KR20190064111A - Energy management system and energy management method including fault tolerant function - Google Patents

Abstract

According to an embodiment of the present invention, provided is an energy management system which comprises: a sensor network installed in one section of a building; a zone agent for managing measurement data acquired from the sensor network; a building agent for receiving system configuration data including setting information on the sensor network from the zone agent and managing the same; and a remote device for generating energy demand prediction data of a zone through a first machine learning model including the measurement data received from the zone agent as input data and generating fault information on the zone agent through a second machine learning model including a part of the measurement data as input data. The building agent generates a virtual agent replacing the zone agent in accordance with the fault information and applies the system configuration data to the virtual agent.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an energy management system and an energy management method including a fault-

This embodiment relates to a technique for managing energy.

Recently, the rapid increase in energy demand has worsened the electricity shortage. In order to overcome this power shortage, social costs have increased rapidly due to the addition of power generation and transmission and distribution facilities, and the supply of electricity has been delayed. As a result, the government is shifting from past supply-oriented to demand management-oriented energy policies.

Power demand management is a way to meet stable power demand at the lowest cost through changing consumer usage patterns. Demand management of electricity can be divided into demand reaction and energy efficiency improvement. The application of this power demand management to buildings, homes, and factories is expected to have a significant effect on energy demand management.

BEMS (Building Energy Management System) is the system that manages the electricity demand of the building and BEMS is called the building agent.

On the other hand, when one demand management policy is applied to the entire building, it is difficult to satisfy the different demands of users residing in different zones. Therefore, a zone agent is installed and different demand management policies are applied to each zone . However, if the agent is installed in each zone, the number of agents increases and it becomes difficult to deal with the failure in terms of maintenance. In addition, when some agents fail, there is a problem that the building agent, who oversees the zone agent in addition to the failed zone agent, can not provide normal service.

In this context, it is an object of this embodiment to provide an energy management technique that includes a fault tolerant function.

In order to achieve the above-mentioned object, one embodiment includes a zone agent for managing energy of a zone constituting a building; A building agent for managing energy of the building based on the zone agent data obtained from the plurality of zone agents; A community agent for managing energy of a community based on building agent data acquired from a plurality of the building agents; And a first machine learning model that includes first zone data of the zone data received from the zone agent as input data, generates energy demand prediction data of the zone, and outputs second zone data of the zone data as input data And a remote device that generates failure information of the zone agent through a second machine learning model that includes the failure information, wherein the building agent provides an energy management system that creates a virtual agent that replaces the zone agent in accordance with the failure information .

And the second machine learning model may be learned by receiving the third zone data of the second zone data as time series data.

The remote device generates the failure information including a failure prediction level and the building agent may replace the zone agent with the virtual agent if the failure prediction level is greater than or equal to a preset reference level.

The building agent may control the virtual agent to back up the measurement data collected by the zone agent if the failure prediction level is lower than the reference level.

The remote device may generate the failure information including a failure type and may control the zone agent so that some of the zone data is not transmitted or received when the failure type is a communication failure.

The building agent may replace the zone agent with the virtual agent if the communication failure persists for a period of time.

And the remote device can control the zone agent so that data of low importance is not transmitted or received among the zone data.

The building agent may receive from the zone agent system configuration data including information of sensors and devices managed by the zone agent and apply the system configuration data to the virtual agent.

Another embodiment provides a method of managing energy in a community, comprising: managing energy in a zone in which a zone agent comprises a building; Managing the energy of the building based on zone agent data obtained from the plurality of zone agents; Managing community energy based on building agent data obtained from a plurality of building agents; The remote device generates energy demand prediction data of the zone through a first machine learning model including first zone data of the zone data received from the zone agent as input data and outputs second zone data of the zone data Generating fault information of the zone agent through a second machine learning model included as input data; And generating a virtual agent that replaces the zone agent according to the failure information by the building agent.

