CN116187791A - Energy consumption detection method and device, electronic equipment and storage medium - Google Patents
Energy consumption detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116187791A CN116187791A CN202111416052.3A CN202111416052A CN116187791A CN 116187791 A CN116187791 A CN 116187791A CN 202111416052 A CN202111416052 A CN 202111416052A CN 116187791 A CN116187791 A CN 116187791A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- equipment
- micro
- consumption information
- moment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention provides an energy consumption detection method, an energy consumption detection device, electronic equipment and a storage medium, wherein the energy consumption detection method can comprise the following steps: acquiring energy consumption information to be detected, and inputting the energy consumption information to be detected into an energy consumption detection model, wherein the energy consumption detection model is obtained through training a training sample set with micro-moment characteristics, and the micro-moment characteristics are characteristics related to equipment energy consumption types; and determining an energy consumption detection result corresponding to the energy consumption information to be detected based on the output result of the energy consumption detection model. The method for detecting the energy consumption can improve the authenticity and the reliability of the energy consumption detection result, and lays a foundation for a user to execute an energy saving scheme and track equipment faults based on the energy consumption detection result.
Description
Technical Field
The present invention relates to the field of energy consumption detection technologies, and in particular, to an energy consumption detection method, an energy consumption detection device, an electronic device, and a storage medium.
Background
Today, most user activities incur high energy costs, e.g. from lamps keeping the room bright to televisions playing throughout the day. Studies have shown that about 10% -40% of the electricity can be saved in the home if an individual's professional profile is embedded in a building energy management system. Due to improvements in living conditions and increases in the use of electric appliances and electric devices, it is expected that the energy consumption rate will further increase for the next several years.
The related art shows that real-time detection and analysis of energy usage patterns not only can facilitate the energy conservation process, but can also help track equipment failures by analyzing sudden and unexpected changes in energy usage. Therefore, energy consumption detection technology is receiving increasing attention from the global energy efficiency point of view.
Disclosure of Invention
The invention provides an energy consumption detection method, an energy consumption detection device, electronic equipment and a storage medium, which are used for solving the problem that a training set with a real mark is lacked in the training process of an energy consumption detection model in the prior art, and providing the training set with the real mark for the energy consumption detection model is realized so as to improve the accuracy of an energy consumption detection result of the energy consumption detection model.
The invention provides an energy consumption detection method, which is characterized by comprising the following steps of: acquiring energy consumption information to be detected, and inputting the energy consumption information to be detected into an energy consumption detection model, wherein the energy consumption detection model is obtained through training a training sample set with micro-moment characteristics, and the micro-moment characteristics are characteristics related to equipment energy consumption types; and determining an energy consumption detection result corresponding to the energy consumption information to be detected based on the output result of the energy consumption detection model.
The energy consumption detection method provided by the invention is characterized in that the training sample set with the micro-moment characteristics is obtained by adopting the following modes: based on equipment energy consumption information, obtaining equipment micro-moment characteristics corresponding to the equipment energy consumption information through a micro-moment energy label model, wherein the equipment energy consumption information at least comprises equipment occupancy rate, equipment power consumption, equipment reference consumption rate, equipment longest standby time and equipment standby energy consumption; and obtaining the training sample set with the micro-moment characteristic based on the equipment energy consumption information and the equipment micro-moment characteristic.
The invention provides an energy consumption detection method, which is characterized in that the micro-moment energy label model is provided with an energy consumption information and micro-moment characteristic mapping table, the micro-moment characteristics of equipment corresponding to the equipment energy consumption information are obtained through the micro-moment energy label model based on the equipment energy consumption information, and the method comprises the following steps: and determining the micro-moment characteristics of the equipment corresponding to the equipment energy consumption information through the energy consumption information and the micro-moment characteristic mapping table based on the equipment energy consumption information.
