Energy consumption prediction method and device, electronic equipment and storage medium
By acquiring and processing energy consumption data in areas such as factory parks and using pre-trained energy consumption prediction models to predict and alarm, the problem of difficulty in effectively managing energy consumption in factory parks in the existing technology is solved, and accurate prediction and management of energy consumption is achieved.
Patent Information
- Application Number
- CN202510006016.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-02
- Publication Date
- 2025-05-09
AI Technical Summary
The existing technology is difficult to effectively predict and manage energy consumption in areas such as factory parks, and it is impossible to detect energy consumption loss points in time and remind them, resulting in the inability to meet the energy consumption management needs.
By obtaining the user's current environmental data and the current usage data of each energy consumption device, as well as the energy consumption per unit period of the previous cycle, the pre-trained energy consumption prediction model is used to process it, predict the energy consumption per unit of the current cycle, and compare it with the standard energy consumption, and alarm is issued if it exceeds it.
It realizes accurate prediction and alarm of energy consumption usage in factory parks and other areas, helps users to timely discover energy consumption loss points, reduce unnecessary energy consumption, and improve the efficiency of energy consumption management.
Smart Images
Figure CN119961822A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to an energy consumption prediction method, device, electronic device and storage medium. Background Art
[0002] Areas designed for industrial production and related activities, such as factory parks, consume huge amounts of energy resources such as water, electricity, and gas. Therefore, energy consumption management in these areas is crucial.
[0003] At present, energy consumption data is collected mainly by installing meters in factory parks and other areas. However, energy consumption analysis and early warning based on energy consumption data have not yet been realized. Energy consumption cannot be effectively predicted and alarmed, and targeted improvements cannot be made to reduce energy consumption. As a result, the energy consumption management needs of factory parks and other areas cannot be met. Summary of the invention
[0004] In view of this, the present disclosure provides an energy consumption prediction method, device, electronic device and storage medium.
[0005] According to a first aspect of the present disclosure, there is provided an energy consumption prediction method, the method comprising:
[0006] Obtain the user's current environmental data and the current usage data of each energy-consuming device of the user and the energy consumption per unit time period in the previous cycle, wherein the energy consumption per unit time period includes the water consumption, electricity consumption and / or natural gas consumption per hour in the previous cycle;
[0007] Using a pre-trained energy consumption prediction model to process the user's current environment data and the current usage data of each energy-consuming device of the user and the unit time energy consumption data in the previous cycle, so as to obtain the predicted value of the energy consumption per unit time period of each monitored object of the user in the current cycle;
[0008] For each of the monitored objects, comparing the predicted value of the energy consumption per unit time period of the monitored object in the current cycle with the previously obtained standard energy consumption per unit time period of the monitored object;
[0009] If the predicted energy consumption per unit time period of a monitored object in the current cycle exceeds its standard energy consumption per unit time period, an alarm will be issued;
[0010] The monitoring object is an energy-consuming device or a node, and the node is a combination of two or more selected energy-consuming devices.
[0011] In some embodiments of the first aspect of the present disclosure, the energy consumption per unit time period of each energy consuming device in the previous cycle is obtained in the following manner: a meter deployed on each energy consuming device collects original energy consumption data of the energy consuming device in the previous cycle; abnormal data processing is performed on the original energy consumption data to eliminate extreme values in the original energy consumption data while making the original energy consumption data contain the cumulative energy consumption at each time node in the previous cycle; the original energy consumption data after abnormal data processing is transmitted to an electronic device so that the electronic device makes energy consumption predictions for the user.
[0012] In some embodiments of the first aspect of the present disclosure, the method further includes: after transmitting the original energy consumption data after abnormal data processing to the electronic device, the electronic device calls a preconfigured operation control to process the original energy consumption data to obtain the energy consumption per unit time period of each energy consumption device in the previous cycle.
[0013] In some embodiments of the first aspect of the present disclosure, the method further includes: for each of the monitored objects or pre-selected specific monitored objects, calculating the predicted value of the energy consumption cost of the monitored object in the current cycle based on the predicted value of the energy consumption per unit time period of the monitored object in the current cycle and issuing a prompt.
[0014] In some embodiments of the first aspect of the present disclosure, the method also includes: collecting and analyzing the energy usage strategy previously adopted by the user and the actual value of the energy consumption cost of each monitored object after the implementation of the energy usage strategy to obtain the energy usage relationship data of the user, the energy usage relationship data including the correspondence between the energy usage strategy and the energy consumption cost of each monitored object; generating energy usage recommendations based on the energy usage relationship data of the user and the predicted value of the energy consumption cost of each monitored object of the user in the current period and providing them to the user.
