Data analysis method and system for power pollution monitoring

Abstract

The invention provides a data analysis method for power pollution monitoring, and the method comprises the following steps: obtaining historical power consumption information, and obtaining historical power pollution data according to the historical power consumption information; constructing an electric power pollution monitoring model, and training the electric power pollution monitoring model according to the historical electric power pollution data; collecting current power consumption information, and obtaining current power pollution data according to the current power consumption information; calculating an electric power pollution eigennumber according to the current electric power pollution data; transmitting the electric power pollution eigennumber to the trained electric power pollution monitoring model to obtain a relative pollution degree; and analyzing the current power pollution data through the relative pollution degree. The electric power pollution data can be quickly processed, so that an electric power company is helped to effectively manage the electric power pollution, and the harm of the electric power pollution to the environment and human beings is reduced.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a data analysis method for power pollution monitoring and a data analysis system for power pollution monitoring. Background Art

[0002] In traditional concepts, people generally think of pollution as industrial pollution, including water pollution, air pollution, etc., while power pollution is not common. However, in real life, power pollution has been around the public all the time. Common symptoms include dizziness and nausea for operators engaged in high-voltage live work after working for a long time, or people in buildings under high-voltage wires often have such symptoms.

[0003] Data analysis of power pollution is a very important technology in the power system, involving the collection, processing, analysis and application of power data. As the power system develops and expands, the data of power pollution also expands. Due to the rapid growth and complexity of big data, traditional data processing technology can no longer process power big data, which causes power pollution to spread, causing serious harm to the surrounding environment and human health. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a data analysis method and system for power pollution monitoring, which can quickly process power pollution data, thereby helping power companies to manage power pollution more effectively, thereby reducing the harm of power pollution to the environment and humans.

[0005] The technical solution adopted by the present invention is as follows:

[0006] A data analysis method for power pollution monitoring comprises the following steps: acquiring historical power consumption information, and obtaining historical power pollution data according to the historical power consumption information; constructing a power pollution monitoring model, and training the power pollution monitoring model according to the historical power pollution data; collecting current power consumption information, and obtaining current power pollution data according to the current power consumption information; calculating power pollution eigenvalues ​​according to the current power pollution data; transmitting the power pollution eigenvalues ​​to the trained power pollution monitoring model to obtain relative pollution degree; and analyzing the current power pollution data according to the relative pollution degree.

[0007] In one embodiment of the present invention, the training of the power pollution monitoring model according to the historical power pollution data specifically includes: recording the historical power pollution data as the starting point research value, and filtering out the target research value from the starting point research value to record it as the target tree sub-endpoint; machine selecting the target intrinsic, and filtering out the eigenvalues ​​corresponding to the target intrinsic in the target tree sub-endpoint; performing two-way segmentation on the target tree sub-endpoint by the eigenvalue to obtain the leaf endpoint of the target tree sub-endpoint, wherein if the set target is achieved, the target tree is obtained; when the number of target numbers reaches the set target, an isolated group is formed, and a trained power pollution monitoring model is obtained.

[0008] In one embodiment of the present invention, the power pollution eigenvalue is calculated according to the current power pollution data, specifically comprising: obtaining an eigengroup of a set eigenpopulation mapping through the current power pollution data; and obtaining the power pollution eigenvalue by extracting an eigenset from the eigengroup of the set eigenpopulation mapping.

[0009] In one embodiment of the present invention, the transmitting the power pollution eigennumber to the trained power pollution monitoring model to obtain the relative pollution degree specifically includes: visiting the trees in the isolated group one by one through the power pollution eigennumber; obtaining the access distance of the power pollution eigennumber, wherein the access distance is the total length of the trees passed by the power pollution eigennumber; calculating the uniform access distance of the power pollution eigennumber in the isolated group through the access distance, and calculating the relative pollution degree mapped by the power pollution eigennumber according to the uniform access distance.

[0010] In one embodiment of the present invention, the collecting of current electricity consumption information and obtaining current electricity pollution data based on the current electricity consumption information specifically includes: collecting the current electricity consumption information and obtaining the optimized electricity consumption information through a preferred method; and classifying the optimized electricity consumption information through a K-means++ algorithm to obtain the current electricity pollution data.

