KR20210089944A - Apparatus and method for estimating outage damage cost for electricity customer - Google Patents

Abstract

The present invention relates to an apparatus for estimating an outage damage cost for electricity customers, which recognizes an identification code for each sub-industry and estimates a precise outage damage cost through a linear transformation model for each sub-industry, and a method thereof. The present invention relates to the apparatus comprises: an industry classification unit categorizing detailed industries of customers who responded to a survey on the basis of survey result data; a hierarchical classification unit classifying a hierarchy on the basis of a classification result of the industry in the industry classification unit; a linear transformation unit linearly transforming an exponential function to estimate the outage damage cost of a customer; and an analysis unit using the derived hierarchical linear function model to extract a hierarchical linear function model and using the extracted hierarchical linear function model to estimate the outage damage cost of the customer.

Description

Apparatus and method for estimating outage damage cost for electricity customer

The present invention relates to an apparatus and method for estimating customer supply cost, and in more detail, an apparatus and method for estimating customer supply equipment cost for recognizing an identification code for each sub-industry and estimating a high-accuracy supply-stop equipment cost through a linear transformation model for each detailed business type is about

The supply interruption cost can mean the cost of damage suffered by consumers due to supply interruption, or the cost that society pays when 100% reliability of power supply cannot be expected. For the cost of supply chain, the estimation function is estimated using the data of the survey result, and the function model used to estimate the supply cost may be in the form of an exponential function.

The reason for using the exponential function to estimate the supply interruption cost is to reduce the gap between the scale of the supply interruption cost and the scale of the power outage damage time.

Supply-stopping equipment costs are estimated for each 'sub-category' industry in the Korean standard industry classification system. The Maximum Likelihood Method was used as a method for estimating the parameters of the functional model. However, in some industries, parameters could not be estimated due to lack of data.

The present invention is to solve the above-described problems, and to provide an apparatus and method for estimating the customer's supply point equipment cost for recognizing the identification code for each detailed industry and estimating the supply point equipment cost with high accuracy through a linear transformation model for each detailed industry. do.

In addition to the technical problems of the present invention mentioned above, other features and advantages of the present invention will be described below or will be clearly understood by those skilled in the art from such description and description.

The device for customer supply stop equipment according to an embodiment of the present invention for achieving the above-described object includes a business category classification unit for classifying detailed industries of customers who responded to a survey based on the survey result data, and a business category in the industry classification unit A hierarchical classification unit that classifies a layer based on the classified result, a linear transformation unit that linearly transforms an exponential function to estimate the cost of supplying a customer, and a hierarchical linear function model using the function linearly transformed by the linear transformation unit can be derived, and the cost of supplying the customer can be estimated using the derived hierarchical linear function model.

In addition, the customer supply station equipment cost method performed by the customer supply station equipment cost device according to an embodiment of the present invention for achieving the above-described object classifies the detailed industries of customers who responded to the survey based on the survey result data A step, a step of classifying a layer based on the result of the classification of the industry in the industry classification unit, a step of linearly transforming the exponential function to estimate the cost of supplying the customer, and a hierarchical linear function model using the linearly transformed function and estimating the cost of supplying the customer by using the derived hierarchical linear function model.

The apparatus and method for estimating the customer's supply stop equipment cost according to an embodiment of the present invention can recognize the identification code for each sub-industry, and estimate the supply-stop equipment cost with high accuracy through a linear transformation model for each sub-industry.

In addition, even if there is not enough result data to be analyzed for each specific industry in the survey, it is possible to estimate the cost of supply disruption with high accuracy by analyzing the correlations with each other.

In addition, by estimating the supply interruption cost with high accuracy, the reliability of the distribution system is improved and it can be used as a decision-making tool to select the optimal investment scale in the system plan.

In addition, other features and advantages of the present invention may be newly recognized through embodiments of the present invention.

1 is a diagram illustrating a system for supplying equipment for customers according to an embodiment of the present invention.
2 is a diagram showing the configuration of an apparatus for estimating the cost of a supply stop according to an embodiment of the present invention.
3 is a diagram illustrating a classification system according to an embodiment of the present invention.
4 is a diagram illustrating the number of data according to an embodiment of the present invention.
5 is a diagram illustrating a parameter estimation result according to an embodiment of the present invention.
6 is a view showing a result of estimating the supply stop equipment cost according to an embodiment of the present invention.
7 is a diagram illustrating a method for estimating the cost of supplying a customer according to an embodiment of the present invention.

In order to clearly explain the present invention, parts irrelevant to the description are omitted, and the same reference numerals are given to the same or similar elements throughout the specification.

