KR102634639B1 - Smart advanced metering infrastructure system capable of checking leakage type and leakage amount based on clustering - Google Patents

Abstract

The operation server included in the smart AMI system is launched. The operation server includes a data receiving unit configured to receive target meter reading data related to water use by target customers, reference meter reading data related to water use by reference customers where actual water leaks occurred, and data storage configured to store reference water leakage amount data indicating the amount of water leakage. By generating a target usage vector for the target consumer from the copied and received target meter reading data, and classifying the target usage vector into one of a plurality of clusters, each of which includes reference usage vectors corresponding to reference meter reading data, It includes a water leak type determination unit configured to determine the water leak type of the target customer.

Description

Smart AMI system capable of determining water leaks or leaks based on clustering and operation server included therein {SMART ADVANCED METERING INFRASTRUCTURE SYSTEM CAPABLE OF CHECKING LEAKAGE TYPE AND LEAKAGE AMOUNT BASED ON CLUSTERING}

Embodiments of the present invention relate to a smart AMI system capable of determining leakage or water leakage and an operating server included therein.

Water and gas are essential elements in life. Water used in each home is supplied from a water purification plant to each home through water pipes, and gas is also supplied to each home through gas pipes.

Meanwhile, these water and gas fees (i.e., public service fees) are calculated based on the amount actually used in each home, and a meter is installed in each home to calculate the amount of usage.

In the conventional case, the fee is set by checking the scale (or number) written on the meter through a visit by a meter reader or self-reading. However, this method not only requires a lot of labor, but also has the problem that errors may occur during the meter reading process.

Accordingly, recently, the advanced metering infrastructure (AMI) method, which transmits usage wired or wirelessly using electronic meters, etc., has become widely popular. This AMI method is not only accurate because it can measure each household's usage in real time, but also has the advantage of being able to easily collect data related to each household's water and gas usage, providing a variety of information by analyzing the data. there is.

The problem to be solved by the present invention is to provide a smart AMI system capable of determining leakage or water leakage and an operation server included therein.

The operating server included in the smart AMI system according to embodiments of the present invention includes a data receiver configured to receive target meter reading data related to water use by target customers, reference meter reading data related to water use by reference customers where actual water leaks occurred, and A data storage unit configured to store reference water leakage amount data representing the water leakage amount and generating a target usage vector for the target customer from the received target meter reading data, each of the target usage vectors including reference usage vectors corresponding to the reference meter reading data. It includes a water leak type determination unit configured to determine the water leak type of the target customer by classifying it into one of the plurality of clusters.

Depending on embodiments, the target meter reading data and the reference meter reading data may include information on the flow rate of water inside the customer's water pipe, the amount of water used by the customer, and the pressure of water inside the customer's water pipe.

According to embodiments, the water leak type determination unit may generate a target usage feature vector from target meter reading data according to the following equation.

[Equation]

(UV represents the target usage vector, U _i (i=0, ??, N, N is a natural number) represents the number usage of target customers in the water leak determination section, and {0, 1, ??, N} is It is an index sequentially indicating the standard time zone of each day during the water leak determination section, where 0 represents the starting point of the water leak determination section, N represents the end point of the water leak determination section, U ₀ is the initial value of water usage in the water leak determination section, and U _N is the end value of water usage in the water leak determination section, U _m is the minimum value of water usage in the water leak determination section, U _M is the maximum value of water usage in the water leak determination section, is the first slope, represents the second slope. Here, m and M are indices within the water leak determination section, which are indices indicating the minimum and maximum water usage days, respectively.)

According to embodiments, the water leak type determination unit determines the time at which the lowest usage occurs most frequently among each hour of the day for a target customer as a reference time zone, and determines the target customer's water usage and the lowest usage in the reference time zone. The point where the actual water usage, which is the difference in usage, exceeds the standard value is considered the starting point of the water leak determination section, and the point where the actual water usage does not exceed the standard value for the first time after the point of the water leak determination section is taken as the end point of the water leak determination section. can do.

According to embodiments, the operation server further includes a leakage amount determination unit configured to determine target reference customers having the same leakage type as the target customer among reference customers and estimate the leakage amount of the target customer based on the reference leakage amount of the target reference customers. can do.

The smart AMI system according to embodiments of the present invention receives target meter reading data from a smart sensor and a smart sensor configured to generate target meter reading data related to the water use of the target consumer, and determines the water leak type of the target consumer from the target meter reading data. and an operation server configured to generate a target usage vector for a target customer from the received target meter reading data, and place the target usage vector among a plurality of clusters, each of which includes reference usage vectors of reference customers. By classifying into one cluster, the type of leakage of the target customer is determined.

