KR20220050843A - Load power analysis apparatus and load power analysis method by clustering technique - Google Patents

Abstract

A load power analysis apparatus and a load power analysis method by a clustering technique are disclosed. The load power analysis apparatus by a clustering technique of the present invention comprises: a smart power meter unit installed at a power inlet point of a consumer to which at least one load device is connected to measure the power usage of the consumer; and a load decomposition unit for analyzing the power usage measured by the smart power meter unit and monitoring the power usage for each load device. The load decomposition unit pre-processes the power usage data measured by the smart power meter unit to obtain active power and apparent power for each time period, and classifies the load devices according to the load power characteristics using the active power and the apparent power. Therefore, the present invention can accurately predict the power usage of the consumer.

Description

Load power analysis apparatus and load power analysis method by clustering technique

The present invention relates to a load power analysis apparatus and a load power analysis method, and more particularly, to a load power analysis apparatus and a load power analysis method by a clustering technique based on a power characteristic of a load.

Due to environmental problems, policy efforts to lower the power generation rate by fossil energy and increase the power generation rate by renewable energy are continuing. At the same time, a power management policy that manages supply and demand in a balanced way to accurately predict the amount of electricity demand and to maintain the supply at a certain level is also being implemented.

In order to realize this energy management policy, an intelligent remote metering infrastructure (AMI) is installed and operated to accurately predict the demand-side power consumption.

AMI metering data not only serves as a standard for calculating electricity rates, but is also being used as a variety of intelligent services in the distribution/sales/customer service fields, such as placebo, challenge detection, electricity quality (voltage, current) monitoring, and real-time information provision.

However, in order to support the planned/reasonable power consumption and voluntary power saving of customers with the existing AMI installed, it should be able to be utilized as more detailed and useful information as well as providing real-time information of AMI data.

For this, it is necessary to be able to analyze each load installed in the consumer (by type of electronic product). there was.

However, there is a need for the development of a new load power analysis device and load power analysis method that can analyze the characteristics of the customer's load without additionally installing a separate device other than the already installed AMI to determine the power consumption for each load.

Patent Document 1: Registered Patent No. 10-1970186 (Announcement Date: April 18, 2019) Patent Document 2: Registered Patent No. 10-1708709 (Announcement Date: February 21, 2017) Patent Document 3: Patent Publication No. 10-2016-0143456 (published date: December 14, 2016)

The present invention devised by the above necessity provides a load power analysis device and a load power analysis method capable of analyzing the power usage and usage pattern of individual loads by identifying the power characteristics of each load of the consumer and classifying them by a clustering technique. aim to do

In order to achieve the above object, an apparatus for analyzing load power by a clustering technique according to an embodiment of the present invention is installed at a power inlet point of a consumer to which at least one load device is connected, smart power for measuring the power consumption of the consumer meter part; and a load decomposing unit for monitoring the power usage for each load device by analyzing the power usage measured by the smart power meter unit, wherein the load decomposing unit includes, the power usage data measured by the smart power meter unit Pre-processing is performed to obtain active power and apparent power for each time period, and the corresponding load devices are classified according to load power characteristics using the active power and the apparent power.

In this case, the load decomposing unit clusters the measured power usage data into a plurality of clusters in units of days or months.

In this case, the load decomposing unit calculates a power factor using the active power and the apparent power, and calculates the measured power usage data based on a meter reading time for reading the active power, the power factor, and the corresponding active power. cluster into multiple clusters.

In this case, the load decomposing unit classifies clusters exhibiting a similar change pattern as homogeneous load devices by using a median value of active power, a median power factor, and a median reading time for each of the plurality of clusters.

In this case, the load decomposition unit calculates the total daily operating time by adding up the daily average generation times of the clusters classified as the same load devices, and uses the active power and the daily total operating time to calculate the corresponding load. Classify the device into one of a plurality of power change types.

In this case, the load decomposing unit is configured to convert the plurality of power change types into a first type having two power change states, a second type having a plurality of power change states, and a third type having a continuous power change state in a short period of time. and a fourth type having a state of repetitive power change over a long period of time, and classified as any one of the first to fourth types.

