Edge-to-edge collaboration approach for real-time scheduling of multi-service heterogeneous resources in distribution networks
By dividing the distribution network business data and evaluating the trust of edge servers, the problem of poor matching of distribution network data processing requirements in traditional methods is solved, and more efficient edge-side collaborative data processing is achieved.
Patent Information
- Application Number
- CN202211551369.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-12-05
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-12-05
AI Technical Summary
The traditional edge-to-edge collaboration method fails to effectively consider the distribution network service type division and the integration of multi-service heterogeneous resource matching and trust, resulting in the distribution network data processing delay, computing resources and storage requirements that cannot be met, reducing the edge. Data offload performance of the server.
By dividing business data in types, scoring and identifying based on differentiated demand indicators, prioritization evaluation is conducted based on the trust and resource matching of edge servers, and selecting the appropriate edge server for collaborative data processing.
It improves the matching and performance of side-by-side collaborative data processing, ensures the real-time scheduling requirements of multi-service heterogeneous resources in the distribution network, and improves the adaptability and efficiency of data processing.
Smart Images

Figure CN116016378B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power systems, and in particular to an edge-to-edge collaboration method and device for real-time scheduling of multi-service heterogeneous resources in a distribution network. Background Art
[0002] As a large number of power business terminals are connected to the distribution network, the business data of the distribution network continues to increase, resulting in a surge in demand for data collection, data analysis and data processing. The processing of massive business data requires real-time dispatch of heterogeneous resources such as marketing, operation and inspection, and dispatch, thereby improving the efficiency of massive business data processing and supporting the safe and stable operation of multiple businesses in the distribution network.
[0003] Edge computing can provide local data processing services for massive business data by sinking computing power to the edge side, reducing data transmission and data processing time, and realizing rapid processing of power business data on the edge side. Considering the limited computing and storage capacity of a single server on the edge side, edge-to-edge collaboration can share computing resources of different edge servers to realize collaborative processing of power business data. However, traditional edge-to-edge collaboration methods do not consider the division of distribution network business types, and it is difficult to meet the differentiated requirements of different distribution network businesses for latency, computing resources, storage, etc. In addition, traditional edge-to-edge collaboration methods do not consider the integration of the matching degree of heterogeneous resources of multiple businesses and the trust of edge-to-edge collaboration, resulting in a decrease in the edge-to-edge collaboration performance of distribution network business data.
[0004] In summary, the existing edge-to-edge collaboration methods have at least the following technical problems:
[0005] First, the traditional edge-to-edge collaboration method does not take into account the division of distribution network business types, and is unable to identify and construct an edge-to-edge collaboration trust and heterogeneous resource matching evaluation model based on business data types, making it difficult to meet the differentiated requirements of different distribution network businesses for latency, computing resources, storage, etc.
[0006] Secondly, the existing edge-to-edge collaboration method in distribution networks only considers the QoS indicators of real-time scheduling, but does not consider the integration of the matching degree of multi-service heterogeneous resources and the edge-to-edge collaboration trust. This results in poor matching between the heterogeneous resources provided by the edge server and the business data processing requirements, thereby reducing the edge-to-edge collaboration offloading performance of distribution network data.
[0007] Therefore, there is an urgent need for an edge-to-edge collaborative method for real-time scheduling of multi-service heterogeneous resources in distribution networks to solve the above technical problems. Summary of the invention
[0008] The embodiments of the present invention provide an edge-to-edge collaboration method and device for instant scheduling of heterogeneous resources for multiple services in a distribution network, so as to solve the problems in the prior art that the differentiated matching performance of the edge-to-edge collaboration method is poor, and the heterogeneous resources provided by the edge server are poorly matched with the business data processing requirements. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or to describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a preface to the detailed description that follows.
[0009] According to a first aspect of an embodiment of the present invention, there is provided an edge-to-edge collaboration method for real-time scheduling of multi-service heterogeneous resources in a distribution network.
[0010] In some embodiments, the method comprises:
[0011] According to the preset differentiated requirements of the target distribution network, the business data is classified to obtain multiple business data types;
[0012] Based on the target demand index, scoring each of the business data types to obtain a scoring result, and identifying each of the business data types according to the scoring result to obtain an identification result;
[0013] Based on the identification result, the priority of the target edge server is evaluated according to the target edge server trust and the multi-service heterogeneous resource matching degree to obtain an evaluation result, and the target edge server for collaborative data processing is selected according to the evaluation result.
[0014] In some embodiments, the business data is divided into types according to the preset differentiated requirements of the target distribution network to obtain multiple business data types, specifically including:
[0015] According to the differentiated requirements of the target distribution network for latency, computing resources and storage capacity for different businesses, the business data is divided into low-latency business data, computing-intensive business data and high-traffic business data.
[0016] In some embodiments, based on the target demand index, each of the business data types is scored to obtain a scoring result, and each of the business data types is identified according to the scoring result to obtain an identification result, specifically including:
[0017] Normalizing the original demand index to obtain the target demand index;
[0018] Scoring each business data type based on the target demand indicator to obtain a score result for each business data type;
[0019] The target demand indicator corresponding to the highest score in the scoring result is used to identify the business data type to obtain the identification result.
[0020] In some embodiments, the original demand index is normalized to obtain the target demand index, specifically including:
[0021] Comprehensively consider the requirements of distribution network services for latency, computing resources, and storage space resources, linearly change the original latency demand index, computing resource demand index, and storage space demand index of the end-side data, map the original demand index to [0-1], and realize the normalization of the demand index.