The energy consumption detection method provided by the invention is characterized in that the energy consumption information and micro-moment characteristic mapping table is determined by adopting the following modes:
if the energy consumption information is first energy consumption information, the micro-moment characteristic corresponding to the first energy consumption information is good micro-moment characteristic of equipment use, wherein the first energy consumption information is that the equipment power consumption of the current time step is larger than or equal to the minimum equipment reference consumption rate and smaller than or equal to the preset multiple of the maximum equipment reference consumption rate; if the energy consumption information is second energy consumption information, the micro-moment characteristic corresponding to the second energy consumption information is a device opening micro-moment characteristic, wherein the second energy consumption information is that the device power consumption of the current time step is larger than or equal to the minimum device reference consumption rate, and the device power consumption of the last time step is smaller than or equal to the maximum device standby energy consumption; if the energy consumption information is third energy consumption information, the micro-moment characteristic corresponding to the third energy consumption information is a device closing micro-moment characteristic, wherein the third energy consumption information is that the device power consumption of the current time step is smaller than or equal to the maximum device standby energy consumption and the device power consumption of the last time step is larger than or equal to the minimum device reference consumption rate; if the energy consumption information is fourth energy consumption information, the micro-moment characteristic corresponding to the fourth energy consumption information is a micro-moment characteristic of excessive equipment energy consumption, wherein the fourth energy consumption information is that the equipment power consumption of the current time step is larger than or equal to a preset multiple of the maximum equipment reference consumption rate, and the longest equipment standby time of the current time step is larger than or equal to the longest equipment standby time of the maximum equipment; if the energy consumption information is fifth energy consumption information, the micro-moment characteristic corresponding to the fifth energy consumption information is abnormal energy consumption micro-moment characteristic of the equipment when the equipment goes out, wherein the fifth energy consumption information is that no one exists in a room, and the equipment power consumption of the current time step is larger than or equal to the preset multiple of the maximum equipment standby energy consumption.
According to the energy consumption detection method provided by the invention, the power consumption of the equipment is determined by adopting the following modes: determining power consumption of a plurality of first devices in a preset time interval; the device power consumption is determined based on a plurality of the first device power consumptions.
The energy consumption detection method provided by the invention is characterized in that the device power consumption is determined based on a plurality of first device power consumption, and the device power consumption is determined by adopting the following formula:
wherein P is N (t) represents the device power consumption at time t, P (t) represents the first device power consumption at time t, mean (P) represents an average value of the plurality of first device power consumptions over a preset time interval, max (P) represents the first device power consumption that is largest over the preset time interval, and min (P) represents the first device power consumption that is smallest over the preset time interval.
The energy consumption detection method provided by the invention is characterized in that the equipment energy consumption information is determined by adopting the following modes: acquiring energy consumption information of first equipment; and carrying out interpolation processing on the first equipment energy consumption information, and taking the processed first equipment energy consumption information as the equipment energy consumption information.
The invention also provides an energy consumption detection device, which is characterized by comprising: the energy consumption detection system comprises an acquisition module, a detection module and a detection module, wherein the acquisition module is used for acquiring energy consumption information to be detected and inputting the energy consumption information to be detected into an energy consumption detection model, the energy consumption detection model is obtained through training a training sample set with micro-moment characteristics, and the micro-moment characteristics are characteristics about equipment energy consumption types; and the processing module is used for determining an energy consumption detection result corresponding to the energy consumption information to be detected based on the output result of the energy consumption detection model.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the energy consumption detection method as described in any one of the above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the energy consumption detection method as described in any of the above.
According to the energy consumption detection method, the device, the electronic equipment and the storage medium, the energy consumption detection model is trained through the training sample set with the micro-moment characteristics, and the detection accuracy of the energy consumption detection model is improved. And the energy consumption detection result corresponding to the energy consumption information to be detected is obtained based on the energy consumption detection model, so that the authenticity and reliability of the energy consumption detection result can be improved, and a foundation is laid for a user to execute an energy saving scheme and track equipment faults based on the energy consumption detection result.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an energy consumption detection method provided by the invention;
FIG. 2 is a schematic flow chart of determining a training sample set with micro-moment features according to the present invention;
FIG. 3 is a schematic diagram of a flow chart for determining power consumption of a device according to the present invention;
FIG. 4 is a schematic flow chart of determining device energy consumption information according to the present invention;
fig. 5 is a schematic diagram of an application scenario of the energy consumption detection method provided by the invention;
FIG. 6 is a schematic diagram of the structure of the energy consumption detecting device provided by the invention;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The related art shows that the overall energy usage and the plug load are closely related to the occupancy. In addition, the presence/absence of personnel in a building can greatly affect the energy consumption rate, as a large number of users keep the equipment on for a long time without actual presence, which represents an abnormal behavior. For example, in the absence of personnel, the devices such as televisions, air conditioners, lights, notebook/desktop computers, fans, etc. are kept on for a long period of time.
Detecting and analyzing energy usage patterns in real time not only can facilitate the energy conservation process, but can also help track equipment failures by analyzing sudden and unexpected changes in energy usage. In the application process, if abnormal energy use behaviors are identified, the user can be notified. The user may accordingly implement the appropriate power efficiency scheme. In addition, today's proliferation of wireless sensors and sub-meters, investigation of detection anomalies in household consumption behavior in buildings has become urgent. Therefore, energy consumption detection technology is receiving increasing attention from the global energy efficiency point of view.