Depending on embodiments, the target meter reading data and the reference meter reading data may include information on the flow rate of water inside the customer's water pipe, the amount of water used by the customer, and the pressure of water inside the customer's water pipe.

According to embodiments, the operation server may generate a target usage feature vector from target meter reading data according to the following equation.

[Equation]

(UV represents the target usage vector, U _i (i=0, ??, N, N is a natural number) represents the number usage of target customers in the water leak determination section, and {0, 1, ??, N} is It is an index sequentially indicating the standard time zone of each day during the water leak determination section, where 0 represents the starting point of the water leak determination section, N represents the end point of the water leak determination section, U ₀ is the initial value of water usage in the water leak determination section, and U _N is the end value of water usage in the water leak determination section, U _m is the minimum value of water usage in the water leak determination section, U _M is the maximum value of water usage in the water leak determination section, is the first slope, represents the second slope. Here, m and M are indices within the water leak determination section, which are indices indicating the minimum and maximum water usage days, respectively.)

According to embodiments, the operation server determines the time at which the lowest usage occurs most frequently among each hour of the day for the target consumer as a standard time zone, and determines the target consumer's water usage and minimum usage in the standard time zone. The point at which the actual water consumption exceeds the standard value, which is the difference between You can.

According to embodiments, the operation server may determine target reference customers having the same leakage type as the target customer among reference customers and estimate the leakage amount of the target customer based on the reference leakage amount of the target reference customers.

According to embodiments of the present invention, when a water leak occurs, a customer who uses water can be charged a fee based on the actual water usage with the water leakage amount deducted, even if no major construction is performed to diagnose and analyze the water leak. there is.

According to embodiments of the present invention, a water leak determination section is determined from the customer's actual water usage amount, and feature values related to the water use amount in the water leak determination section are extracted to calculate a usage vector, so that the usage vector determines the user's water usage pattern. There is an effect that can be expressed accurately.

According to embodiments of the present invention, unlike the prior art, which requires a lot of effort and time to check for water leaks and calculate the amount of water, when a water leak occurs, not only can the type of water leak be determined based on data related to water use, but also the amount of water can be estimated. This has a possible effect.

In addition, embodiments of the present invention have the effect of being applicable to gas leak confirmation and leak amount calculation.

Figure 1 shows a smart AMI system according to embodiments of the present invention.
Figure 2 shows a smart sensor according to embodiments of the present invention.
Figure 3 shows an operating server according to embodiments of the present invention.
Figure 4 is a diagram for explaining the process of calculating a usage vector according to embodiments of the present invention.
Figure 5 is a diagram for explaining clustering according to embodiments of the present invention.
Figure 6 is a diagram for explaining a method of estimating the amount of water leakage according to embodiments of the present invention.
Figure 7 is a flow chart showing a method of operating an operation server according to embodiments of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings.

The examples are provided to more completely explain the present invention to those skilled in the art, and the following examples may be modified in various other forms, and the scope of the present invention is limited to the following examples. It is not limited. Rather, these embodiments are provided to make the disclosure more faithful and complete and to fully convey the spirit of the invention.

The terms used herein are used to describe specific embodiments and are not intended to limit the invention. Additionally, in this specification, singular forms may include plural forms, unless the context clearly indicates otherwise.

In the description of the embodiment, each layer (film), region, pattern or structure is said to be formed “on” or “under” the substrate, each layer (film), region, pad or pattern. When described, “on” and “under” include those formed “directly” or “indirectly” through another layer. In addition, in principle, the standards for the top or bottom of each floor are based on the drawing.

The drawings are only intended to enable understanding of the spirit of the present invention, and should not be construed as limiting the scope of the present invention by the drawings. Additionally, in the drawings, relative thickness, length, or relative size may be exaggerated for convenience and clarity of explanation.

Figure 1 shows a smart AMI system according to embodiments of the present invention. Referring to FIG. 1, the smart AMI system 10 may receive meter reading data of customers (TU, RU) from smart sensors 210 installed in each customer (TU, RU). In addition, the smart AMI system 10 uses the meter reading data of customers (TU, RU) to determine whether there is a water leak (or leakage, hereinafter the same) or the amount of water leakage (or leakage amount, hereinafter the same) of the target customer (TU). You can. For example, the smart AMI system 10 uses meter reading data related to water or gas use of customers (TU, RU) to determine whether there is a water leak (or leak, hereinafter the same) or the amount of water leak (or leak amount, hereinafter) of the target customer (TU). (same) can be judged.