Although not defined otherwise, all terms including technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention belongs. Commonly used terms defined in the dictionary are additionally interpreted as having a meaning consistent with the related technical literature and the presently disclosed content, and unless defined, they are not interpreted in an ideal or very formal meaning.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein.

1 is a diagram illustrating a system for supplying equipment for customers according to an embodiment of the present invention.

Referring to FIG. 1 , a system 1000 for equipment cost for a customer according to an embodiment of the present invention may include an apparatus for estimating equipment cost for a supplier 100 and a questionnaire 200 .

Supply stop equipment costs can be applied to the overall reliability of the distribution system, such as determining the optimal investment and reliability level of the distribution system, and establishing a system reinforcement and expansion plan. Therefore, it can be very important to accurately estimate the cost of supply stop equipment.

Accordingly, the apparatus for estimating the cost of supplying the customer may estimate the cost of supplying the equipment using the result of the survey through the questionnaire 200 . After collecting the results of the survey, the device for estimating the cost of supply stop equipment for consumers removes unanswered questions and answers and abnormal data, removes unanswered questions and answers and abnormal data, and uses the remaining final data to estimate the supply cost. have. However, when the customer supply stop equipment cost estimation device removes unanswered questions and answers and abnormal data, the number of final data available for analysis can be significantly reduced. Here, the final data is classified for each industry group, and for an industry group in which the number of final data is insufficient among the industry groups, it may not be possible to estimate the parameters of the function model.

Accordingly, in order to prevent the occurrence of an industrial group in which the parameters of the function model cannot be estimated due to insufficient number of final data, abnormal data is pre-processed, and the pre-processed abnormal data is included in the final data to estimate the supply stop equipment cost. . However, since the consumer supply stop equipment cost estimation device estimates the supply stop equipment cost based on the results of the survey, when estimating the supply stop equipment cost by including the preprocessed abnormal data in the final data, the accuracy of the estimated supply stop equipment cost is can be reduced.

In addition, since it is not possible to obtain result data on the cost of supply stop according to continuous time during the survey, the survey result may be censored data rather than continuous data. In order to analyze the censoring data, we can estimate the supply cost through censoring regression analysis. However, due to the lack of data volume for each industry group, the supply stop cost estimated through censored regression analysis may not be reliable.

In order to solve this problem, the apparatus 100 for estimating the cost of supplying equipment for a customer according to an embodiment of the present invention may estimate the cost of supplying equipment using hierarchical linear modeling.

When there is one or more subdivided data of the industrial group and data of the entire industrial group exist, the apparatus 100 for estimating the cost of supplying the customer may estimate the cost of supplying equipment with high reliability by combining the given data. Accordingly, it is possible to overcome the limitation of the lack of data on the results of the survey through the questionnaire 200, and it is possible to provide reliable basic data for establishing a mid- to long-term distribution facility investment plan.

2 is a diagram showing the configuration of an apparatus for estimating the cost of a supply stop according to an embodiment of the present invention.

Referring to FIG. 2 , the apparatus 100 for estimating the cost of supplying equipment according to an embodiment of the present invention includes a sector classification unit 110 , a hierarchical classification unit 120 , a linear transformation unit 130 , and an analysis unit 140 . can do.

The industry classification unit 110 may classify detailed industries of customers who have responded to the survey based on the survey result data through the questionnaire 200 . Here, the industry classification unit 110 may classify one or more industries into all other industries. For example, if the customer's business type responding to the survey is an industry included in manufacturing and retail, the industry classification unit 110 may classify the corresponding industry into manufacturing and retail. In addition, the industry classification unit 110 may classify the industries of customers who responded to the survey into a large category, a small/medium category, and a sub-category.

The industry classification unit 110 may classify the industry based on the standard industry code input by customers when filling out the questionnaire 200 . Here, the standard industry code may be stored in a separate database or may be downloaded or read through a network connection.

In addition, the industry classification unit 110 may classify the industry using its own code in the case that the industry type of the customer who responded to the survey does not correspond to the standard industry code. Here, the industry classification unit 110 may classify the industry that does not correspond to the standard industry code according to a preset rule using its own code. The own code may be set in a form similar to the standard industry code, and the industry classification unit 110 may classify the industry of customers who responded to the survey according to the own code into a large category, a small/medium category, and a sub-category.

The hierarchical classification unit 120 may classify the classes of customers who responded to the survey based on the result data classified into a large classification, a small/medium classification, and a sub-category. The hierarchical classification unit 120 may classify the hierarchical level according to the major classification, the medium/small classification, and the sub-classification of the industry classified by the industry classification unit 110 . For example, the hierarchical classification unit 120 classifies the industry corresponding to the large classification into level 3 (level-3), classifies the industry corresponding to the medium/small classification into level 2 (level-2), and the industry corresponding to the subcategory can be classified as level 1 (level-1).

