Intelligent power grid service demand data system with informatization deeply integrated with modern industry

Abstract

The invention discloses an intelligent power grid service demand data system with informatization deeply fused with modern industry, which performs deep datamation model construction for electric energy demand in a large-scale modern industry area, and has multiple continuous or fine discrete ductility in the time dimension of electric energy demand prediction and regulation. On the data intrinsic structure dimension, multiple characterization is emphasized on electric power energy demand surface data of a modern local power grid and regularized data of different layers in the electric power energy demand surface data, and meanwhile, self-feedback adjustability of a data system is considered. The data system provided by the invention comprehensively accords with the electric energy demand planning of a newly built modern industrial area, and has a very fine data structure.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technologies and their data processing, and in particular to a smart grid service demand data system that deeply integrates information technology with modern industries. Background Art

[0002] With the development of grid informatization, intelligence, and dataization, as well as technological progress, higher standards are being put forward for power demand forecasting in the process of planning and construction of modern industrial parks. Large-scale modern industrial parks often serve as standard local area grids in the grid planning system, and they usually have a complete overall plan, including a detailed layout of different industries in terms of space, scale, and industrial chain connection, etc., which can list and control all the factors affecting power energy demand. Based on this, higher requirements for power energy demand forecasting and analysis are also put forward for power planning entities in modern industrial parks. It is necessary to accurately grasp the changing trend of power demand, reduce the operation costs of the power grid and the industrial park through grid planning, and provide necessary digital basis for effectively and accurately optimizing the overall energy allocation.

[0003] In response to the above technical requirements, many studies have been carried out at home and abroad theoretically. The existing data models mainly rely on historical data and social factors such as economic growth for regression analysis, and then use time series models (such as ARIMA) or machine learning models (such as support vector machines, artificial neural networks, etc.) for prediction. However, in practice, there are still many deficiencies in the existing data models. For example, the breadth and depth of data model construction are insufficient. Currently, a multi-dimensional and deep data model construction is generally required, but the existing technical models have relatively weak expandability and representativeness, and it is difficult to reveal the complex laws of power demand; especially the ability to represent local area grid data is insufficient, and it is often unable to accurately reflect the specific needs of a particular local area grid, especially the power grid in a newly built modern large-scale industrial park. Most of the data structures belong to theoretical-level generalization models, and it is difficult to achieve hierarchical and internal regular representation of the power energy demand of local grid units. Therefore, it can be seen that developing a smart grid service demand data system that deeply integrates information technology with modern industries is a technical issue that urgently needs to be solved at present.

[0004] At the same time, based on the smart grid planning of the former Qianhai Cooperation Zone in Shenzhen, the planning of key areas such as the Airport New City, and the mid- and long-term development research of electric power in the dual districts of Shenzhen, etc., combined with the energy power demand of the Qianhai Cooperation Zone, grid development plans are formulated for the strategic positioning and industrial characteristics of each area respectively, the substation layout plan is clarified, the corridor plan for important new construction and transformation power transmission channels is implemented, and the connection between power planning and urban development planning is done well. All these put forward new requirements for the research on new regional grid entities and their power demand forecasting in modern industrial parks. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the various deficiencies of the prior art and provide an intelligent power grid service demand data system for the in-depth integration of information technology and modern industries based on a brand-new data model. This data system fully meets the power energy demand planning of newly built modern industrial areas and has a very fine data structure.

[0006] To solve the above technical problems, the technical solutions adopted by the present invention are as follows.

[0007] The intelligent power grid service demand data system for the in-depth integration of information technology and modern industries constructs a deep data model for the power energy demand in large-scale modern industrial areas. It has multiple continuous or fine discrete extensibilities in the time dimension of power energy demand prediction and regulation, and focuses on multiple representations of the surface data of power energy demand and the regular data at different levels inside the modern local power grid in the data intrinsic structure dimension, while taking into account the self-feedback adjustability of the data system.

[0008] As a preferred technical solution of the present invention, the physical object of this data system is the power grid entity that constitutes the local power grid unit in terms of spatial area division and power grid planning division, especially the newly built modern large-scale industrial area.

[0009] As a preferred technical solution of the present invention, the basic data structure of this data system is expanded according to two data dimensions, that is, according to the energy demand factors that can be discretely listed within the power grid entity, and the discrete duration factor or its fitted continuous duration factor corresponding to the intelligent pre-control of energy demand in the industrial area, to perform orthogonal expansion of two-dimensional data. Thus, the data labels of the power grid entity corresponding to the data system are expanded into a two-dimensional data array.

