CN105608638A - Method and system for evaluating synchronous state of meter code data of intelligent terminal and electric energy meter - Google Patents

Abstract

The invention discloses a method for evaluating the synchronous state of meter code data of an intelligent terminal and an electric energy meter, which includes: obtaining all meter code data collected by the intelligent terminal and the electric energy meter within a preset time from a data master station, and comparing the meter code The data is preprocessed; devaluation processing and XOR processing are performed according to the existence of table code data at the hour; K-means clustering algorithm is used to cluster and analyze table code data after XOR processing to obtain Clustering results; evaluate the synchronization status of the smart terminal and the meter code data of the electric energy meter according to the clustering results. Compared with the existing technology, this method can timely discover the difference between the data collected by the electric energy meter in the metering automation system and the intelligent terminal, so as to have an overall understanding of the operation status of the power grid, improve the operation and maintenance level of the collection terminal, and improve the terminal performance. Integrity rate, and this method is an effective application of data mining and machine learning in power grid data. The invention also discloses a system.

Description

A method and system for evaluating the synchronization status of code data between an intelligent terminal and an electric energy meter

technical field

The invention relates to the technical field of electric power information, in particular to a method and system for evaluating the synchronization state of meter code data of an intelligent terminal and an electric energy meter.

Background technique

Data is one of an organization's most valuable assets. There is a direct link between an enterprise's data quality and business performance, and high-quality data can keep a company competitive and invincible in times of economic turmoil. With pervasive in-depth data quality, businesses can trust all data for all needs at any time.

In the smart grid, the factors affecting the quality of power data mainly include data integrity and data accuracy. Among them, data integrity constraints include entity integrity constraints, referential integrity constraints, functional dependency constraints, and statistical constraints. However, the measurement automation terminal in the smart grid usually has problems such as communication failure and misalignment of recording time. These problems are directly reflected in the data center as missing data records and loose constraints. Based on this, it is necessary to study the overall trend of the lack of synchronization of the electric energy meter code data collected by the metering automation intelligent terminal and the electric energy meter terminal, so as to have an overall understanding of the operating status of the power grid and improve the operation and maintenance level of the collection terminal. Improve terminal integrity.

Contents of the invention

The technical problem to be solved by the present invention is to provide a method and system for evaluating the synchronous state of the code data of the smart terminal and the electric energy meter, so as to analyze the operating state and the consistency of data transmission of the intelligent terminal and the electric energy meter, which is beneficial to operation and maintenance The staff master the operation status of the metering automation system, and improve the operation and maintenance level of the collection terminal and the terminal data integrity rate.

In order to solve the problems of the technologies described above, the technical scheme adopted in the present invention is as follows:

A method for evaluating the synchronization state of the meter code data of the smart terminal and the electric energy meter is provided, including steps:

Obtain all the meter code data collected by the smart terminal and the electric energy meter within a preset period of time from the data master station, and preprocess the meter code data;

According to the existence of the table code data at the whole point, devalue the preprocessed table code data;

Perform XOR processing on the two table code data after devaluation processing;

Use the K-means clustering algorithm to perform clustering analysis on the table code data after XOR processing to obtain the clustering results;

According to the clustering results, the synchronization status of the code data of the smart terminal and the electric energy meter is evaluated.

Compared with the existing technology, this method first obtains all the meter code data collected by the smart terminal and the electric energy meter within a preset period of time from the data master station, and performs preprocessing and devalue processing on it, and then the two data Carry out XOR processing to integrate the data, and then use the K-means clustering algorithm (ie KMEANS algorithm) in its learning to perform cluster analysis on the processed data, and finally perform cluster analysis on the smart terminals and electric energy meters according to the cluster analysis results. The overall evaluation of the synchronization state of the code data; this method can timely discover the difference between the energy meter in the metering automation system and the data collected by the smart terminal, so as to have an overall understanding of the operating state of the power grid, improve the operation and maintenance level of the collection terminal, and improve The complete rate of the terminal is obtained, and this method is an effective application of data mining and machine learning in power grid data, which has certain guiding significance for the improvement of data quality.

Correspondingly, the present invention also provides a system for evaluating the synchronization state of the code data of the smart terminal and the electric energy meter, including:

The acquisition module is used to acquire all the meter code data collected by the smart terminal and the electric energy meter within a preset time from the data master station, and preprocess the meter code data;

A devaluation processing module is used to devalue the preprocessed table code data according to the existence of the table code data at the hour;

The XOR processing module is used to perform XOR processing on the table code data after the devaluation processing;

The analysis module is used to perform cluster analysis on the table code data after XOR processing by using the K-means clustering algorithm to obtain a clustering result;

The evaluation module is used to evaluate the synchronization state of the smart terminal and the meter code data of the electric energy meter according to the clustering result.

