Measure reinterpretation system and measure reinterpretation method

Abstract

This measure reinterpretation system holds area information including a device configuration and an implemented measure in each of a plurality of areas subject to environmental management. The system receives designation of a measure condition relating to a specific area, specifies a reference area having a device configuration that matches or is similar to that of the specific area, and extracts a related measure corresponding to the measure condition from the implemented measure relating to the reference area. Starting from an adjustment target device of the same type as the device adopted in the related measure among devices in the specific area indicated by the area information, the system determines an operation amount of an operation device that can be affected by the control on the basis of information or the like on the device adopted in the related measure.

Description

Policy reinterpretation system and policy reinterpretation method

[0001] This invention generally relates to a policy reinterpretation system and a policy reinterpretation method, and more specifically to a novel technology that can support efficient facility management (e.g., energy management) by taking into account a wide range of environmental factors within the facilities under management.

[0002] In recent years, appropriate facility management that contributes to environmental improvement in buildings such as office buildings and factories is desired not only from the perspective of simple cost reduction, but also from the perspective of the so-called SDGs (Sustainable Development Goals). Energy management is one example of facility management.

[0003] As a prior art related to the above-mentioned energy management, for example, the one described in Patent Document 1 has been proposed. Patent Document 1 discloses a technique for pre-presenting the control results when control rules are applied and calculated to satisfy the power reduction target amount in demand response.

[0004] Japanese Patent Publication No. 2013-236520

[0005] In facility management operations such as energy management, measures are considered and implemented to achieve improvements in the target area (for example, maintaining a temperature within a specified range and saving energy), based on the condition of designated areas and installed equipment within the facility under management (for example, temperature, humidity, and power consumption of air conditioners observed in those areas), as well as past measures implemented regarding the facility (for example, energy management measures) and the observation data from those measures.

[0006] On the other hand, because the resources for personnel and equipment for facility management are limited, policy considerations are often limited to specific areas. Therefore, considering the structure of facilities (such as office buildings) where the existence of numerous areas dramatically increases the types and volume of information to be handled, and the dependencies between these pieces of information tend to be complex, it is difficult to consider policies for a specific area.

[0007] Furthermore, when new equipment or fixtures are introduced, replaced, or discarded, or when the layout is changed within such managed areas, it can lead to significant environmental changes within those areas from a facility management perspective. The preconditions for considering measures for those managed areas will differ before and after such environmental changes. Therefore, measures implemented in the past within those managed areas are difficult to use as reference cases when considering measures after the aforementioned environmental changes. In this case, the facility manager's consideration of measures tends to become trial and error, increasing the likelihood of wasting a lot of time and effort.

[0008] The policy reinterpretation system comprises a memory device and a processor. The memory device holds area information, which includes information on the equipment configuration and implemented measures for environmental management in each of a plurality of areas subject to environmental management. The processor receives a specification regarding policy conditions for environmental management for a specific area, identifies a reference area from among the areas indicated by the area information that has an equipment configuration that matches or is similar to that of the specific area, and extracts related measures from among the implemented measures for the reference area that correspond to the policy conditions. The processor determines the amount of operation for operating devices that may be affected by the control of the operating device, starting from an adjustment target device of the same type as the device adopted in the related measures, based on the information of the device adopted in the related measures and the observed values ​​of the predetermined events.

[0009] According to the present invention, by taking into account a wide range of environmental factors within the facility being managed, it becomes possible to support efficient facility management.

[0010] This is a diagram of an example network configuration including a policy reinterpretation system in an embodiment. This is a diagram of an example hardware configuration of the policy reinterpretation system in an embodiment. This is a diagram of an example functional configuration of the policy reinterpretation system in an embodiment. This is a diagram of an example flow of the policy reinterpretation method in an embodiment. This is a diagram of an example inter-area relationship table in an embodiment. This is a diagram of an example flow of the policy reinterpretation method in an embodiment. This is a diagram of an example flow of the policy reinterpretation method in an embodiment. This is a diagram of an example policy overview of policy information in an embodiment. This is a diagram of an example operating device and content of policy information in an embodiment. This is a diagram of an example type information in device / sensor information in an embodiment. This is a diagram of an example relationship information in device / sensor information in an embodiment. This is a diagram of an example observation sensor state in device / sensor information in an embodiment. This is a diagram of an example setting state of operating device in device / sensor information in an embodiment. This is a diagram of an example graphical model in an embodiment. This is a diagram of an example policy overview in an embodiment. This is a diagram of an example operating device and content in an embodiment. This is a diagram of an example of changed device type and number (average) in an embodiment. This is a diagram of an example graphical model in an embodiment. This is a diagram of an example pre- and post-policy calculation results for observation sensors in an embodiment. This is a diagram of an example pre- and post-policy calculation results for observation sensors in an embodiment. This figure shows an example of the calculation results of the observation sensor before and after the measures taken in the embodiment. This figure shows an example of the change in the observation sensor in the embodiment. This figure shows an example of the power state change rate in the embodiment. This figure shows an example of the setting value change (average) in the embodiment. This figure shows an example of the sensor change amount (average) in the embodiment. This figure shows an example of the output result in the embodiment. This figure shows an example of the UI screen in the embodiment. This figure shows a detailed example of a part of the UI screen shown in Figure 19A.