Meanwhile, the load decomposing unit receives the user's feedback through an application pre-installed in a user terminal pre-registered as a user of the smart power meter unit.

On the other hand, the load decomposing unit receives the identification information about the load device acquired by the smart outlet pre-installed in the consumer in which the smart power meter is installed.

A load power analysis method according to another embodiment of the present invention includes a smart power meter unit installed at a power inlet point of a customer to which at least one or more load devices are connected, and measuring the power consumption of the customer, and the smart power meter unit is measured in the smart power meter unit In the load power analysis method using a load power analysis apparatus by a clustering technique comprising a load decomposing unit for monitoring the power usage for each load device by analyzing the used power consumption, the load decomposing unit includes information on the measured power usage pre-processing to calculate a power factor using predetermined active power and apparent power for each time period, and the active power and the apparent power; The load decomposing unit clustering the measured power usage information into a plurality of clusters on a daily or monthly basis by using the active power, the power factor, and a meter reading time for reading the active power. ; classifying, by the load decomposing unit, clusters exhibiting a similar change pattern into homogeneous load devices using a median value of active power, a median power factor, and a median reading time for each of the plurality of clusters; and the load decomposition unit calculates the total daily operating time by adding up the average daily occurrence time of the clusters classified as the same load devices, and uses the active power and the total daily operating time to calculate the load device. Classifying one of a plurality of power change types; including, wherein the load decomposition unit divides the plurality of power change types into a first type having two power change states, a second type having a plurality of power change states, a short-term It is classified into any one of a third type having a continuous power change state and a fourth type having a power change state that is repetitive for a long period of time.

In this case, the load decomposing unit receives a user's feedback through an application pre-installed on a user terminal pre-registered as a user of the smart power meter unit, or a load obtained by a smart outlet pre-installed in a consumer in which the smart power meter unit is installed. receiving identification information about the device; and using the user's feedback or identification information on the load device to update classification information on the corresponding load device.

According to various embodiments of the present invention, since it is possible to analyze the power characteristics of the consumer's load and classify it by load by the clustering technique, it is possible to accurately predict the consumer's power usage,

By decomposing the AMI power usage by analyzing the power usage pattern by load, customers can reduce costs by providing unnecessary home appliance usage information and progressive tax notification to customers.

It is possible to prevent problems caused by the failure of home appliances in advance by detecting the failure of the home appliance by using the power consumption pattern for each home appliance.

By analyzing the usage patterns of users by household, it is effective in preventing accidents by predicting emergency situations that occur in elderly households living alone.

1 is a block diagram illustrating an apparatus for analyzing load power by a clustering technique according to an embodiment of the present invention;
2 is a graph of four types of power patterns illustrating the power characteristics of a load device;
3 is a three-dimensional simulation diagram according to active power, power factor and meter reading time for explaining the clustering technique of the present invention;
4 is a data distribution graph for each power factor group of 6 clusters according to an embodiment of the present invention;
5 is a data distribution graph of holidays and weekdays of six clusters according to an embodiment of the present invention;
6 is a data distribution graph for each day of the week of 6 clusters according to an embodiment of the present invention;
7 is a data distribution graph for each power factor group of four clusters according to another embodiment of the present invention;
8 is a data distribution graph of holidays and weekdays of four clusters according to another embodiment of the present invention;
9 is a data distribution graph for each day of the week of 4 clusters according to another embodiment of the present invention;
10 is a view exemplarily illustrating a user interface for receiving feedback from a user terminal according to another embodiment of the present invention;
11 is a flowchart for exemplarily explaining a load power analysis method according to another embodiment of the present invention.

Hereinafter, a preferred embodiment of the present invention will be described with reference to the drawings and tables. The embodiments described below describe a preferred example, and various design changes can be made within the scope of the technical spirit of the present invention.

1 is a block diagram exemplarily illustrating an apparatus for analyzing load power using a clustering technique according to an embodiment of the present invention. Referring to FIG. 1 , the load power analysis apparatus 100 by the clustering technique includes a smart power meter unit 110 and a load decomposition unit 130 .