를

로 선형 변환할 수 있다.The linear transformation unit 130 may linearly transform the function in order to estimate the cost of supplying the customer. For example, the linear transformation unit 130 is an exponential function

to

can be linearly transformed into

The analysis unit 140 may derive a linear function model by using the function linearly transformed by the linear transformation unit 130 , and estimate the cost of supplying the customer by using the derived linear function model.

The analysis unit 140 may configure an equation for each level classified by the hierarchical classification unit 120 . The analyzer 140 may derive a hierarchical linear model by integrating the equations configured for each level into one equation. The analysis unit 140 may use a hierarchical linear model as a data generating model for estimating the supply cost.

Here, the hierarchical linear model is a complex model of Ordinary Least Squares (OLS), and as parameters are estimated for each layer, a plurality of error terms may exist.

An equation constituting the level of each layer may be as shown in Equation (1).

[Equation 1]

Here, i may be a value of 1 to n, and n may represent the number of data.

The analysis unit 140 may generate a hierarchical linear model by integrating the equations for each level of each hierarchy, and the hierarchical linear model may be calculated by Equation (2).

[Equation 2]

Here, j may be a value of 1 to J, and J may represent a number indicating each industry.

The analysis unit 140 may estimate the parameters for each industry by using the hierarchical linear model, and by reflecting the estimated parameters in the exponential function, it is possible to estimate the supply interruption cost. Since the analysis unit 140 indirectly uses all the information of the entire data by estimating the parameters for each layer, it can also estimate the parameters of the layer in which only very little data exists.

3 is a diagram illustrating a classification system according to an embodiment of the present invention.

Referring to FIG. 3 , the industry classification unit 110 may classify detailed industries of customers who have responded to the survey based on the survey result data through the questionnaire 200 . The industry classification unit 110 may classify the industries of customers who responded to the survey into a large category 10 , a medium/small category 20 , and a sub-category 30 . The industry classification unit 110 may classify the industry of the customer who responded to the survey based on the standard industry code.

For example, when the industry of the customer who responded to the survey is an industry, the industry classification unit 110 may classify the industry as the large classification 10 . Here, the industry classification unit 110 may represent the large classification 10 as 'A', which means 'industry'.

In addition, when the industry of the customer who responded to the survey is metal mining, the industry classification unit 110 may classify the metal mining industry as small/medium classifications 20 and 30 . Here, the industry classification unit 110 may represent the middle classification 20 as '0' meaning 'mining'. In addition, the industry classification unit 110 may represent the sub-category 30 as '6', which means 'metal mining'.

In addition, when the industry of the customer who responded to the survey is iron mining, the industry classification unit 110 may classify the iron mining industry as the subclass 40 . Here, the industry classification unit 110 may represent the sub-category 40 as '1', which means 'iron mining'.

Accordingly, the industry classification unit 110 may classify the industry type of the customer who responded to the survey as A061 based on the standard industry code.

On the other hand, the industry classification unit 110 may classify the industry by using its own code in the case of the industry in which the industry of the customer who responded to the survey does not correspond to the standard industry code. Here, the industry classification unit 110 may classify the industry that does not correspond to the standard industry code according to a preset rule using its own code. The own code may be set in a form similar to the standard industry code, and the industry classification unit 110 divides the industry of customers who responded to the survey according to the code according to the large classification (10), small / medium classification (20, 30) and It can be classified into a subcategory (40).

For example, the industry classification unit 110 may classify the industry based on its own code according to the Building Act when the industry of the customer who responded to the survey is a construction-related occupation. That is, the industry classification unit 110 may classify 'for housing' as the large classification 10, and may be represented by 'Z', which means 'for housing'. In addition, the industry classification unit 110 may classify 'detached house' as medium/small classification (20, 30), and may be represented by '01', which means 'detached house'. In addition, the industry classification unit 110 may classify the 'multi-family house' as the sub-class 40, and may be represented by '2', which means 'multi-family house'.

Accordingly, the industry classifying unit 110 may classify the industry of the customer who responded to the survey as Z012 based on its own code according to the Building Act.

4 is a diagram illustrating the number of data according to an embodiment of the present invention.