[0015] In some embodiments of the first aspect of the present disclosure, the method also includes: obtaining existing energy consumption relationship data of users of the same type from a pre-built expert database; generating energy consumption recommendations based on the existing energy consumption relationship data of users of the same type and the predicted energy consumption cost values of each monitored object of the user in the current period, and providing them to the user.
[0016] In some embodiments of the first aspect of the present disclosure, the standard energy consumption per unit time period is obtained or updated in the following manner: obtaining and analyzing the unit time period energy consumption and its environmental data and usage data of each monitored object of the user in a predetermined historical time period closest to the current cycle, so as to obtain the standard energy consumption per unit time period of each monitored object under different environmental conditions.
[0017] According to a second aspect of the present disclosure, there is provided an energy consumption prediction device, comprising:
[0018] A data acquisition unit, used to acquire the user's current environmental data and the current usage data of each energy-consuming device of the user and the energy consumption per unit time period in the previous cycle, wherein the energy consumption per unit time period includes the water consumption, electricity consumption and / or natural gas consumption per hour in the previous cycle;
[0019] A real-time prediction unit, used to process the user's current environment data and the current usage data of each energy-consuming device of the user and the unit time energy consumption data of the previous cycle using a pre-trained energy consumption prediction model, so as to obtain the predicted value of the energy consumption per unit time period of each monitored object of the user in the current cycle;
[0020] A real-time alarm unit is used to compare the predicted value of the energy consumption per unit period of the monitored object in the current cycle with the standard energy consumption per unit period of the monitored object obtained in advance for each of the monitored objects, and to alarm when the predicted value of the energy consumption per unit period of the monitored object in the current cycle exceeds its standard energy consumption per unit period;
[0021] The monitoring object is an energy-consuming device or a node, and the node is a combination of two or more selected energy-consuming devices.
[0022] According to a third aspect of the present disclosure, an electronic device is provided, comprising: one or more processors and a memory storing a program, wherein the program comprises instructions, and when the instructions are executed by the processor, the processor executes the above method.
[0023] According to a fourth aspect of the present disclosure, a computer-readable storage medium storing a program is provided, wherein the program includes instructions, which, when executed by one or more processors of a computing device, cause the computing device to execute the above method.
[0024] It can be seen from the above technical solution that the embodiment of the present disclosure can predict the energy consumption per unit time period of each monitored object of the user in the current cycle based on the energy consumption data of the previous cycle of users such as industrial parks, combined with the current environmental data and energy consumption equipment usage data, and issue an alarm when the energy consumption per unit time period exceeds the corresponding standard, so as to timely discover the energy loss points of the user and give reminders, thereby helping the user to save energy better. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0026] Figure 1A schematic diagram of a process of an energy consumption prediction method provided by an embodiment of the present disclosure;
[0027] Figure 2 An example diagram of a computing control involved in an embodiment of the present disclosure;
[0028] Figure 3 Another schematic diagram of a flow chart of an energy consumption prediction method provided by an embodiment of the present disclosure;
[0029] Figure 4 A schematic diagram of the structure of an energy consumption prediction device provided in an embodiment of the present disclosure;
[0030] Figure 5 A schematic structural block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0031] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.
[0032] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. The singular forms "a", "said" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.
[0033] As used herein, the words "if," "if," and the like may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.
[0034] Users with high energy consumption, such as factories and parks, have an urgent need to manage their own energy consumption. However, there is currently no technology that can effectively predict the energy consumption of such users and issue an alarm when necessary.
[0035] In view of this, the embodiments of the present disclosure provide an energy consumption prediction method, device, electronic device and storage medium, which utilize the energy consumption per unit time period of each energy-consuming device of the user in the previous cycle, environmental data, and energy-consuming device usage data to predict the energy consumption per unit time period of each monitored object of the user in the current cycle, and issue an alarm when the energy consumption per unit time period exceeds the corresponding standard energy consumption per unit time period. As a result, the embodiments of the present disclosure can issue early warnings for electricity consumption, water consumption and / or natural gas consumption of users such as factory parks, and can promptly detect abnormal conditions of energy-consuming equipment, helping users to better save energy without affecting normal production and life.
[0036] The specific implementation of the embodiment of the present disclosure is described in detail below.
