AMI failover facility recommendation system and method

Abstract

According to an embodiment, an AMI fault recovery target facility recommendation system is provided, comprising: a communication unit that collects field facility fault data from an AMI fault diagnosis system; a clustering unit that clusters the faulted facilities based on the addresses of the faulted facilities included in the fault data; a cluster priority determination unit that assigns priority to cluster groups according to cluster size; and a worker mapping unit that determines the number of required recovery workers per cluster according to the size of the cluster and sequentially maps the required recovery workers per cluster according to the priority.

Description

Technology Field

[0001] One embodiment of the present invention relates to an AMI failure recovery target facility recommendation system and method. Background Technology

[0003] Advanced Metering Infrastructure (AMI) is a remote metering technology developed to improve the accuracy of the existing metering method, where humans manually checked meters in each household to measure electricity usage, and to reduce metering costs. Furthermore, AMI is an indispensable element for the realization of smart grids, which are currently underway worldwide to reduce carbon emissions. Currently, a government-led AMI deployment project is in progress in Korea, aiming to install AMI in 22.5 million households.

[0004] Every year, failures in AMI field equipment, such as modems or Data Concentrator Units (DCUs), occur at a rate of approximately 5%. If the total number of facilities is estimated at about 10 million, a failure in 5% of these facilities would mean that approximately 500,000 facilities have failed. However, the workforce required to repair these is only about 250 people nationwide. Assuming that one person can repair a maximum of 20 failures per day, the number of facilities that can be repaired daily is only about 5,000.

[0005] The rapid increase in such AMI facilities is leading to increased time and costs for troubleshooting and a decrease in meter reading success rates, making it increasingly important to improve the efficiency of troubleshooting for AMI facilities for the stable establishment of AMI. The problem to be solved

[0007] The technical problem that the present invention aims to solve is to provide a system and method for recommending AMI failure recovery target facilities capable of selecting priorities for the failure recovery of AMI field facilities.

[0008] In addition, the invention provides an AMI fault recovery target facility recommendation system and method capable of automatically recommending recovery target facilities for each worker according to priority.

[0009] In addition, the invention provides a system and method for recommending AMI failure recovery target facilities that can support efficient AMI field facility failure recovery. means of solving the problem

[0011] According to an embodiment, an AMI fault recovery target facility recommendation system is provided, comprising: a communication unit that collects field facility fault data from an AMI fault diagnosis system; a clustering unit that clusters the faulted facilities based on the addresses of the faulted facilities included in the fault data; a cluster priority determination unit that assigns priority to cluster groups according to cluster size; and a worker mapping unit that determines the number of required recovery workers per cluster according to the size of the cluster and sequentially maps the required recovery workers per cluster according to the priority.

[0012] It may further include a preprocessing unit that processes the address of the faulted equipment included in the fault data into location coordinates.

[0013] The above clustering unit can perform clustering using the above location coordinates.

[0014] The above clustering unit can perform clustering using the K-Means algorithm.

[0015] The above field equipment failure data may include a list of field equipment where the D-day of the regular meter reading date is less than or equal to m (m is a natural number) days, and a list of field equipment where a failure occurred.

[0016] The above cluster priority determination unit can determine the size of the cluster based on the number of faulty facilities included in the cluster.

[0017] The above worker mapping unit can determine the number of required recovery workers per cluster using the number of tasks per worker set in advance and the number of faulty facilities.

[0018] The above communication unit can transmit data mapped to the manager by the required recovery worker for each cluster.

[0019] According to an embodiment, a method for recommending AMI failure recovery target facilities is provided, comprising: a communication unit collecting field facility failure data from an AMI failure diagnosis system; a clustering unit clustering the failure facilities based on the addresses of the failure facilities included in the failure data; a cluster priority determining unit assigning priority to the cluster groups according to the cluster size; and a worker mapping unit determining the number of required recovery workers per cluster according to the cluster size and sequentially mapping the required recovery workers per cluster according to the priority.