Referring to FIG. 4 , the industry classification unit 110 may classify data by industry of customers who have responded to the survey. Here, the industry classification unit 110 may classify the customer's industry into a large category, a medium/small category, and a sub-category. As the customer's industry is gradually subdivided into a large category, a medium/small category, and a sub-category, the number of data corresponding to each classified industry may be reduced. For example, in the case of the entire industry, which is a large category, the number of data may be 1,718. On the other hand, in the case of the subcategory iron mining, the number of data may be 34. On the other hand, data determined to be abnormal data among the surveyed data may be removed, whereby the number of data corresponding to each industry may be further reduced. For example, in the case of the subcategory iron mining industry, the number of investigated data may be 34, and the number of data from which abnormal data is removed may be 15.

In this way, as the industry is subdivided and classified, there may be a type of industry having too few data to estimate the supply-stopping cost.

Accordingly, the device for estimating the cost of supply stop equipment 100 according to an embodiment of the present invention can estimate the supply stop equipment cost by combining the data included in the medium/small classification and the large classification of the industry for the industry in which the number of data is insufficient. have.

5 is a diagram illustrating a parameter estimation result according to an embodiment of the present invention.

를

로 선형 변환할 수 있다.Referring to FIG. 5 , the linear transformation unit 130 may linearly transform the function in order to estimate the cost of supplying the customer. For example, the linear transformation unit 130 is an exponential function

to

can be linearly transformed into

The analysis unit 140 may derive a linear function model by using the function linearly transformed by the linear transformation unit 130 , and estimate the cost of supplying the customer by using the derived linear function model.

The analysis unit 140 may configure an equation for each level classified by the hierarchical classification unit 120 . The analysis unit 140 may derive a hierarchical linear model by integrating the equations configured for each level into one equation, and the hierarchical linear model may be calculated by the following equation.

Here, j may be a value of 1 to J, and J may represent a number indicating each industry.

The analysis unit 140 may estimate parameters for each industry by using the hierarchical linear model. Since the analysis unit 140 indirectly uses all the information of the entire data by estimating the parameters for each layer, it can also estimate the parameters of the layer in which only very little data exists.

For example, in the case of the tobacco industry, there may be two surveyed data, but by using the information of the entire data, parameters for the tobacco industry can be estimated. That is, as a result of the analysis unit 140 estimating the parameters of the tobacco industry, the parameter a may be -0.00000749, the parameter b may be -0.01136737, and the parameter c may be 10.09117346.

6 is a view showing a result of estimating the supply stop equipment cost according to an embodiment of the present invention.

Referring to FIG. 6 , the analysis unit 140 may estimate the supply interruption cost by estimating a parameter for each industry and reflecting the estimated parameter in an exponential function.

에 반영하여 공급지장비용을 추정할 수 있다. 분석부(140)는 담배 업종에 대해 추정한 모수 a, b 및 c를 지수 함수에 반영함으로써, 공급지장비용을 추정할 수 있다.For example, the analysis unit 140 converts the estimated parameter into an exponential function.

The cost of supply interruption can be estimated by reflecting in The analysis unit 140 may estimate the supply stop equipment cost by reflecting the parameters a, b, and c estimated for the tobacco industry in the exponential function.

7 is a diagram illustrating a method for estimating the cost of supplying a customer according to an embodiment of the present invention.

Referring to FIG. 7 , the industry classification unit 110 may classify detailed industries of customers who have responded to the survey based on the survey result data through the questionnaire 200 ( S100 ). The industry classification unit 110 may classify the industries of customers who have responded to the survey into a large category, a small/medium category, and a sub-category based on the standard industry code.

The hierarchical classification unit 120 may classify a hierarchy based on the result data in which the industry is classified (S200). The hierarchical classification unit 120 may classify the hierarchical level according to the major classification, the medium/small classification, and the sub-classification of the industry classified by the industry classification unit 110 . For example, the hierarchical classification unit 120 classifies the industry corresponding to the large classification into level 3 (level-3), classifies the industry corresponding to the medium/small classification into level 2 (level-2), and the industry corresponding to the subcategory can be classified as level 1 (level-1).

The linear transformation unit 130 may linearly transform the function in order to estimate the cost of supplying the customer, and the analysis unit 140 may derive a hierarchical linear function model using the transformed function (S300).

를

로 선형 변환할 수 있고, 분석부(140)는 각 레벨별로 구성되는 방정식을 하나의 방정식으로 통합하여 계층 선형 모델(Hierarchical Linear Model)을 도출할 수 있다. 각 계층의 레벨을 구성하는 방정식은 수학식 1과 같을 수 있다.The linear transformation unit 130 is an exponential function

to

, and the analysis unit 140 may derive a hierarchical linear model by integrating the equations configured for each level into one equation. An equation constituting the level of each layer may be as shown in Equation (1).

[Equation 1]

Here, i may be a value of 1 to n, and n may represent the number of data.

