An intelligent building energy consumption anomaly monitoring method, device and storage medium

Abstract

The application discloses a kind of intelligent building energy consumption abnormal monitoring methods, including the multiaspect data of collection building energy consumption form real-time update original data set;Space index matrix is constructed and time-space correlation matrix M is generated;The latest features of real-time extraction time-space correlation matrix push, construct dynamic weight function, and carry out energy consumption abnormal grade determination;According to the abnormal grade of time-space correlation matrix mark layer, generate early warning information, and send control instruction to corresponding internet of things equipment.The intelligent building energy consumption abnormal monitoring method provided in the application can be adapted to various buildings, and after energy consumption abnormality is judged for different energy consumption objects in the building, the intelligent energy consumption monitoring and power dispatching in the building are realized.

Description

Technical Field

[0001] This invention relates to a method, device, equipment, and storage medium for monitoring abnormal energy consumption in intelligent buildings. Background Technology

[0002] With the increase in the number of electrical devices, the demand for power supply also increases. This is especially true for densely populated places such as office buildings, residences, and shopping malls, where a stable power supply is even more important. In particular, in workplaces such as office buildings, the company equipment inside will be constantly replaced as the companies change during their service life. This leads to constant changes in the overall energy demand of the building. Therefore, when the season enters the depths of summer or winter, the energy demand may reach the maximum of the total energy supply capacity.

[0003] To address this situation and ensure the stable operation of businesses within the building, effective energy consumption forecasting and scheduling management are necessary. Current technologies mostly employ manual scheduling, where managers shut down unnecessary electrical facilities when energy consumption reaches its peak. However, this approach cannot address energy shortages promptly, exhibiting significant delays that may impact production. Furthermore, manual forecasting carries a large margin of error, and the repeated shut-down and restarting of these facilities is cumbersome. Summary of the Invention

[0004] The main objective of this invention is to provide a method, device, equipment, and storage medium for monitoring abnormal energy consumption in intelligent buildings, in order to solve the aforementioned technical problems.

[0005] To achieve the above objectives, the present invention provides a method for monitoring abnormal energy consumption in intelligent buildings.

[0006] The intelligent building energy consumption anomaly monitoring method includes the following steps:

[0007] After collecting multi-dimensional data on building energy consumption through a multimodal sensor network, the data is transmitted to the edge gateway based on a hybrid transmission protocol to form a real-time updated raw data set D;

[0008] The original data is segmented using a sliding time window, and a spatial index matrix is ​​constructed by combining three-dimensional spatial coding rules. Based on data normalization and spatiotemporal weight coefficient calculation, a spatiotemporal correlation matrix M is generated.

[0009] Real-time extraction of the latest features pushed by the spatiotemporal correlation matrix M, and construction of a dynamic weight function. The real-time data of M is clustered, and the energy consumption anomaly level is determined by real-time weighted distance calculation and dynamic iteration of cluster centers. The anomaly labeling results are then fed back to the labeling layer of the spatiotemporal correlation matrix M.

[0010] Early warning information is generated based on the anomaly level of the spatiotemporal correlation matrix M-labeled layer, and control commands are sent to the corresponding IoT devices.

[0011] In one embodiment, the step of collecting multi-dimensional data on building energy consumption through a multi-modal sensor network and transmitting it to an edge gateway based on a hybrid transmission protocol to form a real-time updated raw data set D includes power parameters, environmental parameters, equipment operating status data, and outdoor meteorological data.

[0012] In one embodiment, the step of segmenting the original data using a sliding time window, constructing a spatial index matrix based on three-dimensional spatial encoding rules, and generating a spatiotemporal correlation matrix M based on data normalization and spatiotemporal weight coefficients further includes:

[0013] The spatiotemporal correlation matrix M is updated synchronously with the sliding time window, pushing the latest spatiotemporal unit features to the dynamic weight function in real time, while receiving feedback on anomaly annotation results.

