Methods, devices, equipment, and storage media for offloading power distribution IoT service requests

Abstract

This invention discloses a method, apparatus, device, and storage medium for offloading service requests in the power distribution IoT (Internet of Things) system. The method includes: acquiring a new service request and adding it to a service request offloading list; assigning each service request in the offloading list; calculating the offloading utility of each service request based on its importance and urgency, where the importance is represented by inherent importance and the urgency by slackness; sorting the service requests in the offloading list from highest to lowest offloading utility; and processing each service request according to its type based on the sorted list. This invention can adapt to the differentiated needs of power distribution services, meet the high real-time requirements of some power distribution automation services, and avoid problems such as high service timeout rates and low cloud-edge node resource utilization.

Description

Technical Field

[0001] This invention relates to a method, apparatus, device, and storage medium for unloading service requests in the Internet of Things (IoT) for power distribution, belonging to the technical field of power distribution IoT service requests. Background Technology

[0002] The distribution IoT, with IoT technology at its core, applies technologies such as smart sensors, cloud computing, edge computing, and 5G to distribution scenarios. It can address new challenges such as massive distributed resource access and the emergence of new electricity and energy consumption models, representing a feasible evolutionary direction for new distribution systems. Currently, a large number of power system control, trading, and management operations are extending to the distribution side, requiring some business processes to be handled locally at the edge. This places new demands on the system's computing resources in terms of total volume, flexibility, and accessibility, gradually making them a key production factor in the distribution IoT. Cloud-edge collaborative systems integrate heterogeneous and distributed computing resources into a unified resource pool, dynamically responding to various distribution business requests with significant differences and fluctuations. Leveraging the advantages of business, data, and resource collaboration between the cloud and edge, it will become the digital computing power foundation for the distribution IoT.

[0003] Edge service caching and task scheduling are crucial components of resource collaboration methods in the power distribution IoT. In power distribution IoT, service instances need to be deployed on cloud nodes and edge nodes to respond to business requests, i.e., service caching. The advantage of the cloud-edge computing paradigm is that service instances are deployed closer to the data source and service requests, i.e., at the edge, while cloud nodes primarily play a monitoring and scheduling role. Furthermore, static edge service caching schemes cannot adapt to the dynamically changing working environment of power distribution IoT and need to be dynamically adjusted periodically. When a business request arrives, in order to enable the limited edge nodes to respond to more business requests, improve service quality, and increase resource utilization, it is necessary to decide where the business is executed, i.e., to offload the business request (i.e., the task).

[0004] Since business requests can only be offloaded to nodes with corresponding service instances deployed, the task offloading process is deeply coupled with the edge service caching solution. Considering the fast start-up and shutdown characteristics of containers, the two can be considered together. Summary of the Invention

[0005] In view of this, the present invention provides a method, apparatus, computer equipment and storage medium for unloading power distribution IoT service requests. It takes into account the differences in edge service cache state, can adapt to the differentiated needs of power distribution services, can adapt to the high real-time requirements of some power distribution automation services, and can avoid problems such as high service timeout rate and low cloud-edge node resource utilization.

[0006] The first objective of this invention is to provide a method for unloading power distribution IoT service requests.

[0007] The second objective of this invention is to provide a device for unloading Internet of Things (IoT) service requests related to power distribution.

[0008] A third objective of this invention is to provide a computer device.

[0009] A fourth objective of this invention is to provide a storage medium.

[0010] The first objective of this invention can be achieved by adopting the following technical solution:

[0011] A method for offloading power distribution IoT service requests, the method comprising:

[0012] Obtain a new business request and add it to the business request unload list;

[0013] Assign each business request in the business request unloading list;

[0014] Based on the importance and urgency of each business request in the business request unloading list, the unloading utility of each business request is calculated, where the importance is represented by inherent importance and the urgency is represented by relaxation.

[0015] Sort the business requests in the business request uninstallation list from highest to lowest according to their uninstallation effectiveness;

[0016] Based on the sorting of the business request unloading list, each business request is processed accordingly according to its type.

[0017] Furthermore, the step of processing each business request according to its type specifically includes:

[0018] If the business request is a non-urgent business request, the business request is assigned to the corresponding service instance on the edge node with the lowest load rate; if all service instances that can respond to the business request are busy, the service instance that can complete the business request the fastest will be reserved for the business request.