[0011] A data analysis system for power pollution monitoring, comprising: a first acquisition module, the first acquisition module is used to acquire historical power consumption information and obtain historical power pollution data based on the historical power consumption information; a model construction module, the model construction module is used to construct a power pollution monitoring model and train the power pollution monitoring model based on the historical power pollution data; an acquisition module, the acquisition module is used to acquire current power consumption information and obtain current power pollution data based on the current power consumption information; a calculation module, the calculation module is used to calculate power pollution eigenvalues ​​based on the current power pollution data; a second acquisition module, the second acquisition module is used to transmit the power pollution eigenvalues ​​to the trained power pollution monitoring model to obtain relative pollution degree; and an analysis module, the analysis module is used to analyze the current power pollution data through the relative pollution degree.

[0012] In one embodiment of the present invention, the model building module is also used to: record the historical power pollution data as the starting point research value, and filter out the target research value from the starting point research value to record it as the target tree sub-endpoint; machine select the target intrinsic, and filter out the eigenvalue corresponding to the target intrinsic in the target tree sub-endpoint; perform two-way segmentation on the target tree sub-endpoint through the eigenvalue to obtain the leaf endpoint of the target tree sub-endpoint, wherein, if the set target is achieved, the target tree is obtained; when the number of target numbers reaches the set target, an isolated group is formed, and a trained power pollution monitoring model is obtained.

[0013] In one embodiment of the present invention, the calculation module is further used to: obtain the eigengroup of the set eigenpopulation mapping through the current power pollution data; and obtain the power pollution eigennumber by extracting the eigengroup of the set eigenpopulation mapping by selecting an eigenset.

[0014] In one embodiment of the present invention, the second acquisition module is further used to: visit the trees in the isolated group one by one through the power pollution eigennumber; obtain the access distance of the power pollution eigennumber, wherein the access distance is the total length of the trees passed by the power pollution eigennumber; calculate the uniform access distance of the power pollution eigennumber in the isolated group through the access distance, and calculate the relative pollution degree mapped by the power pollution eigennumber based on the uniform access distance.

[0015] In one embodiment of the present invention, the acquisition module is also used to: collect the current electricity consumption information, obtain the optimized electricity consumption information through a preferred method; classify the optimized electricity consumption information through a K-means++ algorithm to obtain the current power pollution data.

[0016] Beneficial effects of the present invention:

[0017] The present invention obtains historical power pollution data by acquiring historical power consumption information, constructs a power pollution monitoring model, and trains the power pollution monitoring model according to the historical power pollution data, then collects current power consumption information to obtain current power pollution data, calculates power pollution eigenvalues ​​according to the current power pollution data, and transmits the power pollution eigenvalues ​​to the trained power pollution monitoring model to obtain relative pollution degree, and analyzes the current power pollution data through the relative pollution degree, thereby being able to quickly process the power pollution data, thereby helping power companies to manage power pollution more effectively, and further reducing the harm of power pollution to the environment and humans. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flow chart of a data analysis method for power pollution monitoring according to an embodiment of the present invention;

[0019] Figure 2 Schematic diagram of a data analysis system for power pollution monitoring according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Figure 1 The present invention is a flowchart of a data analysis method for power pollution monitoring according to an embodiment of the present invention.

[0022] like Figure 1 As shown, the data analysis method for power pollution monitoring according to the embodiment of the present invention comprises the following steps:

[0023] S1, obtaining historical electricity consumption information, and obtaining historical power pollution data based on the historical electricity consumption information.

[0024] In one embodiment of the present invention, the historical electricity usage information may include normal electricity usage information and abnormal electricity usage information in a fixed area, wherein the abnormal electricity usage information may include power pollution data.

[0025] S2, construct a power pollution monitoring model and train the power pollution monitoring model based on historical power pollution data.

[0026] In one embodiment of the present invention, a power pollution monitoring model is trained based on historical power pollution data, which may specifically include: recording the historical power pollution data as the starting point research value, and filtering out the target research value from the starting point research value to record it as the target tree sub-endpoint; machine-selecting the target eigenvalue, and filtering out the eigenvalue number corresponding to the target eigenvalue in the target tree sub-endpoint; performing two-way segmentation on the target tree sub-endpoint by the eigenvalue number to obtain the leaf end point of the target tree sub-endpoint, wherein if the set target is achieved, the target tree is obtained; when the number of target numbers reaches the set target, an isolated group is formed, and a trained power pollution monitoring model is obtained.