[0011] In the following description, "processor" refers to an arithmetic unit and may be one or more processor devices. At least one processor device may typically be a microprocessor device such as a CPU (Central Processing Unit), but may also be other types of processor devices such as a GPU (Graphics Processing Unit). At least one processor device may be single-core or multi-core. At least one processor device may be a processor core. At least one processor device may be a broad-sense processor device such as a hardware circuit that performs some or all of the processing (e.g., FPGA (Field-Programmable Gate Array), CPLD (Complex Programmable Logic Device), or ASIC (Application Specific Integrated Circuit)).

[0012] Furthermore, in the following explanation, "storage device" may refer to one or more persistent storage devices, which are examples of one or more storage devices. Persistent storage devices are typically non-volatile storage devices, and specifically may be, for example, HDDs (Hard Disk Drives), SSDs (Solid State Drives), or NVMe (Non-Volatile Memory Express) drives.

[0013] Furthermore, in the following explanation, "memory" refers to one or more memory devices, which are an example of one or more storage devices. At least one memory device in memory may be a volatile memory device or a non-volatile memory device.

[0014] Furthermore, in the following description, "communication device" may refer to one or more communication interface devices. One or more communication interface devices may be one or more identical communication interface devices (for example, one or more NICs (Network Interface Cards)) or two or more different communication interface devices (for example, a NIC and an HBA (Host Bus Adapter)).

[0015] Furthermore, in the following explanation, we may use expressions such as "xxx table" or "xxx database" to describe information from which an output is obtained for a given input. This information can be data of any structure (for example, structured data or unstructured data), or it can be a neural network that generates an output for a given input, a learning model such as a genetic algorithm or a random forest. Therefore, "xxx table" or "xxx database" can be referred to as "xxx information." Also, in the following explanation, the configuration of each database or table is just an example, and one database or table may be divided into two or more databases or tables, or all or part of two or more databases or tables may be a single database or table.

[0016] Furthermore, in the following explanation, the subject of the process may be "program," but since a program is executed by the CPU and performs defined processes using memory devices and / or interface devices as appropriate, the subject of the process may also be the CPU (or a device such as a controller having that processor). A program may be installed from a program source into a device such as a computer. The program source may be, for example, a program distribution server or a computer-readable (e.g., non-temporary) recording medium. Also, in the following explanation, two or more programs may be implemented as a single program, or one program may be implemented as two or more programs.

[0017] Furthermore, in the following explanation, when describing similar elements without distinction, the common part of the reference code may be used, and when describing similar elements with distinction, the reference code or element identifier may be used.

[0018] Figure 1 shows an example of a network configuration including the policy reinterpretation system 1 in this embodiment.

[0019] The policy reinterpretation system 1 is a system that supports efficient facility management (e.g., energy management) by taking into account a wide range of environmental factors within the facilities under management. This policy reinterpretation system 1 is connected to external servers 2, external systems 3, and input / output devices 17 via the network N as needed, enabling coordinated operation. However, the policy reinterpretation system 1 is primarily responsible for executing the policy reinterpretation method.

[0020] In the above configuration, external server 2 is a server capable of distributing various information regarding facilities subject to environmental management by the policy reinterpretation system 1. A specific example of such a server is a server that provides weather information such as weather, temperature, and humidity at the location of the facility. External system 3 could be, for example, a business system that observes and manages data for the policy reinterpretation system 1 regarding the facilities subject to management. This external system 3 is a system that manages equipment and sensors installed at the facilities subject to management and can appropriately manage and distribute data on their operation and observed values. It should be noted that the policy reinterpretation system 1 may have some or all of the configurations and functions of external server 2 and external system 3.

[0021] Furthermore, the input / output device 17 is a device that handles the input and output of data to the policy reinterpretation system 1, and includes an input unit 171 consisting of a keyboard, mouse, microphone, etc., and an output unit 172 consisting of a display, speaker, touch panel, printer, etc.

[0022] Figure 2 shows an example of the hardware configuration of the policy reinterpretation system 1.

[0023] The policy reinterpretation system 1 includes a processor 11, a main memory 12, an auxiliary memory 13, a user IF 14, and a communication IF 15. "IF" is an abbreviation for interface device.