The smart power meter unit 110 is installed at the consumer's power inlet point to which at least one or more load devices are connected to measure the consumer's power usage. The smart power meter unit 110 measures the power consumption of a plurality of load devices L1 to L5 connected through the smart outlet 300 .

According to an embodiment of the present invention, clustering is performed with the difference between active power and reactive power. In the received data, active power, reactive ground, reactive power, and apparent power of one or more home appliances are accumulated for 15 minutes. Therefore, there is a need to pre-process to fit the structure of the data.

The load decomposition unit 130 pre-processes the power usage data measured by the smart power meter unit 110 . Table 1 below shows an example of the power usage data preprocessed by the load decomposition unit 130 .

Referring to Table 1 above, METR_NO is the identification number of the smart power meter unit, MR_YMD is the meter reading date, MR_HHMI is the meter reading time, WHM_NDL_LP is the active power, ONEA_VAR_LP is the reactive ground power, CDNPH_VARNDL_LP is the reactive advance power, and PH_WHM_NDL_LP is the apparent power. .

In this case, the power factor means a numerical value indicating how efficiently the voltage and current actually applied work. Theoretically, when the efficiency is 100%, it can be obtained as the ratio of the active power to the total amount of power (apparent power). It is defined as power factor = active power/apparent power. A derived variable that defines the power factor based on the active power and the apparent power is added. Table 2 below is a table to which the calculated power factor is added.

A derived variable defining the calculated power factor in Table 2 is defined as factor_check. In addition, P, Q1, Q2, S, factor check, Time, holiday, Day items are defined as shown in Table 3 below.

The load decomposition unit 130 acquires active power and apparent power for each time period from the preprocessed power usage data. The load decomposing unit 140 calculates a power factor using the active power and the apparent power.

The load decomposing unit 130 may classify the power factor value according to four criteria and generate it as a factor group variable item. The factor group item created in this way can be created in the manner shown in Table 4 below.

The types of power factor values are [0.94, 0.93, 1.0, 0.96, 0.99, 0.98, 0.92] for the power factor with a frequency of 95% or more, as shown in Table 5 below, and the types of power factor values with a frequency of 95% or more are 8 in descending order. kind, the load decomposition unit 130 extracts a power factor value assuming that the daily product usage frequency is around 95% of the total.

The load decomposition unit 130 pre-processes the measured power usage data by dividing it into units or months. Table 6 below shows an example of a data set preprocessed on a daily or monthly basis.

The load decomposing unit 130 groups the measured power usage data into a plurality of clusters based on the active power, the power factor, and the meter reading time at which the active power is read. In this case, the load decomposing unit 130 adjusts the number of clusters according to a change in the size (distance) of the clustered group. Preferably, the number of clusters is determined at a critical point where the size (distance) of the clustered group rapidly decreases while increasing the number of clusters. In order to determine the number of clusters in this way, the logic shown in Table 7 below can be used.

More specifically, as shown in Table 8 below, the number of clusters at the point of sharp decrease is selected as the number for clustering by observing the size change of individual clustered groups that are formed while increasing the number of clusters as shown in Table 8 below.

When the number of clusters is determined in the above-described manner, the load decomposition unit 130 clusters the power usage data measured according to the determined number of clusters in units of days or months. Table 9 below shows examples of clustering into 6 groups.

Table 9 shows the meter reading time, active power, power factor value, and generation time for each of the six clusters. At this time, the meter reading time, active power, and power factor values of each cluster mean the median value among the power usage data constituting the cluster, and the generation time means the daily average generation time.

Table 10 shows that clusters 1, 2, and 4 are classified as homogeneous clusters, and the criterion is similarity of active power and power factor values. The sum of the average daily occurrence times of clusters 1, 2, and 4 occupies 13.2 hours, and the load device showing this power usage time pattern can be inferred as a refrigerator.

That is, the load decomposition unit 130 classifies clusters exhibiting a similar change pattern as homogeneous load devices by using the median value of active power, median value of power factor, and median value of meter reading time for each of the plurality of clusters.