[0010] As a preferred technical solution of the present invention, specifically, for the dimension of power demand factors that can be discretely listed within the power grid entity, a set of demand factor data sequences X = {x1, x2,..., xn,...} is constructed, where n corresponds to all energy demand factors involved in the power grid planning of the modern industrial area power grid entity. Obviously, n should be extensible and can be increased or decreased according to the actual needs of the power grid entity. Further, considering the duration factor dimension corresponding to the intelligent prediction and regulation of power demand in the modern industrial area, the power energy demand parameter ε corresponding to any data element xk ∈ X and the duration τ is defined according to the data sequence X. xτ 。

[0011] As a preferred technical solution of the present invention, according to the power energy demand parameter ε xτ, a two-dimensional data model XT is constructed through data expansion. In the power grid planning model, generally, multiple factors related to power energy demand are considered in the early stage. Then, the first expansion paradigm of XT is as follows: First, according to xk ∈ X selected from the sequence of energy demand factors X that can be listed within the power grid entity, for each duration τ in the dimension of the duration factor for power energy demand prediction, the power energy demand parameter ε xτ is sequentially expanded to obtain a data vector calibrated by the numerical serial number of τ under xk. This vector can be artificially defined as a column vector, and its dimension value is equal to the number m of the specified prediction durations for power demand prediction; it can be seen that m has expandability on the one hand and can be increased or decreased according to the actual needs of power grid entity planning and construction; at the same time, it has the self-derivation property within the set because the units of each component in the column vector are uniform and all are time units. After a given τ value, for different m numerical individuals, the power energy demand value after a specific duration can be obtained by linear averaging to get the power energy demand prediction value after the combined duration, and this prediction value has a real reference value. Therefore, it can expand the data set based on addition and subtraction linear operations; Second, according to the same data process as above, xk ∈ X is traversed in X = {x1, x2,..., xn,...}, and n column vectors extending in a neat and regular duration order are correspondingly obtained; in this way, an m×n two-dimensional data array is formed, that is, the two-dimensional data model XT spanned by the orthogonal expansion of the power energy demand parameter ε xτ along the sequence of energy demand factors that can be listed within the power grid entity and the discrete duration factors of power energy demand prediction in an orderly manner;

[0012] As a preferred technical solution of the present invention, a two-dimensional data model XT′ is constructed through data expansion. The second expansion paradigm of XT′ is as follows: First, a uniform duration sequence T′ with sufficient fineness is generated. The so-called sufficient fineness means that the interval between data units in the sequence T′ is set to be no greater than the minimum time interval that may be involved in power energy demand prediction. Let the vector corresponding to the data sequence T′ have m′ components, then m′ is a sufficiently large value compared to the current power grid entity's energy demand prediction; for any component of the uniform T′ vector, considering the demand factor data sequence X = {x1, x2,..., xn,...}, the power energy demand parameter ε xτ is expanded according to the many power demand factors involved in power grid entity planning. For each selected component of T′, an n′-dimensional vector is generated; this vector can be artificially defined as a row vector, and its dimension value n′ is the number of power energy demand factors included in power demand prediction; further, according to the same data process, each component of the uniform T′ vector is sequentially traversed, and m′ row vectors extending in different power energy demand factor orders are correspondingly obtained; in this way, an m′×n′ two-dimensional data array is formed, that is, the power energy demand parameter ε xτThe two-dimensional data model XT' spanned by the ordered orthogonal expansion.

[0013] As a preferred technical solution of the present invention, compared with the data model XT, the data model XT' has m << m' and n ≤ n'; the data model XT is constructed according to pre-determined factors, has a smaller data scale, and performs global filling when filling real data into the data model in the later stage. After the data filling is completed, self-operational expansion of the data model is allowed based on the expandability of the m data and the self-derivative attributes within the m set; the data model XT' is constructed with the maximum data scale, and only intermittent filling can be performed when filling real data in the later stage. After the filling is completed, as long as the blank data bits have row and column standardization after data format inspection, it can be directly applied, or based on the uniformity of the components within the T' vector, global fitting filling of the blank data bits is performed by linear averaging operation according to the filled real data; by artificially distinguishing and defining the rows and columns of the vector, the equivalence of the data model XT and the data model XT' in terms of data structure connotation can be achieved, or the transposed data model XT T And the equivalence of the data model XT' in terms of data structure connotation.

