state in real time and dynamically adjust the scheduling strategy according to the current resource usage situation and task queue to handle emergencies and ensure the stability of system performance and the timely completion of tasks.

[0124] To verify the effectiveness of the method of the present application, we conducted a large number of simulation experiments. The experimental results show that compared with traditional scheduling methods, the method of the present application has significantly improved in terms of task completion rate, system response time, and device lifespan extension. This not only proves the superiority of this method in theory but also demonstrates its great potential in practical applications. In the future, we plan to apply this scheduling method to a wider range of IoT scenarios to further optimize resource scheduling and improve the operating efficiency and sustainability of the entire IoT system.

[0125] In some embodiments, Figure 1 The method shown includes: obtaining the computing power resource data of each IoT device; determining the computing power type and computing power capacity of the minimum computing power unit under each IoT device according to the computing power resource data; and determining the global IoT device resource table for a preset time according to the computing power type and computing power capacity.

[0126] The present application proposes an innovative method for the computing power resource scheduling problem of IoT devices. By obtaining the computing power resource data of each IoT device, we can comprehensively understand the computing power situation of IoT devices. This process includes the detailed collection and analysis of the computing power resources of the devices to ensure the integrity and accuracy of the data. Further, based on these detailed data, we can determine the computing power type and computing power capacity of the minimum computing power unit under each IoT device, so as to more detailedly grasp the computing power details of each device. This step involves an in-depth understanding and classification of the device computing power, providing a solid foundation for subsequent resource scheduling.

[0127] In the process of obtaining the computing power resource data of each IoT device, we have adopted a variety of methods to ensure the real-time and accuracy of the data. For example, real-time data collection can be performed through the monitoring module that comes with the device, so that the computing power status of the device can be tracked in real time, and any changes can be discovered and responded to in a timely manner. Alternatively, we can also update the data by regularly scanning the devices in the network to ensure the timeliness and integrity of the data. To determine the computing power type and computing power capacity of the minimum computing power unit, we can conduct an in-depth analysis of the hardware configuration of the device and infer it based on the historical operation data of the device, so as to obtain a more accurate computing power assessment. The global table of IoT device resources at a preset time can be automatically generated by the software system and dynamically adjusted according to the actual situation to adapt to the changing computing power requirements and scheduling environment.

[0128] Through this method, it is possible to achieve refined management of the computing power resources of IoT devices and improve the rationality and efficiency of computing power resource scheduling. Compared with the prior art, the method of this application can more comprehensively consider the computing power of the device and provide a more accurate scheduling strategy, thereby effectively solving the problem of low scheduling rationality in current scheduling technology. This method not only improves the efficiency of resource utilization, but also optimizes the performance of the entire IoT system, providing strong support for the efficient operation of IoT devices.

[0129] In the process of implementing the method of this application, we also considered the diversity and complexity of IoT devices. We designed a flexible computing resource scheduling strategy for different types of devices. For example, for computing-intensive devices, we may pay more attention to their processing speed and parallel computing capabilities; while for storage-intensive devices, we may pay more attention to their storage capacity and data reading and writing speed. Through this targeted scheduling strategy, we can ensure that each device can maximize its performance in the field where it excels.

[0130] In addition, this application also takes into account the dynamic changes of IoT devices in actual applications. The computing power resources of the device may change due to various factors, such as hardware aging, software updates, network conditions, etc. Therefore, we have designed a dynamic adjustment mechanism that can monitor the computing power status of the device in real time and automatically adjust resource allocation according to actual conditions. This mechanism ensures the flexibility and adaptability of IoT device resource scheduling and can cope with various emergencies.

[0131] In order to further improve scheduling efficiency, this application also introduces artificial intelligence algorithms. Through machine learning and data analysis technology, the system can predict the computing power demand trend of the device, so as to make resource scheduling decisions in advance. This predictive scheduling can not only reduce resource waste, but also improve the response speed and stability of the entire IoT system. Ultimately, this will bring users a smoother and more efficient IoT application experience.

[0132] In some embodiments, determining a candidate scheduling policy corresponding to a data processing request according to the task type, computing power requirements, and the global table of Internet of Things device resources includes: determining optional Internet of Things devices based on the global table of Internet of Things device resources according to the correspondence between the task type and the computing power type; determining candidate Internet of Things devices from the optional Internet of Things devices according to the matching relationship between the computing power requirements and the computing power capacity; and determining the candidate scheduling policy according to the task type, computing power requirements, and the candidate Internet of Things devices.