[0037] Figure 1 The schematic diagram of the flow chart of an energy consumption prediction method provided by an embodiment of the present disclosure is shown. The energy consumption prediction method can be applied to, but not limited to, smart gateways or other similar electronic devices. Figure 1 , the method of the embodiment of the present disclosure may include the following steps:
[0038] Step 101, obtaining the user's current environment data and the current usage data of each energy-consuming device of the user and the energy consumption per unit time period in the previous cycle;
[0039] The energy consumption per unit time period of the previous cycle may include the water consumption, electricity consumption and / or natural gas consumption per unit time period of the previous cycle.
[0040] Here, the duration of the cycle and the unit period can be flexibly set as needed. For example, the duration of a cycle can be set to one day, that is, 24 hours, and the unit period can be set to 1 hour. The energy consumption per unit period of the previous cycle is the hourly energy consumption of the previous 24 hours.
[0041] Here, the energy consumption may be but is not limited to water consumption, electricity consumption and / or natural gas consumption. Those skilled in the art should understand that if the current user also needs to manage other energy consumption, the energy consumption may also include other energy consumption, which is not limited in the embodiments of the present disclosure.
[0042] Environmental data may include but is not limited to weather, temperature, humidity and other data.
[0043] The usage data of energy-consuming equipment may include but is not limited to the operating status of the energy-consuming equipment (for example, on, off, standby, fault, maintenance, etc.), key performance indicators (for example, speed, pressure, temperature, humidity, pressure, flow, etc.), maintenance and repair records (equipment's regular maintenance records, fault repair records, etc.), equipment usage frequency (for example, the number of times and duration of use of the equipment per day), and equipment life (for example, service life, depreciation and update plan, etc.).
[0044] Different types of users have different contents of environmental data and energy consumption equipment usage data. The specific contents of environmental data and energy consumption equipment usage data can be flexibly adjusted or updated according to application scenarios and user types, and the embodiments of the present disclosure do not limit this.
[0045] Step 102, using a pre-trained energy consumption prediction model to process the user's current environment data and the current usage data of each energy-consuming device of the user and the unit time energy consumption data in the previous cycle, so as to obtain the unit time period energy consumption prediction value of each monitored object of the user in the current cycle;
[0046] For example, if the duration of a cycle is set to one day, that is, 24 hours, the unit time period can be set to 1 hour, and the unit time period energy consumption forecast value of each monitored object in the current cycle is the hourly energy consumption forecast value of the current 24 hours.
[0047] The monitoring object is an energy-consuming device or a node, and a node is a combination of two or more selected energy-consuming devices.
[0048] Nodes can be flexibly set up as needed. For example, if the user is an industrial park, the node can be divided according to the factory deployment of the industrial park. For example, the nodes of an industrial park can be divided into two node sets: auxiliary building and N1 factory building. The node set "N1 factory building" includes the following nodes: N1-1F power room-1, N1-1F power room-2,..., N1-1F laboratory room-9, and the node set "auxiliary building" includes the following nodes: auxiliary building canteen 1st floor,..., auxiliary building engineering workshop, auxiliary building training room. These nodes contain all energy-consuming equipment in the corresponding area. For example, the node "N1-1F power room-1" contains all energy-consuming equipment in N1-1F power room-1.
[0049] Energy-consuming equipment may include any equipment that needs to use water, electricity and / or natural gas, and these equipment may be electronic equipment, mechanical equipment, or composite equipment. The specific form of the energy-consuming equipment is not limited in the embodiments of the present disclosure.
[0050] If the user is a factory park, the energy-consuming equipment may include but is not limited to: industrial equipment such as various production machinery, processing equipment, automated production lines, HVAC systems, lighting equipment, data centers and servers, charging piles, boilers and thermal systems, power transmission equipment such as transformers and motors, energy storage systems, water supply and drainage systems, and material handling equipment such as conveyor belts, cranes, and forklifts.
[0051] Step 103, for each monitored object, comparing the predicted value of the energy consumption per unit time period of the monitored object in the current cycle with the previously obtained standard energy consumption per unit time period of the monitored object;
[0052] Step 104: If the predicted energy consumption per unit time period of a monitored object in the current cycle exceeds its standard energy consumption per unit time period, an alarm is issued.
[0053] Furthermore, in step 101, the energy consumption per unit time period of each energy-consuming device in the previous cycle is obtained through the following steps a1 to a3:
[0054] Step a1, the meter deployed on each energy consuming device collects the original energy consumption data of the energy consuming device in the previous cycle;
[0055] In specific applications, water meters, electricity meters and / or natural gas usage meters can be installed on energy-consuming devices to collect the original energy consumption data of these energy-consuming devices in real time.