[0020] After the step of collecting the above-mentioned field equipment failure data, the preprocessing unit may further include a step of converting the address of the failure equipment included in the failure data into location coordinates.

[0021] The above clustering unit can perform clustering using the above location coordinates.

[0022] The above clustering unit can perform clustering using the K-Means algorithm.

[0023] The above field equipment failure data may include a list of field equipment where the D-day of the regular meter reading date is less than or equal to m (m is a natural number) days, and a list of field equipment where a failure occurred.

[0024] The above cluster priority determination unit can determine the size of the cluster based on the number of faulty facilities included in the cluster.

[0025] The above worker mapping unit can determine the number of required recovery workers per cluster using the number of tasks per worker set in advance and the number of faulty facilities.

[0026] The above communication unit can transmit data mapped to the administrator by the required recovery worker for each cluster.

[0027] According to an embodiment, a computer-readable recording medium is provided on which a program for executing the above-described method is recorded. Effects of the invention

[0029] The AMI failure recovery target facility recommendation system and method according to the embodiment can select a priority for failure recovery of AMI field facilities.

[0030] In addition, it can automatically recommend equipment to be restored for each worker based on priority.

[0031] In addition, it can support efficient recovery of AMI field equipment failures. Brief explanation of the drawing

[0033] FIG. 1 is a conceptual diagram of a remote meter reading system according to an embodiment of the present invention. FIG. 2 is a schematic block diagram of an AMI fault diagnosis system according to one embodiment of the present invention. FIG. 3 is a block diagram of an AMI failure recovery target facility recommendation system according to an embodiment. FIG. 4 is a diagram illustrating the operation of a clustering unit according to an embodiment. FIG. 5 is a flowchart of a method for recommending AMI failure recovery target facilities according to an embodiment. Specific details for implementing the invention

[0034] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings.

[0035] However, the technical concept of the present invention is not limited to some of the described embodiments but can be implemented in various different forms, and within the scope of the technical concept of the present invention, one or more of the components among the embodiments may be selectively combined or substituted.

[0036] In addition, terms used in the embodiments of the present invention (including technical and scientific terms) may be interpreted in a sense that is generally understood by those skilled in the art to which the present invention belongs, unless explicitly and specifically defined otherwise. Terms that are commonly used, such as terms defined in advance, may be interpreted in consideration of their meaning in the context of the relevant technology.

[0037] Furthermore, the terms used in the embodiments of the present invention are for the purpose of describing the embodiments and are not intended to limit the present invention.

[0038] In this specification, the singular form may include the plural form unless specifically stated otherwise in the text, and when described as "at least one of A and B and C (or more than one)," it may include one or more of all combinations that can be formed from A, B, and C.

[0039] In addition, terms such as first, second, A, B, (a), (b), etc. may be used when describing the components of the embodiments of the present invention.

[0040] These terms are intended merely to distinguish a component from other components and are not limited by the nature, order, sequence, etc., of the said component.

[0041] And, where it is stated that a component is 'connected', 'combined', or 'joined' to another component, this may include not only cases where the component is directly connected, combined, or joined to the other component, but also cases where it is 'connected', 'combined', or 'joined' due to another component located between the component and the other component.

[0042] Furthermore, when described as being formed or placed "above or below" each component, "above" or "below" includes not only cases where two components are in direct contact with each other, but also cases where one or more other components are formed or placed between the two components. Additionally, when expressed as "above or below," it may include the meaning of a downward direction as well as an upward direction relative to a single component.

[0043] Hereinafter, embodiments will be described in detail with reference to the attached drawings, provided that identical or corresponding components are given the same reference number regardless of the drawing symbols, and redundant descriptions thereof will be omitted.

[0045] FIG. 1 is a conceptual diagram of a remote meter reading system according to an embodiment of the present invention. FIG. 1 is a conceptual diagram of a remote meter reading system according to an embodiment of the present invention. Referring to FIG. 1, the remote meter reading system according to the embodiment may be configured to include a smart meter (10), a data collection device (20), and an AMI server (30).