[0133] The technical solution proposed in this application first identifies a series of optional Internet of Things devices in the global table of Internet of Things device resources according to the correspondence between the task type and the computing power type. This initial screening process ensures that the selected Internet of Things devices can meet the basic type requirements of the task, laying a foundation for subsequent screening and determination of the scheduling policy. Subsequently, according to the matching relationship between the computing power requirements and the computing power capacity, candidate Internet of Things devices that meet the requirements are further screened out from these optional Internet of Things devices. This step ensures that the selected devices not only match the task in type but also meet the specific computing power capacity requirements of the task. Finally, combining the task type, computing power requirements, and the specific situation of the candidate Internet of Things devices, the final candidate scheduling policy is determined. Through this phased screening and comprehensive consideration method, the scheduling policy can be effectively optimized, improving the rationality and efficiency of scheduling and ensuring the smooth completion of the task.

[0134] In the technical solution of this application, the newly added technical features or steps include: first, determining a series of optional Internet of Things devices in the global table of Internet of Things device resources according to the correspondence between the task type and the computing power type; second, screening out candidate Internet of Things devices that meet the requirements from these optional Internet of Things devices according to the matching relationship between the computing power requirements and the computing power capacity; and finally, determining the final candidate scheduling policy by combining the task type, computing power requirements, and the specific situation of the candidate Internet of Things devices. The specific implementation methods of these steps can include: preferentially considering those devices with higher computing power capacity and lower current load as candidate Internet of Things devices; when determining the candidate scheduling policy, comprehensively considering factors such as the communication delay, task execution time, and other factors that may affect the scheduling effect of the device to further optimize the scheduling effect and ensure the efficient execution of the task.

[0135] Through the technical solution proposed in this application, the problem of low scheduling rationality in the prior art is effectively solved. Compared with the prior art, this application not only considers the correspondence between task types and computing power types, but also comprehensively considers the matching relationship between computing power requirements and computing power capacity, so as to more accurately determine candidate Internet of Things devices. Thereby, while ensuring the smooth execution of tasks, the utilization rate of computing power resources can be improved, unnecessary energy consumption can be reduced, and the service life of the device can be extended. In this way, not only the rationality and efficiency of scheduling are improved, but also the computing power resource scheduling process of Internet of Things devices is effectively optimized, providing strong technical support for the further development and application of Internet of Things technology.

[0136] In some embodiments, determining a candidate scheduling strategy corresponding to a data processing request according to a task type, computing power requirements, and a global Internet of Things device resource table includes: determining optional Internet of Things devices based on the global Internet of Things device resource table according to the correspondence between task types and computing power types; obtaining load parameters of each optional Internet of Things device; determining candidate Internet of Things devices from the set of optional Internet of Things devices according to the matching relationship between computing power requirements and computing power capacity, and the load parameters; and determining a candidate scheduling strategy according to the task type, computing power requirements, and candidate Internet of Things devices.

[0137] This technical solution determines candidate Internet of Things devices by obtaining the load parameters of optional Internet of Things devices and combining the matching relationship between computing power requirements and computing power capacity, thereby forming a candidate scheduling strategy. This process not only considers the current load situation of the device, but also comprehensively considers the computing power capacity of the device, ensuring that while meeting the computing power requirements, resources can be utilized more efficiently. In this way, on the premise of ensuring that the computing power requirements are met, the use efficiency of resources can be further optimized, avoiding the problem of low scheduling rationality brought about by the scheduling method based solely on load balancing, thereby improving the overall scheduling efficiency and resource utilization rate.

[0138] Specifically, the solution first screens out the optional IoT devices from the global IoT device resource table according to the correspondence between the task type and the computing power type. This screening process is based on a deep understanding of the task requirements, ensuring that from a global perspective, the most suitable devices for the current task requirements are selected. Then, the load parameters of these optional IoT devices are obtained, which can include the current usage rate, remaining computing power capacity, etc., providing detailed data support for subsequent decision-making. Next, according to the matching relationship between the computing power demand and the computing power capacity, as well as the load parameters, the candidate IoT devices that meet the conditions are further screened out from the set of optional IoT devices. This process is dynamic and can adjust the candidate device list according to real-time data, ensuring the flexibility and adaptability of the scheduling strategy. Finally, based on the task type, computing power demand, and candidate IoT devices, the final candidate scheduling strategy is determined. This strategy is carefully calculated and optimized to maximize the satisfaction of the computing power demand while minimizing resource waste.