[0056] The type of raw energy consumption data is related to the meter. For example, if the meter is an electric energy meter, the raw energy consumption data may include the cumulative electricity consumption from the time the electric energy meter is started to the current time; if the meter is a water meter, the raw energy consumption data may include the cumulative water consumption from the time the water meter is started to the current time; if the meter is a natural gas meter, the raw energy consumption data may include the cumulative natural gas usage from the time the natural gas meter is started to the current time.
[0057] Step a2, performing abnormal data processing on the original energy consumption data to eliminate extreme values in the original energy consumption data while making the original energy consumption data include the accumulated energy consumption at each time node in the previous cycle;
[0058] The original energy consumption data of each energy-consuming device is detected for extreme values and missing values. If the cumulative energy consumption of the first n time nodes is found to be missing, and the cumulative energy consumption of the n+1th time node reaches an extreme value, the cumulative energy consumption of the n+1th time node is smoothly distributed to the "n+1" time nodes to eliminate problems such as missing values and extreme values, and at the same time make the original energy consumption data include the cumulative energy consumption of each time node in the previous period.
[0059] For example, if the duration of a cycle is set to 24 hours and the unit time period is set to 1 hour, if the original energy consumption data of a certain energy-consuming device collected in step a1 in the previous cycle does not include the cumulative energy consumption at 2 o'clock, 3 o'clock and 4 o'clock, but the cumulative energy consumption at 5 o'clock reaches an extreme value, then the cumulative energy consumption at 5 o'clock can be evenly distributed to these four time nodes, namely 2 o'clock, 3 o'clock, 4 o'clock and 5 o'clock. In this way, it can be ensured that there will be no missing values and extreme values in the original energy consumption data.
[0060] For example, if the duration of a cycle is set to 24 hours and the unit time period is set to 1 hour, after abnormal data processing, the original energy consumption data of a certain energy-consuming device in the previous cycle will include the cumulative energy consumption at 0:00, 1:00, 2:00, 3:00, 4:00, ..., 23:00 in the previous 24 hours.
[0061] Step a3, transmitting the original energy consumption data after abnormal data processing to the electronic device, so that the electronic device can make energy consumption prediction for the user.
[0062] In specific applications, a data processing module and a data transmission module can be installed in the meter installed in the energy consumption equipment. The data processing module implements the processing of steps a1 to a2, and the data transmission module is responsible for executing the processing of step a3. In this way, the abnormal processing of energy consumption data can be realized on the energy consumption equipment side, the bandwidth requirement for data transmission can be reduced, and the accuracy of energy consumption data can be improved.
[0063] Furthermore, after step a3, step 101 may also include: step a4, the electronic device calls the pre-configured calculation control to process the original energy consumption data to obtain the energy consumption per unit time period of each energy consuming device in the previous cycle. Thus, when the original energy consumption data does not contain the energy consumption per unit time period, the calculation control can be used to process the original energy consumption data to obtain the energy consumption per unit time period, and the energy consumption per unit time period of different energy consuming devices can be calculated by the calculation control that supports four arithmetic operations, so as to meet the actual application requirements of using different meters.
[0064] Considering that most calculations of energy consumption are based on four arithmetic operations, in some examples, the calculation control can be Figure 2 The four calculation controls shown. In specific applications, if the original energy consumption data collected before is the cumulative energy consumption, it is necessary to calculate the energy consumption per unit time period through the calculation control. At this time, the energy consumption per unit time period can be obtained by calling the calculation control to calculate the difference between the cumulative energy consumption of two adjacent time nodes. For example, if the duration of a cycle is set to 24 hours and the unit time period is set to 1 hour, the calculation control can be called to use the cumulative power consumption at 3 o'clock minus the cumulative power consumption at 2 o'clock to get the "1-hour power consumption from 2 o'clock to 3 o'clock."
[0065] In step 102, the energy consumption prediction model can be but is not limited to a time series analysis model (ARIMA, seasonal decomposition, etc.), a machine learning model (for example, random forest, support vector machine, etc.) or a deep learning model (for example, LSTM, CNN-LSTM, etc.). Using these models as energy consumption prediction models can take into account the impact of multiple factors on energy consumption while achieving accurate prediction of energy consumption.