[0022] In some embodiments, scoring each business data type based on the target demand indicator to obtain a score result for each business data type specifically includes:
[0023] Using the first preset formula, the delay requirement indicator score is calculated to obtain a first score result delay;
[0024] Wherein, the first preset formula is:
[0025]
[0026] In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
[0027] In some embodiments, scoring each business data type based on the target demand indicator to obtain a score result for each business data type specifically includes:
[0028] Using a second preset formula, the computing resource requirement indicator score is calculated to obtain a second score result com;
[0029] Wherein, the second preset formula is:
[0030]
[0031] In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
[0032] In some embodiments, scoring each business data type based on the target demand indicator to obtain a score result for each business data type specifically includes:
[0033] Calculate the storage space requirement index score using a third preset formula to obtain a third score result sto;
[0034] Wherein, the third preset formula is:
[0035]
[0036] In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
[0037] In some embodiments, the target demand indicator corresponding to the highest score in the scoring result is used to identify the business data type to obtain the identification result, specifically including:
[0038] If the latency requirement index score is the highest, the service data type is identified as low-latency service data;
[0039] If the computing resource requirement indicator has the highest score, the business data type is identified as computing-intensive business data;
[0040] If the storage space requirement index scores the highest, the business data type is identified as high-traffic business data.
[0041] In some embodiments, based on the identification result, the priority of the target edge server is evaluated according to the target edge server trust and the multi-service heterogeneous resource matching degree to obtain an evaluation result, and the target edge server for collaborative data processing is selected according to the evaluation result, specifically including:
[0042] Evaluate the trustworthiness of offloading business data to each target edge server to obtain a trustworthiness evaluation result;
[0043] Evaluate the matching degree between the processing requirements of business data and multi-business heterogeneous resources to obtain matching evaluation results;
[0044] Based on the trust evaluation result and the matching evaluation result, the priority of the target edge server is evaluated to obtain an evaluation result;
[0045] The business data is unloaded to the target edge server with the highest score in the evaluation results for edge-to-edge collaborative processing.
[0046] In some embodiments, the trust is evaluated using a first evaluation expression;
[0047] Wherein, the first evaluation expression is:
[0048]
[0049] In the formula, represents the trust of offloading the j-th business data to the i-th target edge server, B i,jIt represents the available channel bandwidth for offloading the j-th service data to the i-th target edge server for data collaborative processing, B i represents the total bandwidth, f i,j It is represented by the available computing resource margin for offloading the j-th business data to the i-th target edge server for data collaborative processing, f i represents the total computing resources of the target edge server i, Q i,j represents the available storage space for the jth type of business data of the i-th target edge server, σ i,j ,δ i,j are the weight parameters of available channel bandwidth, computing resource margin, and available storage space respectively.
[0050] In some embodiments, the matching degree is evaluated using a second evaluation expression;
[0051] Wherein, the second evaluation expression is:
[0052]
[0053] Where η i,j represents the amount of marketing resources that the target edge server i can provide for the jth type of business data, ι i,j represents the amount of data of the inspection resources that the target edge server i can provide for the jth type of business data, κ i,j represents the amount of scheduling resources that the target edge server i can provide for the jth type of business data, a i,j , b i,j 、c i,j They are the weight parameters of marketing resources, operation and maintenance resources, and scheduling resources respectively.
[0054] In some embodiments, the priority is evaluated using a third evaluation expression;
[0055] Wherein, the third evaluation expression is:
[0056]
[0057] In the formula, score i,j represents the score of offloading the j-th business data to edge server i for edge data collaborative processing, represents the trustworthiness of offloading the j-th service data to the i-th target edge server, ψ i,j It represents the matching degree between the j-th service data processing requirement and the multi-service heterogeneous resources provided by the i-th target edge server.
[0058] In some embodiments, selecting a target edge server for collaborative data processing according to the evaluation result further includes:
[0059] Update the priority score of the target edge server based on the processing feedback result.
[0060] According to a second aspect of an embodiment of the present invention, there is provided an edge-to-edge collaboration device for real-time scheduling of multi-service heterogeneous resources in a distribution network.
[0061] In some embodiments, the apparatus comprises:
[0062] A business type classification unit, used to classify business data according to preset differentiated requirements of the target distribution network to obtain multiple business data types;
[0063] An indicator type identification unit, used to score each of the business data types based on the target demand indicator to obtain a scoring result, and identify each of the business data types according to the scoring result to obtain an identification result;
[0064] The result generating unit is used to evaluate the priority of the target edge server based on the identification result, according to the target edge server trust and the multi-service heterogeneous resource matching degree, so as to obtain an evaluation result, and select the target edge server for collaborative data processing according to the evaluation result.
[0065] In some embodiments, the service type classification unit is specifically used to:
[0066] According to the differentiated requirements of the target distribution network for latency, computing resources and storage capacity for different businesses, the business data is divided into low-latency business data, computing-intensive business data and high-traffic business data.
[0067] According to a third aspect of an embodiment of the present invention, a computer device is provided.
[0068] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.
[0069] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:
[0070] The edge-to-edge collaboration method for real-time scheduling of heterogeneous resources for multiple services in a distribution network provided by the present invention divides the service data into types according to the preset differentiated requirements of the target distribution network to obtain multiple service data types; scores each of the service data types based on the target demand index to obtain a scoring result, and identifies each of the service data types according to the scoring result to obtain an identification result; based on the identification result, the priority of the target edge server is evaluated according to the trust of the target edge server and the matching degree of heterogeneous resources for multiple services to obtain an evaluation result, and the target edge server for collaborative data processing is selected according to the evaluation result. This solves the problem that the differentiated matching performance of the edge-to-edge collaboration method in the prior art is poor, and the heterogeneous resources provided by the edge server are poorly matched with the service data processing requirements.