[0139] In this way, the scheduling method provided by this application can optimize the use of computing power resources of IoT devices to a greater extent, improve the rationality and efficiency of scheduling, and solve the problem of low scheduling rationality in the prior art. Thus, while meeting the computing power demand, the use of resources can be optimized, and the overall performance of the IoT system can be improved. This technical solution not only improves the resource utilization efficiency but also enhances the stability and reliability of the system, providing strong technical support for the further development and application of IoT technology.

[0140] In addition, this technical solution also takes into account the diversity and heterogeneity of IoT devices, classifying and managing different types of devices through intelligent algorithms. This enables the scheduling strategy to be more refined and personalized, adapting to the characteristics and working environments of different devices. For example, for those devices with high energy consumption characteristics, the scheduling strategy will give priority to their energy efficiency ratio to reduce energy consumption and extend the service life of the devices.

[0141] In practical applications, this technical solution also introduces a prediction mechanism to predict the computing power demand and device load conditions in the next period of time through historical data and real-time monitoring information. This enables the scheduling strategy to not only respond to the current resource demand but also make adjustments in advance to cope with possible load fluctuations and changes in computing power demand. In this way, the system can handle sudden tasks more smoothly and reduce task delays or failures caused by insufficient resources.

[0142] In summary, by comprehensively considering the load parameters of the device, the relationship between computing power requirements and capacity matching, the device type and working environment, as well as the prediction of future resource requirements, the present technical solution provides an efficient, intelligent, and highly adaptable scheduling strategy for IoT devices. This not only improves the resource utilization efficiency and scheduling rationality of the IoT system, but also enhances the stability and reliability of the system, laying a solid foundation for the wide application of IoT technology.

[0143] Based on the content of the above embodiments, an embodiment of the present application provides an IoT device computing power resource scheduling device, which can be set in a computing power scheduling device in an IoT system. The computing power scheduling device can be any server or a server cluster formed by any combination of these servers. This device is used to execute the method provided in the above method embodiments. Please refer to Figure 2 , and this device includes:

[0144] An acquisition module 201, configured to acquire computing power task information of the data processing request when detecting a data processing request, where the computing power task information includes a task type and computing power requirements;

[0145] A matching module 202, configured to determine a candidate scheduling strategy corresponding to the data processing request according to the task type, the computing power requirements, and the global IoT device resource table;

[0146] A determination module 203, configured to determine a target scheduling strategy from the candidate scheduling strategies according to the IoT device energy status table;

[0147] A scheduling module 204, configured to perform IoT device computing power resource scheduling for the data processing request according to the target scheduling strategy.

[0148] The present application will be further described in conjunction with specific embodiments.

[0149] In some scenarios, the present application proposes an IoT device computing power resource scheduling method, which is applied to a computing power scheduling device in an IoT system, and the IoT system includes multiple IoT devices. This method includes:

[0150] In order to effectively manage the computing power of IoT devices, we are committed to collecting computing power data of various devices. Through these data, we can identify the types and capacities of the smallest computing units in each device. Based on this type and capacity information, we formulate a global IoT device resource table within a predetermined time, thereby providing a basis for the reasonable allocation and scheduling of resources.

[0151] In addition, we have also collected the mains power and new energy power supply parameters of various IoT devices, as well as their energy consumption data when processing different types of task data. Using our well-trained predictive neural network, we integrated the mains power and new energy power supply parameters to generate an energy supply table for IoT devices within a predetermined time range. By combining the energy consumption data with the energy supply table, we created an energy status table for IoT devices, which helps us better understand and manage the energy usage of the devices.

[0152] When the IoT system detects a data processing request, we extract the computing task information in the request. This information details the task type and computing requirements, providing key inputs for subsequent scheduling decisions.

[0153] Based on the task type, computing requirements, and the global IoT device resource table, we determine the candidate scheduling schemes corresponding to the data processing request. Specifically, we use the correspondence between the task type and the computing type to select the optional devices from the global IoT device resource table. Then, according to the matching relationship between the computing requirements and the computing capacity, we determine the candidate devices from the optional devices. Finally, by combining the task type, computing requirements, and candidate devices, we determine the candidate scheduling schemes. In some cases, we also obtain the load parameters of each optional device, and based on the matching relationship between the computing requirements and the computing capacity and the load parameters, we determine the candidate devices from the set of optional devices, and then determine the candidate scheduling schemes according to the task type, computing requirements, and candidate devices.