[0046] The data collection unit (Data Concentrator Unit; DCU) (20) can perform data communication with the smart meter (10) in the group through the modem (11). The data collection unit (20) can collect meter reading data of the electricity meter along with meter reading data of the gas meter and water meter in the house from the smart meter (30).

[0047] Meter reading data may include meter number, meter reading year and day, time and minute of inspection, data collection device ID, active power, leading reactive power, lagging reactive power, apparent power, cumulative active power, cumulative leading reactive power, cumulative lagging reactive power, and cumulative apparent power.

[0048] The data collection device (20) can be installed on a utility pole and can collect electricity, water, and gas meter reading data collected in the smart meter (10) via a modem (11) through power line communication or wireless communication.

[0049] The data collection device (20) can request the transmission of corresponding meter reading data by transmitting an object identification system code corresponding to the meter reading data to be collected to the smart meter (10). The object identification system code transmitted by the data collection device (20) may be composed of a series of codes corresponding to one or more of the following information: the type of medium that the meter or power meter reads, the channel number of the meter or power meter, the physical quantity of the meter reading data, the method of processing the meter reading data, the physical classification of the meter reading data, and the temporal classification of the meter reading data.

[0050] The data collection device (20) can collect meter reading data from multiple smart meters (10). The data collection device (20) that has collected the meter reading data can transmit information via a wide-area transmission network, such as the internet, in response to periodic requests from the AMI (Advanced Metering Infrastructure) server (30) meter reading scheduler.

[0051] FIG. 2 is a schematic block diagram of an AMI fault diagnosis system according to an embodiment of the present invention. Referring to FIG. 2, the AMI fault diagnosis system (100) according to the embodiment may include an AMI data management unit (110), a fault determination model management unit (120), and a fault diagnosis unit (130).

[0052] The AMI data management unit (110) collects field data (e.g., meter reading information (10), NMS (Network Management System) information (20), security information (30), log information (40), etc.) from an AMI operating system (not shown) and generates AMI big data (114) using system operation information registered by the AMI operating system operator (e.g., fault resolution result information (50), field work plan information (60), etc.) and the collected field data. In particular, the AMI data management unit (110) can generate AMI big data (114) including learning AMI log data, learning AMI information data, diagnostic AMI log data, and diagnostic AMI information data.

[0053] At this time, the meter reading information (10) includes the reception date and time, DCU ID, meter ID, status information, collection time, meter / DCU time, and MAC address, the NMS information (20) includes the MAC address, DCU ID, communication performance related items, and collection date and time, the security information (30) includes the equipment type, host information, authentication date and time, authentication status, and trap information, and the log information (40) may include NMS logs, meter reading logs, and security logs. The above field data may be collected by equipment, and such equipment information may include DCU information, modem information, and meter information.

[0054] To this end, the AMI data management unit (110) may include a data collection unit (111) that collects field data from an AMI operating system (not shown), a data processing unit (112) that processes the collected data so that it can be used for learning or diagnosis, and a data storage unit (113) that stores the collected and processed data (AMI data) in an AMI big data (114) (i.e., an AMI big data repository).

[0055] The fault determination model management unit (120) generates a fault determination model for diagnosing AMI faults using training AMI log data and training AMI information data stored in AMI big data (114). At this time, the fault determination model management unit (120) can generate two types of fault determination models for diagnosing faults for each of the three types of AMI facilities (i.e., DCU information, Modem information, Meter), and the two types of fault determination models may be a fault determination model using AMI logs and a fault determination model using AMI information.

[0056] To this end, the fault judgment model management unit (120) may include a first fault judgment model generation unit (121), a second fault judgment model generation unit (122), and a fault judgment model evaluation unit (123).

[0057] The first fault judgment model generation unit (121) applies the training AMI log data stored in the AMI big data (114) to a deep learning algorithm pre-configured for each AMI facility to learn the first past fault situation for each AMI facility and then generates the first fault judgment model. At this time, examples of the first past fault situation may include the facility's 'security error', 'error', 'configuration error', etc.