[0071] In some embodiments, the method provided by the present invention divides business types and identifies business data according to the differentiated requirements of different services in the distribution network for latency, computing resources, storage capacity, etc., and constructs a target edge server trust and heterogeneous resource matching evaluation model based on the business type identification results, thereby effectively improving the adaptability of the target edge server's multi-service heterogeneous resource instant scheduling and business data processing requirements.
[0072] In some embodiments, the method provided by the present invention evaluates the priority of the target edge server by integrating the target edge server trust and the matching degree of multi-service heterogeneous resources, performs edge-to-edge collaborative data processing based on the target edge server priority evaluation, and further uses server status and data processing result feedback to update the priority score of the target edge server, thereby effectively improving the edge-to-edge collaborative data processing performance for real-time scheduling of multi-service heterogeneous resources in distribution networks.
[0073] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0074] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0075] Figure 1 It is one of the flow charts of an edge-to-edge collaboration method for real-time scheduling of multi-service heterogeneous resources in a distribution network according to an exemplary embodiment;
[0076] Figure 2 This is a second flow chart of an edge-to-edge collaboration method for real-time scheduling of multi-service heterogeneous resources in a distribution network according to an exemplary embodiment;
[0077] Figure 3A structural diagram of the system architecture in the edge-to-edge collaboration method provided by the present invention;
[0078] Figure 4 It is a flowchart of a third side-by-side collaborative method for real-time scheduling of multi-service heterogeneous resources in a distribution network according to an exemplary embodiment;
[0079] Figure 5 This is a fourth flow chart of an edge-to-edge collaboration method for real-time scheduling of multi-service heterogeneous resources in a distribution network according to an exemplary embodiment;
[0080] Figure 6 It is a flowchart of a side-by-side collaborative method for real-time scheduling of multi-service heterogeneous resources in a distribution network according to an exemplary embodiment;
[0081] Figure 7 It is a structural block diagram of an edge-to-edge collaboration device for real-time scheduling of multi-service heterogeneous resources in a distribution network according to an exemplary embodiment;
[0082] Figure 8 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment.
[0083] Reference numerals:
[0084] 701-business type classification unit, 702-indicator type identification unit, 703-result generation unit. DETAILED DESCRIPTION
[0085] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.
[0086] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.
[0087] As used herein, unless otherwise specified, the term "plurality" means two or more than two.
[0088] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.
[0089] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.
[0090] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.
[0091] Please refer to Figure 1 , Figure 1 It is one of the flow charts of an edge-to-edge collaboration method for real-time scheduling of multi-service heterogeneous resources in a distribution network according to an exemplary embodiment.
[0092] In a specific implementation, the edge-to-edge collaboration method for real-time scheduling of heterogeneous resources of multiple services in a distribution network provided by the present invention comprises the following steps:
[0093] S110: Classify the business data according to the preset differentiated requirements of the target distribution network to obtain multiple business data types; specifically, the business data types may include classifying the business data into low-latency business data, computing-intensive business data and high-traffic business data according to the differentiated requirements of the target distribution network for latency, computing resources and storage capacity for different businesses.
[0094] S120: Based on the target demand index, scoring each of the business data types to obtain a scoring result, and identifying each of the business data types according to the scoring result to obtain an identification result;
[0095] S130: Based on the identification result, the priority of the target edge server is evaluated according to the target edge server trust and the multi-service heterogeneous resource matching degree to obtain an evaluation result, and the target edge server for collaborative data processing is selected according to the evaluation result.
[0096] Furthermore, in order to improve the offloading performance of edge-to-edge collaboration, e.g. Figure 2 As shown, a target edge server for collaborative data processing is selected according to the evaluation result, and then the following steps may be included:
[0097] S140: updating the priority score of the target edge server according to the processing feedback result.
[0098] In a specific usage scenario, the edge-to-edge collaboration method for real-time scheduling of heterogeneous resources in multiple services of a distribution network provided by the present invention has a system architecture as follows: Figure 3 As shown in the figure. First, according to the differentiated requirements of different services in the distribution network for latency, computing resources, storage, etc., the service data types are divided into low-latency service data, computing-intensive service data, and high-traffic service data; secondly, according to the divided service data types, the service data types are identified by comprehensively considering the multi-service requirements of the distribution network such as latency, computing resources, and available storage space; finally, based on the identified service data types, the priority of the target edge server is evaluated according to the target edge server trust and the matching degree of multi-service heterogeneous resources, the target edge server for collaborative data processing is selected, and the priority score of the target edge server is updated according to the processing feedback results to improve the edge-to-edge collaborative offloading performance.
[0099] In some embodiments, Figure 4 As shown, in the above step S120, based on the target demand index, each of the business data types is scored to obtain a scoring result, and each of the business data types is identified according to the scoring result to obtain an identification result, which specifically includes the following steps:
[0100] S410: Normalize the original demand indicator to obtain the target demand indicator; specifically, when performing the normalization process, comprehensively consider the requirements of the distribution network service for latency, computing resources, and storage space resources, perform linear changes on the original latency demand indicator, computing resource demand indicator, and storage space demand indicator of the end-side data, and map the original demand indicator to between [0-1] to achieve normalization of the demand indicator.
[0101] S420: Score each business data type based on the target demand indicator to obtain a score result for each business data type.
[0102] When the service data types are divided into low-latency service data, computing-intensive service data and high-traffic service data, each of the above data types needs to be scored separately.