[0154] Next, we will select the target scheduling plan from the candidate scheduling plans based on the energy status table of the Internet of Things devices. Specifically, we will determine the task time parameters of each candidate scheduling plan according to the data processing and communication parameters of the Internet of Things devices. Then, we will determine the energy consumption parameters of each candidate scheduling plan based on the energy status table of the Internet of Things devices, where the energy consumption parameter is the difference between the mains power consumption and the new energy consumption. Based on the task time parameters and the energy consumption parameters, we select the target scheduling plan from the candidate scheduling plans. Further, we may obtain a screening function, and determine the sorting parameters of each candidate scheduling plan according to the screening function, the task time parameters, and the energy consumption parameters, and select the target scheduling plan according to the sorting parameters. Or, we may obtain the working environment parameters of each Internet of Things device, and determine the life loss parameters corresponding to each candidate scheduling plan according to the working environment parameters, the data processing parameters, and the computing task information, and select the target scheduling plan from the candidate scheduling plans based on the task time parameters, the energy consumption parameters, and the life loss parameters. Further, based on the task time parameters, the energy consumption parameters, and the life loss parameters, we select the target scheduling plan from the candidate scheduling plans, including obtaining a screening function, determining the sorting parameters of each candidate scheduling plan according to the screening function, the life loss parameters, the task time parameters, and the energy consumption parameters, and selecting the target scheduling plan according to the sorting parameters.

[0155] Once the target scheduling plan is determined, we will schedule the computing resources of the Internet of Things devices according to this plan to meet the data processing requests.

[0156] This technical solution constructs an energy status table of Internet of Things devices by obtaining the computing resource data and energy supply parameters of each Internet of Things device. When a data processing request is detected, candidate scheduling plans are determined based on the task type, computing requirements, and the global resource table of Internet of Things devices, and the target scheduling plan is selected using the energy status table, and finally the computing resource scheduling is executed. This can achieve more reasonable computing resource scheduling, improve the scheduling efficiency, and reduce energy consumption.

[0157] Specifically, by introducing a trained prediction neural network, this technical solution can accurately predict the energy supply of each Internet of Things device within a predetermined time period, and generate an energy status table in combination with the energy consumption parameters, so as to balance the energy supply and consumption during the scheduling process and optimize the use efficiency of computing resources. Further, by obtaining the working environment parameters and life loss parameters, the service life of the device can be considered in the scheduling plan, thereby extending the service life of the device and reducing the maintenance cost.

[0158] In summary, the computing resource scheduling method for Internet of Things devices proposed in this technical solution can optimize energy usage and device lifespan while ensuring task processing efficiency through multi-dimensional data acquisition and analysis, combined with a prediction neural network and a screening function, solving the problem of low scheduling rationality in the prior art.

[0159] In addition, this technical solution also takes into account the real-time status of Internet of Things devices. By dynamically monitoring the device's operating conditions, the global resource table and the energy status table are updated in real time. This dynamic adjustment mechanism ensures that the scheduling strategy can respond promptly to changes in the device status, thereby further improving the flexibility and accuracy of resource scheduling.

[0160] In practical applications, this technical solution can also support the processing of multiple task priorities. By setting different priority rules, the system can dynamically adjust resource allocation according to the urgency and importance of tasks, ensuring that critical tasks can be processed first while ensuring the stable operation of the overall system.

[0161] To further improve the reliability and stability of the system, this technical solution also introduces a fault tolerance mechanism. When a certain Internet of Things device fails or its performance deteriorates, the system can automatically identify and reallocate computing tasks, avoiding the impact of a single point of failure on the entire system and ensuring the continuity and integrity of data processing.

[0162] In summary, by comprehensively considering various factors such as computing resources, energy supply, device status, and task priorities, this technical solution provides an efficient, flexible, and reliable computing resource scheduling method for Internet of Things devices. This method can not only optimize resource utilization, extend device lifespan, but also ensure stable operation in various complex environments, meeting the application requirements in different scenarios.

[0163] Correspondingly, an embodiment of this application also provides a computer device, which includes a server or a terminal, etc.