Energy consumption detection faces a number of difficulties and challenges, and in particular one of the major obstacles in developing and evaluating energy consumption detection techniques is the lack of a labeled real dataset. In short, there is a lack of discussion of how to mark the energy consumption observation as a normal or abnormal work, and to which abnormality the abnormal work belongs. To this end, the invention proposes a method for marking energy consumption events using occupancy patterns, power consumption footprints and micro-moment features of a device.
According to the energy consumption detection method provided by the invention, the energy consumption detection model is trained through the training sample set with the micro-moment characteristics, so that the detection accuracy of the energy consumption detection model is improved. Furthermore, the energy consumption detection result corresponding to the energy consumption information to be detected is obtained based on the energy consumption detection model, so that the authenticity and reliability of the energy consumption detection result can be improved, and a foundation is laid for a user to execute an energy saving scheme and track equipment faults based on the energy consumption detection result.
The present invention will be described with reference to the following examples.
Fig. 1 is a schematic flow chart of an energy consumption detection method provided by the invention.
In an exemplary embodiment of the present invention, as shown in fig. 1, the energy consumption detection method may include a step 110 and a step 120, and each step will be described separately.
In step 110, energy consumption information to be detected is obtained, and the energy consumption information to be detected is input into an energy consumption detection model, wherein the energy consumption detection model is obtained through training of a training sample set with micro-moment characteristics. The micro-moment features are features regarding the class of energy consumption of the device.
In step 120, an energy consumption detection result corresponding to the energy consumption information to be detected is determined based on the output result of the energy consumption detection model.
In one embodiment, energy consumption information to be detected may be obtained, where the energy consumption information to be detected may be energy usage information about an internal device of a building. In one example, device energy usage information may be collected based on energy sensors or device occupancy sensors. The energy consumption information to be detected may include an occupancy rate of the device (denoted by O), a power consumption of the device (denoted by P), a reference consumption rate of the device (denoted by a), a longest standby time of the device (denoted by TM), a standby energy of the device (denoted by S), and the like. Furthermore, the energy consumption information to be detected can be input into the energy consumption detection model, and the energy consumption detection result corresponding to the energy consumption information to be detected can be obtained based on the output result of the energy consumption detection model.
In one embodiment, the energy consumption detection model may be a deep neural network model and is trained based on a training sample set with micro-temporal features. It will be appreciated that the micro-temporal features are features relating to the class of energy consumption of the device. In an example, the micro-temporal features may include both normal consumption and abnormal consumption types. Further, normal consumption may also include three subclasses of good use, set up devices, and shut down devices. Abnormal consumption may include two subclasses of excessive consumption and outgoing consumption. It is understood that the energy consumption detection results corresponding to the energy consumption information to be detected may include detection results regarding good use, equipment opening, equipment closing, excessive consumption, and outgoing consumption.
According to the energy consumption detection method provided by the invention, the energy consumption detection model is trained through the training sample set with the micro-moment characteristics, so that the detection accuracy of the energy consumption detection model is improved. And the energy consumption detection result corresponding to the energy consumption information to be detected is obtained based on the energy consumption detection model, so that the authenticity and reliability of the energy consumption detection result can be improved, and a foundation is laid for a user to execute an energy saving scheme and track equipment faults based on the energy consumption detection result.
In order to further describe the energy consumption detection method provided by the invention, the process of determining the training sample set with the micro-moment characteristic is described in the following embodiment.
FIG. 2 is a schematic flow chart of determining a training sample set with micro-moment features according to the present invention.
In an exemplary embodiment of the present invention, as shown in fig. 2, determining a training sample set having micro-temporal features may include steps 210 through 220, each of which will be described separately.
In step 210, based on the device energy consumption information, a device micro-moment feature corresponding to the device energy consumption information is obtained through a micro-moment energy tag model. The device energy consumption information at least comprises device occupancy rate, device power consumption, device reference consumption rate, device longest standby time and device standby energy consumption.
In step 220, a training sample set with micro-moment features is obtained based on the device energy consumption information and the device micro-moment features.
In one embodiment, the device micro-time feature corresponding to the device energy consumption information may be obtained through the micro-time energy tag model based on the device energy consumption information of each device, such as the device occupancy (denoted by O), the device power consumption (denoted by P), the device reference consumption (denoted by a), the device maximum standby time (denoted by TM), the device standby energy consumption (denoted by S), and the like.
Furthermore, the obtained micro-moment characteristics of the equipment can be used as a label of the energy consumption information of the equipment, and the obtained micro-moment characteristics and the energy consumption information of the equipment together form a training sample set of an energy consumption detection model, namely, the training sample set with the micro-moment characteristics.
In an exemplary embodiment of the present invention, the micro-moment energy tag model may be further provided with an energy consumption information and micro-moment feature mapping table. In an example, the device micro-moment feature corresponding to the device energy consumption information may be determined based on the device energy consumption information through an energy consumption information and micro-moment feature mapping table.