[0103] Specifically, the delay requirement index score is calculated using the first preset formula to obtain a first score result delay; the computing resource requirement index score is calculated using the second preset formula to obtain a second score result com; the storage space requirement index score is calculated using the third preset formula to obtain a third score result sto;
[0104] Wherein, the first preset formula is:
[0105]
[0106] In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
[0107] Wherein, the second preset formula is:
[0108]
[0109] In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
[0110] Wherein, the third preset formula is:
[0111]
[0112] In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
[0113] S430: Using the target demand index corresponding to the highest score in the scoring result, identify the business data type to obtain the identification result. For example, if the latency demand index has the highest score, the business data type is identified as low-latency business data; if the computing resource demand index has the highest score, the business data type is identified as computing-intensive business data; if the storage space demand index has the highest score, the business data type is identified as high-traffic business data.
[0114] In some embodiments, Figure 5 As shown, in the above step S130, based on the identification result, the priority of the target edge server is evaluated according to the target edge server trust and the multi-service heterogeneous resource matching degree to obtain an evaluation result, and the target edge server for collaborative data processing is selected according to the evaluation result, which specifically includes the following steps:
[0115] S510: Evaluate the reliability of offloading the service data to each target edge server to obtain a reliability evaluation result.
[0116] Specifically, the trust is evaluated using a first evaluation expression; wherein the first evaluation expression is:
[0117]
[0118] In the formula, represents the trust of offloading the j-th business data to the i-th target edge server, B i,j It represents the available channel bandwidth for offloading the j-th service data to the i-th target edge server for data collaborative processing, B i represents the total bandwidth, f i,j It is represented by the available computing resource margin for offloading the j-th business data to the i-th target edge server for data collaborative processing, f i represents the total computing resources of the target edge server i, Q i,j represents the available storage space for the jth type of business data of the i-th target edge server, σ i,j ,δ i,j are the weight parameters of available channel bandwidth, computing resource margin, and available storage space respectively.
[0119] S520: Evaluate the matching degree between the processing requirements of the business data and the multi-business heterogeneous resources to obtain a matching degree evaluation result.
[0120] Specifically, the matching degree is evaluated using a second evaluation expression; wherein the second evaluation expression is:
[0121]
[0122] Where η i,j represents the amount of marketing resources that the target edge server i can provide for the jth type of business data, ι i,j represents the amount of data of the inspection resources that the target edge server i can provide for the jth type of business data, κ i,j represents the amount of scheduling resources that the target edge server i can provide for the jth type of business data, a i,j , b i,j 、c i,j They are the weight parameters of marketing resources, operation and maintenance resources, and scheduling resources respectively.
[0123] S530: Based on the reliability evaluation result and the matching evaluation result, the priority of the target edge server is evaluated to obtain an evaluation result.
[0124] Specifically, the priority is evaluated using a third evaluation expression; wherein the third evaluation expression is:
[0125]
[0126] In the formula, score i,j represents the score of offloading the j-th business data to the target edge server i for edge-to-edge collaborative processing, represents the trustworthiness of offloading the j-th service data to the i-th target edge server, ψ i,j It represents the matching degree between the j-th service data processing requirement and the multi-service heterogeneous resources provided by the i-th target edge server.
[0127] S540: Unload the business data to the target edge server with the highest score in the evaluation results for edge-to-edge collaborative processing.
[0128] For the sake of convenience of explanation, the following takes a specific usage scenario as an example to briefly describe the overall process of the edge-to-edge collaboration method for real-time scheduling of multi-service heterogeneous resources in a distribution network provided by the present invention.
[0129] like Figure 6 As shown, the present invention proposes an edge-to-edge collaboration method for real-time scheduling of multi-service heterogeneous resources in a distribution network, and the specific steps are as follows:
[0130] S1: According to the differentiated requirements of different services in the distribution network for latency, computing resources, storage, etc., the present invention divides the service data types into low-latency service data, computing-intensive service data, and high-traffic service data.
[0131] S2: Based on the distribution network multi-service classification rules proposed in step S1, the service data type is identified by comprehensively considering the distribution network multi-service requirements such as latency, computing resources, and storage space indicators.
[0132] S2.1: Comprehensively consider the requirements of distribution network services for latency, computing resources, and storage space resources, linearly change the original latency requirement index, computing resource requirement index, and storage space requirement index of the end-side data, map the original requirement index to [0-1], and realize the normalization of the requirement index.
[0133] S2.2: Based on the distribution network multi-service classification rules proposed in step S1, the data source edge server comprehensively considers the normalized indicators of distribution network multi-service requirements such as latency, computing resources, and storage space to score the service data to be identified, which is expressed as:
[0134]
[0135]
[0136]
[0137] Among them, τ is the normalized index of latency demand, υ is the normalized index of computing resource demand, is the normalized index of storage space demand; delay, com, and sto are the scores of the delay demand index, computing resource demand index, and storage space demand index, respectively, which can reflect the degree of demand of business data for delay, computing resources, and available storage space. Business data is identified by comparing the scores. If the delay demand index score delay is the highest, the business data is identified as low-latency business data; if the computing resource demand index score com is the highest, the business data is identified as computing-intensive business data; if the storage space demand index score sto is the highest, the business is identified as high-traffic business data.
[0138] S3: The data source edge server builds a target edge server priority scoring model based on the target edge server trust and the matching degree of multi-service heterogeneous resources, and makes server scheduling decisions based on the priority scores of each available target edge server to achieve edge-to-edge collaborative data processing.
[0139] S3.1: Target edge server trustworthiness evaluation. The present invention considers the available channel bandwidth, computing resource margin, available storage space and other communication, computing and storage resource indicators of each target edge server, and evaluates the trustworthiness of data offloaded to each target edge server, which is expressed as
[0140]
[0141] in, represents the trust of offloading the j-th business data to the i-th target edge server, B i,j It represents the available channel bandwidth for offloading the j-th service data to the i-th server for data collaborative processing, B i represents the total bandwidth, f i,j It is represented by the available computing resource margin for offloading the j-th business data to the i-th target edge server for data collaborative processing, f i represents the total computing resources of the target edge server i, Q i,j represents the available storage space for the jth type of business data of the i-th target edge server, σ i,j ,δ i,j They are weight parameters of available channel bandwidth, computing resource margin, and available storage space, respectively. The weight parameters vary according to the type of business data identified in step S2, and are used to reflect the degree of demand of different business data for indicators such as available channel bandwidth, computing resource margin, and available storage space.