[0058] The second fault judgment model generation unit (122) applies the learning AMI information data stored in the AMI big data (114) to the deep learning algorithm to learn the second past fault situation for each AMI facility and then generates the second fault judgment model. At this time, examples of the second past fault situation may include the facility's 'communication failure', 'meter reading failure', 'weak signal', etc.

[0059] The fault judgment model evaluation unit (123) evaluates the first and second fault judgment models and manages the evaluation results (e.g., accuracy, precision, etc.). At this time, in order to evaluate the first and second fault judgment models, the fault judgment model evaluation unit (123) may perform an evaluation of the accuracy, precision, and recall used in AI technology, and the formulas for this are commonly used in the AI ​​field.

[0060] The fault diagnosis unit (130) diagnoses whether there is a fault in the AMI facility by applying the diagnostic AMI log data and diagnostic AMI information data stored in the AMI big data (114) to the first and second fault determination models. To this end, the fault diagnosis unit (130) may include a fault analysis unit (131), a fault classification unit (132), and a fault determination unit (133).

[0061] The fault analysis unit (131) primarily determines the fault for each facility using an AMI fault judgment modem for each type of facility and actual AMI data. That is, the fault analysis unit (131) can analyze the fault for each AMI facility by applying the diagnostic log data to the first judgment model and applying the diagnostic meter reading data to the second judgment model.

[0062] The fault classification unit (132) classifies faults secondarily using the fault judgment result primarily generated by the fault analysis unit (131) and AMI network topology information. That is, the fault classification unit (132) can classify faults by AMI facility using the fault analysis result by AMI facility from the fault analysis unit (131) and the physical and logical connection structure between AMI facilities.

[0063] The fault determination unit (133) finally determines the fault using the fault classification result secondarily generated by the fault classification unit (132), the field work plan information (60) registered in advance by the system operator, and the fault diagnosis criteria. That is, the fault determination unit (133) can finally determine whether there is a fault by reflecting the field work plan information (60) and the fault diagnosis criteria included in the AMI big data (114) in the fault classification result.

[0064] Meanwhile, the AMI fault management unit (200) provides a user interface to the AMI operating system administrator. To this end, the AMI fault management unit (200) may include a fault judgment model information management unit (210), a fault diagnosis result management unit (220), and a fault monitoring unit (230).

[0065] The fault judgment model information management unit (210) stores fault judgment model information including registration, modification, history lookup, and evaluation results for fault judgment models generated by the first and second fault judgment model generation units (121, 122), and can provide the stored fault judgment model information in response to a request from an AMI operating system administrator. Additionally, the fault judgment model information management unit (210) may provide a function to manage the registration / modification (including hyperparameter changes), history lookup, and evaluation results of the fault judgment models, compare and display them, and improve the models by retraining them.

[0066] The fault diagnosis result management unit (220) stores the fault diagnosis result of the fault diagnosis unit (130) and the fault judgment model used during the fault diagnosis, and can provide the fault diagnosis result and the corresponding fault judgment model information in response to a request from the AMI operating system manager.

[0067] The fault monitoring unit (230) stores detailed information for each faulty facility (e.g., facility type, facility ID, date and time of failure, time of failure, type of failure, location, etc.) and, in response to a request from the AMI operating system manager, can provide detailed information for each faulty facility or information on faulty facilities by region (e.g., grouped into nearby areas so that nearby faults can be addressed in a single dispatch).

[0068] FIG. 3 is a block diagram of an AMI failure recovery target facility recommendation system according to an embodiment. Referring to FIG. 3, the AMI failure recovery target facility recommendation system (300) according to an embodiment may include a communication unit (310), a database (320), a preprocessing unit (330), a clustering unit (340), a cluster priority determination unit (350), and a worker mapping unit (360).