[0027] Specifically, historical power information can be obtained from the power grid system, wherein the historical power information may include normal power information and historical power pollution data, and the historical power pollution data may be recorded as the starting point research value, and the target research value is selected from the starting point research value to be recorded as the target tree sub-endpoint, and if the sub-endpoint of the target tree is the starting point, the current starting point may be used as the source point. Among them, the target research value may be a part of the research value randomly selected from the starting point research value to be used as the target research value.

[0028] Furthermore, the target intrinsics can be obtained based on the power pollution intrinsics, and the eigenvalues ​​corresponding to the target can be screened in the target tree sub-endpoints. For example, the power pollution intrinsics can include voltage fluctuations, transient currents, three-phase imbalances, eddy currents and other intrinsics.

[0029] Furthermore, the eigenvalue can be used to store the research value of the target tree sub-endpoint whose number of eigenvalue mapping is greater than the eigenvalue in one sub-endpoint, and the research value less than the eigenvalue in another sub-endpoint, and these two sub-endpoints can be recorded as the target tree sub-endpoints. If the set target is completed, the target tree can be obtained, wherein the set target may include a certain height of the target tree and the target tree sub-endpoint cannot be further divided, and the target tree sub-endpoint cannot be further divided may include the target tree sub-endpoint only contains a unique research value and all the research values ​​in the target tree sub-endpoint are the same.

[0030] Furthermore, after obtaining the target trees, it can be determined whether the number of target trees exceeds the set number. If the number of target trees does not exceed the set number, the target trees can continue to be generated through the above steps; if the number of target trees exceeds the set number, all target trees can be clustered into isolated groups, thereby obtaining a trained power pollution monitoring model.

[0031] S3, collecting current electricity consumption information, and obtaining current power pollution data based on the current electricity consumption information.

[0032] Specifically, the electricity usage information can be optimized by optimizing the T-SNE algorithm, and a model can be established for the neighboring points of all the information in the electricity usage information, and the distribution of the model in high dimensions can be a Gaussian distribution, and the distribution in low dimensions can be a t distribution. Among them, the neighboring points of the electricity usage information can be a cluster of points with relatively close distances between the electricity usage information.

[0033] Furthermore, the optimized power information can be grouped using a classification algorithm, that is, each information value in the power information can be grouped into the same group, so that the information in the group is similar or close, and the information in different groups has greater differences.

[0034] S4, calculating the power pollution eigenvalue according to the current power pollution data.

[0035] In one embodiment of the present invention, calculating the power pollution eigenvalue according to the current power pollution data may specifically include: obtaining an eigengroup for setting an eigenpopulation mapping through the current power pollution data; and obtaining the power pollution eigenvalue by extracting an eigengroup by selecting an eigenset for setting an eigenpopulation mapping.

[0036] Specifically, the eigenstructure can be performed through the current power pollution data to obtain the eigengroup mapped by the set eigenpopulation, and all the set eigenpopulations map their own eigengroups accordingly, and the information of the eigengroups mapped by all the set eigenpopulations can be obtained through the current power pollution data.

[0037] Furthermore, subgroups can be screened in the eigengroup of the set eigenpopulation mapping and input into the clustering algorithm as eigensubgroups. The eigensubgroups are evaluated by the evaluation function in the clustering algorithm. When the value of the evaluation function exceeds a preset threshold, the power pollution eigenvalues ​​can be obtained, and the power pollution eigennumbers of the power pollution eigenmap can be obtained from the current power pollution data.

[0038] Among them, the A* algorithm can be used to extract the eigengroup of the set eigenpopulation mapping into the eigensubgroup, and the value of the evaluation function of the eigensubgroup mapping can be calculated. When the value is the same as the set standard, the eigensubgroup can be obtained, and the target eigensubgroup can be recorded as the power pollution eigen.