[0019] If the business request is an urgent business request but not a critical business request, then the business request is assigned to the corresponding service instance on the edge node with the lowest load rate; if all service instances that can respond to the business request are busy, then the business request is assigned to the service instance with the lowest termination cost.

[0020] If the business request is both urgent and important, it is assigned to the corresponding service instance on the edge node with the lowest load. If all service instances capable of responding to the business request are busy, an attempt is made to create a new service instance and assign the business request to the newly created service instance. If the creation fails, a set of service instances with the lowest total termination cost that can meet the computing resource requirements of the business request is found, the service instances in the set are terminated, a new service instance corresponding to the business request is created, and the business request is assigned to the newly created service instance.

[0021] Furthermore, the termination cost is calculated as follows:

[0022]

[0023] Where, q e,g This indicates that the submission has been made to edge node E. e The g-th business request, r(q) e,g ) represents the business request q e,g The amount of computing resources, η(q) e,g ) represents the business request q e,g The inherent importance, where t represents the current time. This indicates the start time of the business process.

[0024] Furthermore, the inherent importance is defined as follows:

[0025] η(q e,g )=η i When s Q (q e,g ) = s i

[0026] Where, η i This indicates the corresponding computing service s i Business request q e,g The inherent importance of q e,g This indicates that the submission has been made to edge node E. e The g-th business request, η(q) e,g ) represents the business request q e,g The inherent importance of s Q (q e,g ) represents the business request q e,g Corresponding computing service types; When η i =η max At that time, s i For important business operations; when η(q) e,g )=η max That is, η(s) Q (q e,g ))=η maxAt that time, q e,g This is an important business request.

[0027] Furthermore, the service request q e,g The time elapsed from reaching the edge node to the completion of the service is the service delay d(q). e,g The service latency d(q) e,g The waiting delay d W (q e,g ), communication delay d T (q e,g ) and calculation delay d C (q e,g )composition;

[0028] The waiting delay d W (q e,g (Refers to the business request q) e,g The time consumed from reaching the edge node to the start of data transmission required for the service; the communication delay d T (q e,g This refers to unloading to edge node E. x Under the condition, at edge node E e and E x The time consumed by the data process required for inter-transmission services to be executed; the calculated delay d C (q e,g This refers to the time consumed during the execution of a business process, starting from the start time of the business execution.

[0029] Furthermore, the relaxation degree is defined as follows:

[0030]

[0031] Among them, l e,g (t) represents the business request q e,g The degree of relaxation, Indicates the deadline, d C (q e,g () indicates the computation delay. Indicates communication delay d T (q e,g The maximum value of ), where t is the current time; l e,g (t) > 0 indicates that there is still a chance to complete the transaction before the deadline, and l e,g The larger the (t) value, the more sufficient the time. e,g The maximum value of (t) is

[0032] Furthermore, the formula for the unloading effect is as follows:

[0033]

[0034] Where, η i This indicates the corresponding computing service s i Business request q e,g The inherent importance of η(q) e,g ) represents the business request q e,g The inherent importance of l e,g (t) represents the business request q e,g The degree of relaxation, Indicate l e,g The maximum value of (t).

[0035] The second objective of this invention can be achieved by adopting the following technical solution:

[0036] A power distribution IoT service request offloading device, the device comprising:

[0037] The acquisition module is used to acquire new business requests and add them to the business request unloading list.

[0038] The assignment module is used to assign each business request in the business request unloading list;

[0039] The calculation module is used to calculate the unloading utility of each business request based on the importance and urgency of each business request in the business request unloading list. The importance is represented by the inherent importance, and the urgency is represented by the relaxation degree.

[0040] The sorting module is used to sort the business requests in the business request unloading list from largest to smallest according to their unloading effectiveness;

[0041] The processing module is used to sort the business request unloading list and process each business request accordingly based on its type.

[0042] The third objective of this invention can be achieved by adopting the following technical solution:

[0043] A computer device includes a processor and a memory for storing a processor-executable program, wherein when the processor executes the program stored in the memory, it implements the above-described method for offloading Internet of Things (IoT) service requests for power distribution.

[0044] The fourth objective of this invention can be achieved by adopting the following technical solution:

[0045] A storage medium storing a program, which, when executed by a processor, implements the above-described method for unloading power distribution IoT service requests.

