A power distribution network operation situation multi-layer data system compatible with front-end early warning and back-end tracking

Abstract

The application discloses a power distribution network operation situation multilayer data system compatible with front-end early warning and back-end tracking, which is integrated with a power grid electricity information collection system, a power grid centralized business application system and other necessary existing power grid data systems in advance, and is constructed in the data orientation of power grid appeal risk data optimization, power application end attribute optimization and power grid bottom layer distributed port support. Meanwhile, the structured data processing method developed and constructed in the data system is matched and constructed according to the dynamics and space-time characteristics of power appeal data, and the data development trend of power appeal data in risk early warning and risk event later stage, and has a brand-new data processing flow and data structure.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid data processing, in particular to a power distribution network operation situation multi-layer data system compatible with front-end early warning and back-end tracking and a structured data processing algorithm thereof. BACKGROUND

[0002] With the continuous improvement of power supply service process control means, State Grid Hubei Electric Power has established a service quality control method of online channels such as 95598, providing a three-level control mechanism for early warning of cities, counties and power supply stations. However, with the continuous improvement of service quality management requirements, the data processing and analysis dimension precision of traditional technology conditions cannot meet the current technical requirements.

[0003] Under this technical background, the power grid service situation monitoring and risk early warning application project is carried out. On the one hand, the overall architecture, application architecture, business and data architecture, and security deployment architecture of the application project are systematically developed and constructed. On the other hand, it is particularly important to build comprehensive adaptive data algorithms on the system architecture.

[0004] According to the pre-investigation of the application development, the existing power grid service situation data processing data algorithm mainly relies on traditional manual data processing and analysis methods. The dependence on manual work makes it only suitable for processing small-scale and simple-structured power demand data sets, which are generally single-event power demand data. When facing global, large-scale, complex-structured and dynamically changing power demand data, the existing data processing method not only has problems in efficiency and accuracy, but also has almost no feasibility.

[0005] Therefore, considering the serious inapplicability of existing manual data processing in the global processing of power demand data, on the basis of the above-mentioned overall architecture of the application project, further matching and constructing the data process according to the dynamic nature and spatio-temporal characteristics of the power demand data, as well as the data development trend of the risk early warning and the risk event later period, is the core problem of the current application system development. SUMMARY

[0006] The technical problem to be solved by the present application is to build a corresponding data system architecture for the power grid service situation application development project, and further match and construct the data process according to the dynamic nature and spatio-temporal characteristics of the power demand data, as well as the data development trend of the risk early warning and the risk event later period.

[0007] To solve the above technical problems, the technical solutions adopted by the present application are as follows.

[0008] A power distribution network operation situation multi-layer data system compatible with front-end early warning and back-end tracking, which is integrated in advance with a power grid electricity information collection system, a power grid centralized business application system and other necessary existing power grid data systems, and is constructed in a data-oriented manner with power grid appeal risk data optimization, power application end attribute optimization and power grid bottom layer distributed port support as the data orientation.

[0009] As a preferred technical solution of the present application, in the overall architecture, the data layer of the data system can optionally include: power appeal index monitoring optimization, power risk early warning application optimization, construction of a power user attribute library, construction of a power grid service strategy library, risk control application scenario construction, data-based and automatic analysis report application construction and optimization.

[0010] As a preferred technical solution of the present application, the data flow architecture of the data system is set as: the data flow architecture mainly includes two parts of basic support data flow and application data flow.

[0011] The basic support data flow: through a multi-dimensional data import port, 95598 call real-time data, marketing business application system data, electricity collection system data, online State Grid data, 95598 business support system data, 12398 power supervision hotline data and the like are gathered to realize storage, integration and preprocessing of various data.

[0012] The application data flow: mainly faces the following data application ports: power appeal index monitoring optimization, service risk early warning application optimization, construction of a power user attribute library, construction of a service strategy library, risk control application scenario construction, data-based and automatic analysis report application optimization, and application expansion and application port expansion are carried out as needed.

[0013] As a preferred technical solution of the present application, the application architecture of the data system is set as including a platform layer, a data layer, an application layer and an application object layer.

[0014] The platform layer is constructed with the following data modules: platform capability management, platform application theme management, platform system management and platform data management; unified management of system applications, capabilities and data is realized.

[0015] The data layer is constructed with the following data modules: data acquisition, data cleaning, data conversion and processing, and the data objects applied by the data modules mainly include 95598 voice translation text data, work order data, power user basic file data and the like.