[0142] S3.2: Data processing and multi-service heterogeneous resource matching evaluation. The present invention comprehensively considers the differentiated requirements of different business data processing for the marketing, operation and inspection, scheduling and other multi-service heterogeneous resources that the target edge server can provide, and defines the matching degree ψ between data processing requirements and multi-service heterogeneous resources i,j , which is expressed as:
[0143]
[0144] Among them, η i,j represents the amount of marketing resources that the target edge server i can provide for the jth type of business data, ι i,j represents the amount of data of the inspection resources that the target edge server i can provide for the jth type of business data, κ i,j represents the amount of scheduling resources that the target edge server i can provide for the jth type of business data, a i,j , b i,j 、c i,j They are weight parameters for marketing resources, operation and inspection resources, and scheduling resources. The weight parameters vary according to the type of business data identified in step S2, and are used to reflect the degree of demand for multi-business heterogeneous resources for different business data processing.
[0145] S3.3: Construction of the target edge server priority scoring model. The present invention comprehensively considers the available communication, computing, storage and other resources of the target edge server and the matching degree of multi-service heterogeneous resources to construct the target edge server priority scoring model, integrates the target edge server trust and data processing requirements obtained by formula (2) and formula (3) with the matching degree of multi-service heterogeneous resources, and calculates the target edge server priority score i,j :
[0146]
[0147] Among them, score i,j represents the score of offloading the j-th business data to the target edge server i for edge-to-edge collaborative processing, represents the trustworthiness of offloading the j-th service data to the i-th target edge server, ψ i,j It represents the matching degree between the j-th service data processing requirement and the multi-service heterogeneous resources provided by the i-th target edge server.
[0148] S3.4: The data source edge server receives the power data from the power business terminal and obtains the priority score of each available target edge server according to formula (3): i,j, thereby making edge-to-edge collaborative decisions and offloading the data to the target edge server with the highest score for edge-to-edge collaborative data processing.
[0149] S3.5: The target edge server feeds back the server status and data processing results to the data source edge server, and updates the priority score of the target edge server.
[0150] In the above specific implementation, the edge-to-edge collaboration method for real-time scheduling of heterogeneous resources for multiple services in a distribution network provided by the present invention divides the service data into types according to the preset differentiated requirements of the target distribution network to obtain multiple service data types; scores each of the service data types based on the target demand index to obtain a scoring result, and identifies each of the service data types according to the scoring result to obtain an identification result; based on the identification result, the priority of the target edge server is evaluated according to the trust of the target edge server and the matching degree of heterogeneous resources for multiple services to obtain an evaluation result, and the target edge server for collaborative data processing is selected according to the evaluation result. This solves the problem that the differentiated matching performance of the edge-to-edge collaboration method in the prior art is poor, and the heterogeneous resources provided by the edge server are poorly matched with the service data processing requirements.
[0151] More specifically, the method provided by the present invention divides business types and identifies business data according to the differentiated requirements of different services in the distribution network for latency, computing resources, storage, etc., and constructs a target edge server trust and heterogeneous resource matching evaluation model based on the business type identification results, thereby effectively improving the adaptability of the target edge server's multi-service heterogeneous resources real-time scheduling and business data processing requirements.
[0152] More specifically, the method provided by the present invention evaluates the priority of the target edge server by integrating the trust of the target edge server and the matching degree of multi-service heterogeneous resources, performs edge-to-edge collaborative data processing based on the target edge server priority evaluation, and further uses the server status and data processing result feedback to update the priority score of the target edge server, thereby effectively improving the edge-to-edge collaborative data processing performance for the real-time scheduling of multi-service heterogeneous resources in the distribution network.
[0153] According to a second aspect of the embodiment of the present invention, Figure 7 As shown, the edge-to-edge collaboration device for real-time scheduling of multi-service heterogeneous resources in a distribution network provided by the present invention includes:
[0154] The service type classification unit 701 is used to classify the service data according to the preset differentiated requirements of the target distribution network to obtain multiple service data types;
[0155] The indicator type identification unit 702 is used to score each of the business data types based on the target demand indicator to obtain a scoring result, and identify each of the business data types according to the scoring result to obtain an identification result;
[0156] The result generating unit 703 is used to evaluate the priority of the target edge server based on the identification result, according to the target edge server reliability and the multi-service heterogeneous resource matching degree to obtain an evaluation result, and select the target edge server for collaborative data processing according to the evaluation result.
[0157] In some embodiments, the service type classification unit is specifically used to:
[0158] According to the differentiated requirements of the target distribution network for latency, computing resources and storage capacity for different businesses, the business data is divided into low-latency business data, computing-intensive business data and high-traffic business data.
[0159] In some embodiments, based on the target demand index, each of the business data types is scored to obtain a scoring result, and each of the business data types is identified according to the scoring result to obtain an identification result, specifically including:
[0160] Normalizing the original demand index to obtain the target demand index;
[0161] Scoring each business data type based on the target demand indicator to obtain a score result for each business data type;
[0162] The target demand indicator corresponding to the highest score in the scoring result is used to identify the business data type to obtain the identification result.
[0163] In some embodiments, the original demand index is normalized to obtain the target demand index, specifically including:
[0164] Comprehensively consider the requirements of distribution network services for latency, computing resources, and storage space resources, linearly change the original latency demand index, computing resource demand index, and storage space demand index of the end-side data, map the original demand index to [0-1], and realize the normalization of the demand index.