[0046] The present invention has the following advantages over the prior art:

[0047] This invention can effectively support the automation business of power distribution IoT system in the context of explosive growth in access objects, increasingly complex operating scenarios, and continuous expansion of task scale. It can flatten the spatiotemporal distribution curve of computing load, cope with the ever-increasing contradiction between computing power supply and demand, take into account the differences in edge service cache state, adapt to the differentiated needs of power distribution business, adapt to the high real-time requirements of some power distribution automation business, and avoid problems such as high business timeout rate and low cloud-edge node resource utilization. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0049] Figure 1 This is a simplified flowchart of the power distribution IoT service request offloading method in Embodiment 1 of the present invention.

[0050] Figure 2 This is a flowchart illustrating the power distribution IoT service request unloading method in Embodiment 1 of the present invention.

[0051] Figure 3 This is a structural block diagram of the power distribution IoT service request offloading device according to Embodiment 2 of the present invention.

[0052] Figure 4 This is a structural block diagram of the computer device according to Embodiment 3 of the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] Example 1:

[0055] Traditional distribution network automation systems do not adopt a cloud-edge architecture. Each subsystem is independent and vertically isolated, lacking a computing resource sharing mechanism. Therefore, corresponding business requests are executed within their respective business systems, without the need to focus on service caching and business request offloading. Existing common cloud-edge computing resource coordination methods are mostly designed for Internet application scenarios, focusing on call loss rate, load balancing rate, etc. On the one hand, they fail to meet the high real-time requirements of some distribution network automation services, and on the other hand, they lack distributed scheduling methods adapted to the distribution network structure. Therefore, this embodiment proposes a distribution and consumption IoT business request offloading method that considers edge service caching.

[0056] like Figure 1 and Figure 2 As shown in this embodiment, the power distribution IoT service request offloading method is implemented using a reservation and preemption based scheduling algorithm (RPSA), which mainly includes the following steps:

[0057] S201. Obtain a new business request and add it to the business request unload list.

[0058] In this embodiment, it is determined whether a new service request has been received. If so, the service request is added to the service request unloading list and the process proceeds to step S202. If not, it is determined whether the service request unloading list is empty. If it is not empty, the process proceeds to step S202. If it is empty, the operation ends.

[0059] S202. Assign each business request in the business request unloading list.

[0060] In this embodiment, after assigning each service request in the service request unloading list, it is determined whether the service request unloading list is empty. If it is not empty, proceed to step S203; if it is empty, end the operation.

[0061] S203. Calculate the unloading utility of each business request based on its importance and urgency in the business request unloading list.

[0062] In this embodiment, assume that the system has a cloud node E0 and a set of edge nodes E = {E1, E2, ..., E...} |E|}, and there is a set of computational business S = {s1, s2, ..., s} |S| Each edge node has a certain amount of computing power resources, denoted as E. e The computing power resources on it are R e A set of service instances are deployed on it, forming a service instance collection. Respond to service requests from endpoints in partition e. Each service instance c e,k It can be described by triples, as shown in equation (1).

[0063] c e,k =(r e,k ,s(c e,k ),u(c e,k )) (1)

[0064] Where, r e,k Regarding its computing resources, since service instances serving similar businesses in the system all correspond to the same service image, their resource consumption is equal. When s(c e,k )=s(c e,x ) = s i ;s(c e,k ) represents the types of business functions that can be executed; u(c e,k The status of a service instance is categorized into three states: creating, busy, and idle, represented by the values ​​2, 1, and 0, respectively. The instance in the creation state cannot provide computing services. The duration of this state depends on the virtualization technology used and can be considered a constant d in scenarios involving computing resource scheduling. P To enable cloud-based perception and control of the edge, edge nodes need to deploy cloud-edge collaborative service instances, which consume r0 resources and are always in a busy state.

[0065] Based on the impact of different types of services on the normal operation of the power distribution IoT, an inherent importance η is used. i Characterizing computing business i The degree of importance, that is, the degree of importance is characterized by inherent importance, for all computing tasks s i Business request q e,g The inherent importance of each is η i As shown in equation (2).