Description of drawings

Fig. 1 is the main flow chart of the method for evaluating the synchronization state of the meter code data of the smart terminal and the electric energy meter in the present invention.

Fig. 2 is a flowchart of an embodiment of the method of the present invention.

FIG. 3 is a sub-flow chart of step S207 in FIG. 2 .

Fig. 4 is a structural block diagram of the system for evaluating the synchronization state of the smart terminal and the meter code data of the electric energy meter according to the present invention.

FIG. 5 is a structural block diagram of the device 300 in FIG. 4 .

FIG. 6 is a structural block diagram of the analysis module in FIG. 5 .

detailed description

Embodiments of the present invention will now be described with reference to the drawings, in which like reference numerals represent like elements.

Please refer to Fig. 1, the method for evaluating the data synchronization state of the smart terminal and the electric energy meter in the present invention includes:

S101. Obtain all the meter code data collected by the smart terminal and the electric energy meter within a preset period of time from the data master station, and preprocess the meter code data;

S102, according to the presence of the table code data at the hour, devalue the preprocessed table code data;

S103, performing XOR processing on the two sets of table code data after the devaluation processing;

S104, using the K-means clustering algorithm to perform cluster analysis on the XOR-processed table code data to obtain a clustering result;

S105, evaluating the synchronization state of the meter code data of the smart terminal and the electric energy meter according to the clustering result.

Please refer to Fig. 2 again, in a preferred embodiment of the present invention, this method specifically comprises:

S201, respectively collect meter code data on the hour through the smart terminal and the electric energy meter, that is, the frequency of collecting meter code data by the smart terminal and the electric energy meter is once every hour.

S202, the meter code data collected by the electric energy meter is transmitted to the intelligent terminal through the 485 bus.

S203, the intelligent terminal transmits the two sets of meter code data to the data master station through the GPRS network; specifically, the intelligent terminal includes a signal transmission module, which can combine the two sets of redundant data collected by itself and transmitted by the electric energy meter It is transmitted to the data master station through the GPRS mobile network. It should be noted that when there are software and hardware problems such as hardware damage, SIM failure, 485 protocol error, no signal, etc., the data collected by the watch code will be lost or damaged when it is transmitted to the master station. Moreover, the table code data sent to the data master station contains the user's real-time power consumption information, and the specific content contained in it is shown in Table 1:

Table 1: Table Code Data Sample Table

S204. Obtain from the data master station all the meter code data collected by the smart terminal and the electric energy meter within a preset period of time, and preprocess the meter code data; specifically, obtain the date of December 1, 2014 from the data master station All the meter code data collected by the smart terminal and the electric energy meter judge whether any important field of the meter code data is missing, and if it is missing, discard the meter code data and regard the meter code data as empty.

S205. According to the existence of the meter code data at the hour, devalue the preprocessed meter code data; specifically, the meter code data of each smart terminal and electric energy meter is Whether the time data exists or not is converted into the data format shown in Table 2:

POINTID DATATIME BM0 BM1 BM2 … BM21 BM22 BM23 54 2014/12/1 1 1 1 … 1 0 1 7782 2014/12/1 1 1 1 … 1 1 1 332208 2014/12/1 1 1 1 … 1 1 1

Table 2: Evaluation model data selection

Among them, POINTID represents the data point number of the smart terminal or electric energy meter, and BM0, BM1, ..., BM23 respectively represent whether the data exists at 0:00, 1:00, ..., 23:00, and if the data exists, it is marked as 1 , otherwise marked as 0.

S206, perform XOR processing on the two pieces of meter code data after the devaluation processing; specifically, perform XOR processing on the two pieces of data of the smart terminal and the electric energy meter that have been devalued and formatted in a corresponding time position. Or process to get the data shown in Table 3:

FPOINTID RIQI XOR0 XOR1 … XOR22 XOR23 123348 2014/12/1 0 0 … 0 0 68217 2014/12/1 0 0 … 0 0 98922 2014/12/1 0 0 … 0 0

Table 3: Evaluation model data structure

Among them, POINTID represents the data point number of the smart terminal, DATATIME represents the data time, which is based on the day, and XOR0, XOR1, ..., XOR23 respectively represent the interconnected smart terminal and the electric energy meter at 0:00, 1:00, ..., 23:00 The XOR result of the devalued data at time, if the meter code data of the smart terminal and the electric energy meter are missing or both exist, it is marked as 1, otherwise it is marked as 0.