[0066] In some implementations, the energy consumption prediction model can be trained in the following manner: collect the user's historical energy consumption data, which includes the user's energy consumption per unit period in each cycle over the past period of time, and record all relevant data corresponding to these historical energy consumption data that may affect energy consumption, such as energy consumption equipment usage data and environmental data such as weather conditions, temperature, humidity, etc. After preprocessing the user's historical energy consumption data and its corresponding energy consumption factor-related data such as data clarity, outlier processing, and data normalization, use these data to construct a training set, a validation set, and a test set, use the training set to train the energy consumption prediction model, and use the validation set and the test set to evaluate the performance of the energy consumption prediction model, and continue in this way until the performance of the energy consumption prediction model meets the predetermined conditions.
[0067] In specific applications, an energy consumption prediction model can be trained for a specific user so that the energy consumption prediction model can better fit the characteristics of the specific user. An energy consumption prediction model can also be trained for different types of users, and the energy consumption prediction model can be applied to multiple users of the same type, with lower training costs.
[0068] In step 103, the standard energy consumption per unit time period can be obtained through the user's historical energy consumption data.
[0069] Furthermore, the method of the embodiment of the present disclosure may also include: obtaining or updating the standard energy consumption per unit period. Specifically, obtaining and analyzing the energy consumption per unit period of each monitored object of the user in a predetermined historical period closest to the current cycle and its environmental data and usage data, so as to obtain the standard energy consumption per unit period of each monitored object under different environmental conditions.
[0070] Here, the predetermined historical period can be one year, one month, one week or other values, that is, the predetermined historical period closest to the current cycle can be the year, one month, one week closest to the current cycle. In specific applications, the predetermined historical period can be flexibly set according to actual application requirements and user types.
[0071] In specific applications, the standard energy consumption per unit time period is obtained by one of the following methods:
[0072] 1) Analyze the energy consumption per unit time period of the monitored object under different working conditions (such as different loads, different operating modes) and different environmental conditions (for example, different weather, different temperature, different humidity), calculate the upper limit of the energy consumption per unit time period under these specific conditions, and use the upper limit of the energy consumption per unit time period as the standard energy consumption per unit time period under the corresponding conditions.
[0073] 2) By conducting statistical analysis on the energy consumption per unit period of a monitored object in a predetermined historical period closest to the current cycle, as well as its environmental data and usage data, such as calculating the standard deviation, variance, etc., the distribution of the energy consumption data of the monitored object can be determined, and the upper limit of the energy consumption per unit period of the monitored object can be determined based on the distribution of the energy consumption data, and the upper limit of the energy consumption per unit period can be used as the aforementioned standard energy consumption per unit period.
[0074] 3) Performing time series analysis based on the energy consumption per unit period of the monitored object in a predetermined historical period closest to the current cycle to fit a trend curve of energy consumption per unit period of the monitored object, determining an upper limit of energy consumption per unit period of the monitored object based on the trend curve of energy consumption per unit period of the monitored object, and using the upper limit of energy consumption per unit period as the aforementioned standard energy consumption per unit period.
[0075] In specific applications, since the production plans of users such as factory parks often change, the performance and energy consumption of energy-consuming equipment will gradually change with their use time. Therefore, the standard energy consumption per unit period of each monitored object needs to be updated in real time. The disclosed embodiment uses the most recent energy consumption data as the basis for determining the standard energy consumption per unit period, and can obtain a standard energy consumption per unit period that is closer to the current actual status of the energy-consuming equipment, thereby further improving the accuracy of energy consumption prediction.
[0076] In step 104, there may be multiple ways of alarming. For example, the alarming method may be, but is not limited to, voice, picture, text, prompt box, etc. The alarm content may include the name of the monitored object whose unit period energy consumption forecast value exceeds its unit period standard energy consumption and its unit period energy consumption forecast value.
[0077] Figure 3 Another flow chart of the energy consumption prediction method provided by an embodiment of the present disclosure is shown.
[0078] Further, see Figure 3 After step 104, the following may be included: step 105, for each monitored object or a pre-selected specific monitored object, the energy consumption cost prediction value of the monitored object in the current cycle is calculated according to the unit time period energy consumption prediction value of the monitored object in the current cycle and a prompt is issued. In this way, the energy consumption of the equipment can be predicted, and the energy consumption cost of the current cycle can be calculated according to the electricity price, water price and / or natural gas price, so that the user can understand the energy consumption situation in real time.
[0079] Further, see Figure 3 After step 104, the method may further include: step 106, generating energy use suggestions based on the predicted value of the energy consumption cost of the monitored object in the current cycle and providing them to the user.