[0039] Specifically, the target eigengroup can be regarded as an empty group, and the eigengroups mapped to the set eigengroup population can be screened out to the eigengroup to obtain the first eigengroup. Then, the first eigengroup can be statistically analyzed by square root statistics to obtain the first statistical value. Secondly, the eigengroups mapped to the set eigengroup can be further screened out to the eigengroup to obtain the secondary eigengroup, and the secondary eigengroup can be statistically analyzed by square root statistics to obtain the secondary statistical value. Finally, the size of the first statistical value and the secondary statistical value can be determined. If the first statistical value is greater than the secondary statistical value, the first eigengroup can be recorded as the target eigengroup, otherwise, the secondary eigengroup can be recorded as the target eigengroup.

[0040] S5, transmitting the power pollution eigenvalues ​​to the trained power pollution monitoring model to obtain the relative pollution degree.

[0041] In one embodiment of the present invention, the power pollution eigennumber is transmitted to the trained power pollution monitoring model to obtain the relative pollution degree, which may specifically include: visiting the trees in the isolated group one by one through the power pollution eigennumber; obtaining the access distance of the power pollution eigennumber, wherein the access distance is the total length of the tree passed by the power pollution eigennumber; calculating the uniform access distance of the power pollution eigennumber in the isolated group through the access distance, and calculating the relative pollution degree mapped by the power pollution eigennumber according to the uniform access distance.

[0042] Specifically, first, the power pollution eigenvalue can be transmitted to all targets in the isolated group, and the branches corresponding to each endpoint of the target tree are visited one by one to obtain the access distance of the power pollution eigenvalue, and the uniform access distance is calculated by the access distance, wherein the uniform access distance can be calculated using the research value and Euler's formula. The calculation formula of the uniform access distance of the target tree is as follows:

[0043] D(x)=2C(n-1)-{2(n-1) / n}

[0044] Where D is the uniform access distance of the target tree, x is the research value, C(n-1)=ln(n-1)+ξ, and ξ is the Euler constant.

[0045] Furthermore, the average access distance experienced by the power pollution eigenvalue in the isolated group can be obtained according to the average access distance of the target tree, that is, the sum of the average access distances of all target trees is divided by the number of target trees.

[0046] Furthermore, the relative pollution degree can be obtained according to the average access distance of the target tree and the average access distance experienced by the power pollution eigenvalue in the isolated group, where the calculation formula of the relative pollution degree is as follows:

[0047]

[0048] Among them, S is the relative pollution degree, F is the average access distance experienced by the power pollution eigenvalue in the isolated group, and y is the access distance of the power pollution eigenvalue on the target tree. Among them, S is greater than 0 and not less than 1.

[0049] S6, analyzing the current power pollution data through relative pollution degree.

[0050] According to the data analysis method for power pollution monitoring of the embodiment of the present invention, historical power pollution data is obtained by acquiring historical power consumption information, and a power pollution monitoring model is constructed, and the power pollution monitoring model is trained according to the historical power pollution data, and then current power consumption information is collected to obtain current power pollution data, and power pollution eigenvalues ​​are calculated according to the current power pollution data, and the power pollution eigenvalues ​​are transmitted to the trained power pollution monitoring model to obtain relative pollution degree, and the current power pollution data is analyzed by relative pollution degree, thereby enabling the power pollution data to be quickly processed, thereby helping power companies to manage power pollution more effectively, thereby reducing the harm of power pollution to the environment and humans.

[0051] In order to implement the data analysis method for power pollution monitoring of the above embodiment, the present invention also proposes a data analysis system for power pollution monitoring.

[0052] like Figure 2 As shown, the data analysis system for power pollution monitoring of the embodiment of the present invention includes: a first acquisition module 100, a model construction module 200, a collection module 300, a calculation module 400, a second acquisition module 500 and an analysis module 600, wherein the first acquisition module 100 is used to acquire historical power consumption information and obtain historical power pollution data based on the historical power consumption information; the model construction module 200 is used to build a power pollution monitoring model and train the power pollution monitoring model based on the historical power pollution data; the collection module 300 is used to acquire current power consumption information and obtain current power pollution data based on the current power consumption information; the calculation module 400 is used to calculate the power pollution eigenvalue based on the current power pollution data; the second acquisition module 500 is used to transmit the power pollution eigenvalue to the trained power pollution monitoring model to obtain the relative pollution degree; the analysis module 600 is used to analyze the current power pollution data through the relative pollution degree.