Embodiments of the present invention relate to confirmation of water leakage or gas leakage (e.g., determination of type or determination of leakage amount) using data related to the use of water or gas used in the target unit (TU). . However, for convenience of explanation, the explanation below will focus on 'water', but it should be understood that the explanation below can be applied to 'gas' as well as 'water'. For example, in the following, 'water usage' may correspond to 'gas usage', and 'water leakage' may correspond to 'gas leakage'.

The smart AMI system 10 may include an operation server 100 and water meter readers 210 installed in each customer (TU, RU).

In this specification, the term “customer” means a household or entity that uses water, such as a home (house, apartment, etc.) or a company, but is not limited thereto. In addition, the target customer (TU) refers to the customer who is the target of the water leak type and water leak amount determination (hereinafter referred to as 'leakage determination') by the operation server 100, and the reference customer (RU) refers to the target customer (TU). These are the customers who respond to the data required to determine water leakage, and are customers for whom actual water leakage has occurred and for whom the water leak has been inspected and analyzed. Reference recipients (RU) may be plural.

The operation server 100 can control the overall operation of the smart AMI system 10. According to embodiments, the operation server 100 may receive meter reading data associated with the water use of each customer (TU, RU) from the water meter readers 210 installed in the customers (TU, RU).

According to embodiments, the operation server 100 may store the received meter reading data and perform water leak determination for the target customer unit (TU) using the stored meter reading data. For example, the operation server 100 may estimate the water leak type of the target customer (TU) and the water leak amount according to the water leak type.

Here, the type of water leak is determined in advance and may include, for example, an internal water pipe water leak, an external water pipe water leak, and a water use water leak. Internal water pipe leakage is a leak that lasts for a long time with a relatively small amount of water, while external water pipe leakage refers to a water leak that lasts for a long time with a relatively small amount of water. Water use leaks are a water leak that appears over a specific period of time with a relatively small amount of water. This is a visible water leak. There may also be other types of leaks.

The smart sensor 210 is installed in each customer (TU, RU) and can collect and generate data related to the customer's water use. Depending on embodiments, the smart sensor 210 may include a water meter and a pressure sensor. The smart sensor 210 can collect and generate data in real time or at predetermined intervals.

Data (meter reading data and water pressure data) generated by the smart sensor 210 may be transmitted directly to the operation server 100, or may be transmitted to the operation server 100 through the repeater 220. In this case, the smart sensor 210 and the repeater 220 exchange data with each other through short-range wireless communication or wired communication, and the repeater 220 and the operation server 100 exchange data with each other through mid- to long-distance wireless communication. You can. Although the repeater 220 is shown in FIG. 1 as being included in the smart AMI system 10, for the above reason, the repeater 220 may be omitted from the smart AMI system 10.

The repeater 220 is an electronic device capable of transmitting and receiving data, and may be, for example, a modem. There is one repeater 220 for each of the consumers (TU, RU) and may be in charge of relaying the data generated from the smart sensor 210 of each consumer (TU, RU). However, depending on the embodiment, One repeater 220 may be responsible for the smart sensors 210 of a plurality of customers (TU, RU).

Figure 2 shows a smart sensor according to embodiments of the present invention. Referring to FIG. 2, the smart sensor 210 includes a water meter 211 and a pressure sensor 213.

The water meter 211 can measure the water flow rate and amount of drainage inside the water pipe of the installed customer (TU, RU), that is, water usage, and generate and transmit meter reading data including the measurement results. At this time, the water flow rate may be a value measured at each point in time, and the water usage amount may be an accumulated value from a reference point in time (eg, the beginning of each month) to the current point in time. Accordingly, the meter reading data generated by the water meter 211 may be data including information on the water flow rate measured at the current point in time and the amount of water used up to the current point in time.

The pressure sensor 213 may measure the pressure or water pressure of water flowing inside the water pipe of the customer (TU, RU), and generate and transmit water pressure data according to the measurement results. However, in order to maintain the same measurement standard, the pressure sensor 213 may be measured inside the water pipe at a specific point based on the water meter 211.

Depending on the embodiment, the pressure sensor 213 may be installed on the inner wall of the water pipe of the customer (TU, RU). For example, the pressure sensor 213 may be a MEMS (micro electro mechanical system) sensor, but is not limited thereto.

Figure 3 shows an operating server according to embodiments of the present invention. Referring to Figure 3, the operation server 100 may include a data reception unit 101, a data storage unit 103, a water leak type determination unit 105, a water leak amount determination unit 107, and a usage correction unit 109. there is. Meanwhile, each of the components 101, 103, 105, 107, and 109 shown in FIG. 3 represents functional components of the operation server 100 according to embodiments of the present invention, and each of the components 101, 103, and 105 , 107, 109) may be implemented as a processor configured to perform a predetermined operation by executing a memory and instructions stored in the memory.