[0014] As a preferred technical solution of the present invention, in terms of data format, first, a data label is assigned to the data system according to its corresponding power grid entity, and then this data label is used as the initial format node for data expansion.

[0015] As a preferred technical solution of the present invention, based on the specific prediction and analysis mode of industrialized power energy demand, the data system allows different interactive side data modules to be loaded according to the basic data structure and considering specific data analysis objectives.

[0016] As a preferred technical solution of the present invention, the development orientation of the interactive side data module includes an outreach orientation and an in-depth orientation; the outreach orientation develops the data module based on the power energy demand analysis program proposed externally; the in-depth orientation conducts data mining on the basic data structure after global filling to reveal the trend data characteristics of industrialized power energy demand and / or the regular data characteristics at different levels deeply contained in the basic data structure.

[0017] As a preferred technical solution of the present invention, for the two-dimensional data array, after being artificially marked, itself and any data element inside it include the data label corresponding to its power grid entity, which brings convenience to subsequent data processing and data planning and data interaction of different power grid entities; the power grid entity data label is artificially specified when constructing the basic data structure of the data system, and other labels are used after adopting digital or letter labels.

[0018] The beneficial effects of adopting the above technical solutions are as follows: The data system developed by the present invention fully conforms to the power planning of the newly built modern industrial park. Its basic data structure has been comprehensively expanded and unfolded. Compared with the traditional data prediction model's dependence on a single indicator and the non-adjustability of errors, this new data model can more comprehensively and meticulously grasp the detailed information of power demand data, not only representing the surface data of power demand in different periods. At the same time, this data system has a high degree of data redundancy and is compatible with mining and prompting the development trends from different angles of power demand and the internal data laws at different levels. In addition, the data system of the present invention also has good extensibility and contains the self-feedback adjustability of the data system, which can more effectively optimize the power planning of regional power grid entities such as modern industrial parks. Detailed implementation manners

[0019] The following embodiments illustrate the present invention in detail. In the description of the following embodiments, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should understand that the present application can also be implemented in other embodiments without these specific details. In other cases, the detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application. It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations. It should also be understood that the term "and / or" used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations. As used in the specification and appended claims of the present application, the term "if" can be interpreted as "when...", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" according to the context.

[0020] In addition, in the description of the specification and the appended claims of this application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance. The reference to "one embodiment" or "some embodiments" etc. described in the specification of this application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of this application. Thus, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprise", "include", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0021] Embodiment 1

[0022] The basic data structure of the data system of the present invention is to assign a data label to the local power grid entity corresponding to the newly built modern industrial park, expand the data according to two data dimensions, and the data labels of the power grid entities corresponding to the data system form a two-dimensional data array; in this way, the data system itself and any data element inside it include the data label corresponding to its power grid entity, which brings convenience to subsequent data processing and data planning and data interaction of different power grid entities; among them, the data label of the power grid entity is artificially specified when constructing the basic data structure of the data system, and other labels are used after adopting digital or letter labels.