[0066] η(q e,g )=η i When s Q (q e,g ) = s i (2)

[0067] Where, q e,g This indicates that the submission has been made to edge node E. e The g-th business request, η(q) e,g ) represents the business request q e,g The inherent importance of s Q (q e,g ) represents the business request q e,g Corresponding computing service types; When ηi =η max At that time, s i For important business operations; when η(q) e,g )=η max That is, η(s) Q (q e,g ))=η max At that time, q e,g This is an important business request.

[0068] Business request q e,g And arrival time Deadline Calculate data volume A e,g With these characteristics, edge nodes can detect the above features when a business request arrives and forward it to the cloud node, from the business request q e,g The time elapsed from the arrival at the edge node to the completion of the service is called the service latency d(q). e,g It consists of a waiting delay d. W (q e,g ), communication delay d T (q e,g ), calculate the delay d C (q e,g The process consists of the following components, as shown in equation (3); where the waiting delay refers to the time from the business request q... e,g The time taken from the arrival at the edge node to the start of data transmission required for the service; communication latency refers to the time taken to offload to the edge node E. x Under the condition, at edge node E e and E x The time consumed by the data transmission process required for the inter-transmission service; the calculation latency refers to the time consumed by the service execution process, and its starting point is called the start time of the service. Right now Since the computing resources of service instances for the same type of business in the system are equal, the computing delay of the business can be predicted, as shown in equation (4); and since the system can sense the communication speed between nodes, the upper bound of the possible transmission delay of the business satisfies equation (5).

[0069] d(q e,g )=d W (q e,g )+d T (q e,g )+d C (q e,g (3)

[0070]

[0071] in, For business request q e,gThe computational complexity coefficient of the corresponding service represents the number of instructions required for that service to process 1MByte of input data, satisfying the following condition: When s Q (q e,h ) = s Q (q e,h ) = s i ;δ max For maximum latency jitter; w e,x For edge node E e To E x The transmission speed.

[0072] As can be seen from the above, the importance of a business request is represented by its inherent importance, and its urgency is represented by its slackness. For business request q... e,g As for the relaxation degree, it is defined as shown in equation (6).

[0073]

[0074] Among them, l e,g (t) represents the business request q e,g The degree of relaxation, Indicates the deadline, d C (q e,g () indicates the computation delay. Indicates communication delay d T (q e,g The maximum value of ), where t is the current time; l e,g (t) > 0 indicates that there is still a chance to complete the transaction before the deadline, and l e,g The larger the (t) value, the more sufficient the time. e,g The maximum value of (t) is

[0075] Based on slackness, the business requests to be scheduled are classified as follows: 1) All non-critical business requests with a slackness of less than 0 and all critical business requests are called urgent business requests; 2) The remaining business requests are called non-urgent business requests.

[0076] Considering the importance and urgency of the comprehensive business requests, this embodiment proposes an offloading utility model, as shown in equation (7).

[0077]

[0078] Where, η i This indicates the corresponding computing service s i Business request q e,g The inherent importance of η(q) e,g ) represents the business request q e,g The inherent importance of l e,g (t) represents the business request qe,g The degree of relaxation, Indicate l e,g The maximum value of (t).

[0079] S204. Sort the business requests in the business request uninstallation list from largest to smallest according to their uninstallation effectiveness.

[0080] S205. According to the sorting of the business request unloading list, process each business request accordingly based on its type.

[0081] This embodiment starts with the first business request in the business request unloading list and processes each business request according to its type, specifically including:

[0082] 1) If the business request is a non-urgent business request, reservation is allowed but preemption is not allowed. That is, the business request is assigned to the corresponding service instance on the edge node with the lowest load rate; if all service instances that can respond to the business request are busy, the service instance that can complete the business request the fastest will be reserved for the business request.

[0083] 2) If the business request is an urgent business request and a non-critical business request, then only service instances of the same type are allowed to be preempted, that is: the business request is assigned to the corresponding service instance on the edge node with the lowest load rate; if all service instances that can respond to the business request are busy, then the service instance with the lowest termination cost for the business request is assigned.

[0084] 3) If the business request is both urgent and important, then it is permissible to create a new service instance using idle computing resources, and it is permissible to preempt different types of service instances. That is, the business request is assigned to the corresponding service instance on the edge node with the lowest load rate. If all service instances that can respond to the business request are busy, then an attempt is made to create a new service instance and assign the business request to the newly created service instance. If the creation fails, then a set of service instances with the lowest sum of termination costs that can meet the computing resource requirements of the business request is found, the service instances in the set are terminated, a new service instance corresponding to the business request is created, and the business request is assigned to the newly created service instance.