The process of determining the energy consumption information and the micro-time feature map will be described below.
In an exemplary embodiment of the present invention, the energy consumption information and micro-time feature map is determined in the following manner:
if the energy consumption information is the first energy consumption information, the micro-moment characteristic corresponding to the first energy consumption information is a good micro-moment characteristic of equipment use. The first energy consumption information is that the device power consumption (P (t)) of the current time step is larger than or equal to the minimum device reference consumption rate (A) and smaller than or equal to the preset multiple of the maximum device reference consumption rate (A). The preset multiple may be adjusted according to practical situations, for example, the preset multiple may be 0.95 times, and in this embodiment, the preset multiple is not specifically limited.
And if the energy consumption information is the second energy consumption information, the micro-moment characteristic corresponding to the second energy consumption information is the equipment opening micro-moment characteristic. The second energy consumption information is that the device power consumption (P (t)) of the current time step is larger than or equal to the minimum device activity consumption rate (A), and the device power consumption (P (t-1)) of the last time step is smaller than or equal to the maximum device standby energy consumption rate (S).
And if the energy consumption information is the third energy consumption information, the micro-moment characteristic corresponding to the third energy consumption information is the equipment closing micro-moment characteristic. The third energy consumption information is that the device power consumption (P (t)) of the current time step is smaller than or equal to the maximum device standby energy consumption (S) and the device power consumption (P (t-1)) of the last time step is larger than or equal to the minimum device activity consumption rate (A).
And if the energy consumption information is fourth energy consumption information, the micro-moment characteristic corresponding to the fourth energy consumption information is the micro-moment characteristic of excessive equipment energy consumption. The fourth energy consumption information is that the device power consumption (P (t)) of the current time step is larger than or equal to a preset multiple of the maximum device activity consumption rate (A), and the device longest standby time (TM (t)) of the current time step is larger than or equal to the maximum device longest standby Time (TM).
If the energy consumption information is the fifth energy consumption information, the micro-moment characteristic corresponding to the fifth energy consumption information is the abnormal energy consumption micro-moment characteristic of the equipment when the equipment goes out. The fifth energy consumption information is that no one is in the room, and the power consumption (P (t)) of the equipment in the current time step is larger than or equal to the preset multiple of the maximum equipment standby energy consumption (S).
The process of extracting the device micro-moment features based on the micro-moment energy tag model will be described in connection with the following embodiments.
Input: device occupancy (O), device power consumption (P), device reference consumption rate (a) for each device operation, device maximum standby Time (TM), and device standby power consumption (S).
And (3) outputting: micro moment eigenvector (MF)
Initializing MF
While t≤N do
if P(t)≥min(A)and P(t)≤0.95×max(A)then
MF(t)＝0(Good usage)；
else if P(t)≥min(A)and P(t-1)≤max(S)then
MF(t)＝1(Turn on device)；
else if P(t)≤max(S)and P(t-1)≥min(A)then
MF(t)＝2(Turn off device)；
else if P(t)≥0.95×max(A)or TM(t)≥max(T)then
MF(t)＝3(Excessive consumption)；
else
if O(t)＝0and P(t)≥0.95×max(S)then
MF(t)＝4(Consumption while outside)；
end
end
The process of determining the power consumption of the device will be described in connection with the following embodiments.
Fig. 3 is a schematic diagram of a flow chart for determining power consumption of a device according to the present invention.
In an exemplary embodiment of the present invention, as shown in fig. 3, the process of determining the power consumption of the device may include steps 310 and 320, each of which will be described separately.
In step 310, a plurality of first device power consumptions are determined over a preset time interval.
In step 320, device power consumption is determined based on the plurality of first device power consumptions.
Most energy consumption databases for energy consumption detection collected through experimental activities can express real modes, but some abnormal data exist, and the accuracy of the model is affected when model training is performed based on the abnormal data. In this embodiment, the accuracy of the training samples may be improved by performing normalization processing on the power consumption of the device. In one embodiment, a plurality of first device power consumption may be acquired within a preset time and the device power consumption may be determined based on the plurality of first device power consumption.
In an exemplary embodiment of the present invention, based on the plurality of first device power consumptions, the determined device power consumption may be determined by the following formula (formula 1):
wherein P is N (t) represents the device power consumption at time t, P (t) represents the first device power consumption at time t, mean (P) represents an average value of the plurality of first device power consumptions over a preset time interval, max (P) represents the first device power consumption that is largest over the preset time interval, and min (P) represents the first device power consumption that is smallest over the preset time interval. By the embodiment, adverse effects of individual abnormal data on the accuracy of the training sample can be effectively avoided.
The present invention will be described with reference to the following examples for determining device energy consumption information.