[0080] In some implementations, step 106 may include: first, collecting and analyzing the energy consumption strategies previously adopted by the user and the actual energy consumption cost values of each monitored object after their implementation to obtain the user's energy consumption relationship data, the energy consumption relationship data including the corresponding relationship between the energy consumption strategies and energy consumption costs of each monitored object; second, generating energy consumption suggestions based on the user's energy consumption relationship data and the predicted energy consumption cost values of each monitored object of the user in the current cycle and providing them to the user. Thus, an energy consumption strategy suitable for the predicted energy consumption cost value of the current cycle can be found by analyzing the energy consumption strategies used by the user in the past and the energy consumption cost conditions after their implementation, and using the energy consumption strategy to generate energy consumption suggestions and provide them to the user. Thus, an effective energy use strategy can be provided in combination with the user's actual production situation to help the user save energy better.
[0081] Furthermore, step 106 may include: obtaining existing energy usage relationship data of users of the same type from a pre-built expert database; generating energy usage suggestions and providing them to the user based on the existing energy usage relationship data of users of the same type and the predicted energy consumption cost values of each monitored object of the user in the current cycle. Thus, effective energy usage strategies can be provided to users by pre-building an expert database. Here, users of the same type refer to other users of the same type as the current user.
[0082] Specifically, energy usage strategies applicable to the predicted energy consumption cost values of each monitored object in the current period are found in the existing energy usage relationship data of users of the same type, and these energy usage strategies are used as content to generate energy usage recommendations.
[0083] Among them, the expert database can include energy consumption relationship data of different types of users. These energy consumption relationship data have labels, and the scores of the labels indicate the validity of the energy consumption relationship data. The energy consumption relationship data of the same type of users can refer to each other to better help users save energy.
[0084] Furthermore, after step 106, the following may be included: scoring the corresponding relationship between the energy consumption strategy and energy consumption cost of each monitored object in the energy consumption relationship data of the current user; using the scoring result (i.e., the score) as a label to mark the corresponding relationship between the energy consumption strategy and energy consumption cost of each monitored object in the energy consumption relationship data; and storing the marked energy consumption relationship data in the expert database. In this way, while providing electricity consumption suggestions in real time, the expert database can be simultaneously constructed and updated, so as to better provide users with energy consumption suggestions that are more in line with actual application conditions in the future.
[0085] It can be seen from the above that the energy consumption prediction method provided by the embodiment of the present disclosure can not only predict the energy consumption of each monitored object of the user in the unit time period of the current cycle in real time based on the energy consumption data of the user in the previous cycle, the user's current environmental data and the current usage data of the energy consumption equipment, and issue an alarm when the energy consumption in the unit time period exceeds the standard, thereby helping the user to discover energy loss points in time, but also can predict the energy consumption costs, and give reasonable energy use suggestions based on the energy consumption costs, thereby helping the user to better save energy.
[0086] Figure 4 FIG. 1 shows a schematic diagram of the structure of the energy consumption prediction device provided by the embodiment of the present disclosure. Figure 4 , the energy consumption prediction device 400 of the embodiment of the present disclosure may include:
[0087] The data acquisition unit 401 is used to acquire the user's current environment data and the current usage data of each energy-consuming device of the user and the energy consumption per unit time period in the previous cycle, where the energy consumption per unit time period includes the water consumption, electricity consumption and / or natural gas consumption per hour in the previous cycle;
[0088] The energy consumption prediction unit 402 is used to process the user's current environment data and the current usage data of each energy-consuming device of the user and the unit time energy consumption data of the previous cycle using a pre-trained energy consumption prediction model to obtain the predicted value of the energy consumption per unit time period of each monitored object of the user in the current cycle;
[0089] The energy consumption alarm unit 403 is used to compare the predicted value of the energy consumption per unit period of the monitored object in the current cycle with the previously obtained standard energy consumption per unit period of the monitored object for each monitored object, and to alarm when the predicted value of the energy consumption per unit period of the monitored object in the current cycle exceeds its standard energy consumption per unit period;
[0090] The monitoring object is an energy-consuming device or a node, and a node is a combination of two or more selected energy-consuming devices.
[0091] Furthermore, the energy consumption prediction device 400 of the embodiment of the present disclosure may also include: an operation unit 404, which is used to call a preconfigured operation control to process the original energy consumption data to obtain the energy consumption per unit time period of each energy consuming device in the previous cycle.