By analyzing this clustered data set, if it shows a similar pattern, it can be inferred as a homogeneous load device. Referring to Table 11, the load decomposing unit 130 may classify the clusters 8 and 10 as a homogeneous load device because the effective power and power factor values are similar.

The load decomposing unit 130 may classify the corresponding cluster into four types corresponding to the corresponding power change pattern by using the change pattern of the active power and the power factor value.

The load decomposition unit 130 calculates the total operation time per day by adding up the average daily occurrence times of clusters classified as homogeneous load devices. The load decomposing unit 130 classifies the load device into one of a plurality of power change types by using the active power and the total operating time per day.

The load decomposition unit 130 divides the plurality of power change types into a first type having two power change states, a second type having a plurality of power change states, a third type having a short-term continuous power change state, and a long-term It is classified into a fourth type having a state of repetitive power change, and is classified as one of the first to fourth types. Referring to Table 12 below, four types are distinguishable as power change patterns, and additional power change patterns can be interpreted in addition to the four representative change patterns.

The load decomposing unit 130 receives a user's feedback through an application pre-installed in the user terminal 200 pre-registered as a user of the smart power meter unit 110 . The load decomposition unit 130 receives identification information about the load device acquired by the smart outlet 300 pre-installed in the consumer in which the smart power meter unit 110 is installed.

2 is a graph of four types of power patterns illustrating power characteristics of a load device. Referring to FIG. 2 , four types are divided into first to fourth types.

The first type is a type having two power change patterns consisting of a section in which the power is turned off and a section in which the power is turned on (see Fig. 2(a)),

The second type is a type having various power change patterns in an operation period (refer to FIG. 2(b) ), for example, a first period in which the power is turned off, a second period in which the power is operated with a first state level value, a second There are various types of power change patterns in the third section operating with the state level value and the fourth section operating with the third state level value.

The third type is a type showing a continuous power change pattern in a short-term operation period (refer to FIG. 2(c)). For example, it is a type in which the power change pattern is made in a short period of time in a section in which the power is turned off, a section in which the power rises to a maximum value, and a section in which the power falls to a level lower than the maximum power value section. Here, short term means several tens of minutes or several hours.

The fourth type is a type having a repetitive power change pattern in a long-term operation period (refer to FIG. 2(d)). For example, while showing a continuous power usage pattern, it shows a repeating pattern at two power levels: operating power and standby power. In the case of this fourth type, a pattern lasting from several tens of hours to several hundred hours is shown.

3 is a three-dimensional simulation diagram according to active power, power factor, and meter reading time for explaining the clustering technique of the present invention. Referring to FIG. 3 , the load decomposing unit 130 clusters the measured power usage data into 10 clusters.

At this time, the standard elements of clustering are active power, meter reading time, and power factor value, and when the characteristics of active power, power factor value, and meter reading time of 10 clusters are grouped together, the cluster is a power use section by the same load device. can be interpreted

4 is a data distribution graph for each power factor group of six clusters according to an embodiment of the present invention. Referring to FIG. 4 , data distributions of 6 groups with respect to 4 power factor groups can be confirmed.

In the case of the first cluster, about 600 power use data of the third power factor group are dense. In the case of the second cluster, 980 and 1100 data of a first power factor group and a second power factor group are distributed, respectively. In the case of the third cluster, data of the third power factor group and the fourth power factor group are distributed. In the case of the fourth cluster, data of the first power factor group and the second power factor group are distributed. In the case of the fifth cluster, data of the first power factor group, the second power factor group, and the third power factor group are distributed. In the case of the sixth cluster, data of the third power factor group and the fourth power factor group are distributed.

As shown in FIG. 4 , this is to accurately analyze the power consumption of load devices even when various load devices are included in the same cluster through data distribution analysis for a plurality of clusters by power factor group.

5 is a data distribution graph of holidays and weekdays of six clusters according to an embodiment of the present invention. Referring to FIG. 5 , the distribution of power use data on public holidays and weekdays may be checked.

In the case of the first to sixth clusters, since the distribution of power use data on holidays and weekdays can be distinguished, it is possible to distinguish which type of load device is used by analyzing this data distribution pattern.