[0024] The processor 11 retrieves and executes programs stored in the auxiliary storage device 13 from the main storage device 12, performing overall control of the system itself, as well as various judgment, calculation, and control processing. In other words, the functional units corresponding to the policy reinterpretation method implemented in the policy reinterpretation system 1 (see Figure 3: input unit 171, related policy extraction unit 121, policy reinterpretation unit 122 (target equipment search unit 1221, operation amount calculation unit 1222), and output unit 172) are implemented by the processor 11 reading programs from the main storage device 12 and executing them.

[0025] Furthermore, some of the processing performed by the processor 11 when executing a program may be performed by other arithmetic units (for example, hardware such as ASICs or FPGAs). Details of the above-mentioned functional units will be described later.

[0026] Furthermore, the generation AI / machine learning model 123 may be used in part of the processing performed by at least one of the related policy extraction unit 121 and the policy reinterpretation unit 122 (for example, at least one of policy extraction and effect calculation). In other words, this generation AI / machine learning model 123 may be responsible for generating the processing results in the related policy extraction unit 121 and the policy reinterpretation unit 122. The generation AI / machine learning model 123 means generation AI and / or machine learning model. The generation AI is, for example, a large-scale language model, which is trained using external data (i.e., data provided externally, not as a set of explanatory variables and objective functions in each process of the related policy extraction unit 121 and the policy reinterpretation unit 122) as training data. On the other hand, the machine learning model is a model that, in each process of the related policy extraction unit 121 and the policy reinterpretation unit 122, is trained using the set of explanatory variables and objective functions in each process as training data in a learning engine with the dataset of explanatory variables and objective variables in that process. The generation AI / machine learning model 123 may generate the results of each of the above processes by inputting area information, policy conditions, and other specified content and predetermined constraints. The generation AI / machine learning model 123 may be included in at least one of the related policy extraction unit 121 and the policy reinterpretation unit 122, or it may be an external module of each of the related policy extraction unit 121 and the policy reinterpretation unit 122.

[0027] The program executed by the processor 11 may be provided to the policy reinterpretation system 1 via removable media (CD-ROM, flash memory, etc.) or network N, and stored in a non-volatile auxiliary storage device 13, which is a non-temporary storage medium.

[0028] Furthermore, the main memory 12 is a storage means composed of a volatile storage device such as RAM (Random Access Memory). The main memory 12 may also be a non-volatile storage element such as ROM (Read Only Memory). ROM stores immutable programs (for example, the BIOS).

[0029] Furthermore, the auxiliary storage device 13 is a storage means composed of non-volatile storage devices such as a hard disk drive or an embedded multimedia card. The data held by the auxiliary storage device 13 includes programs, including the OS (Operating System), as well as area information 130.

[0030] This area information 130 includes area-specific policy information 131, equipment / sensor information 132, and inter-area relationship table 133. Of these, the equipment / sensor information 132 consists of type information 1321, status information 1322, and relationship information 1323. Specific examples of the composition of these various types of information will be described later. Note that "equipment / sensor" can be interpreted as equipment and / or sensors.

[0031] Furthermore, the user interface 14 has the function of connecting to and controlling the input / output device 17. The communication interface 15 is a device that connects to the network N and communicates with the external server 2 and the external system 3.

[0032] The policy reinterpretation system 1 is a computer system that is configured on a single physical computer, or on multiple computers configured logically or physically, and may operate on a virtual computer built on multiple physical computing resources. The policy reinterpretation system 1 may be configured on the cloud, or it may be on-premises configured on a specific computer (hardware).

[0033] Furthermore, the network N connecting the policy reinterpretation system 1, the external server 2, and the external system 3 may be the internet, LAN (Local Area Network), WAN (Wide Area Network), or a mobile phone network, but is not limited to these. Here, as an example of a mobile phone network, a general public network, whether wired or wireless, such as the fifth-generation mobile communication system, or so-called 5G (5th Generation), which enables "massive simultaneous connections" and "ultra-low latency," may be used. Of course, by taking advantage of the features of newer mobile phone systems beyond 5G, secondary effects such as faster processing and higher resolution rendering of output information in the policy reinterpretation method according to the present invention can also be expected.

[0034] Furthermore, data exchange between the policy reinterpretation system 1 and external servers 2 and 3 may be carried out, for example, according to an API (Application Programming Interface) protocol. In that case, it is assumed that each device has already implemented the functions and configurations necessary to perform API-based request and response processing.

[0035] Figure 3 shows an example of the functional configuration of the policy reinterpretation system 1.

[0036] To explain the overall processing flow, the user (for example, a person in charge) inputs the specific area to be processed and the policy conditions (e.g., target state in environmental management, acceptable range of observed values ​​for equipment or sensors) via the input unit 171. Accordingly, the related policy extraction unit 121 obtains the necessary information from the area information 130 (e.g., information on reference areas among each area whose equipment configuration matches or is similar to the specific area), and extracts related policies from the (past) implemented policies for the obtained reference areas that correspond to the policy conditions.