The data receiver 101 may receive data from the smart sensor 210 or the repeater 220. However, for convenience of explanation, this specification assumes that the data receiving unit 101 receives data directly from the smart sensor 210. The data receiver 101 may receive data by periodically communicating with the smart sensor 210 over a wireless network.

The data receiver 101 may receive meter reading data and water pressure data for each customer (RU, TU) from the smart sensor 210. At this time, the meter reading data and water pressure data received by the data receiving unit 101 may be arranged in time series order.

The data storage unit 103 may store reference customer unit (RU) meter reading data and water pressure data. Additionally, the data storage unit 103 may store reference water leakage data related to the actual water leakage of the reference customer (RU). Reference leakage data includes information on the type and amount of leakage for each reference unit (RU). At this time, the amount of water leakage may be the amount of water per unit time, but is not limited thereto.

The water leak type determination unit 105 may determine the water leak type for the target customer (TU). Here, the water leak type also includes no water leak.

The water leak type determination unit 105 uses the meter reading data of the customers (RU, TU) to generate a usage vector representing the characteristics of the water supply of each of the consumers (RU, TU), and uses the generated usage vector, The type of leakage of the target customer (TU) can be determined. At this time, the water leak type determination unit 105 may use the usage vector for a predetermined period (eg, June) to determine the water leak type of the target customer unit (TU) during the predetermined period.

According to embodiments, the leak type determination unit 105 is composed of reference usage vectors of reference users (RU) using a clustering engine, and among the clusters each corresponding to each leak type, the target user (TU) By determining the target usage vector for and the corresponding target cluster, the type of leakage of the target user (TU) can be determined. In this case, the leak type corresponding to the target cluster becomes the leak type of the target customer (TU).

For example, the clustering engine may perform clustering according to a Gaussian Mixture Model (GMM) or clustering according to the K-means algorithm. Here, the K-means algorithm, unlike the Gaussian mixture model, may be a machine learning-based clustering technique that belongs to unsupervised learning.

Specifically, the K-means algorithm sets a vector value corresponding to the initial center point for each of the K clusters and then assigns the customers' usage vectors to clusters with an initial center point close to the usage vector representing each customer. Next, when the cluster allocation for all usage vectors is completed, the center point of each cluster is reset to the median or average value of the usage vectors belonging to the cluster, and the cluster allocation of all customers' usage vectors is again based on the reset center point. Implement. Customers can be assigned to a plurality of clusters by repeating the above-described center point resetting and cluster reallocation until there is no change in the center point.

The water leak amount determination unit 107 uses the water leak type determined by the water leak type decision unit 105 and the data of reference customers of the water leak type to determine (or estimate) the water leak amount in the water leak type of the target customer (TU). can do. According to embodiments, the water leakage amount determination unit 107

The usage correction unit 109 may correct the water usage of the target TU by using the water leakage amount of the determined target TU. According to embodiments, the usage correction unit 109 may correct the water usage by calculating the actual water usage excluding water leakage from the water usage of the target customer unit (TU).

Accordingly, when a water leak occurs, each customer can receive a fee calculated based on the actual water usage with the water leakage amount deducted, even if no major construction work is done to diagnose and analyze the water leakage.

Figure 4 is a diagram for explaining the process of calculating a usage vector according to embodiments of the present invention. Referring to FIG. 4, the water leak type determination unit 105 may generate a usage vector using meter reading data of customers (TU, RU). The usage vector is a variable that characterizes the water usage of customers (TU, RU) in a predetermined period, and can be generated, for example, from the water usage of customers (TU, RU) measured in a reference time period.

According to embodiments, the water leak type determination unit 105 uses meter reading data of customers (TU, RU) to determine a reference time zone for generating a usage vector, and uses the distribution of water usage amounts in the standard time zone to determine the usage amount. Vectors can be created. At this time, the usage vector for each consumer (TU, RU) is generated based on the meter reading data of the corresponding consumer (TU, RU).

First, the water leak type determination unit 105 calculates the water usage amount for each hour of the day by the customer (TU, RU), and determines the time at which the lowest usage occurs most frequently among each hour of the day during a predetermined period as the reference time. And, the average water usage in the standard time zone can be determined as the minimum usage (MU). For example, if the lowest water usage was most often at 03:00 for two months, the reference time period may be 03:00 (or 03:00 to 04:00).

For example, in Figure 4, the water usage amount of each customer in the daily standard time zone is shown as each dot, and a dotted line corresponding to the minimum water usage amount (MU) is shown.