[0069] The communication unit (310) can collect field equipment failure data from the AMI failure diagnosis system. The field equipment failure data may include detailed information about the field equipment where the failure occurred (equipment type, equipment ID, failure date and time, failure duration, failure type, location, etc.) and installation address information of the failed equipment.

[0070] Field equipment failure data may include a list of field equipment for which the D-day (m is a natural number) for the regular meter reading date is m days or less, and a list of field equipment where failures have occurred. That is, field equipment failure data may include a list of field equipment where actual failures have occurred, and a list of equipment for which the regular meter reading date is approaching even if failures have not occurred. For example, if the D-day for the regular meter reading date is 1 day or less, the AMI failure diagnosis system may include the corresponding field equipment in the list.

[0071] Additionally, the communication unit (310) can transmit data in which necessary recovery workers for each cluster are mapped to the manager. The communication unit (310) can transmit data in which necessary recovery workers for each cluster are mapped to each cluster to the manager server or terminal through the worker mapping unit (360). At this time, the manager may include workers for actually performing recovery work corresponding to the aforementioned list of necessary recovery workers for each cluster.

[0072] For example, the communication unit (310) can perform data communication using long-distance communication technologies such as Wireless LAN (WLAN), Wi-Fi, Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed ​​Downlink Packet Access (HSDPA), IEEE 802.16, Long Term Evolution (LTE), and Wireless Mobile Broadband Service (WMBS).

[0073] Alternatively, the communication unit (310) may include Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), Ultra Wideband (UWB), Zigbee, Near Field Communication (NFC), etc. Additionally, as a wired communication technology, data communication can be performed using short-range communication technologies such as USB communication, Ethernet, serial communication, and optical / coaxial cables.

[0074] The database (320) can store information related to failures of the AMI. In an embodiment, the information related to failures of the AMI may include all abnormal condition occurrences, progress, and response situations occurring in the AMI server, data concentrator, smart meter, modem, etc. that constitute the AMI.

[0075] Additionally, the database (320) can store data and programs necessary for the operation of the AMI failure recovery target facility recommendation system. Additionally, the database (320) can store various user interfaces (UI) or graphic user interfaces (GUI).

[0076] The database (320) may include at least one storage medium among Flash Memory Type, Hard Disk Type, Multimedia Card Micro Type, Card Type Memory (e.g., SD or XD memory), Magnetic Memory, Magnetic Disk, Optical Disk, RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), and PROM (Programmable Read-Only Memory). Additionally, it may operate a web storage that performs the storage function of the database (320) on the internet, or operate in relation to the web storage.

[0077] In the embodiment, field equipment failure data may include information on the occurrence of failure phenomena, failure inspection information, information on the cause of failure, information on corrective measures, etc.

[0078] Fault occurrence information may refer to status information of the relevant equipment obtainable by the system in the event of a failure, such as the communication status (ping) between the AMI server and the data concentrator, and status information of the AMI modem and smart meter. For example, fault occurrence information may include ping failure, insufficient signal strength, security authentication failure, initialization failure, and encryption failure.

[0079] In the embodiments, fault inspection information may refer to fault-related information obtained by field AMI maintenance personnel through remote inspection or field device inspection. For example, the fault inspection information may include inability to access the console, incorrect DCU IP settings, incorrect server IP settings, initialization failure, and encryption failure.

[0080] In the embodiments, the cause of failure information may refer to the cause of failure determined by field AMI maintenance personnel through on-site inspection. For example, the cause of failure information may include OS holding, network SW holding, connection port failure, DCU IP configuration failure, and authentication key expiration.

[0081] In the embodiments, the action method information may refer to the method actually taken by field AMI maintenance personnel after determining the cause of the failure through analysis. For example, the action method information may include replacing the DCU board, repairing the connection terminal, resetting the DCU, resetting the DCU IP, and resetting the DCU time.

[0082] The preprocessing unit (330) can process the address of the faulted facility included in the fault data into location coordinates. The preprocessing unit (330) can convert the address of the faulted facility into a Geographic Coordinate System (GCS) consisting of latitude and longitude.