[0016] The application layer is constructed with the following data modules: power appeal index monitoring optimization, service risk early warning application optimization, construction of a power user attribute library, construction of a service strategy library, risk control application scenario construction and data-based and automatic analysis report application optimization.

[0017] As a preferred technical scheme of the present application, the application object layer is constructed with the following data modules: front-line service personnel, management personnel, provincial company personnel, and city company personnel; and the data modules of the above different levels provide front-line staff view, management analysis view, provincial company view, and external service view.

[0018] As a preferred technical scheme of the present application, the data architecture of the data system is set as:

[0019] A, structured data and service risk early warning mechanism data of multiple channels such as 12398, marketing service public opinion, or other offline ways, and power information collection system are obtained by using an interface mode, and at the same time, an output channel supporting the above data aggregation and analysis scene application and analysis report / report is constructed;

[0020] B, for the shared data needs of the power grid related third-party manufacturers and systems, the output data is processed again according to the data permission of the data requester, and the result data provided by the external application system corresponding to the data requester permission is formed, which can be directly provided to the application display page or provided to the data demander through the interface service mode.

[0021] As a preferred technical scheme of the present application, the technical architecture of the data system is set as:

[0022] The system data is mainly based on 95598 voice translation text data, power grid business application system work order, 95598 business support work order, and power information collection system power failure data, which are obtained by RESTAPI form and stored into the power grid situation monitoring and risk early warning application system, and provided to different port data demanders and data analysis applications for use, and the analyzed results are output through data communication protocol; wherein:

[0023] The data analysis list is generated by querying the work order data and call text data with an hour frequency;

[0024] The channel data analysis and text data analysis perform data analysis according to the obtained data, and generate data analysis results;

[0025] The power user demand index monitoring optimization, the power grid service risk early warning application optimization, the construction of the power user attribute library, the construction of the service strategy library, the risk control application scene construction, and the analysis report application optimization each call the data analysis result to perform analysis graphics and report display.

[0026] As a preferred technical scheme of the present application, the security architecture of the data system is set as:

[0027] The information big area boundary of the power grid is taken as the leading boundary involved in application deployment, and on this basis, the information internal network boundary is protected by using the existing logical isolation, hardware firewall, IDS / IPS and other boundary security protection devices of the power grid system; and for the outside of the boundary, identity authentication, access control, intrusion detection, log recording and security audit and other security policies are configured to realize boundary isolation and security protection.

[0028] As a preferred technical solution of the present application, the deployment architecture of the data system is arranged to deploy applications and data based on the provincial information big area.

[0029] The structured data processing method in the power distribution network operation situation multi-layer data system has a brand-new data processing flow and data structure.

[0030] The beneficial effects produced by the above technical solution are as follows:

[0031] The power distribution network operation situation multi-layer data system developed and constructed by the present application can analyze and process power user demand index data in a data-based manner, can control the potential risks in power user demands in advance, can realize various demand anomaly monitoring and disposal, can locate service hidden trouble areas, personnel and problems, can carry out hierarchical supervision and management and gradient control, can expand the breadth and depth of business type analysis while monitoring demand analysis, can realize end-of-line analysis of index analysis business, problem distribution and demand occurrence time, and can analyze and monitor various risks and problems.

[0032] One core development item of the present application is to build a structured processing method of power grid appeal and situation data corresponding to the overall architecture of the application project. The development has deep data connotation, and in-depth research and development is carried out by jointing multiple scientific research teams. The final technical route is to realize the global representation and multi-application oriented processing of power appeal data by building data linkage structure and data situation model. In the front-end data linkage structure construction, the power appeal data is associated with the risk factors of power grid operation situation to identify and predict the associated power appeal data and power grid risk elements; the back-end data situation model construction builds a data situation model framework through the global and dynamic structure representation and algorithm processing of the power appeal data group. The framework can not only analyze the processing and evolution situation of the power appeal, but also can construct different power appeal data application orientations according to the spatial expansion and time dynamic characteristics of the appeal data. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 It is a general architecture diagram of the data system of the present application.

[0034] Figure 2 It is a data flow architecture diagram of the data system of the present application.

[0035] Figure 3 It is an application architecture diagram of the data system of the present application.

[0036] Figure 4 It is a data architecture diagram of the data system of the present application.

[0037] Figure 5 It is a technical architecture diagram of the data system of the present application.

[0038] Figure 6 It is a security architecture diagram of the data system of the present application.

[0039] Figure 7 It is a deployment architecture diagram of the data system of the present application. DETAILED DESCRIPTION

[0040] The following embodiments illustrate the present application in detail. In the description of the following embodiments, specific details such as specific system structures, techniques, etc. are presented for the purpose of explanation, not for the purpose of limitation, so that the embodiments of the present application can be thoroughly understood. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits and methods are omitted to avoid unnecessary details that hinder the description of the present application.