Thereafter, the water leak type determination unit 105 determines the water leak determination section (LKP) based on the water usage amount of customers (TU, RU) in the reference time period during the period subject to water leak determination (i.e., water leak determination period). You can. At this time, the point of the water leak determination section (LKP) is the point when the difference (i.e., actual water usage) between the water usage of the customer (TU, RU) and the minimum usage (MU) in the standard time zone exceeds the standard value, and the water leakage The end point of the determination section (LKP) is the point at which the actual water usage does not exceed the standard value for the first time after the point of the water leak determination section (LKP). If the actual water usage exceeds the standard value until the end of the water leak determination period, the end point of the water leak determination section (LKP) becomes the same as the end point of the water leak determination period.

The water leak type determination unit 105 uses the initial value, end value, maximum value, minimum value, start-end slope, and minimum-maximum slope of the actual water usage of customers (TU, RU) in the water leak determination section (LKP) as components. You can create a usage vector containing: For example, referring to Figure 4, the first point (P1) represents the initial value of water usage in the water leak determination section (LKP), and the second point (P2) represents the end of water usage in the water leak determination section (LKP). value, the third point (P3) represents the minimum value of water usage in the water leak determination section (LKP), the fourth point (P4) represents the maximum value of water usage in the water leak determination section (LKP), and The first slope (A1) represents the slope between the initial and end values of water usage in the water leak determination section (LKP), and the second slope (A2) represents the minimum and maximum values of water usage in the water leak determination section (LKP). represents the slope between

That is, the water leak type determination unit 105 can generate a usage vector for each customer according to Equation 1.

Here, UV represents the usage vector, U _i (i=0, ??, N, N is a natural number) represents the water usage of each customer (TU, RU) in the water leak determination section (LKP), and {0, 1, ??, N} is an index sequentially indicating the reference time zone of each day during the water leak determination section (LKP), 0 represents the starting point of the water leak judgment section (LKP), and N represents the end point of the water leak judgment section (LKP). . U ₀ is the initial value of water usage in the water leak determination section (LKP), U _N is the end value of water usage in the water leak determination section (LKP), and U _m is the water usage amount in the water leak determination section (LKP). is the minimum value, and U _M is the maximum value of water usage in the water leak determination section (LKP), is the first slope, represents the second slope. Here, m and M are indices within the water leak determination section (LKP), and are indices indicating the dates when water usage will be minimum and maximum, respectively.

According to embodiments of the present invention, the lowest water usage of the consumer (TU, RU) can be determined, the actual water usage of the consumer (TU, RU) can be determined from this, and a usage vector can be calculated based on the actual water usage. there is. Furthermore, according to embodiments of the present invention, a water leak determination section (LKP) is determined from the actual water usage amount of the customer (TU, RU), and feature values related to the water use amount in the water leak determination section (LKP) are extracted to create a usage vector. Since , the usage vector has the effect of accurately representing the number of users (TU, RU) and usage patterns.

The water leak type determination unit 105 may store the usage vector of each customer (TU, RU) generated according to Equation 1 above. At this time, the reference number vector of the reference audience (RU) may be created and stored in advance, and the target number vector of the target audience (TU) may be generated and stored in real time or in advance.

Figure 5 is a diagram for explaining clustering according to embodiments of the present invention. Referring to FIG. 5, the water leak type determination unit 105 uses a clustering engine to classify the usage vector (UV) of the customer (TU, RU) into one of a plurality of clusters (CLU), and the usage vector (UV) is By determining the cluster to which it belongs, the leakage type (LKTYPE) of the target customer (TU) can be determined.

In other words, the usage vector of customers (TU, RU) represents the number usage pattern of customers (TU, RU). Since this water usage pattern also includes information about the water leak type, the water leak type determination unit 105 can appropriately classify or cluster the customers (TU, RU) by water leak type by clustering these usage vectors according to a predetermined standard. there is.

At this time, in order to save resources required for clustering, usage vectors of reference users (RUs) may be calculated in advance from the meter reading data of the reference users (RUs) and stored.

Meanwhile, the clustering engine may be based on a Gaussian mixture model. For example, in the case of a Gaussian mixture model, each of the K pre-specified Gaussian distributions (K is a natural number greater than 1) corresponds to a cluster. It operates to classify customers (or usage vectors) into one of K Gaussian distributions. Specifically, in the case of a clustering engine, classification can be done by selecting the Gaussian distribution with the highest result of a given Gaussian distribution selection function among K Gaussian distributions using Bayes' theorem.

According to this clustering, the water leak type determination unit 105 may classify the usage vectors of customers (TU, RU) into a plurality of clusters. According to the principle of clustering, usage vectors with similar properties are classified into one cluster, and as a result, usage vectors with the same or similar leak types (LKTYPE) are classified into one cluster. Accordingly, each cluster (CLU) according to clustering corresponds to a leak type, and the usage vectors (UV) or consumers (TU, RU) belonging to each cluster (CLU) are considered to have the same leak type (LKTYPE). I understand.