Yet another embodiment is a sensor network installed in a section of a building; A zone agent for managing measurement data obtained from the sensor network; A building agent for receiving and managing system configuration data including setting information of the sensor network from the zone agent; And a second machine learning model for generating energy demand prediction data of the zone through a first machine learning model including the measurement data received from the zone agent as input data and including part of the measurement data as input data, Wherein the building agent is configured to generate a virtual agent that replaces the zone agent in accordance with the failure information and to apply the system configuration data to the virtual agent Management system.

The virtual agent may obtain energy demand forecast data for the zone using the same first machine learning model as the zone agent.

The remote device generates the failure information including a failure prediction level and the building agent may replace the zone agent with the virtual agent if the failure prediction level is greater than or equal to a preset reference level.

The building agent may control the virtual agent to back up the measurement data collected by the zone agent if the failure prediction level is lower than the reference level.

The remote device may receive the measurement data from the zone agent and communicate the measurement data to the virtual agent.

The remote device may generate the failure information including a failure type and may control the zone agent so that data having a level of importance less than a reference value is not transmitted or received when the failure type is a communication failure.

As described above, according to the present embodiment, in the energy management system, even if a defect or a failure occurs in the hardware or software constituting the system, the function can be normally or partially performed.

1 is a conceptual diagram of an energy management system according to an embodiment.
2 is a diagram showing a hierarchical structure of a community.
3 is a system configuration diagram of a community level.
4 is a system configuration diagram of a building level.
5 is a system block diagram of a zone level.
6 is a diagram for explaining a fault-tolerant function according to an embodiment.
7 is a block diagram of an agent block of a machine learning apparatus according to an embodiment.
8 is an internal block diagram of an agent block according to an embodiment.
9 is a diagram showing input / output data of a failure detection model (second machine learning model) according to an embodiment.
10 is a first exemplary control flow diagram of an energy management system according to an embodiment.
11 is a second exemplary control flow diagram of an energy management system according to an embodiment.

Hereinafter, some embodiments of the present invention will be described in detail with reference to exemplary drawings. It should be noted that, in adding reference numerals to the constituent elements of the drawings, the same constituent elements are denoted by the same reference symbols as possible even if they are shown in different drawings. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

In describing the components of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are intended to distinguish the constituent elements from other constituent elements, and the terms do not limit the nature, order or order of the constituent elements. When a component is described as being "connected", "coupled", or "connected" to another component, the component may be directly connected to or connected to the other component, It should be understood that an element may be "connected," "coupled," or "connected."

1 is a conceptual diagram of an energy management system according to an embodiment.

Referring to FIG. 1, the energy management system 100 includes a community system and a cloud system.

The community system includes at least one agent device 110, and the cloud system includes at least one or more machine learning devices 120. Since the machine learning apparatus 120 performs a part of the machine learning function, it is referred to as a 'machine learning apparatus'. However, the machine learning apparatus 120 may be referred to as another term such as 'remote apparatus' Hereinafter, the machine learning apparatus will be referred to as a 'machine learning apparatus' for convenience of explanation.

The agent apparatus 110 generates measurement data from various sensors (including meters) located in the space of the community, and transmits the measurement data to the machine learning apparatus 120 through the network. The agent device 110 includes a UI (User Interface) device, and transmits the configuration information acquired from the user to the machine learning device 120 through the UI device.

The machine learning apparatus 120 generates predictive data and optimization data through a machine learning model using measurement data and setting information received from the agent apparatus 110 as input data, and transmits the predictive data and the optimization data to the agent apparatus 110.

The agent apparatus 110 manages the energy of the community by using the predictive data and the optimization data received from the machine learning apparatus 120. [

Agent information transmitted by the agent device 110 to the machine learning device 120 may include measurement data, system configuration data, status data, and the like.

The measurement data is data obtained from the sensors managed by the agent apparatus 110. The agent device 110 may send the measurement data to the machine learning device 120 and, depending on the embodiment, send the machining data that processed the measurement data to the machine learning device 120. [ Alternatively, the agent device 110 may transmit measurement data and machining data to the machine learning device 120. Hereinafter, it is described that the agent apparatus 110 transmits measurement data to the machine learning apparatus 120, and it should be understood that such measurement data can be replaced with the processed data or transmitted together with the processed data.