[0023] Embodiment 2

[0024] The data structure of the data system has sufficient expandability, providing the most generous basis for the prediction of surface power energy demand and subsequent various new power grid planning and data analysis. The expansion method of the data structure is as follows. For the dimension of power demand factors that can be discretely listed within the power grid entity, a set of demand factor data sequences X = {x1, x2,..., xn,...} is constructed, where n corresponds to all energy demand factors involved in the power grid planning of the modern industrial park power grid entity. Obviously, n should be extensible and can be increased or decreased according to the actual needs of the power grid entity; further, considering the time factor dimension corresponding to the intelligent prediction and regulation of power demand within the modern industrial park, then according to the data sequence X, the power energy demand parameter ε corresponding to any data element xk ∈ X and the time τ is defined. xτ。 Here ε xτBased on this, a two-dimensional data model XT is constructed through data expansion. In the power grid planning model, generally, multiple factors related to power energy demand are considered in the early stage. Then, the first expansion paradigm of XT is as follows: First, for xk ∈ X selected from the sequence of energy demand factors X that can be listed within the power grid entity, for each time period τ in the time factor dimension of the energy demand prediction, the power energy demand parameter ε xτ is sequentially expanded to obtain a data vector calibrated by the numerical serial number of τ under xk. This vector can be artificially defined as a column vector, and its dimension value is equal to the number m of the specified prediction time periods for power demand prediction. It can be seen that m has scalability on the one hand and can be increased or decreased according to the actual needs of power grid entity planning and construction. At the same time, it has the self-derivative property within the set because the units of each component in the column vector are uniform and all are time units. Given the value of τ, for different individual values of m, the power energy demand value after a specific time period can be obtained through linear averaging to get the power energy demand prediction value after the combined time period, and this prediction value has real reference value. Therefore, it can expand the data set based on addition and subtraction linear operations. Second, according to the same data process as above, xk ∈ X is traversed in X = {x1, x2,..., xn,...}, and n column vectors extending in a neat and regular time order are correspondingly obtained. In this way, an m×n two-dimensional data array is formed, that is, the two-dimensional data model XT spanned by the orthogonal expansion of the power energy demand parameter ε xτ in an orderly manner along the listable energy demand factors within the power grid entity and the discrete time factors of power energy demand prediction. Based on the specific prediction and analysis mode of industrial power energy demand, different interactive side data modules are allowed to be loaded according to the basic data structure and considering the specific data analysis objectives. The development orientation of the interactive side data module includes the outreach orientation and the introversion orientation. The outreach orientation develops data modules based on the power energy demand analysis program proposed externally. The introversion orientation conducts data mining on the basic data structure filled globally to display the trend data characteristics of industrial power energy demand and / or the regular data characteristics at different levels deeply contained in the basic data structure.

[0025] Example 3

[0026] Based on this ε xτ the second expansion paradigm of XT is as follows: First, a uniform time sequence T with sufficient fineness is generated. The so-called sufficient fineness means that the interval between data units in the sequence T is set to be no greater than the minimum time interval that may be involved in power energy demand prediction. Let the vector corresponding to the data sequence T have m' components, then m' is a sufficiently large value compared to the current power grid entity's energy demand prediction. For any component of the uniform T vector, considering the demand factor data sequence X = {x1, x2,..., xn,...}, the power energy demand parameter εxτ It is carried out in accordance with many power demand factors involved in the power grid entity planning. For each selected T component, an n'-dimensional vector is generated; this vector can be artificially defined as a row vector, and the dimension value n' is the number of power energy demand factors included in the power demand prediction. Further, each component of the average T vector is traversed in turn according to the same data process, and m' row vectors extending in the order of different power energy demand factors are obtained correspondingly inside; in this way, a two-dimensional data array of m'×n' is formed, that is, the two-dimensional data model XT spanned by the ordered orthogonal expansion of the power energy demand parameter ε xτ For the sake of easy distinction, this new model can be denoted as XT'.

[0027] Example 4

[0028] It can be seen that compared with the data model XT, the data model XT' has m << m' and n ≤ n'; the data model XT is constructed according to the pre-determined factors, has a smaller data scale, and performs global filling when filling real data into the data model in the later stage. After the data filling is completed, the self-operational expansion of the data model is allowed based on the expandability of the m data and the self-derivative attributes inside the m set; the data model XT' is constructed with the maximum capacity data scale, and only discontinuous filling can be performed when filling real data in the later stage. After the filling is completed, as long as the blank data bits have row and column normality after the data format check, it can be directly applied, or based on the uniformity of the components in the T' vector, global fitting filling of the blank data bits is performed by performing linear average operation according to the filled real data; by artificially distinguishing and defining the rows and columns of the vector, the equivalence of the data model XT and the data model XT' in the data structure connotation can be realized, or the equivalence of the transposed data model XT T and the data model XT' in the data structure connotation can be realized.

[0029] Example 5

[0030] The data system of the present invention is based on the specific prediction and analysis mode of industrial power energy demand, and allows different interactive side data modules to be loaded according to its basic data structure and considering the specific data analysis objectives. The development orientations of the interactive side data modules include the outreach orientation and the introversion orientation; the outreach orientation develops data modules based on the power energy demand analysis program proposed externally; the introversion orientation conducts data mining on the basic data structure after global filling to show the trend data characteristics and / or regular data characteristics at different levels of the industrial power energy demand deeply contained in the basic data structure.

[0031] Among them, the most basic interactive side data module is constructed and derived based on the discrete duration sequence expanded in the time dimension, including the discrete duration vector […], and the generated variant unit matrix (where the non - diagonal part is 0), and a single - rank matrix {∶∶} for calculating the row / column sums of XT, whose rows or columns are repeated by the respective components of the discrete - time vector […], and so on.

[0032] For the data of any stage, it is also possible to consider subdividing the discrete - data sequence stored in the matrix to improve the accuracy of the prediction result. Consider selecting a data k, and the period length t corresponding to k is further divided into i equal - length time periods; the subdivision of the duration t makes the parameter corresponding to k become a set of parameters containing i parameters, where each parameter k i and its equivalent corresponding time period Δt i has a multiplicative relationship.

[0033] Furthermore, apply the above - mentioned data - processing method for k to all the data in the discrete - data sequence, and further expand the original two - dimensional matrix (considering the three elements of influencing factors, original duration, and subdivided duration, it can be expanded along three dimensions respectively); the new data structure obtained in this way, combined with the corresponding matrix of subdivided period lengths, can more precisely describe the power - demand prediction situation brought by multiple influencing factors in the industrial area, thereby further improving the accuracy of the prediction result. Moreover, the subdivided time length and other related data and calculations (such as when reconstructing sequences, constructing a new three - order extended data structure, etc.) in the power - prediction data - processing process, all of these can be customized and optimized according to actual needs, with high flexibility and scalability.

[0034] In addition, considering the development and maturity of artificial - intelligence technology nowadays, the above - constructed data structure can also be directly adapted to be further analyzed by machine - learning methods (such as introducing existing mature machine - learning algorithms like clustering analysis, classification, and regression, etc.) to achieve applications such as demand - pattern recognition, trend analysis, and prediction.

[0035] It can be seen that the new data structure we constructed, on the one hand, starts from the characteristics of the most basic power data, and at the same time considers the data - analysis target requirements at the end (as the foothold), combines these data considerations at the beginning and the end for the design and construction of the data structure, and it is expected to break through the limitations of traditional power - demand prediction methods and provide accurate data support for the power - supply and - demand planning and grid - optimized operation in modern industrial areas under the influence of complex and diverse factors.

[0036] In the above - mentioned embodiments, the descriptions of each embodiment have their own focuses. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0037] As can be seen from the above embodiments, the present invention constructs a deep data model for the power energy demand in a large-scale modern industrial area. The physical object of this data system is a newly built modern large-scale industrial area that constitutes a local power grid unit in terms of spatial area division and power grid planning division. For such local power grid entities, the data system of the present invention has multiple continuous or fine discrete extensibilities in the time dimension of power energy demand prediction and regulation, and focuses on multiple representations of the surface data of the power energy demand of the modern local power grid and the regularized data at different internal levels in the dimension of the data intrinsic structure. At the same time, the self-feedback adjustability of the data system is taken into account.

[0038] In various embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to 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 into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments and will not be elaborated herein. In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms. The unit described as a separated component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In each embodiment of the present invention, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented.

[0039] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A smart grid service demand data system that deeply integrates information technology with modern industries, characterized by: A deep data-based model is constructed for the power energy demand in large-scale modern industrial areas. It has multiple continuous or fine discrete extensibility in the time dimension of power energy demand prediction and regulation. In terms of the data intrinsic structure dimension, it focuses on multiple characterizations of the power energy demand surface data of the modern local power grid and the regularized data at different levels within it, while taking into account the self-feedback adjustability of the data system.

2. According to claim 1, the smart grid service demand data system with deep information integration into modern industries is characterized by: The physical objects of this data system are the grid entities that constitute local grid units in terms of spatial area division and grid planning division, especially newly built modern large-scale industrial zones.

3. According to claim 2, the smart grid service demand data system with deep information integration into modern industries is characterized by: The basic data structure of the data system is expanded according to two data dimensions, namely, the orthogonal expansion of the two-dimensional data is carried out according to the energy demand factors that can be discretely listed within the power grid entity, and the discrete time factors or their fitted continuous time factors corresponding to the intelligent pre-control of energy demand in the industrial area, thereby expanding the data system into a two-dimensional data array.

4. The smart grid service demand data system with deep information integration into modern industries according to claim 3 is characterized by: Specifically, for the discrete power demand factor dimensions in the power grid entity, a set of demand factor data sequences X = {x1, x2, ..., xn, ...} is constructed, where n corresponds to all energy demand factors involved in the power grid planning of the modern industrial zone power grid entity. Obviously, n should be scalable and increase or decrease according to the actual needs of the power grid entity; further, considering the duration factor dimension corresponding to the intelligent prediction and regulation of power demand in the modern industrial zone power grid, the power energy demand parameter ε corresponding to any data element xk∈X and the duration τ is defined according to the data sequence X xτ .