[0083] The clustering unit (340) can cluster faulted equipment based on the addresses of the faulted equipment included in the fault data. The clustering unit (340) can perform clustering using location coordinates. For example, the clustering unit can perform clustering using the K-Means algorithm.

[0084] FIG. 4 is a diagram illustrating the operation of a clustering unit according to an embodiment. Referring to FIG. 3 and FIG. 4, the clustering unit (340) can map faulty facilities converted into a geographic coordinate system onto a two-dimensional plane. The clustering unit (340) performs K-means clustering using the faulty facilities mapped onto the two-dimensional plane. The clustering unit (340) sets centroid points on the faulty facilities using the K-means algorithm. The clustering unit (340) calculates the range of the clusters using the centroids of each k cluster and the vector information and coordinate information of the faulty facilities included within the clusters. The clustering unit (340) sets the range of the clusters by connecting the centroids of each k cluster and the faulty facilities that are farthest from the centroids of the faulty facilities within the clusters. The clustering unit (340) can calculate the distance between faulty facilities using the Euclidean distance calculation method.

[0085] The cluster priority determining unit (350) can assign priority to cluster groups according to the cluster size. The cluster priority determining unit (350) can determine the size of the cluster according to the number of faulty facilities included in the cluster. The cluster priority determining unit (350) can determine the size of the cluster in proportion to the number of faulty facilities included in the cluster.

[0086] The worker mapping unit (360) can determine the number of recovery workers required per cluster based on the size of the cluster and map the required recovery workers for each cluster sequentially according to priority.

[0087] The worker mapping unit (360) can determine the number of required recovery workers per cluster using the number of tasks per worker and the number of faulty equipment set in advance. That is, the worker mapping unit (360) can determine how many workers are needed according to the size of the cluster and map the workers in order.

[0088] For example, in FIG. 4, if the number of faulty equipment included in cluster 1 is 100, the number of faulty equipment included in cluster 2 is 80, and the number of faulty equipment included in cluster 3 is 20, the cluster priority determining unit can assign priority in the order of cluster 1, cluster 2, and cluster 3 according to the number of faulty equipment.

[0089] And, when the maximum number of failure recovery cases per worker is set to 30, the worker mapping unit (360) calculates the number of required recovery workers for cluster 1 as 3 people according to priority. At this time, the number of required recovery workers per cluster can be calculated as (number of failure facilities in the cluster) / (maximum number of failure recovery cases per worker), and the decimal part is discarded.

[0090] The worker mapping unit (360) calculates the number of required recovery workers for cluster 2 as 2 people according to priority, and the number of required recovery workers for cluster 3 as 1 person. The worker mapping unit (360) maps available workers to the corresponding clusters according to the calculated number of required recovery workers per cluster.

[0091] In this case, if the number of available workers is less than the number of recovery workers required for the entire cluster, workers are mapped sequentially according to priority, and workers are not mapped to lower priority clusters, or fewer workers are mapped than the number of recovery workers required.

[0092] FIG. 5 is a flowchart of a method for recommending AMI failure recovery target facilities according to an embodiment.

[0093] Referring to FIG. 5, first, the communication unit collects field equipment failure data from the AMI failure diagnosis system (S501).

[0094] Next, the preprocessing unit converts the address of the fault equipment included in the fault data into location coordinates (S502).

[0095] Next, the clustering unit clusters the faulty equipment based on the addresses of the faulty equipment included in the fault data (S503).

[0096] Next, the cluster priority determination unit assigns priority to cluster groups according to cluster size (S504).

[0097] Next, the worker mapping unit determines the number of recovery workers required per cluster based on the size of the cluster (S505).

[0098] Next, the worker mapping unit maps the necessary recovery workers for each cluster sequentially according to priority (S506).

[0099] Next, the communications department transmits the data mapped with the necessary recovery workers for each cluster to the manager (S507).