The system configuration data may include information of sensors and devices managed by the agent apparatus 110. [ For example, the system configuration data may include the type of sensors and devices, the communication address-for example, IP-, a communication protocol, and so on. The agent device 110 can receive system configuration data from another agent device and manage it in place of sensors and devices managed by other agent devices.

The status data may include status information of the agent device 110 or status information of the sensors and devices managed by the agent device 110. [ The status information may include, for example, information on whether or not a failure has occurred.

The machine learning information that the machine learning device 120 sends to the agent field 110 may include predicted data, estimated data, optimized data, and control data. The prediction data may include energy demand prediction data, and the estimation data may include occupancy estimation data.

The optimization data may include device control data for controlling the devices managed by the agent device 110. [ The agent apparatus 110 can optimize the energy use of the corresponding area by controlling the devices to be managed according to the device control data included in the optimization data.

The control data may be used as data to be used when the machine learning apparatus 120 wants to control the agent apparatus 110, for example, the operation of the agent apparatus 110 may be started or stopped according to the control data . However, since the control data is not a mandatory signal, the execution of the control value included in the control data can be determined by the determination of the agent device 110. [

In the community, the agent devices 110 can be hierarchically arranged, and the agent devices 110 disposed at each layer can independently transmit and receive information while communicating with the machine learning device 120.

The hierarchical structure of the community will be described with reference to Figs. 2 to 5. Fig.

2 is a diagram showing a hierarchical structure of a community.

2, a community energy management agent (CEMA) is located at the highest community level and at least one building energy management agent (BEMA) is connected to the community agent (CEMA) at the following building level Located. At least one zone agent (ZEMA) is connected to each building agent (BEMA) at the next zone level, and each zone agent (ZEMA) is located at the lowest sensor network level Energy devices - such as HAVC devices, lighting devices, and personalization devices - such as a personal computer (PC) - meters, sensors, and so on.

3 is a system configuration diagram of a community level.

Referring to FIG. 3, at least one building 310 is located in the community. The community may include community devices not belonging to the building 310, for example, a community may include a community load 320 - a streetlight, a traffic signal system, and so on. The community may include a community distributed power source 330, a community ESS (Energy Storage System) 340, a community EV (electric vehicle) charging station 350, etc. as a community device.

The community may include all of the above-described community devices-community load 320, community distributed power 330, community ESS 340, community EV charging station 350, or may include only at least one community device have.

The community has a community agent (CEMA) that manages the energy of the community as a whole. The community agent (CEMA) is associated with the building agent (BEMA) located in each building (310), and supervises each building agent (BEMA). The community agent CEMA is connected to the community devices 320, 330, 340, and 350 that do not belong to the respective buildings and acquires the state information of the community devices 320, 330, 340, and 350, And controls each of the community devices 320, 330, 340, and 350.

4 is a system configuration diagram of a building level.

Referring to FIG. 4, each building is subdivided into at least one zone 410.

The person building the energy management system according to one embodiment can subdivide each building into a plurality of thermal zones. Here, the thermal zone may mean a zone in which a thermal energy device - for example, a cooling / heating device - is independently controlled. Different thermal zones can be controlled in different thermal states. For example, the first thermal zone may be controlled at a room temperature of 23 degrees, and the second thermal zone may be controlled at a room temperature of 28 degrees.

The building may include building devices that do not belong to each zone 410. For example, the building may include a building load 420 - an elevator load, etc., a building distributed power source 430, a building ESS 440, a building EV charging station 450, and the like.

The building has a building agent (BEMA) that manages the energy of the entire building. The building agent (BEMA) is associated with a zone agent (ZEMA) located in each zone 410, and administers each zone agent (ZEMA). In addition, the building agent BEMA is connected to the building devices 420, 430, 440, and 450 that are not included in each zone, and acquires status information of the respective building devices 420, 430, 440, and 450, And controls each of the building devices 420, 430, 440, and 450.

5 is a system block diagram of a zone level.

Referring to FIG. 5, energy zones 312 and 314 and personalization equipment 316 may be located in each zone.