[0037] Further, the target device search unit 1221 in the policy reinterpretation unit 122 identifies a reference area in each area where the device configuration matches or is similar to the specific area, and extracts relevant policies corresponding to the user-specified policy conditions from the implementation policies regarding this reference area. In addition, the target device search unit 1221 identifies, among the devices in the specific area indicated by the area information 130, the operating devices that can be affected by the control by the adjustment target device starting from the adjustment target device arbitrarily selected by the user. The device serving as the starting point is an example, and any device in the target area (for example, a device of the same type as the device adopted in the relevant policy) may serve as the device as the starting point. Further, the operation amount calculation unit 1222 determines the operation amount based on the information of the device adopted in the above relevant policy and the observed value of the above predetermined event.

[0038] Note that the target device search unit 1221 identifies, as the above adjustment target device, among the devices in the specific area indicated by the area information 130, those that are of the same type as the devices adopted in the relevant policy and whose observed values of the predetermined event affected by the operation content deviate from the predetermined standard.

[0039] Further, the target device search unit 1221 calculates relationship information that defines the relationship between the device and the sensor from the time-series observed values obtained from the operation content of the device and the sensors of the events affected by the device indicated by the area information 130, and executes each process of identifying the reference area and identifying the operating device based on the relationship information. The relationship information calculated here is a graph in which the device and the sensor are used as nodes and the edges connect between the respective nodes.

[0040] Further, each piece of information obtained by the policy reinterpretation unit 122 is passed to the output unit 172 and output to the above user.

[0041] FIG. 4 is a diagram showing an example of a flow of the policy reinterpretation method in the present embodiment, and specifically, is a diagram showing an example of a processing flow in the relevant policy extraction unit 121.

[0042] Here, as a premise of the explanation, the target case is a case of supporting the environmental management work of the server room of a data center composed of a plurality of areas in a plurality of buildings.

[0043] Also, this person in charge designates the "area of Building 1_1F_101" as a specific area in the input unit 171, and as one of the policy conditions, at the time of "July 10, 2024", it is assumed that they are considering what policies should be implemented.

[0044] Then, it is assumed that the input unit 171 has received the designation of the specific area of "the area of Building 1_1F_101" designated by the above user, and the designation of "energy saving" as one of the policy purposes of the policy conditions.

[0045] In this case, the related policy extraction unit 121 of the policy reinterpretation system 1 creates a graphical model G10 (see FIG. 12) that connects each of the devices and sensors with edges using the relationship information 1323 (see FIG. 10B) of the device / sensor information 132 as nodes (S11). It is assumed that the related policy extraction unit 121 either holds a generation tool for such a graphical model G10 in advance or can appropriately call and use it via the network N.

[0046] Also, the above relationship information 1323 is a table that defines the relationships of control and observation of devices and sensors installed in the above specific area. In the relationship information 1323 shown in the example of FIG. 10B, the relationships of device connections and controls such as external equipment and switchboard power, air conditioners and switchboard power, and their intensities (relationship values) are defined. In the above example, such a graphical model G10 is constructed based on the relationship information 1323, etc., but it is also possible to directly adopt and use what has already been generated.

[0047] Subsequently, after generating the graphical model G10, the related policy extraction unit 121 determines whether the user designation of the reference area has been received by the input unit 171 (S12). As a result of this determination, if the designation of the reference area has been received (S12: YES), the related policy extraction unit 121 transitions the process to S17. On the other hand, as a result of the above determination, if the designation of the reference area has not been received (S12: NO), the related policy extraction unit 121 determines whether the area relationship table 133 (see FIG. 5) has been held (S13).

[0048] If, as a result of this determination, the inter-area relationship table 133 is not already held (S13: NO), the related measures extraction unit 121 uses the type, quantity, and status (observed values) of equipment and sensors indicated by the equipment / sensor information 132, and the graphical model G10 to calculate the inter-area similarity between the specific area to be adjusted and each of the other areas (S15).

[0049] If this similarity is calculated, for example, by comparing graphical models G10, the related policy extraction unit 121 uses a known graph similarity determination solver or a generating AI / machine learning model 123 to cluster each area based on vector data such as the number of operating devices (e.g., those with the power "ON") and the number of such devices and sensors installed, and determines that those with similar vector data have / high similarity.

[0050] In addition, other methods using the following information can also be adopted. In such cases, the similarity of values ​​between various events such as numerical information of equipment and sensors, fluctuations in sensor time-series data (for example, the change T40 of the observed sensor in Figure 16), floor area, number of installed devices, and external information (e.g., weather information such as indoor and outdoor temperature and humidity) may be determined, and the results may be aggregated. Figure 16 shows an example of the extracted result T40 of changes in observed sensors. For example, the observed sensors may be extracted from those with a change amount above a certain level for each type.

[0051] Now, let's return to the flow explanation. The related measures extraction unit 121 selects areas as reference areas in which the inter-area similarity value obtained in S15 is equal to or greater than a certain threshold (S16). In this embodiment, it is assumed that "Building 1_1F_101", "Building 1_2F_201", and "Building 2_3F_302-2" are selected as reference areas.