Fig. 4 is a schematic flow chart of determining energy consumption information of a device according to the present invention.
In an exemplary embodiment of the present invention, as shown in fig. 4, the process of determining the device power consumption information may include a step 410 and a step 420, each of which will be described separately.
In step 410, first device energy consumption information is obtained.
In step 420, interpolation processing is performed on the first device energy consumption information, and the processed first device energy consumption information is used as device energy consumption information.
The data collected by the different energy sensors and occupancy sensors may first be cleaned and preprocessed to delete or correct invalid records. It will be appreciated that the footprint collected is raw or incomplete data, where missing values occur, and some attribute information is lost during the collection process. The lack of these values is typically due to hardware and/or software failures of the measurement device. In addition, other data is noisy, i.e. contains errors or outliers. For this reason, it is indispensable to use a data cleaning process.
In one embodiment, the attribute average may be used to fill all missing values in the power dataset. In an example, a plurality of first device energy consumption information may be acquired, interpolation processing may be performed based on the first device energy consumption information, and the processed first device energy consumption information may be used as device energy consumption information. By the embodiment, all missing values in the power data set can be effectively filled, and preprocessing of collected data is achieved.
In order to further describe the energy consumption detection method provided by the invention, the invention will be described with reference to the following examples.
Fig. 5 is a schematic diagram of an application scenario of the energy consumption detection method provided by the invention.
In an exemplary embodiment of the present invention, as shown in fig. 5, a resident living in a building is illustrated as an example, in which a room of the resident includes home appliances. During application, resident occupancy data may be collected by an energy sensor or occupancy sensor. The check-in data may be energy consumption information to be detected.
In yet another embodiment, the check-in data may also be raw data for training an energy consumption detection model. During application, the energy consumption detection model may be trained based on a training sample set having micro-temporal features. Further, based on the output result of the energy consumption detection model, an energy consumption detection result corresponding to the energy consumption information to be detected is determined. It can be understood that the energy consumption detection result may be the energy consumption detection result of normal electricity consumption of the device, turning on the device, turning off the device, excessive electricity consumption of the device, electricity consumption of the device when going out, and the like.
In an example, the device micro-moment feature corresponding to the device energy consumption information can be obtained through a micro-moment energy label model based on the device energy consumption information, and the training sample set with the micro-moment feature is obtained based on the device energy consumption information and the device micro-moment feature. The device energy consumption information may include a device occupancy rate (O), a device power consumption (P), a device reference consumption rate (a), a device longest standby Time (TM), a device standby energy consumption (S), and the like.
In one example, the micro-moment energy indicia corresponding to the power consumption specification settings may be derived based on the power consumption specification settings of different appliances. Further, the training sample set for training the energy consumption detection model can be formed based on the power consumption specification settings and the corresponding micro-moment energy markers of different household appliances.
After applying the micro-moment based energy labelling model to label the data (micro-moment features), a dataset for training the energy consumption detection model can be obtained. In one example, a dataset may be obtained having five micro-time feature tags for device normal power usage, device on, device off, device over power usage, device power usage while out. During the application process, the DNN model (energy consumption detection model) may be trained using training data containing five micro-moment feature tags. In one example, K-fold cross-validation may be deployed for training and testing. The training process is a statistical analysis process that means dividing the input data and its labels into K subgroups, then performing supervised training on the (K-1) subgroup, and evaluating the performance of the result in terms of accuracy and F1 score using the remaining subgroup evaluation model. During the application, the training may be repeated K times, with each subgroup being used (K-1) times to train the DNN model, 1 time for DNN model detection. In the training phase, data including a timestamp, a device ID, a device occupancy (O), a device power consumption (P), a device reference consumption rate (a), a device maximum standby Time (TM), and a device standby energy consumption (S) are fed to the DNN model. The DNN model may include a plurality of hidden layers for learning the relationship behavior between normal electricity usage and abnormal electricity usage. A rectifying linear unit (ReLU) activation function may be used at the output.
According to the description, according to the energy consumption detection method provided by the invention, the energy consumption detection model is trained through the training sample set with the micro-moment characteristics, so that the detection accuracy of the energy consumption detection model is improved. And the energy consumption detection result corresponding to the energy consumption information to be detected is obtained based on the energy consumption detection model, so that the authenticity and reliability of the energy consumption detection result can be improved, and a foundation is laid for a user to execute an energy saving scheme and track equipment faults based on the energy consumption detection result.
Based on the same conception, the invention also provides an energy consumption detection device.
The energy consumption detection device provided by the invention is described below, and the energy consumption detection device described below and the energy consumption detection method described above can be referred to correspondingly.
Fig. 6 is a schematic structural diagram of the energy consumption detecting device provided by the invention.