The personalization device 316 is an electric device that reflects the characteristics of the individual. For example, a personal computer (PC), a desk stand illumination, and the like belong to the personalization device 316. The energy devices 312 and 314 are electric devices not corresponding to the personalization device 316 and are mainly electric devices for controlling the environment of each zone. For example, a heating, ventilation, and Ari condition (HVAC) device 312 and a lighting device 314 belong to an energy device. Devices 312, 314, and 316 may be attached with device sensors 560. The device sensor 560 may be, for example, a sensor for the on-off state of the devices 312, 314, and 316 and may be a meter that monitors the energy usage of the devices 312, 314,

A plurality of sensors may be located in each zone. For example, a temperature sensor 520, a CO2 sensor 530, a humidity sensor 540, an illuminance sensor 550, and the like may be located in each zone.

The sensors 520, 530, 540, 550 and the instrument sensor 560 may constitute the sensor network 510. The configurations of the sensor network 510 may then communicate measurement values to the zone agent (ZEMA) while communicating with the zone agent (ZEMA).

The zone is located with the Zone Agent (ZEMA), which manages the energy of the entire area. The zone agent ZEMA obtains the measurement data from the sensors 520, 530, 540 and 550 and the energy energy usage data from the energy devices 312 and 314 and the personalization device 316 Which can be regarded as a kind of measurement data).

Energy management systems can use the hierarchical structure of the community to predict energy demand.

First, energy demand is predicted for each zone.

The zone agent (ZEMA) located in each zone transmits the environmental data acquired from the sensor network and the energy consumption data of the equipment obtained from the electric equipment to the machine learning device and receives the zone energy demand forecast data.

When energy demand is predicted for each district, energy demand for each building is predicted next.

The building agent (BEMA) located in each building transmits the zone energy demand forecast data for each zone and the status information of the building devices not belonging to each zone to the machine learning device and receives the building energy demand forecast data.

When energy demand is predicted for each building, then the energy demand for the entire community is predicted.

The Community Agent (CEMA) transmits the building energy demand forecast data for each building and the status information of the community devices not belonging to each building to the machine learning device and receives the community energy demand forecast data.

This hierarchical structure of the energy management system enables forecasting of energy demand for each district.

The energy management system can estimate the number of occupants using a machine learning device.

The energy management system can predict the number of occupants in each zone before anticipating the energy demand for the zone. The energy management system can predict the number of occupants first, thereby improving user convenience and energy efficiency for residents in each area.

The machine learning model for estimating occupancy numbers can include temperature data, humidity data, CO2 data, and personalization appliance energy usage data as input data. Temperature data, humidity data, CO2 data, and personalization appliance energy usage data are all variables related to attendance. For example, an increase in the number of occupants in each zone leads to a higher CO2 concentration. The machine learning model learns the relationship between the concentration of CO2 and the number of occupants, and predicts the number of occupants when CO2 data is input at the prediction stage. Personalization energy consumption data can also be closely correlated with the number of occupants. For example, if your PC is in a high energy state, it may mean that the person who runs the PC is in that area. The machine learning model learns the relationship between the energy consumption data of the personalization device and the number of occupants, and when the personal consumption energy consumption data is input at the prediction stage, the number of occupants can be predicted.

The machine learning model can further use roughness data or near field communication (Bluetooth) data with the user terminal as input data. In order to generate the local area communication data, a local area communication device (for example, a Bluetooth device) may be arranged in each area. Such a short-range communication device can determine whether the user is located indoors through short-range communication with a user terminal (e.g., mobile phone) and generate it as short-range communication data.

The machine learning model may use both temperature data, humidity data, CO2 data, and personalization device energy usage data as input data, but depending on the embodiment, only a part of the data may be used as input data. For example, a machine learning model can calculate the number of lost workers using CO2 data as input data. According to the embodiment, the temperature data, the humidity data, and the device energy usage data for the personalization device may be further included as input data.

The machine learning model can compare the occupancy number prediction data with the actual data to generate error data and change the parameters and structure in the machine learning model so that the error value in the error data becomes small. At this time, each zone may not include a sensor for measuring the number of occupants. In such a situation, the machine learning model can utilize other information to acquire actual data. For example, a zone agent (ZEMA) may include a UI device, and the user input information may be utilized as measured data of the machine learning model at irregular intervals through the UI device.