[0165] In some embodiments, scoring each business data type based on the target demand indicator to obtain a score result for each business data type specifically includes:
[0166] Using the first preset formula, the delay requirement indicator score is calculated to obtain a first score result delay;
[0167] Wherein, the first preset formula is:
[0168]
[0169] In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
[0170] In some embodiments, scoring each business data type based on the target demand indicator to obtain a score result for each business data type specifically includes:
[0171] Using a second preset formula, the computing resource requirement indicator score is calculated to obtain a second score result com;
[0172] Wherein, the second preset formula is:
[0173]
[0174] In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
[0175] In some embodiments, scoring each business data type based on the target demand indicator to obtain a score result for each business data type specifically includes:
[0176] Calculate the storage space requirement index score using a third preset formula to obtain a third score result sto;
[0177] Wherein, the third preset formula is:
[0178]
[0179] In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
[0180] In some embodiments, the target demand indicator corresponding to the highest score in the scoring result is used to identify the business data type to obtain the identification result, specifically including:
[0181] If the latency requirement index score is the highest, the service data type is identified as low-latency service data;
[0182] If the computing resource requirement indicator has the highest score, the business data type is identified as computing-intensive business data;
[0183] If the storage space requirement index scores the highest, the business data type is identified as high-traffic business data.
[0184] In some embodiments, based on the identification result, the priority of the target edge server is evaluated according to the target edge server trust and the multi-service heterogeneous resource matching degree to obtain an evaluation result, and the target edge server for collaborative data processing is selected according to the evaluation result, specifically including:
[0185] Evaluate the trustworthiness of offloading business data to each target edge server to obtain a trustworthiness evaluation result;
[0186] Evaluate the matching degree between the processing requirements of business data and multi-business heterogeneous resources to obtain matching evaluation results;
[0187] Based on the trust evaluation result and the matching evaluation result, the priority of the target edge server is evaluated to obtain an evaluation result;
[0188] The business data is unloaded to the target edge server with the highest score in the evaluation results for edge-to-edge collaborative processing.
[0189] In some embodiments, the trust is evaluated using a first evaluation expression;
[0190] Wherein, the first evaluation expression is:
[0191]
[0192] In the formula, represents the trust of offloading the j-th business data to the i-th target edge server, B i,j It represents the available channel bandwidth for offloading the j-th service data to the i-th target edge server for data collaborative processing, B i represents the total bandwidth, f i,j It is represented by the available computing resource margin for offloading the j-th business data to the i-th target edge server for data collaborative processing, f i represents the total computing resources of the target edge server i, Q i,j represents the available storage space for the jth type of business data of the i-th target edge server, σ i,j ,δ i,j are the weight parameters of available channel bandwidth, computing resource margin, and available storage space respectively.
[0193] In some embodiments, the matching degree is evaluated using a second evaluation expression;
[0194] Wherein, the second evaluation expression is:
[0195]
[0196] Where η i,jrepresents the amount of marketing resources that the target edge server i can provide for the jth type of business data, ι i,j represents the amount of data of the inspection resources that the target edge server i can provide for the jth type of business data, κ i,j represents the amount of scheduling resources that the target edge server i can provide for the jth type of business data, a i,j , b i,j 、c i,j They are the weight parameters of marketing resources, operation and maintenance resources, and scheduling resources respectively.
[0197] In some embodiments, the priority is evaluated using a third evaluation expression;
[0198] Wherein, the third evaluation expression is:
[0199]
[0200] In the formula, score i,j Indicates that the jth type of business data is offloaded to the edge server The score of data edge-to-edge collaborative processing, represents the trustworthiness of offloading the j-th service data to the i-th target edge server, ψ i,j It represents the matching degree between the j-th service data processing requirement and the multi-service heterogeneous resources provided by the i-th target edge server.
[0201] In some embodiments, selecting a target edge server for collaborative data processing according to the evaluation result further includes:
[0202] Update the priority score of the target edge server based on the processing feedback result.
[0203] In the above specific implementation, the edge-to-edge collaboration device for real-time scheduling of heterogeneous resources for multiple services in a distribution network provided by the present invention divides the service data into types according to the preset differentiated requirements of the target distribution network to obtain multiple service data types; scores each of the service data types based on the target demand index to obtain a scoring result, and identifies each of the service data types according to the scoring result to obtain an identification result; based on the identification result, the priority of the target edge server is evaluated according to the trust of the target edge server and the matching degree of heterogeneous resources for multiple services to obtain an evaluation result, and the target edge server for collaborative data processing is selected according to the evaluation result. This solves the problem that the differentiated matching performance of the edge-to-edge collaboration method in the prior art is poor, and the heterogeneous resources provided by the edge server are poorly matched with the service data processing requirements.
[0204] More specifically, the method provided by the present invention divides business types and identifies business data according to the differentiated requirements of different services in the distribution network for latency, computing resources, storage, etc., and constructs a target edge server trust and heterogeneous resource matching evaluation model based on the business type identification results, thereby effectively improving the adaptability of the target edge server's multi-service heterogeneous resources real-time scheduling and business data processing requirements.
[0205] More specifically, the method provided by the present invention evaluates the priority of the target edge server by integrating the trust of the target edge server and the matching degree of multi-service heterogeneous resources, performs edge-to-edge collaborative data processing based on the target edge server priority evaluation, and further uses the server status and data processing result feedback to update the priority score of the target edge server, thereby effectively improving the edge-to-edge collaborative data processing performance for the real-time scheduling of multi-service heterogeneous resources in the distribution network.