[0092] Furthermore, the energy consumption prediction device 400 of the embodiment of the present disclosure may also include: a cost prediction unit 405, which is used to calculate the energy consumption cost prediction value of the monitored object in the current cycle according to the predicted value of the energy consumption per unit time period of the monitored object in the current cycle and issue a prompt for each monitored object or a pre-selected specific monitored object.
[0093] Furthermore, the energy consumption prediction device 400 of the embodiment of the present disclosure may also include: an energy usage suggestion unit 406, which is used to collect and analyze the energy usage strategies previously adopted by the user and the actual values of the energy consumption costs of each monitored object after the implementation of the energy usage strategies to obtain the user's energy usage relationship data, the energy usage relationship data including the correspondence between the energy usage strategies and the energy consumption costs of each monitored object; based on the user's energy usage relationship data and the predicted values of the energy consumption costs of each monitored object of the user in the current period, energy usage suggestions are generated and provided to the user.
[0094] Furthermore, the energy usage recommendation unit 406 can also be used to: obtain existing energy usage relationship data of users of the same type from a pre-built expert database; generate energy usage recommendations and provide them to users based on the existing energy usage relationship data of users of the same type and the predicted energy consumption cost values of each monitored object of the user in the current period.
[0095] Furthermore, the energy consumption prediction device 400 of the embodiment of the present disclosure may also include: a standard calculation unit 407, which is used to obtain and analyze the unit time period energy consumption and its environmental data and usage data of each monitored object of the user in a predetermined historical period closest to the current cycle, so as to obtain the unit time period standard energy consumption of each monitored object under different environmental conditions.
[0096] In a specific application, the energy consumption prediction device 400 can be implemented by software, hardware or a combination of the two. For example, the energy consumption prediction device 400 can be implemented as software running in the electronic device 500 described below.
[0097] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. The program includes instructions, and when the instructions are executed by one or more processors of a computing device, the steps of the aforementioned energy consumption prediction method are executed.
[0098] Figure 5 FIG. 1 is a schematic diagram showing the structure of an electronic device provided by an embodiment of the present disclosure. Figure 5 The electronic device 500 may include: one or more processors 501, and a memory 502 storing one or more programs, which are executed by the one or more processors 501 to implement the method flow shown in the above embodiments of the present disclosure and / or program units corresponding to each unit in the device.
[0099] The various components are interconnected using different buses and can be mounted on a common motherboard or in other ways as needed. The processor 501 can process instructions executed within the electronic device, including instructions stored in or on the memory to display graphical information of the user interface on an external input / output device (such as a display device coupled to the interface). In other embodiments, if desired, multiple processors and / or multiple buses can be used with multiple memories and multiple memories.
[0100] The processor 501 may include one or more single-core processors or multi-core processors. The processor 501 may include any combination of general-purpose processors or dedicated processors (such as image processors, application processors, baseband processors, etc.).
[0101] The memory 502 is a computer-readable storage medium provided by the present disclosure, which can be used to store non-transient software programs, non-transient computer executable programs and units, such as the following in the embodiments of the present disclosure: Figure 1 The processor 501 executes the non-transient software programs, instructions and units stored in the memory 502, thereby executing the above method embodiments. Figure 1 The programs, instructions and units corresponding to the energy consumption prediction method shown.
[0102] The electronic device 500 may further include: an input device 503 and an output device 504. The processor 501, the memory 502, the input device 503 and the output device 504 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.
[0103] The input device 503 can receive input digital or character information, and generate signal input related to user settings and function control, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 504 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.
[0104] The above-mentioned programs (also referred to as software, software applications, or codes) include machine instructions for programmable processors, and these computer programs can be implemented using object-oriented programming languages, assembly or machine languages.
[0105] With the development of time and technology, the meaning of medium is becoming more and more extensive, and the propagation path of computer programs is no longer limited to tangible media, and can also be downloaded directly from the network, etc. Any combination of one or more computer-readable storage media can be used. Computer-readable storage media can be used but not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing programs, which can be used by or in combination with instruction execution systems, devices or devices.
[0106] In a specific implementation, the electronic device 500 may be implemented as a computer, a server or a cluster thereof. The embodiment of the present disclosure does not limit the specific implementation form of the electronic device 500.
[0107] The technical solution provided by the present disclosure is described in detail above. The principles and implementation methods of the present disclosure are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of the present disclosure. At the same time, for those skilled in the art, according to the idea of the present disclosure, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present disclosure.
[0108] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.