The machine learning model can generate as well as occupancy patterns. The occupancy pattern can be a value indicating the reoccurrence according to the passage of time, and the machine learning model can also generate this occupancy pattern. The machine learning apparatus can generate occupant estimation information including the occupant number and occupant pattern through the machine learning model and generate the area energy demand forecast data using the occupant estimation information.

The energy management system can generate control scenarios for equipment located in the zone in addition to the number of occupants by means of a machine learning device. At this time, the machine learning apparatus can predict the user convenience and create the control scenario so that the user convenience is maintained at a predetermined value or more.

Meanwhile, the energy management system according to an exemplary embodiment may generate a virtual agent to provide a fault-tolerant function.

6 is a diagram for explaining a fault-tolerant function according to an embodiment.

In one embodiment, the agent devices may be hierarchically arranged, where the parent agent (HEMA) creates a virtual agent (VEMA) replacing the failed subagent (LEMA) and the virtual agent (VEMA) ).

A parent agent (HEMA) is a relative concept, for example, for a zone agent, a building agent or a community agent corresponds to a parent agent (HEMA), where the zone agent can be a subagent (LEMA). As another example, a community agent may function as a parent agent (HEMA) for a building agent, where the building agent may function as a subagent (LEMA).

Referring to FIG. 6, the subagent (LEMA) may manage measurement data obtained from the sensor network 620 over the network. The sub-agent (LEMA) sends the measurement data obtained from the sensor network 620 to the machine learning device (e. G., ≪ RTI ID = 0.0 > 120).

The machine learning apparatus 120 can generate energy demand prediction data of the corresponding region through the first machine learning model including the measurement data as input data. Then, the sub-agent (LEMA) can control the appliance 610 of the corresponding area according to the optimization data generated based on the energy demand prediction data.

Meanwhile, the machine learning device 120 may generate failure information for the sub-agent (LEMA) using the measurement data received from the sub-agent (LEMA). For example, the machine learning device 120 may generate failure information for the sub-agent (LEMA) through a second machine learning model that includes some of the measurement data received from the sub-agent (LEMA) as input data .

The generated fault information can be transmitted to the parent agent (HEMA) and utilized. The HEMA checks the fault information and generates a virtual agent (VEMA) when it is judged that a failure has occurred in the subagent (LEMA) or a failure is predicted to occur. The virtual agent (VEMA) LEMA).

A virtual agent (VEMA) can belong to the same hardware as the parent agent (HEMA) in hardware. The virtual agent (VEMA) is generated by software. The host agent (HEMA) may have a hardware specification capable of generating the virtual agent (VEMA) more than the number of the subordinate agents (LEMA) to be managed.

If the virtual agent (VEMA) replaces the subagent (LEMA), the existing data transmission / reception path can be changed. For example, data may be transmitted and received along path 1 shown in FIG. 6 before the sub-agent (LEMA) is replaced. The measurement data generated in the sensor network 620 is transmitted along the path 1 to the sub-agent (LEMA), and the sub-agent (LEMA) can transfer the measurement data along the path 1 to the machine learning device 120. Then, the machine learning apparatus 120 transmits energy demand forecast data and / or optimization data to the sub-agent (LEMA) along path 1, and the sub-agent (LEMA) transmits the control signal to the apparatus 610 Lt; / RTI >

From the time when the virtual agent (VEMA) replaces the sub-agent (LEMA), the data transmission / reception path can be changed from the path 1 to the path 2. The measurement data generated in the sensor network 620 may be transmitted to the virtual agent (VEMA) along the path 2 via the network. At this time, since the virtual agent (VEMA) and the parent agent (HEMA) are installed in the same device in hardware, it can be understood that the measurement data is substantially transferred to the virtual agent (VEMA) via the parent agent (HEMA).

Then, the virtual agent (VEMA) transmits the received measurement data to the machine learning apparatus 120, and the machine learning apparatus 120 transmits the energy demand prediction data and / or the optimization data to the virtual agent (VEMA) Lt; / RTI > Then, the virtual agent (VEMA) can transmit the control signal to the device 610 via the path 2.