In an exemplary embodiment of the present invention, as shown in fig. 6, the energy consumption detecting apparatus may include an acquisition module 610 and a processing module 620, which will be described below.
The acquisition module 610 may be configured to: and acquiring the energy consumption information to be detected, and inputting the energy consumption information to be detected into an energy consumption detection model, wherein the energy consumption detection model is obtained through training a training sample set with micro-moment characteristics, and the micro-moment characteristics are characteristics related to the energy consumption type of the equipment.
The processing module 620 may be configured to: and determining an energy consumption detection result corresponding to the energy consumption information to be detected based on the output result of the energy consumption detection model.
In an exemplary embodiment of the present invention, the obtaining module 610 may obtain the training sample set with the micro-moment feature in the following manner:
acquiring equipment micro-moment characteristics corresponding to equipment energy consumption information through a micro-moment energy label model based on the equipment energy consumption information, wherein the equipment energy consumption information at least comprises equipment occupancy rate, equipment power consumption, equipment activity consumption rate, equipment longest standby time and equipment standby energy consumption; based on the equipment energy consumption information and the equipment micro-moment characteristics, a training sample set with the micro-moment characteristics is obtained.
In an exemplary embodiment of the present invention, the micro-moment energy tag model is provided with an energy consumption information and micro-moment feature mapping table, and the obtaining module 610 may obtain, based on the device energy consumption information, the device micro-moment feature corresponding to the device energy consumption information through the micro-moment energy tag model in the following manner:
and determining the micro-moment characteristics of the equipment corresponding to the equipment energy consumption information through the energy consumption information and the micro-moment characteristic mapping table based on the equipment energy consumption information.
In an exemplary embodiment of the present invention, the obtaining module 610 may determine the energy consumption information and the micro-moment feature mapping table in the following manner:
if the energy consumption information is first energy consumption information, the micro-moment characteristic corresponding to the first energy consumption information is good micro-moment characteristic of equipment use, wherein the first energy consumption information is that the equipment power consumption of the current time step is greater than or equal to the minimum equipment activity consumption rate and less than or equal to the preset multiple of the maximum equipment reference consumption rate; if the energy consumption information is second energy consumption information, the micro-moment characteristic corresponding to the second energy consumption information is a device opening micro-moment characteristic, wherein the second energy consumption information is that the device power consumption of the current time step is larger than or equal to the minimum device reference consumption rate, and the device power consumption of the last time step is smaller than or equal to the maximum device standby energy consumption; if the energy consumption information is third energy consumption information, the micro-moment characteristic corresponding to the third energy consumption information is a device closing micro-moment characteristic, wherein the third energy consumption information is that the device power consumption of the current time step is smaller than or equal to the maximum device standby energy consumption and the device power consumption of the last time step is larger than or equal to the minimum device reference consumption rate; if the energy consumption information is fourth energy consumption information, the micro-moment characteristic corresponding to the fourth energy consumption information is a micro-moment characteristic of excessive equipment energy consumption, wherein the fourth energy consumption information is that the equipment power consumption of the current time step is larger than or equal to a preset multiple of the maximum equipment reference consumption rate, and the equipment longest standby time of the current time step is larger than or equal to the maximum equipment longest standby time; if the energy consumption information is fifth energy consumption information, the micro-moment characteristic corresponding to the fifth energy consumption information is abnormal energy consumption micro-moment characteristic of the equipment when going out, wherein the fifth energy consumption information is that no person is in a room, and the equipment power consumption of the current time step is larger than or equal to the preset multiple of the maximum equipment standby energy consumption.
In an exemplary embodiment of the present invention, the acquisition module 610 may determine the device power consumption in the following manner:
determining power consumption of a plurality of first devices in a preset time interval; the device power consumption is determined based on the plurality of first device power consumptions.
In an exemplary embodiment of the present invention, the acquisition module 610 may determine the device power consumption based on the plurality of first device power consumptions using the following formula (formula 2):
wherein P is N (t) represents the device power consumption at time t, P (t) represents the first device power consumption at time t, mean (P) represents an average value of the plurality of first device power consumptions over a preset time interval, max (P) represents the first device power consumption that is largest over the preset time interval, and min (P) represents the first device power consumption that is smallest over the preset time interval.
In an exemplary embodiment of the present invention, the acquisition module 610 may determine the device energy consumption information in the following manner:
acquiring energy consumption information of first equipment; and carrying out interpolation processing on the first equipment energy consumption information, and taking the processed first equipment energy consumption information as equipment energy consumption information.