[0164] As Figure 3 shown, this computer device may include a processor 301 with one or more processing cores, a memory 302 including one or more computer-readable storage media, an input unit 303, a display unit 304, a wireless fidelity (WiFi) module 305, a power supply 306, and a radio frequency (RF) circuit 307, and other components. Those skilled in the art can understand that Figure 3 the computer device structure shown in

[0165] The processor 301 is the control center of the computer device, connecting various parts of the entire mobile phone through various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 302, and by invoking the data stored in the memory 302, it executes various functions of the computer device and processes data.

[0166] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302. The input unit 303 can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0167] The display unit 304 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the computer device. These graphical user interfaces can be composed of graphics, text, icons, videos, and any combination thereof.

[0168] WiFi belongs to short - range wireless transmission technology. The computer device can help users send and receive emails, browse the web, and access streaming media through the WiFi module 305. It provides users with wireless broadband Internet access. Although Figure 3 the WiFi module 305 is shown, it can be understood that it does not belong to an essential component of the computer device and can be completely omitted within the scope of not changing the essence of the application as needed.

[0169] The computer device also includes a power supply 306 (such as a battery) for powering each component. Preferably, the power supply can be logically connected to the processor 301 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system.

[0170] The radio frequency circuit 307 can be used for receiving and sending signals during information reception or call processes. Specifically, after receiving the downlink information from the base station, it is handed over to one or more processors 301 for processing; in addition, the data related to the uplink is sent to the base station.

[0171] Although not shown, the computer device may also include a Bluetooth module, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 301 in the computer device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302.

[0172] For example, the computer device implements the following functions:

[0173] When a data processing request is detected, obtain the computing power task information of the data processing request, where the computing power task information includes the task type and the computing power requirement;

[0174] According to the task type, the computing power requirement, and the global IoT device resource table, determine the candidate scheduling strategy corresponding to the data processing request;

[0175] According to the IoT device energy status table, determine the target scheduling strategy from the candidate scheduling strategies;

[0176] According to the target scheduling strategy, perform IoT device computing power resource scheduling for the data processing request.

[0177] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the detailed descriptions above, and details will not be repeated here.

[0178] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling relevant hardware through instructions. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0179] Therefore, an embodiment of the present application provides a computer-readable storage medium, which stores multiple instructions that can be loaded by a processor and are used to implement the following functions on the server side:

[0180] When a data processing request is detected, obtain the computing power task information of the data processing request, where the computing power task information includes the task type and the computing power requirement;

[0181] According to the task type, the computing power requirement, and the global IoT device resource table, determine the candidate scheduling strategy corresponding to the data processing request;

[0182] According to the IoT device energy status table, determine the target scheduling strategy from the candidate scheduling strategies;

[0183] According to the target scheduling strategy, perform IoT device computing power resource scheduling for the data processing request.

[0184] For the specific implementation of the above operations, reference can be made to the previous embodiments, and details will not be repeated here.

[0185] Among them, the storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk, optical disk, etc.

[0186] Since the instructions stored in the storage medium can execute the steps in any of the methods provided in the embodiments of the present application, the beneficial effects achievable by any of the methods provided in the embodiments of the present application can be realized. For details, refer to the previous embodiments and will not be elaborated herein.

[0187] Meanwhile, the embodiments of the present application provide a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above various optional implementation manners. For example, the following functions can be realized:

[0188] When a data processing request is detected, obtain the computing power task information of the data processing request, where the computing power task information includes a task type and a computing power requirement;

[0189] According to the task type, the computing power requirement, and the global table of Internet of Things device resources, determine a candidate scheduling policy corresponding to the data processing request;

[0190] According to the energy state table of Internet of Things devices, determine a target scheduling policy from the candidate scheduling policies;

[0191] According to the target scheduling policy, perform scheduling of the computing power resources of Internet of Things devices for the data processing request.

[0192] The above has introduced in detail a method for scheduling computing power resources of Internet of Things devices and related devices provided in the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the technical solution and its core idea of the present application, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for scheduling computing power resources of an Internet of Things device, characterized in that, A computing power scheduling device applied to an Internet of Things (IoT) system, where the IoT system includes multiple IoT devices; the method includes: When detecting a data processing request, obtaining the computing power task information of the data processing request, where the computing power task information includes the task type and the computing power requirement; Determining a candidate scheduling strategy corresponding to the data processing request according to the task type, the computing power requirement, and the global IoT device resource table; Determining a target scheduling strategy from the candidate scheduling strategies according to the IoT device energy status table; Performing IoT device computing power resource scheduling for the data processing request according to the target scheduling strategy.