[0085] In this embodiment, when computing resources are preempted, the computing resources occupied by the service request with the lower termination cost should be preempted first. The termination cost is characterized by the computing resources invested in the service request and the inherent importance of the service request, as shown in Equation (8).

[0086]

[0087] Where, q e,g This indicates that the submission has been made to edge node E. eThe g-th business request, r(q) e,g ) represents the business request q e,g The amount of computing resources, η(q) e,g ) represents the business request q e,g The inherent importance, where t represents the current time. This indicates the start time of the business process.

[0088] In the above embodiments, the design process of the service request offloading algorithm is as follows:

[0089] When a new service request arrives, it is added to the unloading list (SRL), which stores information about the service requests to be unloaded. When unloading service requests, cloud nodes first attempt to assign each request based on a greedy strategy. During this process, service requests with higher unloading efficiency are prioritized, and service instances on edge nodes with lower real-time load rates are given priority, as shown in Algorithm 1. Here, SI is used to temporarily store information related to the set of service instances.

[0090]

[0091] In the above embodiments, the reservation mechanism for non-urgent service requests is implemented as follows:

[0092] The WL (Service Request List) is used to record non-urgent business requests that were not successfully assigned by `request_assign()`, for service instance reservation. Whenever a new business request is recorded in the WL, the reservation results for business requests belonging to the same category are refreshed. The refresh process still follows a greedy principle, prioritizing service instances reserved for business requests with high offloading efficiency, and prioritizing those with high efficiency to shorten the waiting latency of business requests, as shown in Algorithm 2a. `WL_temp_i` is used to temporarily store information related to the service request set awaiting refresh. Considering that the slackness of business requests decreases over time, non-urgent business requests may become urgent business requests; therefore, the cloud scheduler needs to detect whether there are urgent business requests and handle them accordingly.

[0093]

[0094] When a service instance finishes executing a business request, it also needs to check if the service instance has any reserved business requests. If so, the reserved business request is executed and the Write-Level (WL) is refreshed, as shown in Algorithm 2b.

[0095]

[0096] The implementation process of the preemption mechanism for urgent but non-critical business requests is as follows:

[0097] When the total number of business requests is small, there may be edge computing resources that are not utilized by service instances due to the influence of edge service caching. Using these resources as "backup" to respond to important business requests can effectively reduce the timeout rate of important business. Priority should be given to creating new service instances on nodes with good communication conditions. The specific implementation is shown in Algorithm 4a.

[0098]

[0099] When all nodes lack sufficient idle computing resources to create new service instances to respond to urgent and critical business requests, q i In such cases, computing resources for non-urgent business requests can be preempted. This involves finding a set of service instances with the lowest sum of termination costs that can meet the computing resource requirements of the business request, terminating the service instances in the set, creating a new service instance corresponding to the business request, and assigning q to it. i To the newly created service instance, as shown in Algorithm 4b.

[0100]

[0101] It should be noted that although the method operations of the above embodiments are described in a specific order, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the described steps may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0102] Example 2:

[0103] like Figure 3 As shown, this embodiment provides a power distribution IoT service request offloading device. The device includes an acquisition module 301, an assignment module 302, a calculation module 303, a sorting module 304, and a processing module 305, with the following specific functions:

[0104] The acquisition module 301 is used to acquire new business requests and add them to the business request unloading list.

[0105] The assignment module 302 is used to assign each business request in the business request unloading list;

[0106] The calculation module 303 is used to calculate the unloading utility of each business request based on the importance and urgency of each business request in the business request unloading list, wherein the importance is represented by the inherent importance and the urgency is represented by the relaxation degree.

[0107] The sorting module 304 is used to sort the business requests in the business request unloading list from largest to smallest according to their unloading effectiveness;

[0108] The processing module 305 is used to sort the business request unloading list and process each business request accordingly based on its type.

[0109] It should be noted that the device provided in this embodiment is only an example of the above-described division of functional units. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure can be divided into different functional units to complete all or part of the functions described above.