[0014] In one embodiment, the steps of segmenting the original data using a sliding time window, constructing a spatial index matrix based on three-dimensional spatial encoding rules, and generating a spatiotemporal correlation matrix M based on data normalization and spatiotemporal weight coefficients are as follows:

[0015] The spatiotemporal correlation matrix M is a three-dimensional matrix of size m*n*d, where m is the number of time windows, n is the number of spatial coding regions, and d is the data dimension. The formula for calculating matrix element M(k,i,j) is as follows:

[0016] ;

[0017] in, Improved Z-Score normalization factor:

[0018] Weighting based on time contribution;

[0019] Weighting of spatial contribution.

[0020] In one embodiment, the Z-Score normalization factor in the matrix element calculation formula... Time contribution weight and spatial contribution weight The calculation formula is:

[0021] ;

[0022] ;

[0023] ;

[0024] ;

[0025] in:

[0026] Let be the mean of the j-th dimension data within the k-th time window. Standard deviation =10-6;

[0027] The probability distribution of the j-th dimension data within the k-th time window;

[0028] The maximum information entropy across all time windows;

[0029] Let be the energy consumption priority coefficient for the j-th region, and be the core region. =0.8-1.0, normal area =0.4-0.7;

[0030] n is the number of connected components.

[0031] In one embodiment, the latest features pushed by the real-time extraction of the spatiotemporal correlation matrix M are used to construct a dynamic weight function. The specific steps are as follows:

[0032] Dynamic weight function The calculation formula is:

[0033] ;

[0034] in:

[0035] For time feature weights, For spatial feature weights, These are the weights for data features.

[0036] In addition, to achieve the above objectives, the present invention also provides a method for monitoring abnormal energy consumption in intelligent buildings. The method includes: a memory, a processor, and an abnormal monitoring program stored in the memory and executable on the processor. When the abnormal monitoring program is executed by the processor, it implements the steps of the method for monitoring abnormal energy consumption in intelligent buildings as described above.

[0037] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing an anomaly monitoring program, which, when executed by a processor, implements the steps of the intelligent building energy consumption anomaly monitoring method described above.

[0038] The beneficial effects that this invention can achieve are: the intelligent building energy consumption anomaly monitoring method proposed in the embodiments of this invention can be adapted to various types of buildings, and after judging the energy consumption anomalies of different energy-consuming objects in the building, it can realize intelligent energy consumption monitoring and power dispatching in the building. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0040] Figure 1 This is a schematic diagram of the hardware operating environment of the device involved in the embodiments of the present invention;

[0041] Figure 2 This is a flowchart illustrating the intelligent building energy consumption anomaly monitoring method of the present invention.

[0042] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0043] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0044] like Figure 1 As shown, Figure 1 This is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiments of the present invention.

[0045] The terminal in this invention embodiment can be a PC, or a smartphone, tablet computer, e-book reader, MP3 (Moving Picture Experts Group Audio Layer III) player, MP4 (Moving Picture Experts Group Audio Layer IV) player, portable computer, or other portable terminal devices with display functions.

[0046] like Figure 1As shown, the terminal may include: a processor 1001, such as a CPU; a communication bus 1002; a user interface 1003; a network interface 1004; and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0047] Optionally, the terminal may also include a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, and so on. Sensors may include light sensors, motion sensors, and other sensors. Specifically, light sensors may include ambient light sensors and proximity sensors. The ambient light sensor can adjust the display brightness according to the ambient light level, while the proximity sensor can turn off the display and / or backlight when the mobile terminal is moved to the ear. As a type of motion sensor, a gravity accelerometer can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity, and can be used for applications that identify the mobile terminal's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition functions (such as pedometers, taps), etc. Of course, the mobile terminal may also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which will not be elaborated here.

[0048] Those skilled in the art will understand that Figure 1 The terminal structure shown does not constitute a limitation on the terminal and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0049] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an anomaly monitoring program.

[0050] exist Figure 1 In the terminal shown, network interface 1004 is mainly used to connect to the backend server and communicate with it; user interface 1003 is mainly used to connect to the client (user terminal) and communicate with it; while processor 1001 can be used to call the exception monitoring program stored in memory 1005 and perform the following operations:

[0051] After collecting multi-dimensional data on building energy consumption through a multimodal sensor network, the data is transmitted to the edge gateway based on a hybrid transmission protocol to form a real-time updated raw data set D;

[0052] The original data is segmented using a sliding time window, and a spatial index matrix is ​​constructed by combining three-dimensional spatial coding rules. Based on data normalization and spatiotemporal weight coefficient calculation, a spatiotemporal correlation matrix M is generated.