After clustering, the water leak type determination unit 105 may determine a reference customer (RU) having a water leak type corresponding to (i.e., the same as) the water leak type of the target customer (TU). At this time, the reference consumers (RUs) included in the cluster to which the target consumer (TU) is assigned will soon have a leak type that corresponds to (i.e., is the same as) the leak type of the target user (TU).

Figure 6 is a diagram for explaining a method of estimating the amount of water leakage according to embodiments of the present invention. Referring to FIG. 6, the water leakage amount determination unit 107 may estimate the water leakage amount (LK) for the target customer (TU) based on the reference water leakage amount of reference customers having the same water leak type as the water leakage type of the target customer (TU). there is.

According to embodiments, the water leak amount determination unit 107 selects a water leak type included in the same cluster (CLU) as the target customer (TU), that is, the same water leak type as the target customer (TU), among the reference customers (RU). The reference customers (RU1, RU2, ??, RUk; k is a natural number) can be determined. This can be determined during the clustering process. Hereinafter, these reference customers (RU1, RU2, ??, RUk) are referred to as target reference customers.

The water leakage amount determination unit 107 may estimate (or determine) the water leakage amount of the target customer base (TU) using data related to the determined target reference customers. According to embodiments, the water leakage amount determination unit 107 may determine the water leakage amount of the target customer (TU) based on the reference water leakage amounts (RLK1, RLK2, ??, RLKk) of each of the target reference customers.

For example, the water leakage amount determination unit 107 may determine the water leakage amount of the target customer (TU) according to Equation 2 below.

[Equation 2]

Here, LK is the leakage amount of the target audience (TU), a is the weight corresponding to the target audience (TU), and a _i is the weight corresponding to the ith target reference audience (RUi; i is a natural number from 1 to k). , RLKi is the reference leakage amount of the ith target reference users (RUi), and p is the leakage type coefficient of the cluster to which the usage vector of the target user (TU) belongs, and may be a predetermined value for each leakage type.

Meanwhile, with regard to the water leak type coefficient, the water leak type coefficient is a value determined for each cluster, and is the second slope (between the minimum and maximum values of water usage in the water leak determination section (LKP)) among the components of the representative usage vector representing the cluster. A value determined as a function of (slope of), for example, may be a value determined according to Equation 3 below, but is not limited thereto.

[Equation 3]

Here, p _j is the leak type coefficient for the j-th cluster, c is a positive constant, and A2 _j represents the second gradient component of the representative usage vector of the j-th cluster. Here, the representative usage vector may be a vector whose components are representative values (eg, average values) of each component of usage vectors included in the class.

In addition, the weight a _i in Equation 2 is a value determined by the properties of the target reference customers (RU1, RU2, ??, RUk) included in the corresponding cluster (CLU), and the target reference customers (RU1, RU2, It can be determined based on the water pressure of ??, RUk) and the minimum value of water usage in the water leakage determination section. For example, the weight a _i can be determined according to Equation 4 below.

[Equation 4]

Here, di is a positive constant, P _i is the water pressure of the ith target reference customers (RUi), and U _m,i is the minimum value of water usage in the water leakage determination section of the ith target reference customers (RUi). indicates. At this time, pressure P _i may mean the average pressure in the reference time period during the water leakage determination period of the relevant customer (RUi). Meanwhile, in Equation 4, when i=0, it can be understood as an equation applied to the target audience (TU). That is, a ₀ =a.

As above, according to the embodiments of the present invention, it is possible to estimate the water leakage amount of the target customer (TU) using the water leakage amount and other data of the target reference customers (RU1, RU2, ??, RUk). In particular, when a water leak occurs, it takes a lot of time and effort to check the water leak and calculate the amount of water leak. In this case, water charges are usually calculated based on the amount of water used previously. According to embodiments of the present invention, when a water leak occurs, it is possible to not only determine the type of water leak based on data related to water use, but also estimate the amount of water leak.

In particular, according to embodiments of the present invention, when estimating the water leakage amount of the target customer (TU), individual characteristics of each customer, such as the pressure of each customer and the usage amount (lowest) in the water leak determination section, are taken into consideration, which has the effect of enabling a more accurate estimate of the water leakage amount. .