[0110] Example 3:

[0111] This embodiment provides a computer device, such as... Figure 4 As shown, it includes a processor 402, a memory, an input device 403, a display device 404, and a network interface 405 connected via a system bus 401. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium 1406 and internal memory 407. The non-volatile storage medium 406 stores an operating system, computer programs, and a database. The internal memory 407 provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. When the processor 402 executes the computer programs stored in the memory, it implements the power distribution IoT service request offloading method of Embodiment 1 above, as follows:

[0112] A new business request is obtained and added to the business request offload list; each business request in the business request offload list is assigned; the offload utility of each business request is calculated based on its importance and urgency, where the importance is represented by inherent importance and the urgency by slackness; the business requests in the business request offload list are sorted from highest to lowest offload utility; and each business request is processed accordingly based on its type, according to the sorting of the business request offload list.

[0113] Example 4:

[0114] This embodiment provides a storage medium, which is a computer-readable storage medium, storing a computer program. When the computer program is executed by a processor, it implements the power distribution IoT service request offloading method of Embodiment 1 above, as follows:

[0115] A new business request is obtained and added to the business request offload list; each business request in the business request offload list is assigned; the offload utility of each business request is calculated based on its importance and urgency, where the importance is represented by inherent importance and the urgency by slackness; the business requests in the business request offload list are sorted from highest to lowest offload utility; and each business request is processed accordingly based on its type, according to the sorting of the business request offload list.

[0116] It should be noted that the computer-readable storage medium in this embodiment can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0117] In this embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this embodiment, the computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0118] The computer-readable storage medium described above can be used to write computer programs for executing this embodiment in one or more programming languages ​​or combinations thereof. These programming languages ​​include object-oriented programming languages—such as Java, Python, and C++—and conventional procedural programming languages—such as C or similar programming languages. The program can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0119] In summary, this invention, targeting regional power distribution systems, adopts a distributed deployment architecture based on edge computing technology. This architecture allows for on-site collection, processing, and storage of power data at different levels of power distribution equipment. Compared to centralized processing, edge computing alleviates the pressure on backbone communication networks and cloud data centers. In this distributed deployment architecture, hardware functions are defined based on business requirements, enabling flexible allocation and expansion of computing, communication, and storage resources. This facilitates extensive device management, massive data collection, and efficient business processing, thereby comprehensively enhancing the ability to support power business processing and improving the operational efficiency of the power distribution system. To meet the computing and storage needs of access users, this invention first determines the number and location of distributed edge computing terminals, then plans the communication network between devices, and further configures the computing and storage hardware models of the distributed edge computing terminals, avoiding redundant waste of distributed edge computing terminal resources. By formulating a reasonable power distribution IoT service request offloading strategy, this invention can improve the economic efficiency and operational stability of regional power distribution system construction, and enhance the power distribution system's ability to support massive power business.

[0120] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope disclosed by the present invention, based on the technical solution and inventive concept of the present invention, shall fall within the scope of protection of the present invention.

Claims

1. A method for unloading power distribution IoT service requests, characterized in that, The method includes: Obtain a new business request and add it to the business request unload list; Assign each business request in the business request unloading list; Based on the importance and urgency of each business request in the business request unloading list, the unloading utility of each business request is calculated, where the importance is represented by inherent importance and the urgency is represented by relaxation. Sort the business requests in the business request uninstallation list from highest to lowest according to their uninstallation effectiveness; Based on the sorting of the business request unload list, each business request is processed accordingly according to its type. The relaxation degree is defined as follows: Among them, l e,g (t) represents the business request q e,g The degree of relaxation, Indicates the deadline, d C (q e,g () indicates the computation delay. Indicates communication delay d T (q e,g The maximum value of ), where t is the current time; l e,g (t) > 0 indicates that there is still a chance to complete the transaction before the deadline, and l e,g The larger the (t) value, the more sufficient the time. e,g The maximum value of (t) is The formula for the unloading effect is as follows: Where, η i This indicates the corresponding computing service s i Business request q e,g The inherent importance of η(q) e,g ) represents the business request q e,g The inherent importance of l e,g (t) represents the business request q e,g The degree of relaxation, Indicate l e,g The maximum value of (t).