[0206] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.
[0207] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0208] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0209] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
Claims
1. An edge-to-edge collaboration method for real-time scheduling of multi-service heterogeneous resources in distribution networks, characterized in that: The method comprises: According to the preset differentiated requirements of the target distribution network, the business data is classified to obtain multiple business data types; Based on the target demand index, scoring each of the business data types to obtain a scoring result, and identifying each of the business data types according to the scoring result to obtain an identification result; Based on the identification result, the trust of unloading the business data to each target edge server is evaluated to obtain a trust evaluation result; the matching degree between the processing demand of the business data and the multi-business heterogeneous resources is evaluated to obtain a matching evaluation result; based on the trust evaluation result and the matching evaluation result, the priority of the target edge server is evaluated to obtain an evaluation result; the business data is unloaded to the target edge server with the highest score in the evaluation result for edge-to-edge collaborative processing; evaluating the trust using the first evaluation expression; Wherein, the first evaluation expression is: In the formula, represents the trust of offloading the j-th business data to the i-th target edge server, B i,j It represents the available channel bandwidth for offloading the j-th service data to the i-th target edge server for data collaborative processing, B i represents the total bandwidth, f i,j It is represented by the available computing resource margin for offloading the j-th business data to the i-th target edge server for data collaborative processing, f i represents the total computing resources of the target edge server i, Q i,j represents the available storage space for the jth type of business data of the i-th target edge server, σ i,j ,δ i,j are weight parameters of available channel bandwidth, computing resource margin, and available storage space respectively; Using the second evaluation expression to evaluate the matching degree; Wherein, the second evaluation expression is: Where η i,j represents the amount of marketing resources that the target edge server i can provide for the jth type of business data, ι i,j represents the amount of data of the inspection resources that the target edge server i can provide for the jth type of business data, κ i,j represents the amount of scheduling resources that the target edge server i can provide for the jth type of business data, a i,j , b i,j 、c i,j They are the weight parameters of marketing resources, operation and inspection resources, and dispatching resources respectively; evaluating the priority using the third evaluation expression; Wherein, the third evaluation expression is: In the formula, score i,j represents the score of offloading the j-th business data to the target edge server i for edge-to-edge collaborative processing, represents the trustworthiness of offloading the j-th service data to the j-th target edge server, ψ i,j It represents the matching degree between the j-th service data processing requirement and the multi-service heterogeneous resources provided by the i-th target edge server.
2. The edge-to-edge collaboration method for real-time scheduling of heterogeneous resources in multiple services of distribution networks according to claim 1 is characterized in that: According to the preset differentiated requirements of the target distribution network, the business data is divided into types to obtain multiple business data types, including: According to the differentiated requirements of the target distribution network for latency, computing resources and storage capacity for different businesses, the business data is divided into low-latency business data, computing-intensive business data and high-traffic business data.
3. The edge-to-edge collaboration method for real-time scheduling of heterogeneous resources in multiple services of distribution networks according to claim 2 is characterized in that: Based on the target demand index, each of the business data types is scored to obtain a scoring result, and each of the business data types is identified according to the scoring result to obtain an identification result, which specifically includes: Normalizing the original demand index to obtain the target demand index; Scoring each business data type based on the target demand indicator to obtain a score result for each business data type; The target demand indicator corresponding to the highest score in the scoring result is used to identify the business data type to obtain the identification result.
4. The edge-to-edge collaboration method for real-time scheduling of heterogeneous resources in multiple services of distribution networks according to claim 3 is characterized in that: The original demand index is normalized to obtain the target demand index, which specifically includes: Comprehensively consider the requirements of distribution network services for latency, computing resources, and storage space resources, linearly change the original latency demand index, computing resource demand index, and storage space demand index of the end-side data, map the original demand index to [0-1], and realize the normalization of the demand index.
5. The edge-to-edge collaboration method for real-time scheduling of heterogeneous resources in multiple services of distribution networks according to claim 4 is characterized in that: Scoring each business data type based on the target demand indicator to obtain a score result for each business data type, specifically including: Using the first preset formula, the delay requirement indicator score is calculated to obtain a first score result delay; Wherein, the first preset formula is: Where τ is the normalized index of latency requirement, v is the normalized index of computing resource requirement, and ζ is the normalized index of storage space requirement.
6. The edge-to-edge collaboration method for real-time scheduling of heterogeneous resources in multiple services of distribution networks according to claim 4 is characterized in that: Scoring each business data type based on the target demand indicator to obtain a score result for each business data type, specifically including: Using a second preset formula, the computing resource requirement indicator score is calculated to obtain a second score result com; Wherein, the second preset formula is: In the formula, τ is the normalized index of latency requirement, v is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
7. The edge-to-edge collaboration method for real-time scheduling of heterogeneous resources in multiple services of distribution network according to claim 4 is characterized in that: Scoring each business data type based on the target demand indicator to obtain a score result for each business data type, specifically including: Calculate the storage space requirement index score using a third preset formula to obtain a third score result sto; Wherein, the third preset formula is: In the formula, τ is the normalized index of latency requirement, v is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
8. The edge-to-edge collaboration method for real-time scheduling of heterogeneous resources in multiple services of distribution network according to claim 1 is characterized in that: Using the target demand indicator corresponding to the highest score in the scoring result, the business data type is identified to obtain the identification result, which specifically includes: If the latency requirement index score is the highest, the service data type is identified as low-latency service data; If the computing resource requirement indicator has the highest score, the business data type is identified as computing-intensive business data; If the storage space requirement index scores the highest, the business data type is identified as high-traffic business data.