[0053] Real-time extraction of the latest features pushed by the spatiotemporal correlation matrix M, and construction of a dynamic weight function. The real-time data of M is clustered, and the energy consumption anomaly level is determined by real-time weighted distance calculation and dynamic iteration of cluster centers. The anomaly labeling results are then fed back to the labeling layer of the spatiotemporal correlation matrix M.

[0054] Early warning information is generated based on the anomaly level of the spatiotemporal correlation matrix M-labeled layer, and control commands are sent to the corresponding IoT devices.

[0055] Furthermore, the processor 1001 can call the exception monitoring program stored in the memory 1005 and also perform the following operations:

[0056] The spatiotemporal correlation matrix M is updated synchronously with the sliding time window, pushing the latest spatiotemporal unit features to the dynamic weight function in real time, while receiving feedback on anomaly annotation results.

[0057] The specific embodiments of the intelligent building energy consumption anomaly monitoring device of the present invention are basically the same as the embodiments of the intelligent building energy consumption anomaly monitoring method described below, and will not be repeated here.

[0058] Reference Figure 2 The first embodiment of the present invention provides a method for monitoring abnormal energy consumption in intelligent buildings, the method comprising:

[0059] Step S10: After collecting multi-dimensional data on building energy consumption through a multimodal sensor network, the data is transmitted to the edge gateway based on a hybrid transmission protocol to form a real-time updated raw data set D.

[0060] In this application, multimodal sensors can be deployed according to functional areas and equipment types. For example, the functional areas are divided into core energy consumption areas (computer room, air conditioning main computer room) and general energy consumption areas. The equipment types are divided into power parameter sensors, environmental parameter sensors, equipment status sensors and outdoor meteorological sensors according to the data collected, which can be changed according to user needs.

[0061] Step S20: The original data is segmented using a sliding time window, and a spatial index matrix is ​​constructed by combining three-dimensional spatial coding rules. Based on data normalization and spatiotemporal weight coefficient calculation, a spatiotemporal correlation matrix M is generated.

[0062] In this application, a four-level spatial topology coding rule is adopted to encode each monitoring area and device, and a spatial topology matrix T is constructed. The coding format adopts the "ZFQS" four-level coding, where Z is the building zone code (1 digit, such as "1" for building 1 and "2" for building 2), F is the floor code (2 digits, such as "10" for floor 10 and "03" for floor 3), Q is the area code (2 digits, such as "03" for area 03 and "12" for area 12), and S is the device code (2 digits, such as "08" for device 08 and "25" for device 25). For example, the code "1-10-03-08" represents air conditioner device 08 in area 03 on the 10th floor of building 1, and the code uniquely corresponds to each IoT device.

[0063] Construct a spatial topology matrix T with n×n dimensions (n ​​is the total number of spatial coding regions, i.e., the total number of regions corresponding to all “ZFQ” codes).

[0064] Furthermore, the spatiotemporal correlation matrix M is a three-dimensional matrix of size m*n*d, where m is the number of time windows, n is the number of spatial coding regions, and d is the data dimension. The formula for calculating the matrix element M(k,i,j) is as follows:

[0065] ;

[0066] in, Improved Z-Score normalization factor:

[0067] Weighting based on time contribution;

[0068] Weighting of spatial contribution.

[0069] Among them, the Z-Score normalization factor in the matrix element calculation formula Time contribution weight and spatial contribution weight The calculation formula is:

[0070] ;

[0071] ;

[0072] ;

[0073] ;

[0074] in:

[0075] Let be the mean of the j-th dimension data within the k-th time window. Standard deviation =10-6;

[0076] The probability distribution of the j-th dimension data within the k-th time window;

[0077] The maximum information entropy across all time windows;

[0078] Let be the energy consumption priority coefficient for the j-th region, and be the core region. =0.8-1.0, normal area =0.4-0.7;

[0079] n is the number of connected components.