2. The method for offloading power distribution IoT service requests according to claim 1, characterized in that, The process of processing each business request according to its type specifically includes: If the business request is a non-urgent business request, the business request is assigned to the corresponding service instance on the edge node with the lowest load rate; if all service instances that can respond to the business request are busy, the service instance that can complete the business request the fastest will be reserved for the business request. If the business request is an urgent business request but not a critical business request, then the business request is assigned to the corresponding service instance on the edge node with the lowest load rate; if all service instances that can respond to the business request are busy, then the business request is assigned to the service instance with the lowest termination cost. If the business request is both urgent and important, it is assigned to the corresponding service instance on the edge node with the lowest load. If all service instances capable of responding to the business request are busy, an attempt is made to create a new service instance and assign the business request to the newly created service instance. If the creation fails, a set of service instances with the lowest total termination cost that can meet the computing resource requirements of the business request is found, the service instances in the set are terminated, a new service instance corresponding to the business request is created, and the business request is assigned to the newly created service instance.

3. The method for offloading power distribution IoT service requests according to claim 2, characterized in that, The termination cost is calculated as follows: Where, q e,g This indicates that the submission has been made to edge node E. e The g-th business request, r(q) e,g ) represents the business request q e,g The amount of computing resources, η(q) e,g ) represents the business request q e,g The inherent importance, where t represents the current time. This indicates the start time of the business process.

4. The method for offloading power distribution IoT service requests according to any one of claims 1-3, characterized in that, The inherent importance is defined as follows: η(q e,g )=η i , Q (what e,g )=s i Where, η i This indicates the corresponding computing service s i Business request q e,g The inherent importance of q e,g This indicates that the submission has been made to edge node E. e The g-th business request, η(q) e,g ) represents the business request q e,g The inherent importance of s Q (q e,g ) represents the business request q e,g Corresponding computing service types; When η i =η max At that time, s i For important business operations; when η(q) e,g )=η max That is, η(s) Q (q e,g ))=η max At that time, q e,g This is an important business request.

5. The method for offloading power distribution IoT service requests according to claim 4, characterized in that, The service request q e,g The time elapsed from reaching the edge node to the completion of the service is the service delay d(q). e,g The service latency d(q) e,g The waiting delay d W (q e,g ), communication delay d T (q e,g ) and calculation delay d C (q e,g )composition; The waiting delay d W (q e,g (Refers to the business request q) e,g The time consumed from reaching the edge node to the start of data transmission required for the service; the communication delay d T (q e,g This refers to unloading to edge node E. x Under the condition, at edge node E e and E x The time consumed by the data process required for inter-transmission services to be executed; the calculated delay d C (q e,g This refers to the time consumed during the execution of a business process, starting from the start time of the business execution.

6. A device for offloading Internet of Things (IoT) service requests related to power distribution, characterized in that, The device includes: The acquisition module is used to acquire new business requests and add them to the business request unloading list. The assignment module is used to assign each business request in the business request unloading list; The calculation module is used to calculate the unloading utility of each business request based on the importance and urgency of each business request in the business request unloading list. The importance is represented by the inherent importance, and the urgency is represented by the relaxation degree. The sorting module is used to sort the business requests in the business request unloading list from largest to smallest according to their unloading effectiveness; The processing module is used to sort the business request unloading list and process each business request accordingly based on its type. The relaxation degree is defined as follows: Among them, l e,g (t) represents the business request q e,g The degree of relaxation, Indicates the deadline, d C (q e,g () indicates the computation delay. Indicates communication delay d T (q e,g The maximum value of ), where t is the current time; l e,g (t) > 0 indicates that there is still a chance to complete the transaction before the deadline, and l e,g The larger the (t) value, the more sufficient the time. e,g The maximum value of (t) is The formula for the unloading effect is as follows: Where, η i This indicates the corresponding computing service s i Business request q e,g The inherent importance of η(q) e,g ) represents the business request q e,g The inherent importance of l e,g (t) represents the business request q e,g The degree of relaxation, Indicate l e,g The maximum value of (t).

7. A computer device comprising a processor and a memory for storing a processor-executable program, characterized in that, When the processor executes the program stored in the memory, it implements the power distribution IoT service request unloading method as described in any one of claims 1-5.

8. A storage medium storing a program, characterized in that, When the program is executed by the processor, it implements the power distribution IoT service request unloading method according to any one of claims 1-5.

Images