[0052] Based on the policy summary 1311 (see Figure 8) of the area-specific policy information 131, the above reference area corresponds to policy IDs 1, 2, 3, 4, and 5. On the other hand, the policy objective specified by the user as a policy condition, "energy saving," corresponds to policy IDs 1, 2, 3, and 4, excluding "5". Therefore, the related policy extraction unit 121 extracts policy IDs 1, 2, 3, and 4 as reference policies (S17).

[0053] Next, the related policy extraction unit 121, with respect to the reference policies extracted in S17, calculates the state before and after the implementation of the relevant policies within the target area using time-series data indicated by the observation sensor state 13231 (Figure 11A) and the setting state of the operating equipment 13232 (Figure 11B) in the equipment / sensor information 132, and the "date" indicated by the policy summary 1311 in the area-specific policy information 131. For example, it designates one day before the policy date as "Before" and one day after as "After," and the result of averaging the time-series data daily is the calculation result of the before and after policies shown in Figures 15A to 15C (S18). Note that in Figures 11A and 11B, the target area is Building 1_1F_101. In Figures 11A and 11B, the specified date and time are the same date and time (July 10, 2024 in this example). In Figure 11A, the data as observation sensor information 13231 represents the average temperature, humidity, and power for each day. In Figure 11B, the data as the setting status of the operating equipment 13232 represents the operating mode, set temperature, set humidity, and power status for each operating equipment. The set temperature and set humidity are examples of set values ​​for environmental items in the area. Figure 15A shows the pre- and post-measure calculation results T31 for the observation sensor for Building 1_1F_101 (Measure ID: 1). Figure 15B shows the pre- and post-measure calculation results T32 for the observation sensor for Building 1_2F-201 (Measure ID: 2, 3). Figure 15C shows the pre- and post-measure calculation results T32 for the observation sensor for Building 2_F_301-2 (Measure ID: 4).

[0054] If, as a result of the determination in S13, the inter-area relationship table 133 is already held (S13: YES), the related policy extraction unit 121 selects a reference area from the inter-area relationship table 133 whose relationship with the specified area is defined (S14). Subsequent processing will be the same as that in S17 and S18.

[0055] Figure 6 is a diagram showing an example of a policy reinterpretation method in an embodiment, and specifically, it is a diagram showing the processing flow by the target device search unit 1221.

[0056] In this case, the target device search unit 1221 determines whether the device / sensor to be adjusted has already been set in the input unit 171 (S21). If the result of this determination is that the device / sensor to be adjusted has already been set (S21: YES), the target device search unit 1221 proceeds to S23.

[0057] On the other hand, if the above determination indicates that the equipment / sensor to be adjusted has not been set in the input unit 171 (S21: NO), the target equipment search unit 1221 selects the equipment / sensor to be adjusted based on the results of comparing the state of the specified date and time (the date and time specified by the user as a measure condition) in the specific area with the target value (e.g., temperature) or setting range (e.g., the allowable range of deviation from the target value of temperature, etc.) of the operating equipment and observation sensor, which are the measure conditions (S22).

[0058] Here, the target device search unit 1221, in making the above selection, selects devices as devices to be adjusted if the deviation between the conditions, such as the target value and setting range, and the state (such as the observed value on the specified date) satisfies a predetermined condition (for example, devices whose deviation is greater than a predetermined deviation, or devices in the top N category with a relatively large deviation).

[0059] Next, the target equipment search unit 1221 calculates the following based on each record of "Operating Equipment and Content" T12 (see Figure 13B) for the above-mentioned related measures (Measure IDs = 1, 2, 3, 4; Measure Summary T11 (see Figure 13A)): the average value obtained by dividing the number of equipment counted for each type of operating equipment (e.g., air conditioners, outdoor air handling units, and humidifiers) by the number of measure IDs; the power status change rate for equipment of that type (calculating the percentage of records where the operation content is "power status change"); the operating mode change rate for equipment of that type (calculating the percentage of records where the operation content is "operating mode change"); and the setting value change rate (calculating the percentage of records where the operation content is "set temperature change" or "set humidity change") (S23). The result of this calculation is, for example, the changed equipment type and number (average) T21 shown in Figure 14A. Figure 13A and Measure Summary T11 may be data as an example of the measure extraction results by the related measure extraction unit 121. In Figure 13B, "Operating device and content" T12 may be data representing the policy, the name and type of operating device, the content of the operation, and the relationship before and after the operation. In Figure 13B, the search conditions may include the reference area "Building 1_1F_101, Building 1_2F_201, Building 2_3F_301-2" and the policy objective "Energy saving".