The data transmission / reception path may be changed by changing the network configuration, by changing the settings of the router, or by changing the settings of the sensor network 620, the device 610, and the like.

Meanwhile, the machine learning apparatus 120 can generate and manage independent blocks for each agent.

FIG. 7 is a block diagram of an agent block of a machine learning apparatus according to an embodiment, and FIG. 8 is an internal block diagram of an agent block according to an embodiment.

Referring to FIG. 7, the machine learning apparatus 120 can generate and manage independent agent blocks 710a, 710b, and 710c for each agent. For example, the machine learning device 120 may generate a zone agent block 710a for each of the zone agents, a building agent block 710b for each of the building agents, and a community agent block 710c.

Referring to FIG. 8, the agent block 710 may include portions for generating prediction data and / or optimization data, and portions for generating failure information and corresponding portions.

Various data received from the agent apparatus can be transmitted to the preprocessing units 822, 832, and 842 through the data receiving unit 810. [ The pre-processing units 822, 832, and 842 may include a filtering function for removing noise, and may generate secondary data by processing raw data. For example, the preprocessing units 822, 832, and 842 can generate power data using voltage data and current data. The data processed in the preprocessing units 822, 832, and 842 may be transferred to subsequent blocks.

The data processed by the first preprocessing unit 822 may be transmitted to the occupant estimating unit 824. [ The occupant estimating unit 824 can estimate occupancy of a specific region through a third machine learning model including transmitted data as input data. The estimated number of occupants or occupancy patterns can be transmitted to the agent apparatus via the data transmission unit 850 and utilized in another block (e.g., prediction unit 834).

The data processed by the second preprocessing unit 832 may be transmitted to the predicting unit 834. [ The prediction unit 834 can generate energy demand prediction data of a specific region through a first machine learning model including transmitted data as input data. For example, the predictor 834 of the agent block 710 corresponding to the zone agent may determine the energy of the corresponding zone through the first machine learning model including the first zone data of the zone data received from the zone agent as input data Demand forecast data can be generated. The first zone data may include, for example, measurement data generated in the sensor network or user data generated by the user's settings, e.g., the user's preferred room temperature, indoor illumination, and the like.

The energy demand prediction data generated by the prediction unit 834 may be transmitted to the agent apparatus via the data transmission unit 850 and utilized in another block (for example, the optimization unit 836).

The optimizing unit 836 can generate optimization data of the corresponding region through the fourth machine learning model including the energy demand prediction data generated by the predicting unit 834 and the user data as input data. The optimization data may be transmitted to the agent apparatus via the data transmission unit 850. [

The data processed by the third preprocessing unit 842 may be transmitted to the failure detection unit 844. The failure detection unit 844 can generate failure information of the agent device through the second machine learning model including the transmitted data as input data. For example, the failure detection unit 844 of the agent block 710 corresponding to the zone agent may detect the failure of the zone agent through the second machine learning model including the second zone data of the zone data received from the zone agent as input data. It is possible to generate fault information. The second zone data may include, for example, status data for devices and sensor networks, control data for devices consuming power, energy usage data for devices consuming power, control data for sensor networks, Control data for devices that generate power, energy generation data for devices that generate power, control data for devices connected to external systems, data received from devices connected to external systems, and the like.

The failure detection unit 844 generates the failure information and transmits the failure information to the agent apparatus via the data transmission unit 850 and to the other blocks (for example, the failure processing unit 846).

The failure processing unit 846 can determine a failure of the sub-agent based on the failure information, generate a control process corresponding to the failure, and transmit the generated control process to the parent agent apparatus.

9 is a diagram showing input / output data of a failure detection model (second machine learning model) according to an embodiment.

9, the failure detection model 910 includes status data for the device, the sensor network, and the agent device, control data for consuming devices consuming power, energy usage data for consuming devices consuming power, The control data for the power generation equipment that generates power, the energy generation amount data for the power generation equipment for generating power, the control data for the external system linkage device, the data received from the external system linkage device And the like as input data.