Figure 7 is a flow chart showing a method of operating an operation server according to embodiments of the present invention. Referring to FIG. 7, the operation server 100 receives target meter reading data related to water usage by the target customer (TU) (S110). Depending on the embodiment, the operation server 100 may receive target meter reading data through a smart sensor 210 installed in the target customer unit (TU) or through a repeater 220 linked to the smart sensor 210. . The target meter reading data may include data related to the water use of the target customer (TU), for example, information on the flow rate of water inside the water pipe of the target customer (TU), water usage amount, water pressure, etc.

The operation server 100 may store the reference usage vector of the reference number of users (RU) (S120). According to embodiments, the operation server 100 may generate and store a reference usage vector from reference meter reading data of a reference customer unit (RU). The reference usage vector can be created in the same way as the target usage vector described later.

The operation server 100 may generate a target usage vector (S130). Depending on embodiments, the operation server 100 may analyze target meter reading data and generate a target usage vector. For example, the operation server 100 may analyze target meter reading data to determine a water leak determination section and generate a target usage vector using meter reading data belonging to the water leak determination section.

The operation server 100 may determine the water leak type of the target customer (TU) through clustering (S140). According to embodiments, the operation server 100 may classify these vectors into one of a plurality of clusters, each corresponding to a leak type, by clustering the target usage vector and the reference usage vector. According to clustering, the target usage vector belongs to one cluster, and the leak type indicated by the cluster is determined as the leak type of the target customer (TU).

The operation server 100 may estimate the leakage amount of the target customer (TU) based on the reference leakage amount of reference customers (i.e., target reference customers) belonging to the cluster corresponding to the leakage type of the target customer (TU) ( S150). According to embodiments, the operation server 100 may estimate the water leakage amount of the target customer (TU) by calculating based on the reference water leakage amount of the reference customers.

As described above, according to the embodiments of the present invention, it is possible to estimate the water leakage amount of the target customer (TU) using the water leakage amount and other data of the target reference customers. In particular, when a water leak occurs, it takes a lot of time and effort to check the water leak and calculate the amount of water leak. In this case, water charges are usually calculated based on the amount of water used previously. According to embodiments of the present invention, when a water leak occurs, it is possible to not only determine the type of water leak based on data related to water use, but also estimate the amount of water leak.

The above description is merely an illustrative explanation of the technical idea of the present invention, and various modifications and variations will be possible to those skilled in the art without departing from the essential characteristics of the present invention. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but are for illustrative purposes, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be construed as being included in the scope of rights of the present invention.

The device (unit) described above may be implemented with hardware elements and/or software elements. For example, hardware elements may include microphones, amplifiers, bandpass filters, A/D converters, and processing devices. Processing devices include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), and a programmable logic unit (PLU). , a microprocessor, or other devices capable of responding to and executing instructions in a defined manner, may be implemented using one or more general-purpose or special-purpose computers. The processing device may run an operating system (OS) and one or more software applications running on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the sake of brevity, the processing device may be described as one, but those skilled in the art will recognize that the processing device may include multiple processing elements and/or multiple types of processing elements. can be seen. For example, a processing device may include a plurality of processors or a processor and a controller. Additionally, other processing configurations, such as parallel processors, are possible.

Software may include computer programs, code, instructions, or combinations thereof, which may independently or collectively configure or instruct a processing device to operate as desired. Software and data are defined as propagated signal waves that can be interpreted by or provide instructions or data to a processing device, or as various types of machines, components, physical devices, or virtual devices. It may be embodied permanently or temporarily in computer storage media or devices, etc. Software may be distributed over networked computer systems, so that it can be stored and executed in a distributed manner. The software and data may be stored in one or more computer-readable recording media, including a data storage device that stores data so that it can be later read by a computer system or processing device. The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. Magnetic media such as hard disks, floppy disks, and magnetic tapes; optical media such as CD-ROMs and DVDs; and magneto-optical media such as floptical disks. ), and hardware devices specifically configured to store and perform program instructions, such as ROM, RAM, flash memory, etc. Additionally, 7, the functional programs, code, and code segments that complete the examples disclosed herein can be created by a programmer of ordinary skill in the art related to these examples based on or using the drawing flow diagrams and block diagrams and related descriptions provided herein. It is easy to understand and implement.

Although it may not be universal, the terminals or devices described herein include cellular phones, PDAs, digital cameras, portable game consoles, MP3 players, portable/personal multimedia players (PMPs), portable e-books, portable laptop PCs, and GPS. It can be applied to mobile devices such as navigation systems, tablets, sensors, desktop PCs, HDTVs, optical disc players, set-top boxes, home appliances, and devices capable of wireless or network communication.