[0041] It should be understood that the word “comprise” or variations such as “comprises” or “comprising”, when used in this specification and in the accompanying claims, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0042] It should also be understood that the term “and / or” when used in this specification and in the following claims is to be interpreted as “one or the other or both” and / or “any combination of the items in the list.” It should be understood that the terms “a” and “an” as used in this specification and in the following claims indicate “one or more.”

[0043] As used in this specification and in the claims, the term “if’ can be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context. Similarly, the phrase “if it is determined” or “if [a described condition or event] is detected” can be construed to mean “upon determining” or “in response to determining” or “upon [the described condition or event] being detected” or “in response to [the described condition or event] being detected,” depending on the context.

[0044] In addition, the terms “first,” “second,” “third,” etc. as used in the description and the following claims are used only to distinguish one element from another, and do not imply a relative importance or a specific order.

[0045] Reference throughout this specification to “one embodiment” or “an embodiment” or “some embodiments” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, the appearances of the phrases “in one embodiment,” “in some embodiments,” “in other embodiments,” “in additional embodiments,” and so on, in various places throughout this specification are not necessarily all referring to the same embodiment, unless otherwise specified. The terms “comprise,” “comprises,” “comprising,” “include,” “includes,” “including,” and “contain,” “contains,” “containing,” and the like, are used synonymously, unless otherwise specifically noted.

[0046] Example 1, Power Grid Situation Monitoring and Risk Early Warning Application Overall Project

[0047] Currently, the power grid system has initially completed the construction of the power user information management and control platform, and based on this platform, it has initially realized the real-time acquisition of provincial 95598 power user call data, power user appeal classification and automatic identification, power user service risk index assessment, service management and control index monitoring, marketing event appeal analysis, service risk early warning application, service management quality index monitoring and other dimensions of power user service quality control. Relying on the platform, through the access of marketing business application system, industry expansion and installation system and 95598 real-time data (less than 30 minutes), the real-time analysis of power user call appeals of each local company is initially realized, and the analysis results are applied to all provincial cities, districts and counties. At the same time, by building a risk theme model, the risk problems contained in the dispatched opinion work order are initially realized, and through the construction of a three-level risk early warning method, red, orange and yellow three levels are set.

[0048] The State Grid Hubei Service Situation Monitoring and Risk Early Warning Application Project is carried out under this background.

[0049] The benefit analysis of this project construction is as follows: from the management benefit, with the company continuously strengthening the power supply service quality control, the number of complaints decreases year by year, but from the power user demand situation, potential service risks still exist, and typical problems and red line problems still occur from time to time; through the analysis of power user demand and service early warning and process quality control, the current main demands of power users and possible service risks can be grasped in time; through the construction of power user attribute library and service strategy library, combined with the historical problem solving scheme, accurate service disposal means are pushed to front-line business personnel, decision support is provided for operators, resources are effectively tilted, work scheduling is optimized, work accuracy is improved, service risks are discovered early, early warning is achieved, and fast processing is realized, and the power supply service quality level is effectively improved. From the economic benefit, through the monitoring of the service situation of each city company and the construction of risk early warning scene, the operator can discover the current main demands of power users, main service risk points and personnel and material links quality and efficiency differences in time, and through the corresponding dredging strategy, the work efficiency is improved, the resource optimization is realized, and the business analysis personnel's investment and the secondary risk caused by personnel subjective judgment are reduced, and the enterprise's operation cost is reduced. From the social benefit, the service risk prevention and control and quality management work are carried out, the massive unstructured data resources are fully utilized, the risk early warning disposal model is combined, the possible service risk escalation events are predicted, the effective public relations measures are taken to inform or appease the power users in advance, the prevention is achieved in advance, the large-scale group event is prevented, the service level is improved, the good social image of the enterprise is established, and the power user perception and power user experience are continuously improved. Through the analysis of power supply quality problems, the company can understand the distribution network operation from the headquarters side, provide data reference for the provincial company to do well in power grid construction and transformation, strengthen operation and maintenance management, and improve power supply controllability.

[0050] Embodiment 2, architecture of power grid situation monitoring and risk early warning application

[0051] Overall, the development project constructs a multi-layer data system of distribution network operation situation, so that it is integrated with power grid electricity information collection system, power grid centralized business application system and other necessary existing power grid data systems in advance, and is constructed with data orientation of power grid demand risk data optimization, power application end attribute optimization and power grid bottom layer distributed port support.

[0052] Referring to the accompanying drawings Figure 1 In the overall architecture, the data layer of the power grid situation monitoring and risk early warning application data system can include: power demand index monitoring optimization, power risk early warning application optimization, construction of power user attribute library, construction of power grid service strategy library, risk control application scene construction, data and automatic analysis report application construction and optimization.

[0053] Referring to the accompanying drawings Figure 2 The data flow architecture of the power grid situation monitoring and risk early warning application data system is given, which mainly includes two parts of basic support data flow and application data flow.

[0054] Referring to the accompanying drawings Figure 3 The application architecture of the data system is set to include a platform layer, a data layer, an application layer, and an application object layer. The platform layer is constructed with the following data modules: platform capability management, platform application theme management, platform system management, and platform data management. The unified management of system applications, capabilities, and data is realized. The data layer is constructed with the following data modules: data acquisition, data cleaning, data conversion and processing, and the application data objects mainly include 95598 voice translation text data, work order data, and power user basic profile data. The application layer is constructed with the following data modules: power appeal index monitoring optimization, service risk early warning application optimization, construction of a power user attribute library, construction of a service strategy library, risk control application scenario construction, and data-based automatic analysis report application optimization. The application object layer is constructed with the following data modules: front-line business personnel, management personnel, provincial company personnel, and city company personnel. The front-line employee view, management analysis view, provincial company view, and external service view capabilities are provided for the above different levels of data modules.

[0055] Referring to the accompanying drawings Figure 4 The data architecture of the power grid situation monitoring and risk early warning application data system is given, which uses interface methods to obtain structured data and service risk early warning mechanism data from multiple channels such as 12398, marketing service public opinion, or other offline ways, and power information collection systems. At the same time, the output channels of the above data aggregation and analysis scene application and analysis report / report are constructed. At the same time, in view of the sharing data needs of the related third-party manufacturers and systems of the power grid, the output data is processed again according to the data permission of the data requester, forming the result data provided by the external application system corresponding to the data requester's permission. These result data can be directly provided to the application display page or provided to the data demander through the interface service method.

[0056] Referring to the accompanying drawings Figure 5The technical architecture of the data system is set as follows: the system data is mainly based on the 95598 voice translation text data, the work order of the power grid business application system, the 95598 business support work order, and the power information collection system outage data, which are obtained in the form of RESTAPI and stored in the power grid situation monitoring and risk early warning application system, and provided to different port data demanders and data analysis applications for use. The analyzed results are output in the form of reports through data communication protocols. The data analysis list is generated by querying the work order data and call text data at an hourly frequency, and generating a data analysis list. The channel data analysis and text data analysis are based on the obtained data for data analysis, and the data analysis results are summarized. The power user demand index monitoring optimization, the power grid service risk early warning application optimization, the construction of the power user attribute library, the construction of the service strategy library, the risk control application scenario construction, and the analysis report application optimization each call the data analysis results for analysis graphics and report display.

[0057] Referring to the accompanying drawings Figures 6-7 The security and deployment architecture is set to deploy applications and data based on provincial information zones.

[0058] Embodiment 3, structured data processing method of distribution network operation situation data system

[0059] The development of the power grid service situation monitoring and risk early warning application project involves the systematic development and construction of the overall architecture, application architecture, business and data architecture, and security and deployment architecture of the application project. On the other hand, it is particularly important to build comprehensive adaptive data algorithms on the system architecture. According to the pre-investigation of the application project development, the existing data algorithms for processing power grid service situation data mainly rely on traditional manual data processing and analysis methods. The dependence on manual work limits the processing of small-scale and simple-structured power demand data sets, which are usually single-event power demand data. When facing global, large-scale, complex-structured, and dynamically changing power demand data, the existing data processing methods not only have problems in efficiency and accuracy, but also have almost no feasibility.

[0060] Therefore, considering the serious inapplicability of existing manual data processing in the global processing of power demand data, on the basis of the above-mentioned overall architecture of the application project, further matching and constructing the data process according to the dynamic and spatio-temporal characteristics of power demand data, as well as the development of power demand data in the risk early warning and post-event data development situation, are the core problems of the current application system development.

[0061] Specifically, the expert team inside and outside the joint power grid in-depth development and construction of the power distribution network operation situation multi-layer data system inside the structured data processing method, this structured data processing method according to the dynamic and spatial and temporal characteristics of power demand data, as well as the power demand data in the risk warning and risk event after the development of data situation data process matching construction, with a new data processing flow and data structure.

[0062] The technical development achievements of this part are introduced as follows.

[0063] (1) Front-end structured processing of power demand data

[0064] The front-end structured processing of power demand data is oriented towards the pre-data processing of power distribution network operation situation, and is mainly based on the construction of data link structure to associate power demand data with risk factors of power grid operation situation. Its application orientation is mainly pre-data risk warning. The construction path is as follows: through the equal position exchange processing of power demand data and 95598 audio data power demand type on the data model, the data link structure of power grid operation risk element data extracted and marked based on 95598 audio data power demand type is transferred to the data association structure of power demand data and risk factors of power grid operation situation. The specific data structuring process is described as follows.

[0065] At the bottom of the data structure, the data entity set is constructed in the form of data collection, each of which represents a data entity; the data collection E initialization includes several independent data entities: power demand data, power grid operation risk factor data; and other subsequent expandable data entities such as power grid operation state data, etc.; the direct consistency of each data entity is represented by its attribute set, that is, in the data structure, the data entity itself and the attribute of the data entity are directly processed in a one-to-one manner; for each attribute in the attribute set, based on the bottom layer data collection E initialization of the data model including power demand data, power grid operation state data, power grid operation risk factor data and allowing subsequent expansion of other data entity types, the attribute is initialized to be compatible with the widest data object data type range, including basic data types such as integers, strings, etc. or text data and other non-structured data. Based on the data relationship between the attribute sets of each data entity, the data collection further establishes its multidirectional data relationship link in principle on the basis of the data entity accommodation; in particular, regarding the data structure of the data relationship, the data relationship link inside the data collection is constructed as the core guide type of multi-directional link, that is, the data link initially takes a selected data entity as the core, based on the data relationship between the attribute sets of each data entity, and combining the data standard for measuring the data relationship between the attribute sets set in advance or artificially designated as the data guide of the data relationship link, the selected core data entity is guided and linked with other one or more data entities. Among them, the guide of the data link relationship takes a subset in the attribute set as the initialization data processing object, that is, based on the selected subset to construct the data processing relationship and its data processing process; among them, the most simplified and most practical data selection is to take a single subset of the attribute set as the initialization data processing object of the data link relationship guide. Here, different types of power demand are directly used as a single subset and as the initialization data object of the data link relationship guide in the data process.

[0066] The specific data step is: first, the attribute set of the data entity "power appeal data" is set to at least include: different power appeal types (unstructured text appeal data or structured vector data after text vectorization); the attribute set of the power grid operation risk element data is constructed as a two-dimensional array structure, first according to the type of the power grid risk event to expand the data along one dimension, and at the same time according to the risk level of the power grid operation to expand the data of each data bit column of the first data dimension along the second dimension, thereby obtaining the two-dimensional data attribute set of the power grid operation risk element data entity; when the risk event type and the risk level value are equal, the two-dimensional array structure corresponds to a second-order tensor; as for the attribute set of the power grid operation state data or other attributes, it can include power grid electrical and signal data, power grid operation and maintenance related data, etc. At this time, the single subset of the attribute set, that is, "power appeal type", is taken as the initial data processing object guided by the data link relationship, = {power appeal type}; for example, the link relationship between the power appeal type and the power grid operation risk element data corresponds to: which power appeal types mean which types of power grid risk elements will occur or have a high probability of occurring.

[0067] The link relationship of the data at this time is designed as follows: Step 1, all possible power appeal types are constructed into a unified non-repeated data group, which is mathematically represented as a data set. Step 2, there are two possible implementations: A, for any selected or subsequently added target power grid risk monitoring elements (whether for a specific power user individual or a combined power user group), a subset of all possible power appeal types is first generated by combination traversal, and then based on artificial standards or historical data fitting, from the all power appeal type subsets and all possible power appeal type combinations generated in the combination traversal mode, one to several groups of the most effective power appeal type combinations are selected as the best power appeal type combinations of the selected target power grid risk monitoring elements; at the same time, the best power appeal type combinations obtained in this way allow dynamic adjustment according to subsequent application effectiveness or other factors; B, compared with the data path in A above, the data process is adopted, but all power appeal type subsets obtained in A are further ordered, that is, each power appeal type subset in the power appeal type subset group generates n! new subsets according to the ordering of the power appeal types within the set (where n is the number of power appeal types within the specified power appeal type subset); in this way, the parameter path of the order of power appeal type occurrence is constructed on the data model, that is, the parameters associated with the order of power appeal type occurrence in a specific power grid risk event or in the power appeal data stream; among them, based on artificial standards or historical data fitting, from the all power appeal type subsets and all possible power appeal type combination modes generated in the combination traversal mode, one to several groups of the most effective power appeal type combinations are selected as the best power appeal type combinations of the selected target power grid risk monitoring elements; generally, this data step is realized by constructing a data fitting and testing system, which is based on artificial analysis and historical data or expert knowledge base for comparison and correction; this mode has an additional outstanding advantage, that is, it can very conveniently introduce existing artificial intelligence algorithms for iterative fitting optimization, which can greatly improve the efficiency and accuracy of fitting and correction compared with the original data optimization based on application feedback.Step 3: The implementation path of this step is to convert the data processes in steps 1 and 2 into data relationships and data storage methods in the data system. Specifically, in the final data model, instead of storing various optimized power demand type combinations for various power grid operation risk factor data, etc., only the full set of power demand types in the data set in step 1 and the combination parameters corresponding to the final selected optimal power demand type combination, denoted as A parameters, or combination parameters + ordered parameters, denoted as A + B parameters, are stored. At the same time, such A parameters or A + B parameters are constructed and stored in the form of instructions to optimize and simplify the data capacity of the data system. In subsequent risk early warning or other data analysis applications, the backend server directly calls the instructions corresponding to the A parameters or A + B parameters. These instructions may appear in the form of a few bytes of text and have good calling and transmission efficiency, while the restoration and display of the real power demand type combination rely on the backend server for calculation and generation, thereby avoiding the consumption of current data model calculation resources and optimizing the energy efficiency of the constructed data system in terms of calculation model consumption. Among them, each power demand type subset in the power demand type subset group generates n! new subsets according to the ordering of the power demand types within the set. On the one hand, when these ordered subsets are linked with the data points of the power grid risk event or 95598 audio data stream, their order is associated with the time order of the elements within the ordered subsets in the power grid risk event or 95598 audio data stream, and the order association is built on the time dimension. Therefore, implementation path b is a significantly higher-order and more refined data model than implementation path a. Based on the accumulation of big data and the improvement of cloud server analysis power, the data correspondence structure existing in the correspondence between the appearance order of power demand types in the power demand data stream and the risk event has strong certainty and distinguishability. Therefore, the data model under implementation path B has higher data refinement and accuracy. On the other hand, implementation path B can further introduce more variable parameters in the time association of elements within its ordered subsets. For example, in the first aspect described above, the default time dimension order association is based on the sequential order of the appearance time of power demand types. However, the data structure may not necessarily use this sequential order, but may allow any kind of front-back disorder order to be set according to data analysis or data model use effectiveness, as long as the final selected and entered power demand types have a determined order in the time dimension.

[0068] (2) Backend structured processing of power demand data

[0069] The back-end structured processing of power demand data is oriented to the construction of dynamic data space-time situation model. It is oriented to the post-data processing of power distribution network operation situation. For known power demand data groups, including the power grid operation risk events linked and associated with them that have been recorded or concerned, a data situation model framework is constructed for the global and dynamic structural characterization and algorithmic processing of power demand data groups. The construction of this data situation model framework is anchored to the application orientation of power demand processing and evolution situation. The specific data process is as follows.

[0070] The first aspect is to establish a dynamic data space for integrating power appeal representation, considering that the final data space is associated with the division and dynamic change of power appeal data in different geographical regions and different time points of the power grid, and the data space constructed is denoted as a data space-time model m (of power appeal data), and then a data set k representing power appeal is constructed as a vector in the data space-time model m, denoted as a power appeal data vector s, and the analysis and processing of the vector s are performed to analyze and process the spatial correlation variation and time dynamic evolution characteristics of the power appeal data; in general, it can be denoted as a m-k-s data architecture. In the m-k-s data architecture, the source of the power user data is generally from power user service records, social media, user surveys, etc., and in the initial framework, the user appeal recorded on the 95598 electronic work order is mainly used; the core of the construction path of the m-k-s data architecture can first combine the power appeals from the same region into a data set k, and then the data set k can be constructed as a vector s in the data space-time model m in the following way: ① first, the dimension of the data space-time model M is defined by the data set k, at this time, the number of dimensions of the data space-time model m is directly mapped to the number of dimensions of the data set k, here, more dimension numbers can be set as redundant backup as needed, so that the data space-time model m is compatible with the overall global vector representation of the data set k in terms of data capacity; ② next, the position of the power appeal data vector s in the data space needs to be specified; ②-①, here the specific definition is made through the following data relationship: the projection distance of the vector s in each dimension, that is, the distance between the end point of the vector s and the zero point of the data space-time model M center, is represented by the number of repetitions of different types of power appeals in the data set k; ②-②, in addition, other types of projection distance representation algorithms can be constructed, such as: based on the intensity data of the power appeal, the time urgency data, the time length data from the appeal processing deadline, or other data types representing different aspects of the power appeal to form multiple different variation data space models; under the above given distance algorithm based on the number of repetitions of the same appeal data type, the projection distance of the power appeal data vector s in any dimension of the data space-time model m is proportional to the number of user appeals of this type; thus the basic data space model is obtained, that is, the data space-time model m for representing power appeal.

[0071] The second aspect is, for the data space-time model, the first aspect is in space, since the data set and the vector are derived from the power demand data in a region, different regions of the distribution network correspond to different power demand data sets and different vectors corresponding thereto, so that in the framework of the data space-time model, the geographical distribution corresponding to the entire power grid constructs a vector space with a certain density of power demand data, and the vector space performs global data structure construction and data content representation on the power demand data of the entire power grid system. It should be noted that in the construction of the power demand data vector space or in its subsequent application, the division of the power demand data in different regions of the distribution network, the regions can be adjacent peripheral regions, or selected discrete distributed regions based on certain standards such as the proximity of the power consumption type, the high and low attributes of the power consumption load, the power consumption peak valley difference or other standards.

[0072] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in a certain embodiment can be referred to the related description of other embodiments.

[0073] In each embodiment, the hardware implementation of the technology can directly use existing intelligent devices, including but not limited to industrial computers, PC computers, smart phones, handheld computers, floor-standing computers, etc. The input device is preferably a screen keyboard, the data storage and calculation module uses existing memory, calculator, controller, the internal communication module uses existing communication port and protocol, and the remote communication uses existing gprs network, world wide web, etc.

[0074] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically independent, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the unit and module in the above system can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

[0075] In the embodiments of the present application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other manners. For example, the embodiments of the apparatus / terminal device described above are merely schematic, and the division of the modules or units is merely logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms. The units described as separate components can or can not be physically separate, and can or can not be physical units, i.e., can be located in one place or distributed on a plurality of network units. In actual implementation, some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0076] The units in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated units can be implemented in the form of hardware or in the form of software function units. When the integrated units are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such an understanding, the present application implements all or part of the flow of the above-mentioned embodiment methods, and can also be completed by computer programs instructing related hardware. The computer program can be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer readable medium can include appropriate contents according to the requirements of legislation and patent practice in the jurisdiction.

[0077] The above-described embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A multi-layer data processing method for distribution network operation status compatible with front-end early warning and back-end tracking, characterized by: A. For the front-end structured processing of power demand data, the construction path is as follows: through the equivalent position exchange processing of power demand data and 95598 audio data power demand types in the data model, the grid operation risk factor data link structure extracted and labeled based on the 95598 audio data power demand types is transferred to the data association structure of power demand data and grid operation status risk factors. Specifically, a data entity set is constructed in the form of a data set. The data set E initially includes several independent data entities: power demand data and grid operation risk factor data. and other subsequently extensible data entities; each data entity is directly and consistently characterized by its attribute set, that is, in terms of data structure, the data entity itself and its attributes are directly treated as equivalent; For each attribute in the attribute set, the underlying data set E based on the data model is initialized to be compatible with the widest range of data object data types, including basic data types such as integers, strings or text data, and other unstructured data; based on the data entity accommodation, the data set further establishes its multi-directional data relationship links based on the data relationship between the attribute sets of each data entity; Regarding the data structure of data relationships, the data relationship links within the data set are constructed as a core-guided multi-directional link. That is, the data link initially takes a selected data entity as the core. Based on the data relationship between the attribute sets of each data entity and in combination with pre-set or manually specified data standards for measuring the data relationship between attribute sets, the data guide of the data relationship link is used to guide the selected core data entity to link with one or more other data entities. Among them, the guidance of the data link relationship takes a subset of the attribute set as the initial data processing object, that is, the data processing relationship and its data processing process are constructed based on the selected subset. B. For the back-end structured processing of power demand data, for known power demand data groups, including the linked and associated grid operation risk events that have been recorded or paid attention to, a data situation model framework is constructed to perform global and dynamic structural representation and algorithmic processing of the power demand data groups.

2. The data processing method according to claim 1, wherein: In A, the simplest and most practical data selection is: initializing data processing objects guided by data link relationships using a single subset of attribute sets; At this time, different types of power demands are directly adopted as a single subset and used as the initialization data object guided by the data link relationship in the data process.

3. The data processing method according to claim 1, wherein: In B, the back-end structured processing of power demand data specifically includes: A dynamic data space is established to integrate and represent power demands. Considering the division and dynamic changes of the resulting data space-related power demand data across different geographic regions and time points in the power grid, the constructed data space is denoted as the data spatiotemporal model M. The data set k representing power demands is then constructed as a vector within the data spatiotemporal model M, denoted as the power demand data vector s. By analyzing and processing vector s, the spatial correlation and variation of power demand data, as well as its dynamic evolution over time, are analyzed and processed. The overall structure is an mks data architecture.

4. The data processing method according to claim 3, wherein: Regarding the construction path of the mks data architecture, first, the power demands from the same region are merged into a data set k. In the data space-time model M, the data set k is constructed as a vector s in the data space-time model M in the following way: ① First, the data set k is used to define the dimension of the data space-time model M. At this time, the types of power demands in the data set k are directly mapped to the number of dimensions of the data space-time model M. Here, more dimensions are set as redundant backup as needed, so that the data space-time model M is compatible with the overall global vector representation of the data set k in terms of data capacity; ② Next, the position of the power demand data vector s in the data space needs to be specified; ②-①, specifically defined through the following data relationship: the projection distance of the vector s in each dimension, that is, the distance between the end point of the vector s and the center zero point of the data space-time model M, is represented by the number of repetitions of different types of power demands in the data set k; ②-②, construct other types of projection distance characterization algorithms, including: projection distance characterization based on power demand intensity data, time urgency data, duration data to the demand processing deadline, or other data types that characterize different aspects of power demands, thereby forming a variety of different variant data space models; under the above-given distance algorithm based on the number of repetitions of the same demand data type, the projection distance of the power demand data vector s in any dimension of the data space-time model M is proportional to the number of user demands of this type; thus, the basic data space model is obtained, that is, the data space-time model M used to characterize power demands.

5. The data processing method according to claim 4, wherein: For the data spatiotemporal model, spatially, since the data sets and vectors are derived from the power demand data within a certain area, different areas of the distribution network will generate different power demand data sets and corresponding different vectors. In this way, under the framework of the data spatiotemporal model, a vector space of power demand data with a certain density is constructed corresponding to the geographical distribution of the entire power grid. This vector space constructs the global data structure and represents the data content of the power demand data of the entire power grid system.

6. The data processing method according to claim 5, wherein: In the construction of the power demand data vector space or its subsequent application, the power demand data is divided into different areas of the distribution network. The areas are adjacent surrounding areas, or areas selected as discrete distribution areas based on the similarity of power consumption types, high and low power load attributes, peak and valley differences in power consumption, or other criteria.

7. The data processing method according to claim 1, wherein: The data flow architecture setting of the data processing method includes: the data flow architecture includes two parts: basic support data flow and application data flow; Basic supporting data flow: Through the multi-dimensional data import port, it aggregates 95598 call real-time data, marketing business application system data, electricity consumption collection system data, online State Grid data, 95598 business support system data, and 12398 power supervision hotline data to achieve storage, integration, and pre-processing of various data types; Application data flow: For the following data application ports: power demand indicator monitoring optimization, service risk warning application optimization, construction of customer attribute library, construction of service strategy library, risk management application scenario construction, data-based automated analysis report application optimization, and application expansion and application port expansion as needed.

8. The data processing method according to claim 1, wherein: The data transmission settings of this data processing method include: A. Use interfaces to obtain structured data and service risk warning mechanism data from multiple channels, including 12398, marketing service public opinion, or other offline channels, as well as electricity consumption information collection systems. At the same time, build output channels that support the aggregation and analysis of these data scenarios and analytical statements / reports. B. In response to the shared data needs of third-party manufacturers and systems related to the power grid, the output data is processed secondary according to the data permissions of the data requester to form result data provided to the external application system corresponding to the permissions of the data requester. These result data are directly provided to the application display page or provided to the data requester through interface services.

9. The data processing method according to claim 1, wherein: The security architecture setting of this data processing method includes: taking the boundary of the power grid information area as the dominant boundary involved in application deployment, and on this basis, utilizing the existing logical strong isolation, hardware firewall, IDS / IPS boundary security protection equipment of the power grid system for the information intranet boundary; for the outside of the boundary, configuring identity authentication, access control, intrusion detection, logging and security audit security policies to achieve boundary isolation and security protection; the deployment architecture setting of this data processing method includes: application and data deployment based on provincial information areas.

Images