S207. Perform cluster analysis on the XOR-processed table code data by using a K-means clustering algorithm to obtain a clustering result. Considering that the meter code data collected by the metering automation system is not completely marked, and it is necessary to distinguish the difference between the data collected by the smart terminal and the electric energy meter from the original meter code data, it is more appropriate to use an unsupervised machine learning model. Among them, the K-means clustering algorithm can group similar objects into the same cluster and is easy to implement, and has application advantages in massive data processing. Among them, the specific steps of the K-means clustering algorithm will be described in detail below.

S208. Evaluate the synchronization state of the smart terminal and the meter code data of the electric energy meter according to the clustering result.

Specifically, referring to FIG. 3, step S207 includes:

S2071, setting multiple clusters, extracting any one of the table code data and distributing the table code data in any cluster;

S2072, setting the value of K in the algorithm; wherein, K is determined by the accuracy of the clustering result, if you want to make the data result more accurate, you can increase the value of K locally, in this embodiment, take K=4;

S2073, randomly determining K initial points as the initial centroids of each cluster, and assigning the remaining table code data to the closest cluster according to the Euclidean distance between the remaining table code data and the initial centroid of each cluster;

S2074, calculate the mean value of all table code data in each cluster, and use the mean value as the new centroid of the cluster;

S2075, redistribute all table code data according to the new centroid;

S2076, iterating S2074 and S2075 until all the table code data allocations no longer change;

S2077. Classify all table code data into their proper categories.

Correspondingly, referring to FIG. 4, the present invention also provides a system for evaluating the synchronization state of the meter code data of the smart terminal and the electric energy meter. 400 connections. Among them, the electric energy meter 100 and the intelligent terminal 200 are used to collect the meter code data at the hour respectively, and the meter code data collected by the electric energy meter 100 is transmitted to the intelligent terminal 200 through the 485 bus, and the intelligent terminal 200 transmits the two meter code data through the GPRS The network is transmitted to the data master station 400, and the device 300 obtains the meter code data from the data master station 400 to complete the evaluation of the synchronization status of the meter code data of the smart terminal 200 and the electric energy meter 100.

Please refer to FIG. 5 again, the device 300 includes:

The acquiring module 30 is used to acquire all the meter code data collected by the smart terminal 200 and the electric energy meter 100 within a preset time from the data master station 400, and preprocess the meter code data; wherein, the preset time is 24 hours.

The devaluation processing module 31 is used to carry out devaluation processing to the preprocessed table code data according to the existence of the table code data at the whole hour;

XOR processing module 32, for carrying out XOR processing to the table code data after devalue processing;

An analysis module 33, configured to use a K-means clustering algorithm to perform cluster analysis on the XOR-processed table code data to obtain a clustering result;

The evaluation module 34 is used to evaluate the synchronization state of the smart terminal and the meter code data of the electric energy meter according to the clustering result.

Specifically, the acquisition module 30 specifically includes:

An acquisition unit, configured to acquire all meter code data collected by the smart terminal 200 and the electric energy meter 100 within a preset period of time from the data master station 400;

The preprocessing unit is used for judging whether an important field of any piece of table code data is missing, discarding the piece of table code data according to the judgment result and treating the piece of table code data as empty.

Specifically, referring to FIG. 6, the analysis module 33 includes:

A setting unit 331, configured to set the value of K in multiple clusters and algorithms, wherein K is determined by the accuracy of the clustering result, and K=4;

Extraction unit 332, for extracting any table code data and distributing the table code data in any cluster;

A determining unit 333, configured to randomly determine K initial points as the initial centroids of each cluster;

The first allocation unit 334 is used for distributing the remaining table code data to the closest cluster according to the Euclidean distance between the remaining table code data and the initial centroid of each cluster;

Calculation unit 335, used to calculate the mean value of all table code data in each cluster, and use the mean value as the new centroid of the cluster;

The second distribution unit 336 redistributes all table code data according to the new centroid;

The iteration unit 337 is used to iterate the data in the calculation unit and the second allocation unit 336 until all table code data allocations no longer change;

The classification unit 338 is configured to classify all table code data into their proper categories.

As can be seen from the above description, the method and system of the present invention have the following advantages:

(1) Devalue the electric energy data collected by the electric energy meter and the intelligent terminal, and obtain the existence or non-existence of the data representing it at the corresponding time, and then perform the XOR operation on the processed data at the corresponding time position , and finally use the machine learning algorithm to cluster the data as a whole, and get the overall evaluation of the data synchronization status;

(2) The prediction model has been established. After strict logical reasoning and experimental demonstration, the difference between the energy meter in the metering automation system and the data collected by the smart terminal can be found in time, so as to have an overall understanding of the operating status of the power grid and improve the collection terminal. The operation and maintenance level improves the terminal integrity rate, and this method is an effective application of data mining and machine learning in power grid data, which has certain guiding significance for the improvement of data quality.