[0060] Furthermore, the target equipment search unit 1221 extracts the operating equipment and observation sensor groups related to the equipment to be adjusted from the graphical model of the operating equipment and observation sensors, starting from the equipment or sensor to be adjusted, using a search range such as the type and number of equipment to be adjusted (S24). Here, the operating equipment is defined as all types of energy-saving equipment (air conditioners, air handling units, humidifiers) on the reference floor. In this embodiment, all were extracted (however, the graphical model also includes hardware measures such as curtains and server equipment, which are not included in past measures and are therefore not selected), but for example, the value of "Number of Operating Equipment (Average)" in "Type and Number of Changed Equipment (Average)" T21 in Figure 12 (e.g., 2) could be set as the maximum number of searchable equipment for extraction. Also, as a method for searching for equipment etc. in the above extraction, a method can be adopted in which the node of the operating equipment is searched when the edge on the graphical model G10 is followed from the equipment / sensor to be adjusted. In this case, the search will continue until the number of operating equipment equal to the "Maximum Number of Searchable Equipment" is found. Figure 12 shows an example of a graphical model using information representing the type and / or relationship of equipment / sensors. In Figure 12, the target area is Building 1_1F_101.

[0061] In this process S24, the relevant operating equipment and observation sensor group are determined from the three types of equipment mentioned above and the search range with a search edge length of "2". In this case, the targets of the graphical model G20 (Figure 14B) and the output result T61 (Figure 18) are determined. For Figure 14B, the search conditions may include the adjustment target equipment "P1-1101-0" and the search edge length "2". The search edge length may be the edge length (number of edges) as the search range from the node corresponding to the adjustment target equipment. The output result T61 exemplified in Figure 18 shows the equipment name, type, equipment / sensor type, target, and status before and after operation for each operating equipment. The specified date and time is July 10, 2024, and the purpose is energy saving measures.

[0062] Figure 7 is a diagram showing an example of a policy reinterpretation method in an embodiment, and specifically, it is a diagram showing the processing flow by the operation amount calculation unit 1222.

[0063] In this case, the manipulated variable calculation unit 1222 calculates the status of the equipment to be adjusted, and each of the related operating equipment and observation sensors for the specified date and time (S31).

[0064] Next, the operation amount calculation unit 1222 uses the information of the target operation equipment and the observation sensor to calculate the operation amount of the related operation equipment (S32). As shown in Figure 14B, in this case, two "air conditioners" and one "outdoor air handling unit" are selected as search results, and the state on "2024 / 7 / 10" becomes the state in the "Before" column of the output result T61 (Figure 18).

[0065] In this calculation of the amount of manipulation, one air conditioner ("AC1-1101-0") and one outdoor air handling unit ("OAC1-1101-0") are ON. Based on the average number and type of changed equipment T21 (Figure 14A), the proportion of energy-saving measures is 50% for "power state change" and 50% for "temperature setting". Also, based on the average setting value change T52 (Figure 17B), the setting change value for the air conditioner is -2 to +2.33 degrees, so setting changes within this range are considered as the candidate range for change. Furthermore, based on the average number and type of changed equipment T21 (Figure 14A), the setting change for the outdoor air handling unit is 100% "power state change", so only ON / OFF is considered as the setting change range. The data T21 representing the type and number (average) of changed equipment may be an example of the search results from the target equipment search unit 1221, and may include data representing various change percentages for each type of operating equipment, such as the number of operating equipment, the power state change percentage, the operating mode change percentage, and the setting value change percentage. Figure 17A shows an example of data T51 representing the power state change percentage of operating equipment with respect to the amount of change in operating equipment and the amount of change in observation sensors for related measures. Figure 17B shows an example of data T52 representing the setting value change (average) of operating equipment with respect to the amount of change in operating equipment and the amount of change in observation sensors for related measures. Figure 17C shows an example of data T53 representing the sensor change amount (average) of observation sensors with respect to the amount of change in operating equipment and the amount of change in observation sensors for related measures.

[0066] This time, we will show the logic of output result T61 (Figure 18). As a result, the output is a measure to turn off the outdoor air handling unit and raise the temperature setting of the air conditioner by 2 degrees. However, multiple options or a range may be shown as candidates. In parallel with this, there are estimations by machine learning models and responses by generative AI. In addition, the change in the observed sensor is estimated using the sensor change amount (average) data T53 (Figure 17C), but this also includes responses from trained machine learning models and generative AI. However, outputting the change in the observed sensor is not mandatory. Furthermore, in the calculation of the manipulated quantity in S32, for example, a combination of manipulated equipment and quantity that exceeds a threshold of a certain overall evaluation function may be determined by a genetic algorithm or the like. In this case, the estimated effect shall be determined from the equipment manufacturer's catalog, performance curve, and recommended setting values.