For example, in the case of the 6th cluster shown in FIG. 5, since the distribution of power use data on weekdays is much larger than the distribution of power use data on holidays, it is estimated as a load device frequently used on weekdays, and to increase the accuracy of this estimation For this purpose, if information on characteristics of each load device is received from the user as feedback information and reflected, the corresponding load device can be inferred more precisely. If you analyze the power usage data distribution by day of the week more precisely than analyzing the power usage data distribution on weekdays or holidays, you can further improve the classification accuracy of load devices.

6 is a data distribution graph for each day of the week of six clusters according to an embodiment of the present invention. Referring to FIG. 6 , in the case of the second cluster, since the distribution of power usage data is concentrated on Saturday, it is inferred as a load device with a high frequency of use on Saturday. It is possible to classify the load device by receiving identification information of the operating load device from a device capable of identifying the type of the load device, such as an outlet.

Although the power usage data pattern shown in FIG. 6 is exemplary, when analyzing the power usage data pattern for each day of the second cluster, it is used evenly on weekdays, and power due to the use of a load device (eg, washing machine) that is frequently used on Saturdays represents a change pattern.

7 is a data distribution graph for each power factor group of four clusters according to another embodiment of the present invention. Referring to FIG. 7 , distribution characteristics for each power factor group for the first to fourth clusters can be confirmed. It can be seen that in the case of the third cluster, the distribution of power use data of the first power factor group appears, and in the remaining clusters, the distribution of power use data of the second power factor group appears.

8 is a data distribution graph of holidays and weekdays of four clusters according to another embodiment of the present invention. Referring to FIG. 8 , a specific cluster may be classified as a cluster indicating the operation characteristics of a specific load device through the power usage distribution patterns of the first to fourth clusters on holidays and weekdays.

For example, the fourth cluster may be classified as a load device having a high frequency of use on weekdays, and the second cluster may be classified as a load device having a high frequency of use on holidays. If feedback information is received from the user in order to identify the characteristics of the load device, the type of the main load device used in the cluster can be identified more accurately by using the power usage data distribution and the feedback information of the cluster.

9 is a data distribution graph for each day of the week of four clusters according to another embodiment of the present invention. Referring to FIG. 9 , since the data distribution characteristics can be confirmed for each of the four clusters by day of the week, in the case of the 10th cluster, the frequency of use tends to be high on Wednesday, so it shows the characteristics of load devices that are frequently used on Wednesday. can be analyzed as clusters.

10 is a diagram exemplarily illustrating a user interface for receiving feedback from a user terminal according to another embodiment of the present invention. Referring to FIG. 10 , if feedback information on the usage cycle, usage time, day of week, etc. is received from the user terminal for each load device and referenced in data analysis, the power change pattern in each cluster after clustering is analyzed to classify the load devices by type. It can be disassembled to analyze power consumption.

11 is a flowchart for exemplarily explaining a load power analysis method according to another embodiment of the present invention. Referring to FIG. 11 , the load power analysis method pre-processes the information of the measured power usage to calculate a power factor using the active power and apparent power for each predetermined time period and the active power and the apparent power (S1101), effective A step of clustering information on power usage measured using the power, power factor and the meter reading time for reading the corresponding active power into a plurality of clusters on a daily or monthly basis (S1103), effective for each cluster Classifying a cluster showing a similar change pattern as a homogeneous load device using the median value of power, median power factor, and median reading time (S1105), the average daily occurrence time of the cluster classified as the homogeneous load device and calculating the total daily operating time by combining them, and classifying the load device into one of a plurality of power change types by using the active power and the daily total operating time (S1107).

At this time, before and after executing step S1107, the user's feedback is received through an application pre-installed in the user terminal 200 pre-registered as a user of the smart power meter unit 110, or the smart power meter unit 110 is installed. Receiving identification information about the load device acquired by the smart outlet 300 installed in advance in the consumer (S1108) may be further executed. In addition, after step S1108, a step S1109 of updating or correcting classification information for a corresponding load device by using the user's feedback or identification information about the load device may be further performed.