[0080] After calculating the above three parameters, substitute them into the matrix element calculation formula to obtain the value of each M(k,i,j), and finally construct a complete three-dimensional spatiotemporal correlation matrix M. The matrix data is stored in real time at the platform layer for subsequent construction of dynamic weight functions and cluster anomaly detection.

[0081] Step S30: Extract the latest features pushed by the spatiotemporal correlation matrix M in real time and construct a dynamic weight function. The system clusters the real-time data of M, and uses real-time weighted distance calculation and dynamic iteration of cluster centers to determine the energy consumption anomaly level. The anomaly labeling results are then fed back to the labeling layer of the spatiotemporal correlation matrix M.

[0082] In this embodiment, the following can be adopted: The distance is calculated using the formula.

[0083] Let M(k,i) be the sample vector M(k,i) of the k-th time window and the i-th spatial region, and C be the cluster center C. p The weighted distance between the samples is used to determine the similarity between the samples and the cluster centers. The smaller the distance, the higher the similarity between the samples and the cluster centers.

[0084] Let be the value of the j-th dimension of the p-th cluster center.

[0085] Therefore, for each sample M(k,i), the weighted Manhattan distance between it and the K cluster centers can be calculated, and the distance calculation results can be stored for subsequent sample clustering assignment.

[0086] Furthermore, the weighted distance between the obtained samples and the cluster centers can be used as a basis. The deviation is obtained by comparing the average weighted Manhattan distance of all samples within the cluster described in the sample. The system classifies the abnormality level according to the preset deviation threshold.

[0087] Step S40: Generate early warning information based on the anomaly level of the spatiotemporal correlation matrix M labeling layer, and send control commands to the corresponding IoT devices.

[0088] In this embodiment, if If the energy consumption is ≤1.8, it is considered normal energy consumption, indicating that the sample has high similarity to other samples within the cluster, and the energy consumption is within the normal range; if 1.8 < ≤2.5 indicates a slight anomaly, suggesting minor fluctuations in sample energy consumption, requiring monitoring but no immediate intervention; if If the value is greater than 2.5, it is considered a severe anomaly, indicating that there is a significant abnormality in the energy consumption of the sample, which may indicate equipment failure and requires immediate intervention.

[0089] Finally, after receiving the control command, the user reverses the process by locating the abnormal device's position according to the encoding rules of the spatial topology matrix T, and then intervenes. The information of the IoT device after intervention is updated again to ensure that the matrix data reflects the device's status in real time.

[0090] Furthermore, embodiments of the present invention also propose a computer-readable storage medium storing an anomaly monitoring program, which, when executed by a processor, performs the following operations:

[0091] After collecting multi-dimensional data on building energy consumption through a multimodal sensor network, the data is transmitted to the edge gateway based on a hybrid transmission protocol to form a real-time updated raw data set D;

[0092] The original data is segmented using a sliding time window, and a spatial index matrix is ​​constructed by combining three-dimensional spatial coding rules. Based on data normalization and spatiotemporal weight coefficient calculation, a spatiotemporal correlation matrix M is generated.

[0093] Real-time extraction of the latest features pushed by the spatiotemporal correlation matrix M, and construction of a dynamic weight function. The real-time data of M is clustered, and the energy consumption anomaly level is determined by real-time weighted distance calculation and dynamic iteration of cluster centers. The anomaly labeling results are then fed back to the labeling layer of the spatiotemporal correlation matrix M.

[0094] Early warning information is generated based on the anomaly level of the spatiotemporal correlation matrix M-labeled layer, and control commands are sent to the corresponding IoT devices.

[0095] Furthermore, when the anomaly monitoring program is executed by the processor, it also performs the following operations:

[0096] The spatiotemporal correlation matrix M is updated synchronously with the sliding time window, pushing the latest spatiotemporal unit features to the dynamic weight function in real time, while receiving feedback on anomaly annotation results.

[0097] The specific embodiments of the computer-readable storage medium of the present invention are basically the same as the embodiments of the above-described intelligent building energy consumption anomaly monitoring method, and will not be described in detail here.