Fig. 7 illustrates a physical schematic diagram of an electronic device, as shown in fig. 7, which may include: processor 710, communication interface (Communications Interface) 720, memory 730, and communication bus 740, wherein processor 710, communication interface 720, memory 730 communicate with each other via communication bus 740. Processor 710 may invoke logic instructions in memory 730 to perform an energy consumption detection method, where the energy consumption detection method may include: acquiring energy consumption information to be detected, and inputting the energy consumption information to be detected into an energy consumption detection model, wherein the energy consumption detection model is obtained through training a training sample set with micro-moment characteristics, and the micro-moment characteristics are characteristics related to equipment energy consumption types; and determining an energy consumption detection result corresponding to the energy consumption information to be detected based on the output result of the energy consumption detection model.
Further, the logic instructions in the memory 730 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, where the computer program product includes a computer program, where the computer program can be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer can execute the energy consumption detection method provided by the above methods, where the energy consumption detection method may include: acquiring energy consumption information to be detected, and inputting the energy consumption information to be detected into an energy consumption detection model, wherein the energy consumption detection model is obtained through training a training sample set with micro-moment characteristics, and the micro-moment characteristics are characteristics related to equipment energy consumption types; and determining an energy consumption detection result corresponding to the energy consumption information to be detected based on the output result of the energy consumption detection model.
In still another aspect, the present invention further provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the energy consumption detection method provided by the above methods, wherein the energy consumption detection method may include: acquiring energy consumption information to be detected, and inputting the energy consumption information to be detected into an energy consumption detection model, wherein the energy consumption detection model is obtained through training a training sample set with micro-moment characteristics, and the micro-moment characteristics are characteristics related to equipment energy consumption types; and determining an energy consumption detection result corresponding to the energy consumption information to be detected based on the output result of the energy consumption detection model.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An energy consumption detection method, the method comprising:
acquiring energy consumption information to be detected, and inputting the energy consumption information to be detected into an energy consumption detection model, wherein the energy consumption detection model is obtained through training a training sample set with micro-moment characteristics, and the micro-moment characteristics are characteristics related to equipment energy consumption types;
and determining an energy consumption detection result corresponding to the energy consumption information to be detected based on the output result of the energy consumption detection model.
2. The energy consumption detection method according to claim 1, wherein the training sample set with micro-moment features is obtained by:
based on equipment energy consumption information, obtaining equipment micro-moment characteristics corresponding to the equipment energy consumption information through a micro-moment energy label model, wherein the equipment energy consumption information at least comprises equipment occupancy rate, equipment power consumption, equipment reference consumption rate, equipment longest standby time and equipment standby energy consumption;
and obtaining the training sample set with the micro-moment characteristic based on the equipment energy consumption information and the equipment micro-moment characteristic.
3. The energy consumption detection method according to claim 2, wherein the micro-moment energy tag model is provided with an energy consumption information and micro-moment feature mapping table, and the obtaining, based on the device energy consumption information, the device micro-moment feature corresponding to the device energy consumption information through the micro-moment energy tag model includes:
and determining the micro-moment characteristics of the equipment corresponding to the equipment energy consumption information through the energy consumption information and the micro-moment characteristic mapping table based on the equipment energy consumption information.
4. The energy consumption detection method according to claim 3, wherein the energy consumption information and micro-time feature map is determined by:
if the energy consumption information is first energy consumption information, the micro-moment characteristic corresponding to the first energy consumption information is good micro-moment characteristic of equipment use, wherein the first energy consumption information is that the equipment power consumption of the current time step is larger than or equal to the minimum equipment reference consumption rate and smaller than or equal to the preset multiple of the maximum equipment reference consumption rate;
if the energy consumption information is second energy consumption information, the micro-moment characteristic corresponding to the second energy consumption information is a device opening micro-moment characteristic, wherein the second energy consumption information is that the device power consumption of the current time step is larger than or equal to the minimum device reference consumption rate, and the device power consumption of the last time step is smaller than or equal to the maximum device standby energy consumption;
if the energy consumption information is third energy consumption information, the micro-moment characteristic corresponding to the third energy consumption information is a device closing micro-moment characteristic, wherein the third energy consumption information is that the device power consumption of the current time step is smaller than or equal to the maximum device standby energy consumption and the device power consumption of the last time step is larger than or equal to the minimum device reference consumption rate;
if the energy consumption information is fourth energy consumption information, the micro-moment characteristic corresponding to the fourth energy consumption information is a micro-moment characteristic of excessive equipment energy consumption, wherein the fourth energy consumption information is that the equipment power consumption of the current time step is larger than or equal to a preset multiple of the maximum equipment reference consumption rate, and the longest equipment standby time of the current time step is larger than or equal to the longest equipment standby time of the maximum equipment;
if the energy consumption information is fifth energy consumption information, the micro-moment characteristic corresponding to the fifth energy consumption information is abnormal energy consumption micro-moment characteristic of the equipment when the equipment goes out, wherein the fifth energy consumption information is that no one exists in a room, and the equipment power consumption of the current time step is larger than or equal to the preset multiple of the maximum equipment standby energy consumption.