Additionally, the computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and usable by those skilled in the art of computer software. Examples of program instructions include machine language code, such as that created by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although several embodiments have been described above, it should be understood that various modifications can be made. For example, appropriate results may be achieved if the techniques described are performed in a different order and/or if elements of the described system, structure, device, circuit, etc. are combined in a different way, or if replaced or supplemented by other elements or equivalents. It can be. Accordingly, other implementations also fall within the scope of the claims described below.

TU: Target audience RU: Reference audience
100: Operation server 210: Smart sensor
220: repeater

Claims (10)

a data receiving unit configured to receive target meter reading data related to water use by target consumers;
a data storage unit configured to store reference meter reading data related to water use by reference customers where actual water leakage occurred and reference water leakage amount data indicating the water leakage amount; and
By generating a target usage vector for the target consumer from the received target meter reading data, and classifying the target usage vector into one of a plurality of clusters, each of which includes reference usage vectors corresponding to reference meter reading data, Comprising a water leak type determination unit configured to determine the water leak type of the target customer,
The target meter reading data and the reference meter reading data are,
Contains information on the flow rate of water inside the customer's water pipe, the amount of water used by the customer, and the pressure of water inside the customer's water pipe,
The water leak type determination unit,
Generating the target usage vector from the target meter reading data according to the equation below,

(UV represents the target usage vector, U _i (i=0, ..., N, N is a natural number) represents the water usage of the target customer in the water leak determination section, {0, 1, ..., N} is an index that sequentially represents the standard time zone of each day during the water leak determination section, 0 represents the starting point of the water leak determination section, N represents the end point of the water leak judgment section, and U ₀ is the initial value of water usage in the water leak determination section. , U _N is the end value of water usage in the water leak determination section, U _m is the minimum value of water usage in the water leak determination section, U _M is the maximum value of water usage in the water leak determination section, is the first slope, represents the second slope. Here, m and M are indices within the water leak determination section, which are indices indicating the minimum and maximum water usage days, respectively.)
Operational server. delete delete The method of claim 1, wherein the water leak type determination unit,
For the target consumer, the time when the lowest usage occurs most frequently among each hour of the day during a predetermined period is determined as the standard time,
The point in time when the actual water usage amount, which is the difference between the water usage amount of the target consumer in the standard time zone and the minimum usage amount, exceeds the standard value is set as the point in time of the water leak determination section,
The point at which the actual water usage does not exceed the reference value for the first time after the point in time of the water leak determination section is set as the end point of the water leak determination section,
Operational server. According to paragraph 1,
The operation server further includes a water leakage amount determination unit configured to determine target reference customers having the same leakage type as the target customer among the reference customers and estimate the water leakage amount of the target customer based on the reference leakage amount of the target reference customers. doing,
Operational server. A smart sensor configured to generate targeted meter reading data related to water usage by target consumers; and
An operation server configured to receive the target meter reading data from the smart sensor and determine a water leak type of the target customer from the target meter reading data,
The operating server is,
By generating a target usage vector for the target customer from the received target meter reading data and classifying the target usage vector into one of a plurality of clusters, each of which includes reference usage vectors of reference customers, the target customer Determine the type of water leak,
The target meter reading data is,
Contains information on the flow rate of water inside the customer's water pipe, the amount of water used by the customer, and the pressure of water inside the customer's water pipe,
The operating server is,
Generating the target usage vector from the target meter reading data according to the equation below,

(UV represents the target usage vector, U _i (i=0, ..., N, N is a natural number) represents the water usage of the target customer in the water leak determination section, {0, 1, ..., N} is an index that sequentially represents the standard time zone of each day during the water leak determination section, 0 represents the starting point of the water leak determination section, N represents the end point of the water leak judgment section, and U ₀ is the initial value of water usage in the water leak determination section. , U _N is the end value of water usage in the water leak determination section, U _m is the minimum value of water usage in the water leak determination section, U _M is the maximum value of water usage in the water leak determination section, is the first slope, represents the second slope. Here, m and M are indices within the water leak determination section, which are indices indicating the dates when water usage is minimum and maximum, respectively),
Smart AMI system. delete delete The method of claim 6, wherein the operating server,
For the target consumer, the time when the lowest usage occurs most frequently among each hour of the day during a predetermined period is determined as the standard time,
The point in time when the actual water usage amount, which is the difference between the water usage amount of the target consumer in the standard time zone and the minimum usage amount, exceeds the standard value is set as the point in time of the water leak determination section,
The point at which the actual water usage does not exceed the reference value for the first time after the point in time of the water leak determination section is set as the end point of the water leak determination section,
Smart AMI system. The method of claim 6, wherein the operating server,
Determining target reference customers having the same leakage type as the target customer among the reference customers, and estimating the leakage amount of the target customer based on the reference leakage amount of the target reference customers,
Smart AMI system.