[0067] The overall evaluation function is given by the following formula: F(X) = α・dx １ +β・dx ２ +γ・d ３ dx １ : Energy efficiency improvement (PUE) dx ２ :Reduced power consumption [kWh] dx ３ : Improvement in temperature control [°C] α, β, γ are weighting coefficients α: 0.3 β: 0.5 γ: 0.2

[0068] In this case, the measure will be adopted when the improvement effect F(X) ≥ 10. Note that "PUE" is one of the indicators representing the energy efficiency of IT-related facilities such as data centers, and is calculated by dividing the total power consumption of the facility by the power consumption of the IT equipment. Furthermore, "temperature management" means that the server area temperature is within a specified range (e.g., 25 degrees Celsius or higher and 27 degrees Celsius or lower).

[0069] More specifically, the current PUE is "1.5", and the effects of operating the equipment are as follows: (1) When the air conditioner temperature setting is changed from 19 to 21 degrees, the amount of electricity saved is 10 kWh, and the temperature rise in the spot area is 1.6°C (performance curve). (2) When the outdoor air handling unit is turned OFF, the amount of electricity saved is 10 kWh, and the temperature rise in the overall area is 0.4 degrees (catalog value). (3) Based on the amount of electricity saved in (1) and (2), the PUE is improved (estimated: improvement of about 0.1 ⇒ 1.4).

[0070] Therefore, the operation amount calculation unit 1222 searches for candidates in a exploratory manner within the range defined by the policy conditions for the above (1) and (2) (for example, by means of a genetic algorithm or the like).

[0071] Therefore, the comprehensive evaluation function is as follows. F(X) = α·dx １ + β·dx ２ + γ·d ３ = 0.3×0.1 + 0.5×(10 + 10) + 0.2×(1.6 + 0.4) = 10.43 ≥ 10

[0072] As a result, as in the output result T61 (FIG. 18), a policy of turning off the outdoor unit and increasing the temperature setting of the air conditioner twice is adopted. Note that such an output result T61 may be presented to the user in a form shown on the UI screen G30 (FIGS. 19A and 19B).

[0073] As described above, according to the policy reinterpretation system in the present embodiment, it is possible to support efficient facility management by comprehensively considering each environment in the facility to be managed.

[0074] Note that the present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the scope of the appended claims. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and the present invention is not necessarily limited to those having all the configurations described. Also, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Also, the configuration of another embodiment may be added to the configuration of one embodiment. Also, for a part of the configuration of each embodiment, addition, deletion, or replacement with other configurations may be performed.

[0075] In addition, each of the above-described configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them, for example, by means of an integrated circuit, or may be realized in software by a processor interpreting and executing a program for realizing each function.

[0076] Information such as programs, tables, and files that implement each function can be stored in memory, hard disks, SSDs (Solid State Drives), or other storage devices, or on recording media such as IC cards, SD cards, or DVDs. Furthermore, some or all of the above configurations, functions, processing units, and processing means may be implemented in hardware, for example, by designing them as integrated circuits. Alternatively, the above configurations and functions may be implemented in software by a processor interpreting and executing programs that implement each function. Information such as programs, tables, and files that implement each function can be stored in memory, hard disks, SSDs (Solid State Drives), or other recording devices, or on recording media such as IC cards, SD cards, or DVDs.

[0077] Furthermore, the control lines and information lines shown are those deemed necessary for explanatory purposes and do not necessarily represent all control lines and information lines required for implementation. In reality, it can be assumed that almost all components are interconnected.

[0078] Furthermore, although this embodiment has described the scope of facility management as floors and areas within floors that constitute facilities such as office buildings, it can also be applied to various other structures that may be subject to facility management (for example, event facilities such as concert halls, gymnasiums, live music venues, and stadiums, zoos and botanical gardens, factories for manufacturing, warehouses, airplane cabins, ship cabins, train and bus cabins, substations, power distribution rooms, stations, etc.). In other words, the scope of application is not limited to what has been described in this embodiment.

[0079] Furthermore, the various explanations above can be summarized as follows. The following summary may include supplementary explanations and explanations of variations of the above explanations.

[0080] In the policy reinterpretation system, the processor may identify as the device to be adjusted any device in the specific area indicated by the area information that is of the same type as the device adopted in the related policy, and whose observed values ​​of a predetermined event affected by the operation deviate from a predetermined standard.

[0081] This allows for the efficient selection of appropriate equipment to be adjusted, even in cases where the user does not specify or is unable to specify equipment to be adjusted, and to be included in subsequent processing. Ultimately, by taking into account a wide range of environments within the managed facilities, it becomes possible to support more efficient facility management.

[0082] Furthermore, in the policy reinterpretation system, the processor may calculate relationship information defining the relationship between the equipment and the sensors from time-series observed values ​​obtained from sensors of the operating content of the equipment and events affected by the equipment, as indicated by the area information, and then execute the processes of identifying the reference area and identifying the operating equipment based on the relationship information.

[0083] This allows for efficient and accurate identification of reference areas for past implemented measures. Ultimately, by broadly considering the various environments within the managed facilities, it becomes possible to support more efficient facility management.