2. The method for scheduling computing power resources of the Internet of Things device according to claim 1, characterized in that It further includes: Obtaining the mains power supply parameters and new energy supply parameters of each IoT device; Obtaining the energy consumption parameters of each IoT device when processing data processing requests of different task types; Processing the mains power supply parameters and new energy supply parameters according to the trained prediction neural network to obtain an IoT device energy supply table for a preset time period; Associating the energy consumption parameters and the IoT device energy supply table to generate the IoT device energy status table.

3. The method for scheduling computing power resources of an Internet of Things device according to claim 2, wherein Determining a target scheduling strategy from the candidate scheduling strategies according to the IoT device energy status table includes: Determining the task time parameters of each candidate scheduling strategy according to the data processing parameters and communication parameters of the IoT device; Determining the energy consumption parameters of each candidate scheduling strategy according to the IoT device energy status table; the energy consumption parameter is the difference between the mains power consumption and the new energy consumption; Determining a target scheduling strategy from the candidate scheduling strategies based on the task time parameters and the energy consumption parameters.

4. The method for scheduling computing power resources of an Internet of Things device according to claim 3, wherein Determining a target scheduling strategy from the candidate scheduling strategies based on the task time parameters and the energy consumption parameters includes: Obtaining a screening function; Determining the sorting parameters of each candidate scheduling strategy according to the screening function, the task time parameters, and the energy consumption parameters; Determining the target scheduling strategy according to the sorting parameters.

5. The method for scheduling computing power resources of the Internet of Things device according to claim 2, wherein Determining a target scheduling strategy from the candidate scheduling strategies according to the IoT device energy status table includes: Obtaining the working environment parameters of each IoT device; Determining the life loss parameters corresponding to each candidate scheduling strategy according to the working environment parameters, the data processing parameters, and the computing power task information; Determining a target scheduling strategy from the candidate scheduling strategies based on the task time parameters, the energy consumption parameters, and the life loss parameters.

6. The method for scheduling computing power resources of the Internet of Things device according to claim 5, characterized in that, Determining a target scheduling strategy from the candidate scheduling strategies based on the task time parameters, the energy consumption parameters, and the life loss parameters includes: Obtaining a screening function; Determining the sorting parameters of each candidate scheduling strategy according to the screening function, the life loss parameters, the task time parameters, and the energy consumption parameters; Determining the target scheduling strategy according to the sorting parameters.

7. The method for scheduling computing power resources of an Internet of Things device according to any one of claims 1 to 6, characterized in that, It further includes: Obtaining the computing power resource data of each IoT device; Determining the computing power type and computing power capacity of the minimum computing power unit under each IoT device according to the computing power resource data; Determining the global IoT device resource table for a preset time according to the computing power type and computing power capacity.

8. The method for scheduling computing power resources of the Internet of Things device according to claim 7, wherein Determine a candidate scheduling policy corresponding to the data processing request according to the task type, the computing power requirement, and the global table of Internet of Things device resources, including: Based on the correspondence between the task type and the computing power type, determine optional Internet of Things devices based on the global table of Internet of Things device resources; Determine candidate Internet of Things devices from the optional Internet of Things devices according to the matching relationship between the computing power requirement and the computing power capacity; Determine a candidate scheduling policy according to the task type, the computing power requirement, and the candidate Internet of Things devices.

9. An Internet of Things device computing power resource scheduling device, characterized in that, A computing power scheduling device disposed in an Internet of Things system, the Internet of Things system including a plurality of Internet of Things devices; the device includes: An acquisition module, configured to acquire computing power task information of the data processing request when detecting the data processing request, where the computing power task information includes a task type and a computing power requirement; A matching module, configured to determine a candidate scheduling policy corresponding to the data processing request according to the task type, the computing power requirement, and the global table of Internet of Things device resources; A determination module, configured to determine a target scheduling policy from the candidate scheduling policies according to the Internet of Things device energy status table; A scheduling module, configured to perform Internet of Things device computing power resource scheduling for the data processing request according to the target scheduling policy.

10. A computer device, characterized in that, The computer device includes a processor and a memory, and the memory stores a plurality of instructions, and the instructions are suitable for being loaded by the processor to execute the steps in the method according to any one of claims 1 to 8.

Images