[0053] In one embodiment of the present invention, the historical electricity usage information may include normal electricity usage information and abnormal electricity usage information in a fixed area, wherein the abnormal electricity usage information may include power pollution data.

[0054] In one embodiment of the present invention, the model building module 200 can also be used to: record the historical power pollution data as the starting point research value, and filter out the target research value from the starting point research value to record it as the target tree sub-endpoint; machine select the target eigenvalue, and filter out the eigenvalue number corresponding to the target eigenvalue in the target tree sub-endpoint; perform two-way segmentation on the target tree sub-endpoint through the eigenvalue number to obtain the leaf end point of the target tree sub-endpoint, wherein, if the set target is achieved, the target tree is obtained; when the number of target numbers reaches the set target, an isolated group is formed, and a trained power pollution monitoring model is obtained.

[0055] Specifically, historical power information can be obtained from the power grid system, wherein the historical power information may include normal power information and historical power pollution data, and the historical power pollution data may be recorded as the starting point research value, and the target research value is selected from the starting point research value to be recorded as the target tree sub-endpoint, and if the sub-endpoint of the target tree is the starting point, the current starting point may be used as the source point. Among them, the target research value may be a part of the research value randomly selected from the starting point research value to be used as the target research value.

[0056] Furthermore, the target intrinsics can be obtained based on the power pollution intrinsics, and the eigenvalues ​​corresponding to the target can be screened in the target tree sub-endpoints. For example, the power pollution intrinsics can include voltage fluctuations, transient currents, three-phase imbalances, eddy currents and other intrinsics.

[0057] Furthermore, the eigenvalue can be used to store the research value of the target tree sub-endpoint whose number of eigenvalue mapping is greater than the eigenvalue in one sub-endpoint, and the research value less than the eigenvalue in another sub-endpoint, and these two sub-endpoints can be recorded as the target tree sub-endpoints. If the set target is completed, the target tree can be obtained, wherein the set target may include a certain height of the target tree and the target tree sub-endpoint cannot be further divided, and the target tree sub-endpoint cannot be further divided may include the target tree sub-endpoint only contains a unique research value and all the research values ​​in the target tree sub-endpoint are the same.

[0058] Furthermore, after obtaining the target trees, it can be determined whether the number of target trees exceeds the set number. If the number of target trees does not exceed the set number, the target trees can continue to be generated through the above steps; if the number of target trees exceeds the set number, all target trees can be clustered into isolated groups, thereby obtaining a trained power pollution monitoring model.

[0059] In one embodiment of the present invention, the acquisition module 300 can optimize the power usage information by optimizing the T-SNE algorithm, and establish a model for the neighboring points of all the information in the power usage information, and the distribution of the model in high dimensions can be a Gaussian distribution, and the distribution in low dimensions can be a t distribution. Among them, the neighboring points of the power usage information can be a cluster of points with relatively close distances between the power usage information.

[0060] Furthermore, the optimized power information can be grouped using a classification algorithm, that is, each information value in the power information can be grouped into the same group, so that the information in the group is similar or close, and the information in different groups has greater differences.

[0061] In one embodiment of the present invention, the calculation module 400 can also be used to: obtain an eigengroup for setting an eigengroup mapping through current power pollution data; and obtain a power pollution eigennumber by selecting an eigenset extraction method for the eigengroup for setting an eigengroup mapping.

[0062] Specifically, the eigenstructure can be performed through the current power pollution data to obtain the eigengroup mapped by the set eigenpopulation, and all the set eigenpopulations map their own eigengroups accordingly, and the information of the eigengroups mapped by all the set eigenpopulations can be obtained through the current power pollution data.

[0063] Furthermore, subgroups can be screened in the eigengroup of the set eigenpopulation mapping and input into the clustering algorithm as eigensubgroups. The eigensubgroups are evaluated by the evaluation function in the clustering algorithm. When the value of the evaluation function exceeds a preset threshold, the power pollution eigenvalues ​​can be obtained, and the power pollution eigennumbers of the power pollution eigenmap can be obtained from the current power pollution data.