Claims
1. A method for predicting energy consumption, characterized in that: The method comprises: Obtain the user's current environmental data and the current usage data of each energy-consuming device of the user and the energy consumption per unit time period in the previous cycle, wherein the energy consumption per unit time period includes the water consumption, electricity consumption and / or natural gas consumption per hour in the previous cycle; Using a pre-trained energy consumption prediction model to process the user's current environment data and the current usage data of each energy-consuming device of the user and the unit time energy consumption data in the previous cycle, so as to obtain the predicted value of the energy consumption per unit time period of each monitored object of the user in the current cycle; For each of the monitored objects, comparing the predicted value of the energy consumption per unit time period of the monitored object in the current cycle with the previously obtained standard energy consumption per unit time period of the monitored object; If the predicted energy consumption per unit time period of a monitored object in the current cycle exceeds its standard energy consumption per unit time period, an alarm will be issued; The monitoring object is an energy-consuming device or a node, and the node is a combination of two or more selected energy-consuming devices.
2. The method according to claim 1, characterized in that The energy consumption per unit time period of each energy-consuming device in the previous cycle is obtained in the following way: The meters deployed on the energy consuming devices collect the original energy consumption data of the energy consuming devices in the previous cycle; Performing abnormal data processing on the original energy consumption data to eliminate extreme values in the original energy consumption data while making the original energy consumption data include the accumulated energy consumption at each time node in the previous cycle; The original energy consumption data after abnormal data processing is transmitted to the electronic device, so that the electronic device predicts the energy consumption of the user.
3. The method according to claim 2, characterized in that The method further comprises: After the original energy consumption data after abnormal data processing is transmitted to the electronic device, the electronic device calls the preconfigured operation control to process the original energy consumption data to obtain the energy consumption per unit time period of each energy consuming device in the previous cycle.
4. The method according to claim 1, characterized in that: The method further comprises: For each of the monitored objects or pre-selected specific monitored objects, the predicted value of the energy consumption cost of the monitored object in the current cycle is calculated based on the predicted value of the energy consumption per unit time period of the monitored object in the current cycle, and a prompt is issued.
5. The method according to claim 4, characterized in that The method further comprises: Collecting and analyzing the energy consumption strategy previously adopted by the user and the actual value of energy consumption cost of each monitored object after the energy consumption strategy is implemented to obtain the energy consumption relationship data of the user, wherein the energy consumption relationship data includes the corresponding relationship between the energy consumption strategy and the energy consumption cost of each monitored object; Based on the energy consumption relationship data of the user and the predicted value of energy consumption cost of each monitored object of the user in the current cycle, energy consumption suggestions are generated and provided to the user.
6. The method according to claim 4, characterized in that The method further comprises: Obtain existing energy usage relationship data of similar users from the pre-built expert database; Based on the existing energy consumption relationship data of the same type of users and the predicted energy consumption cost value of each monitored object of the user in the current cycle, energy consumption suggestions are generated and provided to the user.
7. The method according to claim 1, characterized in that The standard energy consumption per unit time period is obtained or updated in the following manner: The energy consumption per unit period of each monitored object of the user in a predetermined historical period closest to the current cycle and its environmental data and usage data are obtained and analyzed to obtain the standard energy consumption per unit period of each monitored object under different environmental conditions.
8. An energy consumption prediction device, characterized in that: include: A data acquisition unit, used to acquire the user's current environmental data and the current usage data of each energy-consuming device of the user and the energy consumption per unit time period in the previous cycle, wherein the energy consumption per unit time period includes the water consumption, electricity consumption and / or natural gas consumption per hour in the previous cycle; A real-time prediction unit, used to process the user's current environment data and the current usage data of each energy-consuming device of the user and the unit time energy consumption data of the previous cycle using a pre-trained energy consumption prediction model, so as to obtain the predicted value of the energy consumption per unit time period of each monitored object of the user in the current cycle; A real-time alarm unit is used to compare the predicted value of the energy consumption per unit period of the monitored object in the current cycle with the standard energy consumption per unit period of the monitored object obtained in advance for each of the monitored objects, and to alarm when the predicted value of the energy consumption per unit period of the monitored object in the current cycle exceeds its standard energy consumption per unit period; The monitoring object is an energy-consuming device or a node, and the node is a combination of two or more selected energy-consuming devices.
9. An electronic device, characterized in that: include: One or more processors and a memory storing a program, wherein the program comprises instructions, and when the instructions are executed by the processor, the processor executes the method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a program, wherein the program comprises instructions, and when the instructions are executed by one or more processors of a computing device, the instructions cause the computing device to execute the method according to any one of claims 1 to 7.