[0100] 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 recording medium. In this case, the medium may continuously store a program executable by a computer, or temporarily store it for execution or download. Additionally, the medium may be various recording or storage means in the form of a single or several hardware combined, and is not limited to a medium directly connected to a computer system, but may exist distributed over a network. Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software.

[0102] The term "part" as used in this embodiment refers to a software or hardware component, such as a field-programmable gate array (FPGA) or an ASIC, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to run one or more processors. Thus, as an example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0103] Although the present invention has been described above with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as described in the following claims. Explanation of the symbols

[0105] 300: AMI Fault Recovery Target Facility Recommendation System 310: Communications Department 320: Database 330: Preprocessing section 340: Clustering section 350: Cluster Priority Determination Unit 360: Worker Mapping Section

Claims

Claim 1 A system for recommending equipment for AMI failure recovery, comprising: a communication unit for collecting field equipment failure data from an AMI failure diagnosis system; a clustering unit for clustering the equipment based on the address of the equipment included in the failure data; a cluster priority determination unit for assigning priority to cluster groups according to cluster size; and a worker mapping unit for calculating the number of required recovery workers per cluster using the number of maximum daily work possible per worker and the number of equipment within the cluster, and sequentially mapping available workers to the cluster according to the assigned priority. Claim 2 An AMI fault recovery target facility recommendation system according to claim 1, further comprising a preprocessing unit that processes the address of a fault facility included in the fault data into location coordinates. Claim 3 In paragraph 2, the clustering unit is an AMI fault recovery target facility recommendation system that performs clustering using the location coordinates. Claim 4 In claim 1, the clustering unit is an AMI fault recovery target facility recommendation system that performs clustering using the K-Means algorithm. Claim 5 In claim 1, the above field facility failure data is an AMI failure recovery target facility recommendation system that includes a list of field facilities where the D-day of the regular meter reading date is less than or equal to m (m is a natural number) days and a list of field facilities where a failure occurred. Claim 6 In paragraph 5, the cluster priority determining unit determines the size of the cluster according to the number of faulty facilities included in the cluster, an AMI fault recovery target facility recommendation system. Claim 7 delete Claim 8 In paragraph 1, the communication unit is an AMI fault recovery target facility recommendation system that transmits data mapped to a manager with required recovery workers for each cluster. Claim 9 A method for recommending AMI failure recovery target facilities, comprising: a communication unit collecting field facility failure data from an AMI failure diagnosis system; a clustering unit clustering the failure facilities based on the addresses of the failure facilities included in the failure data; a cluster priority determining unit assigning priorities to the cluster groups according to the cluster size; and a worker mapping unit calculating the number of required recovery workers per cluster using the number of maximum daily work possible per worker and the number of failure facilities within the cluster, and sequentially mapping available workers to the clusters according to the assigned priorities. Claim 10 A method for recommending AMI failure recovery target facilities according to claim 9, further comprising, after the step of collecting field facility failure data, a step in which a preprocessing unit converts the address of the failure facility included in the failure data into location coordinates. Claim 11 In item 10, the above-mentioned clustering unit performs clustering using the above-mentioned location coordinates. A method for recommending AMI failure recovery target facilities. Claim 12 In claim 9, the clustering unit is a method for recommending AMI failure recovery target facilities that performs clustering using the K-Means algorithm. Claim 13 In claim 9, the above-mentioned field facility failure data includes a list of field facilities where the D-day of the regular meter reading date is less than or equal to m (m is a natural number) days and a list of field facilities where a failure occurred, a method for recommending AMI failure recovery target facilities. Claim 14 In paragraph 13, the cluster priority determining unit determines the size of the cluster according to the number of faulty facilities included in the cluster, in an AMI fault recovery target facility recommendation method. Claim 15 delete Claim 16 A method for recommending AMI failure recovery target facilities according to claim 9, further comprising the step of the communication unit transmitting data mapped to a manager for each cluster of required recovery workers. Claim 17 A computer-readable recording medium having a program recorded thereon for executing the method of any one of paragraphs 9 through 14 and paragraph 16 on a computer.

Images