[0064] Among them, the A* algorithm can be used to extract the eigengroup of the set eigenpopulation mapping into the eigensubgroup, and the value of the evaluation function of the eigensubgroup mapping can be calculated. When the value is the same as the set standard, the eigensubgroup can be obtained, and the target eigensubgroup can be recorded as the power pollution eigen.

[0065] Specifically, the target eigengroup can be regarded as an empty group, and the eigengroups mapped to the set eigengroup population can be screened out to the eigengroup to obtain the first eigengroup. Then, the first eigengroup can be statistically analyzed by square root statistics to obtain the first statistical value. Secondly, the eigengroups mapped to the set eigengroup can be further screened out to the eigengroup to obtain the secondary eigengroup, and the secondary eigengroup can be statistically analyzed by square root statistics to obtain the secondary statistical value. Finally, the size of the first statistical value and the secondary statistical value can be determined. If the first statistical value is greater than the secondary statistical value, the first eigengroup can be recorded as the target eigengroup, otherwise, the secondary eigengroup can be recorded as the target eigengroup.

[0066] In one embodiment of the present invention, the second acquisition module 500 can also be used to: visit the trees in the isolated group one by one through the power pollution eigennumber; obtain the access distance of the power pollution eigennumber, wherein the access distance is the total length of the tree passed by the power pollution eigennumber; calculate the uniform access distance of the power pollution eigennumber in the isolated group through the access distance, and calculate the relative pollution degree mapped by the power pollution eigennumber based on the uniform access distance.

[0067] Specifically, first, the power pollution eigenvalue can be transmitted to all targets in the isolated group, and the branches corresponding to each endpoint of the target tree are visited one by one to obtain the access distance of the power pollution eigenvalue, and the uniform access distance is calculated by the access distance, wherein the uniform access distance can be calculated using the research value and Euler's formula. The calculation formula of the uniform access distance of the target tree is as follows:

[0068] D(x)=2C(n-1)-{2(n-1) / n}

[0069] Where D is the uniform access distance of the target tree, x is the research value, C(n-1)=ln(n-1)+ξ, and ξ is the Euler constant.

[0070] Furthermore, the average access distance experienced by the power pollution eigenvalue in the isolated group can be obtained according to the average access distance of the target tree, that is, the sum of the average access distances of all target trees is divided by the number of target trees.

[0071] Furthermore, the relative pollution degree can be obtained according to the average access distance of the target tree and the average access distance experienced by the power pollution eigenvalue in the isolated group, where the calculation formula of the relative pollution degree is as follows:

[0072]

[0073] Among them, S is the relative pollution degree, F is the average access distance experienced by the power pollution eigenvalue in the isolated group, and y is the access distance of the power pollution eigenvalue on the target tree. Among them, S is greater than 0 and not less than 1.

[0074] In summary, the present invention obtains historical power consumption information through a first acquisition module to obtain historical power pollution data, and constructs a power pollution monitoring model through a model construction module, then collects current power consumption information through a collection module to obtain current power pollution data, and calculates power pollution eigenvalues ​​through a calculation module, and transmits the power pollution eigenvalues ​​to the trained power pollution monitoring model to obtain relative pollution degree, and finally analyzes the current power pollution data through an analysis module, thereby enabling rapid processing of power pollution data, thereby helping power companies to manage power pollution more effectively, and thereby reducing the harm of power pollution to the environment and humans.

[0075] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0076] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0077] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0078] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0079] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0080] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0081] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0082] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0083] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0084] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A data analysis method for power pollution monitoring, characterized in that: The following steps are involved: Acquiring historical electricity consumption information, and obtaining historical power pollution data based on the historical electricity consumption information; Constructing a power pollution monitoring model, and training the power pollution monitoring model according to the historical power pollution data; Collecting current electricity consumption information, and obtaining current power pollution data according to the current electricity consumption information; Calculating the power pollution intrinsic number according to the current power pollution data; Transmitting the power pollution eigenvalues ​​to the trained power pollution monitoring model to obtain relative pollution degree; The current power pollution data is analyzed according to the relative pollution degree.