Then, the failure detection model 910 can generate failure information. The fault information may include fault information. The fault information may include fault conditions and fault types. The fault type may be, for example, a communication failure, a system failure, or the like.

The failure information may include failure prediction information. The failure prediction information may include a failure prediction level and a failure type. For example, when the failure prediction level is 10, the failure prediction level is 10, and if the failure prediction level is 1, the failure prediction level may be an initial stage of the failure .

The failure information can be compared with the actual data, and the difference between the failure data and the actual data can be fed back to the failure detection model 910 as error data. The failure detection model 910 can learn the internal variable so that the error value contained in the error data becomes small.

Some of the data input to the failure detection model 910 may be time series data. The failure detection model 910 can be learned by receiving such time series data. Here, the time series data is data for confirming the time at which the included information is generated, and the time series data may include the information generation time together with information or information generated at a predetermined period. For example, the failure detection model 910 may periodically receive status data, which may generate failure information based on the duration of the status data, the frequency with which the status data is missing, and so on.

10 is a first exemplary control flow diagram of an energy management system according to an embodiment.

Referring to FIG. 10, the machine learning apparatus can check the failure information and determine whether the failure type is a communication failure (S1002).

If the failure type is a communication failure (YES in S1002), the machine learning apparatus can adjust the data amount of the agent apparatus (S1004). For example, the machine learning device may send a control signal to the zone agent, such that, if the fault type is a communication failure, some of the zone data received from the zone agent is not transmitted or received.

At this time, the data to which transmission / reception is restricted may be low-importance data. In the zone data, importance can be set for each data, and the machine learning apparatus can control the zone agent so that low importance data of the zone data is not transmitted or received.

Specifically, in step S1004, the machine learning apparatus can increase the importance level variable and control the agent apparatus so that data corresponding to the importance level variable is not transmitted or received.

The machine learning apparatus can control the parent agent to replace the subagent as a virtual agent when the communication failure persists for a predetermined time or more.

As another example, if the communication failure continues and the importance level variable becomes equal to or greater than a preset value (N, N is a natural number) (NO1 in S1006), the machine learning apparatus performs control can do.

If the communication failure persists and the importance level variable is smaller than a preset value (N, N is a natural number) (YES in S1006), the machine learning apparatus waits for a predetermined period of time and re-executes step S1004.

Then, when the failure of the machine learning apparatus is not sustained (NO2 in S1006), the situation can be terminated.

If the failure type is not a communication failure (NO in step S1002), or if a communication failure lasts for a predetermined time or longer and the virtual agent replaces the subagent, the parent agent can create and initialize the virtual agent (S1008). The communication path via the failed sub-agent may be reconfigured to a communication path via the virtual agent (S1010).

11 is a second exemplary control flow diagram of an energy management system according to an embodiment.

Referring to FIG. 11, when a failure prediction level is generated, a machine learning apparatus can cause a parent agent to create a virtual agent and initialize a virtual agent (S1102). The parent agent can receive the system configuration data including the information of the sensors and devices managed by the sub-agent from the sub-agent or the machine learning device, and apply the received system configuration data to the virtual agent.

The machine learning apparatus can compare the failure prediction level included in the failure information with a preset reference level (L, L is a natural number) (S1104).

If the failure prediction level is equal to or higher than a preset reference level (NO in S1104), the subagent can be replaced with the virtual agent and the communication path can be reset (S1112). Then, the machine learning apparatus or the parent agent may terminate the sub-agent or block data transmission / reception of the sub-agent (S1114).

If the failure prediction level is lower than a predetermined reference level (YES in S1104), the parent agent may control the virtual agent to back up data (e.g., measurement data) that the virtual agent collects in the subagent (S1106) . At this time, the virtual agent can receive data from the machine learning device.

The machine learning apparatus continuously monitors the failure prediction level. If the failure prediction level is lower than the reference level (YES in S1108), the machine learning apparatus can re-execute the step S1106 of backing up the data.

If the failure prediction level becomes higher than the reference level (NO in S1108), the host agent may reset the communication path (S1112) and terminate the subagent (S1114).

As described above, according to the present embodiment, in the energy management system, even if a defect or a failure occurs in the hardware or software constituting the system, the function can be normally or partially performed.