[0084] Furthermore, in the policy reinterpretation system, the processor may generate a graph in which the devices and sensors are nodes, and each node is connected by edges, as relational information.

[0085] According to this, when identifying the above-mentioned reference areas, it becomes possible to efficiently and accurately identify them by visually presenting equipment configurations and other details as needed. Ultimately, by taking into account a wide range of environments within the facilities under management, it becomes possible to support more efficient facility management.

[0086] Furthermore, in the policy reinterpretation system, the processor may, when performing the processes of identifying the reference area, extracting the related policies, and determining the operation amount, input the area information, the specified content, and predetermined constraints into a machine learning model that has been trained using the set of explanatory variables and objective functions in each of the above processes as training data, and / or a generative AI (e.g., a language model) that has been trained using external training data different from the said training data, thereby generating the results of each of the above processes.

[0087] According to this, various processes such as identifying reference areas, extracting relevant measures, and determining the amount of work can be performed accurately and efficiently by a machine learning model that has comprehensively learned from past cases and / or a generative AI trained using external training data. In turn, by taking into account a wide range of environments within the facilities being managed, it becomes possible to support more efficient facility management.

[0088] Furthermore, in the policy reinterpretation system, the processor may accept inputs such as a target state that is the goal in environmental management, and an acceptable range of observed values ​​related to the equipment or the sensor, as the specification of the policy conditions.

[0089] This allows for direct input from users regarding their intentions and objectives. Ultimately, by taking into account a wide range of environments within the managed facilities, it becomes possible to support more efficient facility management.

[0090] Furthermore, in the policy reinterpretation system, the processor may accept date input from the user when performing the processes of identifying the reference area, extracting the related policies, and determining the amount of operation.

[0091] This allows for the efficient specification of important factors for users, such as the planned implementation date of a measure. Ultimately, by taking into account a wide range of environments within the managed facilities, it becomes possible to support more efficient facility management.

[0092] 1: Policy reinterpretation system, 11: Processor, 12: Main memory, 13: Auxiliary memory

Claims

1. A policy reinterpretation system comprising: a storage device that holds area information including information on the equipment configuration and implementation measures for environmental management in each of several areas subject to environmental management; a process that accepts a specification regarding policy conditions for environmental management for a specific area; a process that identifies a reference area from among the areas indicated by the area information whose equipment configuration matches or is similar to that of the specific area; a process that extracts related measures from among the implementation measures for the reference area that correspond to the policy conditions; and a processor that executes a process that determines the amount of operation for operating devices that may be affected by the control of the adjustment target device, starting from an adjustment target device of the same type as the device adopted in the related measures, based on information on the device adopted in the related measures and observed values ​​of a predetermined event.

2. The policy reinterpretation system according to claim 1, wherein the processor identifies as the device to be adjusted the device that is of the same type as the device adopted in the related policy, among the devices in the specific area indicated by the area information, and whose observed values ​​of a predetermined event affected by the operation content deviate from a predetermined standard.

3. The policy reinterpretation system according to claim 1, wherein the processor calculates relationship information defining the relationship between the equipment and the sensors from time-series observed values ​​obtained from sensors of the operating content of the equipment and events affected by the equipment, as indicated by the area information, and performs the processes of identifying the reference area and identifying the operating equipment based on the relationship information.

4. The policy reinterpretation system according to claim 3, wherein the processor generates a graph in which the device and the sensor are nodes and the nodes are connected by edges as relational information.

5. The policy reinterpretation system according to claim 1, wherein the processor, in the process of identifying the reference area, extracting the related policy, and determining the operation amount, generates the results of each process by inputting the area information, the specified content, and predetermined constraints into a machine learning model which has been trained using a set of explanatory variables and objective functions in each of the processes as training data, and / or a generating AI which is a model trained using external training data different from the said training data.

6. The policy reinterpretation system according to claim 1, wherein the processor accepts input of a target state that is the target in environmental management and an acceptable range of observed values ​​relating to the equipment or sensor as the specification of the policy conditions.

7. The policy reinterpretation system according to claim 1, wherein the processor accepts input from the user for specifying a date when performing the processes of identifying the reference area, extracting the related policy, and determining the amount of operation.

8. A method for reinterpreting policies, performed by computer, which involves: accepting a designation of policy conditions for environmental management in a specific area; identifying reference areas whose equipment configuration matches or is similar to that of the specified area, from among the areas indicated by area information, which includes information on the equipment configuration and implementation policies for environmental management in each of the multiple areas subject to environmental management; extracting related policies from among the implementation policies for the reference areas that correspond to the policy conditions; and determining the amount of operation for operating devices that may be affected by the control of the adjustment target device, starting from an adjustment target device of the same type as the device adopted in the related policy, based on information on the device adopted in the related policy and observed values ​​of a predetermined event.

Images