5. According to claim 4, the smart grid service demand data system with deep information integration into modern industries is characterized by: According to the power energy demand parameter ε xτ , a two-dimensional data model XT is constructed by data expansion. In the power grid planning model, multiple factors related to power energy demand are generally considered in advance. The first expansion paradigm of XT is: First, according to the selected xk∈X in the energy demand factor sequence X that can be listed in the power grid entity, for each duration τ of the energy demand forecast under the duration factor dimension, the power energy demand parameter ε xτ The data vector marked with τ numerical sequence under xk is obtained by sequential expansion. This vector can be artificially defined as a column vector, and its dimension value is equal to the number m of forecast durations specified by the power demand forecast. It can be seen that m is scalable on the one hand, and can be increased or decreased according to the actual needs of power grid entity planning and construction; at the same time, it has the self-derivative property within the set, because the units of each component in the column vector are uniform and are all time units, and after the τ value is given, for different m numerical individuals, the corresponding power energy demand value after a specific duration can be obtained by linear averaging to obtain the power energy demand forecast value after the combined duration, and this forecast value has real reference value, so it can expand the data set based on addition and subtraction linear operations; secondly, according to the same data process as above, xk∈X is traversed in X={x1,x2,...,xn,...}, corresponding to n column vectors extending in a neat and standardized duration order; thus, an m×n two-dimensional data array is formed, that is, the power energy demand parameter ε xτ The two-dimensional data model XT is formed by orthogonally expanding the energy demand factors and discrete time factors of power energy demand forecast that can be listed in the power grid entity in an orderly manner.

6. The smart grid service demand data system with deep information integration into modern industries according to claim 4 is characterized by: The two-dimensional data model XT′ is constructed by data expansion. The second expansion paradigm of XT′ is as follows: first, a uniform time sequence T′ with sufficient granularity is generated. The so-called sufficient granularity means that the interval between data units in the sequence T′ is set to be no greater than the minimum time interval that may be involved in the power energy demand forecast. Assuming that the vector corresponding to the data sequence T′ has m′ components, m′ is a sufficiently large value compared to the current energy demand forecast of the power grid entity; for any component of the uniform T′ vector, considering the demand factor data sequence X={x1,x2,...,xn,...}, the power energy demand parameter ε xτ According to the many power demand factors involved in the physical planning of the power grid, an n′-dimensional vector is generated for each selected T′ component; this vector can be artificially defined as a row vector, and its dimension value n′ is the number of power energy demand factors included in the power demand forecast; further, according to the same data process, each component of the uniform T′ vector is traversed in turn, and m′ row vectors extending in the order of different power energy demand factors are obtained; thus, an m′×n′ two-dimensional data array is formed, which is composed of the power energy demand parameter ε xτ The two-dimensional data model XT′ formed by ordered orthogonal expansion.

7. The smart grid service demand data system with deep information integration into modern industries according to claim 3 is characterized by: In terms of data format, the data system is first assigned a data label according to its corresponding power grid entity, and then the data label is used as the initial format node for data expansion.

8. The smart grid service demand data system with deep information integration into modern industries according to claim 3 is characterized by: The data system is based on a specific prediction and analysis model for industrialized electric power energy demand, allowing different interactive data modules to be loaded according to the basic data structure and taking into account specific data analysis objectives.

9. The smart grid service demand data system with deep information integration into modern industries according to claim 8 is characterized by: The development orientation of the interactive data module includes outward orientation and inward orientation; the outward orientation develops the data module based on the electric power energy demand analysis program proposed externally; the inward orientation performs data mining on the basic data structure after global filling to show the industrialized electric power energy demand trend data characteristics and / or regularized data characteristics at different levels deeply contained in the basic data structure.

10. The smart grid service demand data system with deep information integration into modern industries according to claim 3 is characterized by: For the two-dimensional data array, after being manually marked, it and any data element inside it contain the data label corresponding to its power grid entity, thereby facilitating subsequent data processing and data planning and data interaction of different power grid entities; The grid entity data labels are manually assigned when constructing the basic data structure of the data system, using numbers or letters followed by other labels.