2. The data analysis method for power pollution monitoring according to claim 1, characterized in that: The training of the power pollution monitoring model according to the historical power pollution data specifically includes: Record the historical power pollution data as the starting point research value, and select the target research value from the starting point research value to record it as the target tree sub-end point; The target eigenvalue is selected by the machine, and the eigenvalue number corresponding to the target eigenvalue is screened out from the target tree sub-endpoints; Performing two-way splitting of the target tree sub-endpoints by the eigenvalues ​​to obtain leaf endpoints of the target tree sub-endpoints, wherein if the set goal is achieved, the target tree is obtained; When the number of targets reaches the set target, an isolated group is formed and a trained power pollution monitoring model is obtained.

3. The data analysis method for power pollution monitoring according to claim 2 is characterized in that: The calculating of the power pollution eigenvalue according to the current power pollution data specifically includes: Acquire an eigengroup for setting an eigenpopulation mapping through the current power pollution data; The power pollution eigenvalue is obtained by extracting an eigengroup selected from an eigensubset by setting the eigenpopulation mapping.

4. The data analysis method for power pollution monitoring according to claim 3 is characterized in that: The transmitting the power pollution eigenvalue to the trained power pollution monitoring model to obtain the relative pollution degree specifically includes: Visit the trees in the isolated group one by one according to the power pollution eigennumber; Obtaining an access distance of the power pollution eigenvalue, wherein the access distance is a total length of a tree through which the power pollution eigenvalue passes; The uniform access distance of the power pollution eigenvalue in the isolated group is calculated by using the access distance, and the relative pollution degree mapped by the power pollution eigenvalue is calculated according to the uniform access distance.

5. The data analysis method for power pollution monitoring according to claim 4 is characterized in that: The collecting of current electricity consumption information and obtaining current power pollution data according to the current electricity consumption information specifically includes: Collecting the current electricity usage information, and obtaining optimized electricity usage information through an optimization method; The optimized electricity usage information is classified by the K-means++ algorithm to obtain the current electricity pollution data.

6. A data analysis system for power pollution monitoring, characterized in that: include: A first acquisition module, the first acquisition module is used to acquire historical electricity consumption information, and obtain historical power pollution data according to the historical electricity consumption information; A model building module, the model building module is used to build a power pollution monitoring model and train the power pollution monitoring model according to the historical power pollution data; A collection module, the collection module is used to collect current electricity consumption information and obtain current power pollution data according to the current electricity consumption information; A calculation module, the calculation module is used to calculate the power pollution eigenvalue according to the current power pollution data; A second acquisition module, the second acquisition module is used to transmit the power pollution eigenvalue to the trained power pollution monitoring model to obtain a relative pollution degree; An analysis module is used to analyze the current power pollution data according to the relative pollution degree.

7. The data analysis system for power pollution monitoring according to claim 6, characterized in that: The model building module is also used to: Record the historical power pollution data as the starting point research value, and select the target research value from the starting point research value to record it as the target tree sub-end point; The target eigenvalue is selected by the machine, and the eigenvalue number corresponding to the target eigenvalue is screened out from the target tree sub-endpoints; Performing two-way splitting of the target tree sub-endpoints by the eigenvalues ​​to obtain leaf endpoints of the target tree sub-endpoints, wherein if the set goal is achieved, the target tree is obtained; When the number of targets reaches the set target, an isolated group is formed and a trained power pollution monitoring model is obtained.

8. The data analysis system for power pollution monitoring according to claim 7, characterized in that: The calculation module is also used for: Acquire an eigengroup for setting an eigenpopulation mapping through the current power pollution data; The power pollution eigenvalue is obtained by extracting an eigengroup selected from an eigensubset by setting the eigenpopulation mapping.

9. The data analysis system for power pollution monitoring according to claim 8, characterized in that: The second acquisition module is also used for: Visit the trees in the isolated group one by one according to the power pollution eigennumber; Obtaining an access distance of the power pollution eigenvalue, wherein the access distance is a total length of a tree through which the power pollution eigenvalue passes; The uniform access distance of the power pollution eigenvalue in the isolated group is calculated by using the access distance, and the relative pollution degree mapped by the power pollution eigenvalue is calculated according to the uniform access distance.

10. The data analysis system for power pollution monitoring according to claim 9, characterized in that: The acquisition module is also used for: Collecting the current electricity usage information, and obtaining optimized electricity usage information through an optimization method; The optimized electricity usage information is classified by the K-means++ algorithm to obtain the current electricity pollution data.

Images