100: load power analysis device
110: smart power meter unit
130: load decomposition unit
200: user terminal
300: smart outlet

Claims (10)

In the load power analysis apparatus by the clustering technique,
a smart power meter unit installed at a power inlet point of a customer to which at least one or more load devices are connected to measure the power consumption of the customer; and
Including; and a load decomposition unit for monitoring the power usage for each load device by analyzing the power usage measured by the smart power meter unit,
The load decomposition unit pre-processes the power usage data measured by the smart power meter unit to obtain active power and apparent power for each time period, and uses the active power and the apparent power to select a corresponding load device according to load power characteristics Load power analysis device by the clustering technique, characterized in that the classification.
According to claim 1,
The load decomposing unit, a load power analysis apparatus by a clustering technique, characterized in that the clustering of the measured power usage data into a plurality of clusters in units of days or months.
3. The method of claim 2,
The load decomposing unit calculates a power factor using the active power and the apparent power, and converts the measured power usage data to a plurality of clusters based on a meter reading time for reading the active power, the power factor, and the corresponding active power A load power analysis device by a clustering technique, characterized in that clustering.
4. The method of claim 3,
The load decomposing unit is a clustering technique, characterized in that for each of the plurality of clusters, a cluster showing a similar change pattern is classified as a homogeneous load device by using a median value of active power, a median value of a power factor, and a median value of a meter reading time. by load power analysis device.
5. The method of claim 4,
The load decomposing unit calculates the total daily operating time by adding up the average daily occurrence time of the clusters classified as homogeneous load devices, and divides the load device into a plurality of units using the active power and the daily total operating time. A load power analysis device by a clustering technique, characterized in that it is classified as one of the power change types.
6. The method of claim 5,
The load decomposing unit divides the plurality of power change types into a first type having two power change states, a second type having a plurality of power change states, a third type having a continuous power change state in a short period, and repetitively over a long period of time. A load power analysis apparatus according to a clustering technique, characterized in that it is classified into a fourth type having a power change state, and classified into any one of the first to fourth types.
According to claim 1,
The load decomposing unit, the load power analysis apparatus according to the clustering technique, characterized in that for receiving the feedback of the user through an application pre-installed in the user terminal pre-registered as a user of the smart power meter unit.
According to claim 1,
The load decomposing unit, load power analysis apparatus by a clustering technique, characterized in that for receiving the identification information about the load device acquired by the smart outlet pre-installed in the consumer in which the smart power meter is installed.
A smart power meter that is installed at the power inlet point of a consumer to which at least one or more load devices are connected and measures the power usage of the corresponding consumer, and the power consumption measured by the smart power meter unit are analyzed to determine the power consumption for each load device In the load power analysis method using a load power analysis device by a clustering technique including a load decomposing unit to monitor,
The load decomposing unit may include: preprocessing the information of the measured power usage to calculate a power factor using an active power and an apparent power for each predetermined time period, and the active power and the apparent power;
The load decomposing unit clustering the measured power usage information into a plurality of clusters on a daily or monthly basis by using the active power, the power factor, and a meter reading time for reading the active power. ;
classifying, by the load decomposing unit, clusters exhibiting a similar change pattern into homogeneous load devices using a median value of active power, a median power factor, and a median reading time for each of the plurality of clusters; and
The load decomposing unit calculates the total daily operating time by adding up the average daily occurrence time of the clusters classified as the same load devices, and collects a plurality of corresponding load devices using active power and the total daily operating time. classifying it as one of the power change types of
The load decomposing unit divides the plurality of power change types into a first type having two power change states, a second type having a plurality of power change states, a third type having a continuous power change state in a short period, and repetitively over a long period of time. Load power analysis method, characterized in that it is classified into any one of the fourth type having a power change state.
10. The method of claim 9,
The load decomposing unit may receive user feedback through an application pre-installed on a user terminal registered in advance as a user of the smart power meter unit, or identify a load device acquired by a smart outlet pre-installed in a consumer in which the smart power meter unit is installed. receiving information; and
Load power analysis method, characterized in that for updating the classification information for the load device by using the user's feedback or the identification information about the load device.

Images