[0098] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0099] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0100] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0101] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for monitoring abnormal energy consumption in intelligent buildings, characterized in that, The intelligent building energy consumption anomaly monitoring method includes the following steps: After collecting multi-dimensional data on building energy consumption through a multimodal sensor network, the data is transmitted to the edge gateway based on a hybrid transmission protocol to form a real-time updated raw data set D; The original data is segmented using a sliding time window, and a spatial index matrix is ​​constructed by combining three-dimensional spatial coding rules. Based on data normalization and spatiotemporal weight coefficient calculation, a spatiotemporal correlation matrix M is generated. Real-time extraction of the latest features pushed by the spatiotemporal correlation matrix M, and construction of a dynamic weight function. The real-time data of M is clustered, and the energy consumption anomaly level is determined by real-time weighted distance calculation and dynamic iteration of cluster centers. The anomaly labeling results are then fed back to the labeling layer of the spatiotemporal correlation matrix M. Early warning information is generated based on the anomaly level of the spatiotemporal correlation matrix M-labeled layer, and control commands are sent to the corresponding IoT devices.

2. The intelligent building energy consumption anomaly monitoring method as described in claim 1, characterized in that, In the step of collecting multi-dimensional data on building energy consumption through a multi-modal sensor network and transmitting it to an edge gateway based on a hybrid transmission protocol to form a real-time updated raw data set D, the multi-dimensional data includes power parameters, environmental parameters, equipment operating status data, and outdoor meteorological data.

3. The intelligent building energy consumption anomaly monitoring method as described in claim 1, characterized in that, The steps of segmenting the original data using a sliding time window, constructing a spatial index matrix based on three-dimensional spatial encoding rules, and generating a spatiotemporal correlation matrix M based on data normalization and spatiotemporal weight coefficients further include: The spatiotemporal correlation matrix M is updated synchronously with the sliding time window, pushing the latest spatiotemporal unit features to the dynamic weight function in real time, while receiving feedback on anomaly annotation results.

4. The intelligent building energy consumption anomaly monitoring method according to claim 3, characterized in that, The steps for segmenting the original data using a sliding time window, constructing a spatial index matrix based on three-dimensional spatial coding rules, and generating a spatiotemporal correlation matrix M based on data normalization and spatiotemporal weight coefficients are as follows: The spatiotemporal correlation matrix M is a three-dimensional matrix of size m*n*d, where m is the number of time windows, n is the number of spatial coding regions, and d is the data dimension. The formula for calculating matrix element M(k,i,j) is as follows: ； in, Improved Z-Score normalization factor: Weighting based on time contribution; Weighting of spatial contribution.

5. The intelligent building energy consumption anomaly monitoring method according to claim 4, characterized in that, The Z-Score normalization factor in the matrix element calculation formula Time contribution weight and spatial contribution weight The calculation formula is: ； ； ； ； in: Let be the mean of the j-th dimension data within the k-th time window. Standard deviation =10-6; The probability distribution of the j-th dimension data within the k-th time window; The maximum information entropy across all time windows; Let be the energy consumption priority coefficient for the j-th region, and be the core region. =0.8-1.0, normal area =0.4-0.7; n is the number of connected components.

6. The intelligent building energy consumption anomaly monitoring method according to claim 5, characterized in that, The latest features pushed by the real-time extraction of the spatiotemporal correlation matrix M are used to construct a dynamic weight function. The specific steps are as follows: Dynamic weight function The calculation formula is: ； in: For time feature weights, For spatial feature weights, These are the weights for data features.

7. An intelligent building energy consumption anomaly monitoring device, characterized in that, The intelligent building energy consumption anomaly monitoring device includes: a memory, a processor, and an anomaly monitoring program stored in the memory and executable on the processor. When the anomaly monitoring program is executed by the processor, it implements the steps of the intelligent building energy consumption anomaly monitoring method as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an anomaly monitoring program, which, when executed by a processor, implements the steps of the intelligent building energy consumption anomaly monitoring method as described in any one of claims 1 to 6.

Images