9. The edge-to-edge collaboration method for real-time scheduling of heterogeneous resources in multiple services of distribution networks according to claim 1 is characterized in that: Selecting a target edge server for collaborative data processing according to the evaluation result, and then further comprising: Update the priority score of the target edge server based on the processing feedback result.
10. An edge-to-edge collaboration device for real-time scheduling of heterogeneous resources of multiple services in a distribution network, characterized in that: The device comprises: A business type classification unit, used to classify business data according to preset differentiated requirements of the target distribution network to obtain multiple business data types; An indicator type identification unit, used to score each of the business data types based on the target demand indicator to obtain a scoring result, and identify each of the business data types according to the scoring result to obtain an identification result; A result generating unit is used to evaluate the trust of unloading the business data to each target edge server based on the identification result to obtain a trust evaluation result; evaluate the matching degree between the processing requirements of the business data and the multi-business heterogeneous resources to obtain a matching evaluation result; evaluate the priority of the target edge server based on the trust evaluation result and the matching evaluation result to obtain an evaluation result; unload the business data to the target edge server with the highest score in the evaluation result for edge-to-edge collaborative processing; evaluating the trust using the first evaluation expression; Wherein, the first evaluation expression is: In the formula, represents the trust of offloading the j-th business data to the i-th target edge server, B i,j It represents the available channel bandwidth for offloading the j-th service data to the i-th target edge server for data collaborative processing, B i represents the total bandwidth, f i,j It is represented by the available computing resource margin for offloading the j-th business data to the i-th target edge server for data collaborative processing, f i represents the total computing resources of the target edge server i, Q i,j represents the available storage space for the jth type of business data of the i-th target edge server, σ i,j ,δ i,j are weight parameters of available channel bandwidth, computing resource margin, and available storage space respectively; Using the second evaluation expression to evaluate the matching degree; Wherein, the second evaluation expression is: Where η i,j represents the amount of marketing resources that the target edge server i can provide for the jth type of business data, ι i,j represents the amount of data of the inspection resources that the target edge server i can provide for the jth type of business data, κ i,j represents the amount of scheduling resources that the target edge server i can provide for the jth type of business data, q i,j , b i,j 、c i,j They are the weight parameters of marketing resources, operation and inspection resources, and dispatching resources respectively; evaluating the priority using the third evaluation expression; Wherein, the third evaluation expression is: In the formula, score i,j represents the score of offloading the j-th business data to the target edge server i for edge-to-edge collaborative processing, represents the trustworthiness of offloading the j-th service data to the i-th target edge server, ψ i,j It represents the matching degree between the j-th service data processing requirement and the multi-service heterogeneous resources provided by the i-th target edge server.
11. The edge-to-edge collaboration device for real-time scheduling of heterogeneous resources in multiple services in a distribution network according to claim 10, characterized in that: The service type classification unit is specifically used for: According to the differentiated requirements of the target distribution network for latency, computing resources and storage capacity for different businesses, the business data is divided into low-latency business data, computing-intensive business data and high-traffic business data.
12. The edge-to-edge collaboration device for real-time scheduling of heterogeneous resources in multiple services in a distribution network according to claim 11, characterized in that: The indicator type identification unit is specifically used to: normalize the original demand indicator to obtain the target demand indicator; Scoring each business data type based on the target demand indicator to obtain a score result for each business data type; The target demand indicator corresponding to the highest score in the scoring result is used to identify the business data type to obtain the identification result.
13. The edge-to-edge collaboration device for real-time scheduling of heterogeneous resources in multiple services in a distribution network according to claim 12, characterized in that: The original demand index is normalized to obtain the target demand index, which specifically includes: Comprehensively consider the requirements of distribution network services for latency, computing resources, and storage space resources, linearly change the original latency demand index, computing resource demand index, and storage space demand index of the end-side data, map the original demand index to [0-1], and realize the normalization of the demand index.
14. The edge-to-edge collaboration device for real-time scheduling of heterogeneous resources in multiple services in a distribution network according to claim 13, characterized in that: Scoring each business data type based on the target demand indicator to obtain a score result for each business data type, specifically including: Using the first preset formula, the delay requirement indicator score is calculated to obtain a first score result delay; Wherein, the first preset formula is: In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
15. The edge-to-edge collaboration device for real-time scheduling of heterogeneous resources in multiple services in a distribution network according to claim 13, characterized in that: Scoring each business data type based on the target demand indicator to obtain a score result for each business data type, specifically including: Using a second preset formula, the computing resource requirement indicator score is calculated to obtain a second score result com; Wherein, the second preset formula is: In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
16. The edge-to-edge collaboration device for real-time scheduling of heterogeneous resources in multiple services in a distribution network according to claim 13, characterized in that: Scoring each business data type based on the target demand indicator to obtain a score result for each business data type, specifically including: Calculate the storage space requirement index score using a third preset formula to obtain a third score result sto; Wherein, the third preset formula is: In the formula, τ is the normalized index of latency requirement, υ is the normalized index of computing resource requirement, Normalized metric for storage space requirements.
17. The edge-to-edge collaboration device for real-time scheduling of heterogeneous resources in multiple services in a distribution network according to claim 10, characterized in that: Using the target demand indicator corresponding to the highest score in the scoring result, the business data type is identified to obtain the identification result, which specifically includes: If the latency requirement index score is the highest, the service data type is identified as low-latency service data; If the computing resource requirement indicator has the highest score, the business data type is identified as computing-intensive business data; If the storage space requirement index scores the highest, the business data type is identified as high-traffic business data.
18. The edge-to-edge collaboration device for real-time scheduling of multi-service heterogeneous resources in distribution networks according to claim 10, characterized in that: Selecting a target edge server for collaborative data processing according to the evaluation result, and then further comprising: Update the priority score of the target edge server based on the processing feedback result.
19. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.