The analysis unit 140 may generate a hierarchical linear model by integrating the equations for each level of each hierarchy, and the hierarchical linear model may be calculated by Equation (2).

[Equation 2]

Here, j may be a value of 1 to J, and J may represent a number indicating each industry.

The analysis unit 140 may estimate the cost of supplying the customer by using the hierarchical linear function model (S400). The analysis unit 140 may estimate a parameter for each industry by using the hierarchical linear model, and by reflecting the estimated parameter in an exponential function, may estimate the supply disruption cost of the corresponding industry.

As described above, according to an embodiment of the present invention, it is possible to realize an apparatus and method for estimating the supply cost of a customer for recognizing the identification code for each sub-industry and estimating the cost of supplying equipment with high accuracy through a linear transformation model for each sub-industry.

Those skilled in the art to which the present invention pertains should understand that the present invention may be embodied in other specific forms without changing the technical spirit or essential characteristics thereof, so the embodiments described above are illustrative in all respects and not restrictive. only do The scope of the present invention is indicated by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. .

110: industry classification unit
120: hierarchical classification unit
130: linear transformation unit
140: analysis unit

Claims (14)

an industry classification unit for classifying detailed industries of customers who responded to the survey based on the survey result data;
a hierarchical classification unit for classifying a hierarchy based on the result of the classification of the industry in the industry classification unit;
a linear transformation unit that linearly transforms the exponential function to estimate the cost of supplying the customer; and
and an analysis unit for deriving a hierarchical linear function model using the function linearly transformed by the linear transformation unit, and estimating the customer supply unit cost using the derived hierarchical linear function model.
According to claim 1,
The industry classification unit is a consumer supply equipment cost device for classifying the customer's industry into a large classification, a medium / small classification and a subcategory based on the standard industry code.
3. The method of claim 2,
The hierarchical classification unit classifies the industry corresponding to the large classification into a hierarchy of level 3 (level-3), classifies the industry corresponding to the medium/small classification into a hierarchy of level 2 (level-2), and corresponds to the subcategory A device for supply-side equipment for consumers that classifies the industry into a level 1 hierarchy.
According to claim 1,
The linear transformation unit is an exponential function

to

A device for customer supply and equipment that converts linearly into
According to claim 1,
The analysis unit derives a hierarchical linear model by integrating the equations configured for each level classified by the hierarchical classification unit into one equation,
The equation composed for each level is the following equation,

i is a value from 1 to n, and n is the number of data.
6. The method of claim 5,
The hierarchical linear model is calculated by the following equation,

j is a value of 1 to J, J is a number that means each industry, the consumer supply equipment for the equipment.
7. The method of claim 6,
The analysis unit estimates the parameters for each industry by using the hierarchical linear model, and applies the estimated parameters to the exponential function to estimate the customer supply and demand equipment cost device.
A method for customer station equipment performed by a device for customer station equipment, the method comprising:
Classifying the detailed industries of customers who responded to the survey based on the survey result data;
classifying the class based on the result of the classification of the industry in the industry classification unit;
linear transformation of the exponential function to estimate the customer supply cost; and
Deriving a hierarchical linear function model using the linearly transformed function, and estimating the customer supply cost by using the derived hierarchical linear function model.
9. The method of claim 8,
The step of classifying the detailed industry is,
A method for customer supply and equipment cost for classifying the customer's industry into a large classification, a small / medium classification, and a subcategory based on the standard industry code
10. The method of claim 9,
The step of classifying the layer is
Classify the industry corresponding to the large classification into a hierarchy of level 3 (level-3), classify the industry corresponding to the medium/small classification into a hierarchy of level 2 (level-2), and classify the industry corresponding to the subcategory into a level A method of customer supply-stop equipment cost classifying into 1 (level-1) tiers.
11. The method of claim 10,
The linear transformation of the exponential function comprises:
exponential function

to

A customer-supply-stop-equipment cost method that linearly transforms into
12. The method of claim 11,
The step of estimating the cost of supplying the customer is,
A hierarchical linear model is derived by integrating the equations composed of each classified level into one equation,
The equation composed for each level is the following equation,

i is a value from 1 to n, and n is the number of data.
13. The method of claim 12,
The step of estimating the cost of supplying the customer is,
The hierarchical linear model is calculated by the following equation,

j is a value of 1 to J, and J is a number that means each industry, the customer supply point equipment cost method.
14. The method of claim 13,
The step of estimating the cost of supplying the customer is,
A method of estimating a parameter for each industry by using the hierarchical linear model, and estimating the consumer supply and demand cost by applying the estimated parameter to the exponential function.

Images