The present invention has been described above in conjunction with the best embodiments, but the present invention is not limited to the above-disclosed embodiments, but should cover various modifications and equivalent combinations made according to the essence of the present invention.

Claims (10)

1. A method for evaluating the meter code data synchronization state of an intelligent terminal and an electric energy meter, characterized in that, comprising the steps: Obtain all the meter code data collected by the smart terminal and the electric energy meter within a preset period of time from the data master station, and preprocess the meter code data; According to the presence of the table code data at the hour, devalue the preprocessed table code data; Exclusive OR processing is performed on the two sets of table code data after devaluation processing; Using the K-means clustering algorithm to carry out cluster analysis on the table code data after XOR processing, to obtain a clustering result; Evaluating the synchronization state of the smart terminal and the meter code data of the electric energy meter according to the clustering result. 2. The method according to claim 1, wherein the preset time is 24 hours. 3. The method according to claim 1, wherein the preprocessing of the table code data specifically comprises: Judging whether any important field of the table code data is missing; Discard the table code data according to the judgment result and regard the table code data as empty. 4. method as claimed in claim 3, is characterized in that, cluster analysis specifically comprises: (1) Set multiple clusters; (2) extract any one of the table code data and distribute the table code data in any one of the clusters; (3) setting the numerical value of K in the algorithm, wherein K is determined by the precision of the clustering result, and K=4; (4) Randomly determine K initial points as the initial centroids of each cluster; (5) according to remaining described table code data and the Euclidean distance of the initial centroid of each cluster, remaining described table code data is distributed in the closest cluster; (6) calculate the mean value of all described table code data in each cluster, and use described mean value as the new centroid of this cluster; (7) redistribute all the table code data according to the new centroid; (8) iterations (6) and (7) are no longer changed until all the table code data allocations; (9) All the table code data are classified into the categories they should belong to. 5. The method according to any one of claims 1-4, further comprising: Collecting the meter code data at the hour on the hour respectively through the smart terminal and the electric energy meter; The meter code data collected by the electric energy meter is transmitted to the smart terminal through the 485 bus; The intelligent terminal transmits two copies of the table code data to the data master station through the GPRS network. 6. A system for evaluating the synchronous state of the meter code data of an intelligent terminal and an electric energy meter, characterized in that, comprising: The acquisition module is used to acquire all the meter code data collected by the smart terminal and the electric energy meter within a preset time from the data master station, and preprocess the meter code data; A devaluation processing module, configured to perform devaluation processing on the preprocessed table code data according to the existence of the table code data at the hour; An XOR processing module, configured to perform XOR processing on the table code data after devaluation processing; An analysis module, configured to use a K-means clustering algorithm to perform cluster analysis on the table code data after XOR processing, so as to obtain a clustering result; An evaluation module, configured to evaluate the synchronization state of the smart terminal and the meter code data of the electric energy meter according to the clustering result. 7. The system according to claim 6, wherein the preset time is 24 hours. 8. The system according to claim 6, wherein the acquiring module specifically comprises: The acquisition unit is used to acquire all the meter code data collected by the smart terminal and the electric energy meter within a preset period of time from the data master station; The preprocessing unit is used for judging whether any important field of the table code data is missing, discarding the table code data according to the judgment result and treating the table code data as empty. 9. The system according to claim 8, wherein the analysis module specifically comprises: A setting unit, configured to set a plurality of clusters and the value of K in the algorithm, wherein K is determined by the accuracy of the clustering result, and K=4; An extracting unit, configured to extract any piece of table code data and assign the table code data to any of the clusters; Determining a unit for randomly determining K initial points as the initial centroids of each cluster; The first allocation unit is used to allocate the remaining table code data to the closest cluster according to the Euclidean distance between the remaining table code data and the initial centroid of each cluster; A calculation unit, configured to calculate the mean value of all the table code data in each cluster, and use the mean value as the new centroid of the cluster; The second allocating unit redistributes all the table code data according to the new centroid; an iteration unit, configured to iterate the data in the calculation unit and the second allocation unit until all the table code data allocations no longer change; The taxonomy unit is used to classify all the table code data into their proper categories. 10. The system according to any one of claims 6-9, further comprising: The intelligent terminal is used to collect the table code data at the hour on the hour; The electric energy meter is used to collect the meter code data at the hour on the hour; Wherein, the meter code data collected by the electric energy meter is transmitted to the smart terminal through the 485 bus, and the smart terminal transmits two copies of the meter code data to the data master station through the GPRS network.