It is to be understood that the terms "comprises", "comprising", or "having" as used in the foregoing description mean that the constituent element can be implanted unless specifically stated to the contrary, But should be construed as further including other elements. All terms, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Commonly used terms, such as predefined terms, should be interpreted to be consistent with the contextual meanings of the related art, and are not to be construed as ideal or overly formal, unless expressly defined to the contrary.

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, 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 construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

Claims (15)

A zone agent that manages the energy of a section of the building;
A building agent for managing energy of the building based on the zone agent data obtained from the plurality of zone agents;
A community agent for managing energy of a community based on building agent data acquired from a plurality of the building agents; And
Generates energy demand prediction data of the zone through a first machine learning model including first zone data as input data from the zone data received from the zone agent and includes second zone data of the zone data as input data And a remote device for generating failure information of the zone agent via a second machine learning model,
Wherein the building agent creates a virtual agent that replaces the zone agent according to the failure information. The method according to claim 1,
And the second machine learning model inputs the third zone data of the second zone data as time series data. The method according to claim 1,
The remote device comprising:
Generating the failure information including a failure prediction level,
Wherein the building agent comprises:
And replaces the zone agent with the virtual agent if the failure prediction level is equal to or greater than a preset reference level. The method of claim 3,
Wherein the building agent comprises:
And to control the virtual agent to back up the measurement data collected by the zone agent if the failure prediction level is lower than the reference level. The method according to claim 1,
The remote device comprising:
Generates the fault information including a fault type and controls the zone agent so that a part of the zone data is not transmitted or received when the fault type is a communication failure. 6. The method of claim 5,
Wherein the building agent comprises:
And replaces the zone agent with the virtual agent if the communication failure persists for a predetermined time or longer. 6. The method of claim 5,
In the zone data, importance is set for each data,
The remote device comprising:
Wherein the zone agent is controlled so that data of low importance is not transmitted or received among the zone data. The method according to claim 1,
Wherein the building agent comprises:
Receiving from the zone agent system configuration data including information of sensors and devices managed by the zone agent and applying the system configuration data to the virtual agent. In a way to manage the energy of the community,
Managing the energy of a zone where the zone agent comprises the building;
Managing the energy of the building based on zone agent data obtained from the plurality of zone agents;
Managing community energy based on building agent data obtained from a plurality of building agents;
The remote device generates energy demand prediction data of the zone through a first machine learning model including first zone data of the zone data received from the zone agent as input data and outputs second zone data of the zone data Generating fault information of the zone agent through a second machine learning model included as input data; And
The building agent creating a virtual agent replacing the zone agent in accordance with the failure information
Lt; / RTI > A sensor network installed in a part of a building;
A zone agent for managing measurement data obtained from the sensor network;
A building agent for receiving and managing system configuration data including setting information of the sensor network from the zone agent; And
A second machine learning model that generates energy demand prediction data of the zone through a first machine learning model including the measurement data received from the zone agent as input data and includes a part of the measurement data as input data, And a remote device for generating fault information of the zone agent via the network,
Wherein the building agent creates a virtual agent that replaces the zone agent in accordance with the failure information, and applies the system configuration data to the virtual agent. 11. The method of claim 10,
Wherein the virtual agent acquires energy demand forecast data of the zone using the same first machine learning model as the zone agent. 11. The method of claim 10,
The remote device comprising:
Generating the failure information including a failure prediction level,
Wherein the building agent comprises:
And replaces the zone agent with the virtual agent if the failure prediction level is equal to or greater than a preset reference level. 13. The method of claim 12,
Wherein the building agent comprises:
And to control the virtual agent to back up the measurement data collected by the zone agent if the failure prediction level is lower than the reference level. 14. The method of claim 13,
The remote device comprising:
Receive the measurement data from the zone agent, and forward the measurement data to the virtual agent. 11. The method of claim 10,
The remote device comprising:
Wherein the zone agent is configured to generate the failure information including a failure type and to control the zone agent so that data having a priority level lower than a reference value is not transmitted or received when the failure type is a communication failure.

Images