5. The energy consumption detection method according to claim 2, wherein the device power consumption is determined in the following manner:
determining power consumption of a plurality of first devices in a preset time interval;
the device power consumption is determined based on a plurality of the first device power consumptions.
6. The energy consumption detection method according to claim 5, wherein the determining the device power consumption based on the plurality of first device power consumptions is determined using the following formula:
wherein P is N (t) represents the device power consumption at time t, P (t) represents the first device power consumption at time t, mean (P) represents an average value of the plurality of first device power consumptions over a preset time interval, max (P) represents the first device power consumption that is largest over the preset time interval, and min (P) represents the first device power consumption that is smallest over the preset time interval.
7. The energy consumption detection method according to claim 2, wherein the device energy consumption information is determined by:
acquiring energy consumption information of first equipment;
and carrying out interpolation processing on the first equipment energy consumption information, and taking the processed first equipment energy consumption information as the equipment energy consumption information.
8. An energy consumption detection apparatus, the apparatus comprising:
the energy consumption detection system comprises an acquisition module, a detection module and a detection module, wherein the acquisition module is used for acquiring energy consumption information to be detected and inputting the energy consumption information to be detected into an energy consumption detection model, the energy consumption detection model is obtained through training a training sample set with micro-moment characteristics, and the micro-moment characteristics are characteristics about equipment energy consumption types;
and the processing module is used for determining an energy consumption detection result corresponding to the energy consumption information to be detected based on the output result of the energy consumption detection model.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the energy consumption detection method according to any one of claims 1 to 7 when the program is executed by the processor.
10. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the energy consumption detection method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111416052.3A CN116187791A (en) | 2021-11-25 | 2021-11-25 | Energy consumption detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111416052.3A CN116187791A (en) | 2021-11-25 | 2021-11-25 | Energy consumption detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116187791A true CN116187791A (en) | 2023-05-30 |
Family
ID=86434982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111416052.3A Pending CN116187791A (en) | 2021-11-25 | 2021-11-25 | Energy consumption detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116187791A (en) |
-
2021
- 2021-11-25 CN CN202111416052.3A patent/CN116187791A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rahimpour et al. | Non-intrusive energy disaggregation using non-negative matrix factorization with sum-to-k constraint | |
| Wang et al. | From time series to complex networks: The phase space coarse graining | |
| Batra et al. | NILMTK: An open source toolkit for non-intrusive load monitoring | |
| Szczurek et al. | Occupancy determination based on time series of CO2 concentration, temperature and relative humidity | |
| CN105307200B (en) | A kind of trajectory-based wireless sensor network multidimensional data rejecting outliers method | |
| US9310865B2 (en) | Method and system for optimizing a composite load disaggregation | |
| US20110307200A1 (en) | Recognizing multiple appliance operating states using circuit-level electrical information | |
| CN111459700A (en) | Method and apparatus for diagnosing device failure, diagnostic device, and storage medium | |
| CN110381126A (en) | Electrical equipment recognition methods, system, equipment and medium based on edge calculations | |
| EP3039587A1 (en) | Identifying anomalous behavior of a monitored entity | |
| CN114254879B (en) | Multi-sensor information fusion type power equipment safety diagnosis method and device | |
| CN105320834B (en) | Method for calculating number of people based on using state of electric appliance and monitoring system thereof | |
| Jazizadeh et al. | Spatiotemporal lighting load disaggregation using light intensity signal | |
| Chen et al. | Significant correlation pattern mining in smart homes | |
| CN111275069B (en) | Non-invasive load monitoring method | |
| Jin et al. | Bayesian hierarchical model for change point detection in multivariate sequences | |
| Katenka et al. | Tracking multiple targets using binary decisions from wireless sensor networks | |
| CN116842330B (en) | Health care information processing method and device capable of comparing histories | |
| CN109949190A (en) | Adaptive learning method and computer system based on learning efficiency | |
| CN113076354A (en) | User electricity consumption data analysis method and device based on non-invasive load monitoring | |
| Ghasemzadeh et al. | Energy-efficient signal processing in wearable embedded systems: An optimal feature selection approach | |
| CN116187791A (en) | Energy consumption detection method and device, electronic equipment and storage medium | |
| EP4166951A1 (en) | Method for estimating load by energy meter including load estimation model based on neural network and energy meter using the same | |
| Englert et al. | Electricity-metering in a connected world: Virtual sensors for estimating the electricity consumption of iot appliances | |
| Zhao et al. | An outlier management framework for building performance data and its application to the power consumption data of building energy systems in non-residential buildings |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |