WO2020024534A1 - 基于电量预测的用电控制方法、装置、设备和存储介质 - Google Patents

基于电量预测的用电控制方法、装置、设备和存储介质 Download PDF

Info

Publication number
WO2020024534A1
WO2020024534A1 PCT/CN2018/122805 CN2018122805W WO2020024534A1 WO 2020024534 A1 WO2020024534 A1 WO 2020024534A1 CN 2018122805 W CN2018122805 W CN 2018122805W WO 2020024534 A1 WO2020024534 A1 WO 2020024534A1
Authority
WO
WIPO (PCT)
Prior art keywords
power consumption
power
current time
time information
standard
Prior art date
Application number
PCT/CN2018/122805
Other languages
English (en)
French (fr)
Inventor
孙闳绅
金戈
徐亮
肖京
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2020024534A1 publication Critical patent/WO2020024534A1/zh

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Definitions

  • the present application relates to the field of power consumption control, and in particular, to a method, device, device, and computer storage medium for power consumption control based on electricity quantity prediction.
  • a resource-saving society is one of the strategic deployments to implement the scientific outlook on development. Resource conservation involves all aspects of people's lives. Among them, saving electricity is an extremely critical aspect.
  • the estimation and control of people's electricity consumption for production and living has become an important measure for saving electricity.
  • the current electricity consumption assessment is based on historical data. Specifically, monitoring equipment collects the electricity consumption of users on each floor in real time. Historical data for the same period, and the historical data for the same period of time are used to take the average value, and the average value of electricity is used as the predicted value of future power consumption, that is, the existing power forecast must rely on historical data.
  • Such a power forecast scheme has a lagging nature Since the predicted power data is not accurate, it is not possible to automatically control power consumption based on the estimated power consumption. How to perform automatic power control has become a technical problem that needs to be solved at present.
  • the main purpose of the present application is to provide a power consumption control method, device, equipment and storage medium based on power quantity prediction, by implementing automatic power consumption control to reduce unnecessary power consumption.
  • the present application provides a power consumption control method based on power consumption prediction.
  • the power consumption control method based on power consumption prediction includes the following steps:
  • a power consumption control instruction is generated to adjust the working state of the power consumption equipment for power consumption control.
  • the present application also provides a power consumption control device based on power quantity prediction.
  • the power consumption control device based on power quantity prediction includes:
  • a receiving module configured to receive a power consumption monitoring instruction, determine current time information, and obtain power consumption characteristic information associated with the current time information
  • An input module configured to input the power consumption characteristic information into a preset regression model to obtain a standard power consumption corresponding to the current time information
  • An acquisition comparison module configured to acquire an actual power consumption corresponding to the current time information, and compare the actual power consumption with the standard power consumption
  • a policy determination module configured to determine a power control strategy according to the actual power consumption, the standard power consumption, and the power consumption characteristic information if the actual power consumption is higher than the standard power consumption;
  • a control module is configured to generate a power consumption control instruction based on the power consumption control strategy to adjust a working state of the power consumption equipment for power consumption control.
  • the present application also provides a power consumption control device based on power quantity prediction
  • the power consumption control device based on the power prediction includes: a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor, wherein:
  • the present application also provides a computer storage medium
  • Computer-readable instructions are stored on the computer storage medium, and when the computer-readable instructions are executed by a processor, the steps of the power consumption control method based on the power prediction described above are implemented.
  • a power consumption control method, device, device, and computer storage medium based on power forecasting provided in the embodiments of the present application, receives a power monitoring instruction through a server, determines current time information, and obtains power consumption characteristic information associated with the current time information. Inputting the power consumption characteristic information into a preset regression model to obtain a standard power consumption corresponding to the current time information; obtaining the actual power consumption corresponding to the current time information, and comparing the actual power consumption with all The standard power consumption is compared; if the actual power consumption is higher than the standard power consumption, power control is determined according to the actual power consumption, the standard power consumption, and the power consumption characteristic information.
  • the power consumption control strategy based on the power consumption control strategy is to generate power consumption control instructions to adjust the working state of the power equipment for power control, in this application, the standard power consumption is obtained by processing the power consumption characteristic information through a preset regression model, and the server is based on Calculate the standard power consumption, actual power consumption and power consumption characteristics information, determine the power control strategy of the currently working power equipment, and determine Based strategy generating power control command is transmitted to the respective electrical equipment, the electrical equipment used to adjust the operational state of the power control command, in the present application to achieve the automatic power control, power control such that more intelligent and flexible.
  • FIG. 1 is a schematic structural diagram of a device for a hardware operating environment involved in a solution according to an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a first embodiment of a power consumption control method based on power forecasting in this application;
  • FIG. 3 is a schematic diagram of functional modules of an embodiment of a power consumption control device based on power forecasting in this application.
  • FIG. 1 is a server of a hardware operating environment (also referred to as a power consumption control device based on power consumption prediction) according to an embodiment of the present application.
  • the power consumption control device based on power prediction may be a separate power consumption
  • the predicted power consumption control device may also be formed by combining other devices with the power consumption control device based on the power forecast).
  • a server refers to a computer that manages resources and provides services to users, and is generally divided into a file server, a database server, and an application-readable instruction server.
  • a computer or computer system running the above software is also called a server.
  • the server may include a processor 1001, such as a central processing unit (Central Processing Unit, CPU), network interface 1004, user interface 1003, memory 1005, communication bus 1002, chipset, disk system, network and other hardware.
  • the communication bus 1002 is used to implement connection and communication between these components.
  • the user interface 1003 may include a display, an input unit such as a keyboard, and the optional user interface 1003 may further include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity WIreless-FIdelity, WIFI interface).
  • the memory 1005 may be a high-speed random access memory (random access memory (RAM), or non-volatile memory), such as disk storage.
  • RAM random access memory
  • non-volatile memory such as disk storage.
  • the memory 1005 may optionally be a storage device independent of the foregoing processor 1001.
  • the server may further include a camera, RF (Radio Frequency, radio frequency) circuits, sensors, audio circuits, WiFi modules; input units, display screens, touch screens; network interfaces are optional.
  • RF Radio Frequency, radio frequency
  • the server structure shown in FIG. 1 does not constitute a limitation on the server, and may include more or fewer components than shown in the figure, or some components may be combined, or different components may be arranged.
  • the computer software product is stored in a storage medium (storage medium: also called computer storage medium, computer medium, readable medium, readable storage medium, computer-readable storage medium, or directly called medium, etc., such as RAM , Magnetic disk, CD-ROM, the storage medium may be a non-volatile readable storage medium), including a number of instructions to make a terminal device (can be a mobile phone, computer, server, air conditioner, or network device, etc.) execute this
  • the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and computer-readable instructions.
  • the network interface 1004 is mainly used to connect to a background database and perform data communication with the background database; the user interface 1003 is mainly used to connect to a client (client, also called a client or a terminal.
  • the terminal can be a fixed terminal or a mobile terminal.
  • fixed terminals such as "Internet of Things equipment", intelligent air conditioners with networking functions, smart lights, intelligent power supplies, etc .
  • mobile terminals such as AR / VR devices with networking functions, Smart speakers, self-driving cars, PCs, smart phones, tablets, e-book readers, portable computers and other terminal devices with display functions.
  • the terminal contains sensors such as light sensors, motion sensors, and other sensors.
  • the mobile terminal can also be equipped with a gyroscope.
  • the processor 1001 can be used to call the computer-readable instructions stored in the memory 1005 and execute Electricity control based on power prediction provided in the following embodiments of the present application Step method.
  • a power consumption control method based on power prediction is proposed.
  • developers need to establish a preset regression model before the server can calculate a standard power consumption based on the preset regression model. Based on the comparison result of the standard power consumption and the actual power consumption, whether to perform power control of the power consumption equipment is determined.
  • the step of establishing a preset regression model in this embodiment includes:
  • Step S01 obtaining power samples from a preset power sample set, classifying each of the power samples according to a preset classification rule, and obtaining n power sample subsets;
  • the server obtains a power sample from a preset power sample set, where the preset power sample set refers to pre-stored historical power related information, the server obtains the included power samples from the preset power sample set, and sets each power sample as preset
  • the classification rules are used to classify and obtain n subsets of power samples.
  • the preset classification rules refer to the preset power sample classification rules.
  • the preset classification rules are set to the collection time classification rules. The collection time is classified to obtain a subset of power samples corresponding to each year and month.
  • the server will collect the historical power consumption and related information: the power consumption on Tuesday, June 5, 2018 from 13:00 to 13:05, the outdoor temperature is 30 degrees Celsius, and the address is xxx office building in Shenzhen Room, Guangdong province. Information such as the working day is saved to the memory; when receiving a request to establish a preset regression model, the server randomly extracts a certain amount of historical power consumption and its related information from the memory as a power sample, and uses the extracted power samples Forms a preset power sample set, and the server classifies each power sample in the preset power sample set according to the power sample collection time to obtain n power sample subsets in different time periods, where the power samples in each power sample subset may be the same May also be different.
  • Step S02 the following steps are performed for each of the power sample subsets: using the power sample subset as a target power sample subset, generating an initial regression model based on the target power sample subset, and obtaining the n power samples Removing other electric power sample subsets of the target electric power sample subset in the subset, and using the other electric power sample subsets to iteratively train the initial regression model to obtain a regression submodel corresponding to the target electric power sample subset;
  • the server performs the following steps for each of the power sample subsets: using the power sample subset as the target power sample subset, and generating an initial regression model according to the target power sample subset, where the initial regression model uses power as f (x) As a function of the power consumption characteristic data, the initial regression model is established to extract the characteristic data of each sample in the target power sample subset.
  • the characteristic data includes: time data, temperature data, holiday data, and time data is determined according to a preset model Function temperature, temperature data, holiday data, and power consumption, and use this function relationship as the initial regression model; specifically, a model of characteristic data and power consumption is set in advance according to experience, and when the initial regression model is established, it is obtained
  • Each power sample in the target power sample subset is used to determine the initial value of the parameter through equal division states, and the determined initial value of the parameter is assigned to a preset model to obtain an initial regression model.
  • the server uses the other power sample subsets other than the target power sample subset to iteratively train the initial regression model until the previously set The number of iterations may have converged.
  • an optimal model parameter may be obtained, and a regression submodel corresponding to the target power sample subset may be obtained according to the optimal model parameter.
  • the server generates an initial regression model for each target power sample subset and iteratively trains to generate a regression submodel using the XGBoost principle.
  • the server uses the power consumption in the power sample as f (x) and establishes it.
  • f (x) For the initial regression model of the feature data, the server uses the current time information, whether it is holidays and temperature information as the feature data, and sets the corresponding weights for each feature data to generate each target power sample subset The corresponding initial regression model, wherein the generated initial regression model is related to the above-mentioned feature data.
  • the server After the initial regression model is generated, the server iteratively trains the initial regression model using n-1 power sample subsets other than the target power sample subset.
  • the server uses n-1 power sample subsets to iteratively train the initial regression model to obtain the target power sample.
  • the regression submodel corresponding to the subset f (x) a 1 x + b 1 x 2 -c 1 x 3 ; the server generates a regression submodel corresponding to each target power sample subset.
  • step S03 the regression sub-model corresponding to each of the target power sample subsets is encapsulated to generate a preset regression model.
  • the server obtains the regression submodel corresponding to each target power sample subset, encapsulates each regression submodel, and generates a preset regression model, that is, in this embodiment, the n regression submodels obtained by training are packaged as a preset Regression model.
  • a preset regression model is created and generated based on historical power consumption information.
  • the power consumption prediction is based on the generated preset regression prediction.
  • the power consumption prediction based on the generated preset regression prediction can effectively consider the time series characteristics while not introducing too much the strong influence of time series on the time point, which can effectively An abnormal point was detected.
  • a method of establishing multiple regression sub-models is used in the scenario where a preset regression model is established, which effectively reduces the possible occurrence of the theoretical calculation of power consumption based on the preset regression model. Overfitting.
  • the power consumption control method based on power quantity prediction includes:
  • Step S10 Receive a power consumption monitoring instruction, determine current time information, and obtain power consumption characteristic information associated with the current time information.
  • the server determines the current time information. For example, the current time information is 9:30, June 27, 2018, Wednesday The server obtains power consumption characteristic information related to the current time information, wherein the power consumption characteristic information refers to the affected power consumption information.
  • the server determines the current time information and the holiday information corresponding to the current time information; and obtains the temperature information corresponding to the current time information through a preset detection device, where the preset detection device refers to a preset temperature detection device (for example, a thermometer) , Used to collect temperature information, the temperature information includes indoor temperature and outdoor temperature, the server uses the temperature information and holiday information as the current time information associated power consumption characteristic information, for example, the current time information: At 9:30 am on June 27, 2018, after determining the current time information, the server obtains the power consumption information related to the current time information according to the time information including: Wednesday, work day, previous day work, next day work, location is xxx The office building and the temperature are 30 degrees Celsius, that is, whether it is a rest day will affect the power consumption, and the temperature will also affect the power consumption.
  • the preset detection device refers to a preset temperature detection device (for example, a thermometer)
  • the server uses the temperature information and holiday information as the current time information associated power consumption characteristic information, for example
  • the feature information is added to predict the power consumption, which can make the result of power consumption prediction more accurate.
  • the power consumption prediction can effectively eliminate the abnormal factors affecting the power consumption and the impact on the power consumption. Makes electricity prediction more accurate.
  • step S20 the power consumption characteristic information is input into a preset regression model to obtain a standard power consumption corresponding to the current time information.
  • the server inputs the power consumption characteristic information to each regression sub-model of the preset regression model (the preset regression model: a model for predicting power consumption trained in the above embodiment), and each of the regressions
  • the sub-model processes the power consumption characteristic data and calculates a corresponding basic power consumption; the server adds up the calculated basic power consumption and obtains the average value as the standard power consumption, that is, the server predicts the power consumption request
  • the power consumption characteristic information in each input is entered into each regression sub-model, and the n basic power consumption is obtained according to the calculation formula in each regression sub-model.
  • the server sums up the n basic power consumption and calculates the average value. An average value obtained by adding and summing n basic power consumptions is used as a standard power consumption corresponding to the time information.
  • f (x) a 2 x + b 2 x 2 -c 2 x 3
  • f (x) a n x + b n x 2 -c n x 3, etc.
  • the server inputs the temperature information, holidays, and other information in the power consumption characteristic information to each regression sub-model.
  • Each regression sub-model calculates the basic power consumption based on the input information.
  • k 1 , k 2 up to k n ; standard power consumption k (k 1 + k 2 +... + kn) / n.
  • the electricity prediction management platform processes the respective regression sub-models to obtain corresponding prediction values, adds a plurality of prediction values to obtain an average value, and corresponds the calculated average value as current time information.
  • the standard value of electricity used in this embodiment is the predicted value calculated by the n regression sub-models and the average value is calculated, which effectively reduces the over-fitting phenomenon that may occur during the prediction process, and makes the power prediction more accurate.
  • Step S30 Acquire the actual power consumption corresponding to the current time information, and compare the actual power consumption with the standard power consumption.
  • the server obtains the actual power consumption corresponding to the current time information, and the server compares the actual power consumption with the standard power consumption to determine whether to use power control based on the comparison result, that is, if the actual power consumption is less than or equal to the standard Power consumption, the server determines that there is no waste of power (or there is no abnormal power consumption). The server does not control power consumption, and the power-consuming equipment operates according to the current operating status. If the amount is higher than the standard power consumption, the server determines that there is a waste of power (or an abnormal power consumption), and the server controls the power consumption of each power consumption device, specifically:
  • step S40 if the actual power consumption is higher than the standard power consumption, a power control strategy is determined according to the actual power consumption, the standard power consumption, and the power consumption characteristic information.
  • the server determines an adjustment amount (also referred to as an abnormal power consumption amount) according to the actual power consumption and the standard power consumption, and the server according to the power consumption characteristic information Determine the power priority of each power device (for example, determine the power priority of the air conditioner based on the temperature information in the power characteristic data, and determine the power priority of the office equipment based on whether the power characteristic data is a working day Etc.), the server determines the power consumption control strategy by combining the power adjustment amount and the priority of the power equipment.
  • an adjustment amount also referred to as an abnormal power consumption amount
  • the server determines the power consumption control strategy by combining the power adjustment amount and the priority of the power equipment.
  • the server determines the power priority of each power device according to the temperature information in the power consumption characteristic information. For example, if the current indoor temperature is 23 degrees Celsius and the outdoor temperature is 33 degrees Celsius, it determines that the power priority of the air conditioner is low.
  • the power generation control strategy generated by the server is to reduce the working frequency of the air conditioner to make the actual power consumption approach the standard power consumption.
  • the adjustment amount of the working frequency of each air conditioner can be determined according to the total number of the air conditioners and the current working frequency.
  • the adjustment degree is determined by integrating the actual power consumption and the standard power consumption
  • the power consumption priority of the power consumption equipment is determined by combining the power consumption characteristic information, and according to
  • the adjustment degree and power consumption priority generate power consumption control strategies, and the implementation of power consumption control is more intelligent and flexible.
  • Step S50 Generate a power consumption control instruction based on the power consumption control strategy to adjust the working state of the power consumption equipment for power consumption control.
  • a corresponding power control instruction is generated according to the determined power control strategy, that is, the server obtains the total power adjustment amount in the power control strategy, the power priority of each power device, and the number of power devices.
  • the power consumption control instructions are generated by the working conditions of each power consumption device, and the power consumption control instructions are sent to each power consumption device, and the power consumption device adjusts the power of the power consumption device according to the received power control instruction to perform the power consumption device Power control.
  • the standard power consumption is obtained by processing the power consumption characteristic information through a preset regression model, and the server obtains the standard power consumption, the actual power consumption, and the power consumption characteristic information according to the calculation to determine the power control of the current working power equipment.
  • Strategy and generate power consumption control instructions according to the power consumption control strategy and send them to each electrical equipment to use the electrical equipment to adjust the working state according to the power consumption control instructions.
  • automatic power consumption control is implemented, making the power consumption control more intelligent and flexible. .
  • the present embodiment of the power consumption control method based on the power quantity prediction of the present application is further proposed.
  • the power consumption control method based on the power prediction includes:
  • step S41 if the actual power consumption is higher than the standard power consumption, a difference between the actual power consumption and the standard power consumption is used as a total adjustment amount.
  • the server determines that there is a waste of power consumption, the server makes a difference between the actual power consumption and the standard power consumption, and uses the difference as a total Adjustment amount to distribute the total adjustment amount to different electrical equipment, for example, the standard power consumption of an office building is 40kwh, the actual power consumption is 53kwh, and the total power adjustment is 13 kwh, the server decomposes the total power consumption adjustment amount to different electrical equipment for sharing, that is, the power of different electrical equipment is adjusted so that the actual power consumption is less than or equal to the standard power consumption.
  • step S42 the power consumption characteristic information is compared with a preset power consumption priority table to determine the power consumption priority of various types of equipment.
  • the server compares the power consumption characteristic information with a preset power consumption priority table to obtain the power consumption priorities of various types of equipment, wherein the preset power consumption priority rules refer to different preset power consumption characteristic information corresponding to The power consumption priority table of each type of device, for example: Table 1.
  • the server determines the power supply priority of each type of device under the power consumption characteristic information according to the preset power consumption priority table.
  • Power characteristics information / power priority Electrical equipment air conditioning computer Water dispenser Room temperature above 26 °C high in low Working day Room temperature above 26 °C low high in Holiday Room temperature 20 ° C to 26 ° C low high in Working day Room temperature 20 ° C to 26 ° C low high in Holiday
  • the indoor temperature is below 20 °C high in low Working day
  • the indoor temperature is below 20 °C low high in Holiday
  • Step S43 Determine adjustment components of various types of the equipment according to the total adjustment amount and the power consumption priority, and generate a power consumption control strategy.
  • the server will determine the adjustment component of each type of the device according to the total adjustment amount and the power consumption priority, that is, when determining the adjustment component of each type of electrical equipment, comprehensively consider the actual power consumption situation to generate a power consumption control Strategies, for example, the total adjustment amount is 13kwh, the air conditioning power priority is low (low power priority corresponds to 60% of the total adjustment amount), the air conditioning adjustment component is 6.5kwh; office equipment power priority is high (power consumption High priority corresponds to 10% of the total adjustment amount), the adjustment component of office equipment is 1.3kwh; other equipment has a medium power priority (high power consumption corresponds to 30% of the total adjustment amount), and office equipment's adjustment component is 3.9 kwh, and correspondingly generate electricity control strategy.
  • the total adjustment amount is 13kwh
  • the air conditioning power priority is low (low power priority corresponds to 60% of the total adjustment amount)
  • the air conditioning adjustment component is 6.5kwh
  • office equipment power priority is high (power consumption High priority corresponds to 10% of the total adjustment amount)
  • the power consumption control method based on the power prediction includes:
  • Step S51 Determine the currently used power consumption equipment and the power of the power consumption equipment, and obtain adjustment components of various types of the equipment in the power consumption control strategy;
  • the server is communicatively connected with each power consumption device.
  • the server can monitor the working conditions of each power consumption device.
  • the server obtains the power of each power consumption device and the power consumption device that are currently in the working state.
  • the server obtains the various types of power consumption control strategies.
  • the adjustment component of the device so that the server determines the adjustment amount corresponding to each electrical device according to the current power of the electrical device and the adjustment component of each type of the device in the power control strategy.
  • Step S52 Allocate the adjustment component to each of the power consumption devices according to the power, and generate a power consumption control instruction including the adjustment amount;
  • the server distributes the adjustment component to each of the electric devices according to the power of the electric devices, that is, the server determines the air conditioner, computer, and water dispenser of the current electric device, and the server obtains the adjustment components of various devices, and adjusts the adjustment components.
  • Correspondingly allocated to each electric device and generates an electric control command including the adjustment amount, wherein the electric control command can be set according to the specific electric appliance, for example, the working frequency can be adjusted for the air conditioner, and the water dispenser can be switched off. Electrical processing, screen brightness can be adjusted for the computer.
  • the adjustment component when the adjustment component is allocated to each of the electrical equipment according to the power, the number of various types of electrical equipment needs to be considered according to the actual situation. For example, the total adjustment is 13kwh. Low level, air conditioning adjustment component is 6.5kwh; office equipment power priority is high, office equipment adjustment component is 1.3kwh; other equipment power priority, office equipment adjustment component is 3.9kwh, server based on various types of equipment Power and the number of equipment, the adjustment components of each type of equipment are correspondingly allocated to the electric equipment at work, and electricity control instructions are generated.
  • Step S53 Send the power control instruction to each of the power consumption devices, so that the power consumption device performs power control according to the power consumption control instruction.
  • the server can prompt the user for confirmation to prevent the power control instruction from affecting the operation of the power equipment.
  • the server sends the power control instruction to each of the users. An electric device, so that the electric device performs electric power control according to the electric power control instruction.
  • the actual working conditions of each power consumption device are comprehensively considered, and the total adjustment amount of power consumption is allocated to each power consumption device, so that the power consumption adjustment is more scientific.
  • the power consumption control method based on the power prediction includes: :
  • step S60 when it is detected that the power consumption control is completed, the current actual power consumption is obtained.
  • the power consumption equipment adjusts the power consumption according to the power consumption control instruction, and sends feedback information to the server after the power consumption equipment adjustment is completed.
  • the server receives the feedback information sent by the power consumption equipment, it detects that the power consumption control is completed and the server Obtain the actual power consumption after the power consumption control adjustment is completed.
  • step S70 when it is detected that the difference between the current actual power consumption and the standard power consumption exceeds a preset threshold, reverse power regulation is performed according to the power control strategy.
  • the server compares the current actual power consumption with the standard power consumption, and detects that the difference between the current actual power consumption and the standard power consumption exceeds a preset threshold (the preset threshold refers to a preset power consumption difference , It can be set according to specific conditions), when the power consumption is reversely regulated according to the power consumption control strategy, that is, if the current actual power consumption is low after adjustment, it may affect the actual working situation, and the server can also The control strategy performs reverse regulation of power consumption, so that the work of the power equipment is restored to the initial state. In this embodiment, not only the power consumption control of the power consumption equipment is ensured, but also the actual power usage situation is combined to make the power consumption control more optimized.
  • an embodiment of the present application further proposes a power consumption control device based on a power quantity prediction.
  • the power consumption control device based on a power quantity prediction includes: Collins
  • the receiving module 10 is configured to receive a power consumption monitoring instruction, determine current time information, and obtain power consumption characteristic information associated with the current time information;
  • An input module 20 is configured to input the power consumption characteristic information into a preset regression model to obtain a standard power consumption corresponding to the current time information;
  • An obtaining and comparing module 30 configured to obtain the actual power consumption corresponding to the current time information, and compare the actual power consumption with the standard power consumption;
  • the policy determining module 40 is configured to determine a power control strategy according to the actual power consumption, the standard power consumption, and the power consumption characteristic information if the actual power consumption is higher than the standard power consumption. ;
  • the control module 50 is configured to generate a power consumption control instruction based on the power consumption control strategy, so as to adjust a working state of the power consumption equipment and perform power control.
  • the power consumption control device based on the power prediction includes:
  • a sample acquisition module configured to obtain a power sample from a preset power sample set, classify each of the power samples according to a preset classification rule, and obtain n power sample subsets;
  • a training module is configured to perform the following steps for each of the power sample subsets: use the power sample subset as a target power sample subset, generate an initial regression model based on the target power sample subset, and obtain the n Remove the other power sample subsets of the target power sample subset from the power sample subset, and use the other power sample subsets to iteratively train the initial regression model to obtain a regression submodel corresponding to the target power sample subset ;
  • a model generation module is configured to encapsulate the regression sub-model corresponding to each of the target power sample subsets to generate a preset regression model.
  • the input module 20 includes:
  • An information input unit is configured to input the power consumption characteristic information into each regression sub-model of a preset regression model, process the power consumption characteristic information through each of the regression sub-models, and obtain a corresponding value of each regression sub-model.
  • a determining unit is configured to obtain an average value after accumulating the basic power consumptions, and use the average value as a standard power consumption corresponding to the current time information.
  • the receiving module 10 includes:
  • An instruction receiving unit configured to receive an electricity monitoring instruction and determine current time information and holiday information corresponding to the current time information
  • the determining unit is configured to obtain temperature information corresponding to the current time information through a preset detection device, and use the temperature information and the holiday information as power consumption characteristic information associated with the current time information.
  • the policy determination module 40 includes:
  • An adjustment amount determining unit configured to, if the actual power consumption is higher than the standard power consumption, use a difference between the actual power consumption and the standard power consumption as a total adjustment amount
  • a priority determining unit configured to compare the power consumption characteristic information with a preset power priority table to determine the power priority of various types of equipment
  • a policy generating unit is configured to determine adjustment components of various types of the devices according to the total adjustment amount and the power consumption priority, and generate a power consumption control strategy.
  • control module 50 includes:
  • a determination acquisition unit configured to determine a currently working power consumption device and power of the power consumption device, and obtain adjustment components of various types of the devices in the power consumption control strategy
  • An instruction generating unit configured to distribute the adjustment component to each of the power consumption devices according to the power, and generate a power consumption control instruction including the adjustment amount
  • a sending control unit is configured to send the electric control instruction to each of the electric equipment, so that the electric equipment performs electric power control according to the electric power control instruction.
  • the power consumption control device based on the power prediction includes:
  • a detection and acquisition module configured to acquire the current actual power consumption after detecting that the power consumption control is completed
  • the reverse control module is configured to perform reverse power regulation according to the power control strategy when it is detected that the difference between the current actual power consumption and the standard power consumption exceeds a preset threshold.
  • an embodiment of the present application also provides a computer storage medium.
  • Computer-readable instructions are stored on the computer storage medium, and when the computer-readable instructions are executed by a processor, the operations in the power consumption control method based on the power amount prediction provided by the foregoing embodiment are implemented.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

一种基于电量预测的用电控制方法装置、设备和计算机存储介质。所述方法包括以下步骤：接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息(S10)；将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量(S20)；获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较(S30)；若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略(S40)；基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制(S50)。实现了用电自动控制。

Description

基于电量预测的用电控制方法、装置、设备和存储介质
本申请要求于2018年08月02日提交中国专利局、申请号为201810876240.6发明名称为“基于电量预测的用电控制方法、装置、设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请涉及用电控制领域，尤其涉及基于电量预测的用电控制方法、装置、设备和计算机存储介质。
背景技术
资源节约型社会是贯彻落实科学发展观的战略部署之一。资源节约涉及到人们生活的方方面面，其中，节约用电是一个极其关键的方面。
对人们生产、生活用电电量的预估和控制成为了节约用电的重要措施，当前的用电电量评估都是基于历史数据作出的，具体地，监测设备实时采集各个楼层用户的用电的历史同期数据，并将历史同期用电数据整理取平均值，将电量的平均值作为未来用电的预测值，即，现有的电量预测必须依赖于历史数据，这样的电量预测方案具有滞后性，由于预测的电量数据不准确，因而并不能根据预估的用电量对用电进行自动控制，如何进行用电自动控制成为了当前亟待解决的技术问题。
上述内容仅用于辅助理解本申请的技术方案，并不代表承认上述内容是现有技术。
发明内容
本申请的主要目的在于提供一种基于电量预测的用电控制方法、装置、设备和存储介质，通过实现用电自动控制，以降低不必要的用电消耗。
为实现上述目的，本申请提供一种基于电量预测的用电控制方法，所述基于电量预测的用电控制方法包括以下步骤：
接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息；
将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量；
获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较；
若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略；
基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制。
此外，为实现上述目的，本申请还提供一种基于电量预测的用电控制装置，所述基于电量预测的用电控制装置包括：
接收模块，用于接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息；
输入模块，用于将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量；
获取比较模块，用于获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较；
策略确定模块，用于若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略；
控制模块，用于基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制。
此外，为实现上述目的，本申请还提供一种基于电量预测的用电控制设备；
所述基于电量预测的用电控制设备包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机可读指令，其中：
所述计算机可读指令被所述处理器执行时实现如上所述的基于电量预测的用电控制方法的步骤。
此外，为实现上述目的，本申请还提供计算机存储介质；
所述计算机存储介质上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现如上述的基于电量预测的用电控制方法的步骤。
本申请实施例提出的一种基于电量预测的用电控制方法、装置、设备和计算机存储介质，通过服务器接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息；将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量；获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较；若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略；基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制，本申请中通过预设回归模型处理用电特征信息得到标准用电量，服务器根据计算得到标准用电量、实际用电量和用电特征信息，确定当前工作的用电设备的用电控制策略，并根据用电控制策略生成用电控制指令发送至各个用电设备，以使用电设备根据用电控制指令调节工作状态，本申请中实现了自动用电控制，使得用电控制更加智能灵活。
附图说明
图1是本申请实施例方案涉及的硬件运行环境的装置结构示意图；
图2为本申请基于电量预测的用电控制方法第一实施例的流程示意图；
图3为本申请基于电量预测的用电控制装置一实施例的功能模块示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
如图1所示，图1是本申请实施例方案涉及的硬件运行环境的服务器（又叫基于电量预测的用电控制设备，其中，基于电量预测的用电控制设备可以是由单独的基于电量预测的用电控制装置构成，也可以是由其他装置与基于电量预测的用电控制装置组合形成）结构示意图。
本申请实施例服务器指一个管理资源并为用户提供服务的计算机，通常分为文件服务器、数据库服务器和应用可读指令服务器。运行以上软件的计算机或计算机系统也被称为服务器。相对于普通PC(personal computer)个人计算机来说，服务器在稳定性、安全性、性能等方面都要求较高；如图1所示，该服务器可以包括：处理器1001，例如中央处理器（Central Processing Unit，CPU），网络接口1004，用户接口1003，存储器1005，通信总线1002、芯片组、磁盘系统、网络等硬件等。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard），可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口（如无线保真WIreless-FIdelity，WIFI接口）。存储器1005可以是高速随机存取存储器（random access memory，RAM），也可以是稳定的存储器（non-volatile memory），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
可选地，服务器还可以包括摄像头、RF（Radio Frequency，射频）电路，传感器、音频电路、WiFi模块；输入单元，比显示屏，触摸屏；网络接口可选除无线接口中除WiFi外，蓝牙、探针、3G/4G/5G（前面的数字表示的是蜂窝移动通信网络的代数。就是表示是第几代的网络。英文字母G表示generation）联网基站设备等等。本领域技术人员可以理解，图1中示出的服务器结构并不构成对服务器的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图1所示，该计算机软件产品存储在一个存储介质（存储介质：又叫计算机存储介质、计算机介质、可读介质、可读存储介质、计算机可读存储介质或者直接叫介质等，如RAM、磁碟、光盘，存储介质可以为非易失性可读存储介质）中，包括若干指令用以使得一台终端设备（可以是手机，计算机，服务器，空调器，或者网络设备等）执行本申请各个实施例所述的方法，作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及计算机可读指令。
在图1所示的服务器中，网络接口1004主要用于连接后台数据库，与后台数据库进行数据通信；用户接口1003主要用于连接客户端（客户端，又叫用户端或终端，本申请实施例终端可以固定终端，也可以是移动终端，其中，固定终端如“物联网设备”、带联网功能的智能空调、智能电灯、智能电源等等；移动终端，如带联网功能的AR/VR设备，智能音箱、自动驾驶汽车、PC，智能手机、平板电脑、电子书阅读器、便携计算机等具有显示功能的终端设备，终端中包含传感器比如光传感器、运动传感器以及其他传感器，移动终端还可配置陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述），与客户端进行数据通信；而处理器1001可以用于调用存储器1005中存储的计算机可读指令，并执行本申请以下实施例提供的基于电量预测的用电控制方法中的步骤。
在实施例提出一种基于电量预测的用电控制方法，在第一实施例的步骤之前，需要开发人员先建立预设回归模型，服务器才可以基于该预设回归模型计算一个标准用电量，以根据标准用电量和实际用电量比较结果，确定是否进行用电设备的用电控制，具体地，本实施例中建立预设回归模型的步骤，包括：
步骤S01，从预设电量样本集中获取电量样本，将各所述电量样本按预设分类规则进行分类，得到n个电量样本子集；
服务器从预设电量样本集中获取电量样本，其中，预设电量样本集是指预先存储的历史用电相关信息，服务器从预设电量样本集中获取包含的电量样本，并将各个电量样本按预设分类规则进行分类，得到n个电量样本子集；其中，预设分类规则是指预先设置的电量样本分类规则，例如，预设分类规则设置为采集时间分类规则，即，服务器按照各个电量样本的采集时间进行分类，得到各个年份、各个月份对应的电量样本子集。
例如，服务器将采集的历史用电量和相关信息：2018年6月5日星期二下午13：00-到13：05分的用电量，室外温度30摄氏度，地址广东省深圳室xxx办公楼，工作日等等的信息保存至存储器；在接收到预设回归模型的建立请求时，服务器从存储器中随机抽取一定数量的历史用电量及其相关信息作为电量样本，并将抽取的各个电量样本组成预设电量样本集，服务器将预设电量样本集中的各个电量样本按照电量样本采集时间进行分类，得到不同时间段的n个电量样本子集，其中，各个电量样本子集中的电量样本可能相同也可能不同。
步骤S02，针对每一个所述电量样本子集执行如下步骤：将所述电量样本子集作为目标电量样本子集，基于所述目标电量样本子集生成初始回归模型，获取所述n个电量样本子集中去除所述目标电量样本子集的其他电量样本子集，利用所述其他电量样本子集对所述初始回归模型进行迭代训练，得到所述目标电量样本子集对应的回归子模型；
服务器针对每一个所述电量样本子集执行如下步骤：分别将电量样本子集作为目标电量样本子集，并根据目标电量样本子集生成初始回归模型，其中，初始回归模型的是用电量为f（x）关于用电特征数据的函数，建立初始回归模型是提取目标电量样本子集中的各个样本的特征数据，特征数据包括：时间数据、温度数据、节假日数据，根据预设模型确定时间数据、温度数据、节假日数据与用电量的函数关系，并将该函数关系作为初始回归模型；具体地，根据经验预先设置了一个特征数据与用电量的模型，在建立初始回归模型时，获取目标电量样本子集中的各个电量样本，并将各个电量样本通过等划分状态确定参数初始值，并将确定的参数初始值赋值给预设模型，以得到初始回归模型。
在初始回归模型建立完成后，设置最大的迭代次数和收敛阈值；服务器用除所述目标电量样本子集之外的其他电量样本子集对所述初始回归模型进行迭代训练，直到达到先前设置的迭代次数或已经收敛，此时，可得到最优模型参数，进而根据该最优模型参数获得到所述目标电量样本子集对应的回归子模型。
即，本实施例中服务器将每一个目标电量样本子集生成初始回归模型并迭代训练生成回归子模型是采用XGBoost原理实现的，服务器将用电样本中的用电量作为f（x）并建立f（x）关于特征数据的初始回归模型，服务器将当前时间信息信息、是否为节假日和温度信息的作为特征数据，并为各个特征数据设置相对应的权重，以生成每一个目标电量样本子集对应的初始回归模型，其中，生成的初始回归模型跟上述的特征数据相关。
在初始回归模型生成完成之后，服务器利用除目标电量样本子集之外的n-1个电量样本子集对初始回归模型进行迭代训练，例如，目标电量样本子集对应的初始回归模型为f（x）=ax+ bx2- cx3，其中，a是当前时间信息系数，b是温度系数，c是节假日系数，服务器利用n-1个电量样本子集对初始回归模型进行迭代训练得到目标电量样本子集对应的回归子模型f（x）=a1x+ b1x2- c1x3；服务器生成每一个目标电量样本子集对应的回归子模型。
步骤S03，将每个所述目标电量样本子集对应的所述回归子模型进行封装，生成预设回归模型。
服务器获取每个目标电量样本子集对应的所述回归子模型，将各个回归子模型进行封装，生成预设回归模型，即，本实施例中将训练得到n个回归子模型封装为一个预设回归模型。
在本实施例中根据历史用电信息建立生成预设回归模型。以基于生成的预设回归预测进行用电量预测，基于生成的预设回归预测进行用电量预测可以在有效考虑时序特征的同时并不过多引入时序对时间点的强影响关系，可以有效地检测出异常点，此外，本实施里中在预设回归模型建立的场景下的采用建立多个回归子模型的方式，有效降低了基于预设回归模型进行用电量理论值计算过程中可能产生的过拟合现象。
参照图2，在本申请基于电量预测的用电控制方法的第一实施例中，所述基于电量预测的用电控制方法包括：
步骤S10，接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息。
用户在触发用电监测指令，服务器（或者又叫用电管理平台）接收到用电监测指令时，服务器确定当前时间信息，例如，当前时间信息为：2018年6月27日9:30、周三，服务器获取当前时间信息相关的用电特征信息，其中，用电特征信息是指影响的用电量信息。
即，服务器确定当前时间信息及当前时间信息对应的节假日信息；并通过预设检测装置获取当前时间信息对应的温度信息，其中，预设检测装置是指预先设置的温度检测装置（例如，温度计），用于采集温度信息，温度信息包括室内温度和室外温度，服务器将温度信息和节假日信息作为当前时间信息关联的用电特征信息，例如，当前时间信息: 2018年6月27日上午9:30，在确定当前时间信息之后，服务器根据时间信息获取当前时间信息相关的用电特征信息包括：周三，上班日、前一天上班、后一天上班、位置为xxx办公楼和气温30摄氏度，即，是否为休息日会对用电量产生影响，气温的高低也会对用电量产生影响。
在本实施例中加入特征信息对用电进行预测，可以使得用电预测的结果更加准确，根据用电特征信息进行用电预测，可以有效的排除影响用电的异常因素，对用电的影响使得用电的预测更加准确。
步骤S20，将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量。
服务器将用电特征信息分别输入至所述预设回归模型的各个回归子模型中（预设回归模型：为上述实施例中训练得到的用于预测用电量的模型），每一个所述回归子模型对用电特征数据进行处理，计算得到一个对应的基础用电量；服务器将计算得到的基础用电量累加后求取平均值作为标准用电量，即，服务器将用电量预测请求中的用电特征信息输入每一个回归子模型中，根据各个回归子模型中的计算公式得到n个基础用电量，服务器将n个基础用电量进行累加求和并计算平均值，并将n个基础用电量累加求和得到的平均值作为该时间信息对应的标准用电量。
例如，各个回归子模型分别为f（x）=a1x+ b1x2- c1x3 、f（x）=a2x+ b2x2 - c2x3 至f（x）=anx+ bnx2 - cnx3 等等，服务器将用电特征信息中的温度信息、节假日等信息输入至各个回归子模型，各个回归子模型根据输入的信息进行计算得到基础用电量k1、k2直至kn；标准用电量k=（k1 +k2 +…+kn）/n。
在本实施例中，用电预测管理平台将各个回归子模型中处理得到对应的预测值，并将多个预测值进行加和运算得到平均值，并将计算得到的平均值作为当前时间信息对应的标准用电值，本实施例中通过n个回归子模型计算的预测值，求取平均值，有效降低了预测过程中可能产生的过拟合现象，使得电量预测更加准确。
步骤S30，获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较。
服务器获取当前时间信息对应的实际用电量，服务器将实际用电量与标准用电量进行比较，以根据比较结果判断是否进行用电控制，即，若实际用电量小于或等于所述标准用电量，则服务器判定不存在用电浪费（或者不存在是用电异常）的情况，服务器不进行用电量的控制，用电设备按照当前的运行状态进行运行，若所述实际用电量高于所述标准用电量，则服务器判定存在用电浪费（或者存在是用电异常）的情况，服务器对各个用电设备的用电进行控制，具体地：
步骤S40，若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略。
若所述实际用电量高于所述标准用电量，则服务器根据所述实际用电量、所述标准用电量确定调整量（又叫用电异常量），服务器根据用电特征信息确定各个用电设备的用电优先级（例如，根据用电特征数据中的温度信息，确定空调的用电优先级，根据用电特征数据的中是否为工作日确定办公设备的用电优先级等等），服务器结合用电调整量和用电设备优先级，确定用电控制策略。
例如，办公楼的标准用电量为40kwh实际用电量为53kwh，用电总调整量为13 kwh，然后，服务器根据用电特征信息中的温度信息确定各个用电设备的用电优先级，例如，当前室内温度为23摄氏度，室外温度为33摄氏度，则确定空调的用电优先级低，服务器生成的用电控制策略为：通过降低空调的工作频率来使得实际用电量趋于标准用电量，具体地，各个空调的工作频率调整量可以根据空调的总数和当前工作频率确定。
本实施例中在确定用电控制策略时结合不同的因素考虑，即，综合实际用电量和标准用电量确定调整度，结合用电特征信息确定用电设备的用电优先级，并根据调整度和用电优先级生成用电控制策略，实施用电控制更加智能灵活。
步骤S50，基于所述用电控制策略生成用电控制指令，以调整用电设备的工作状态进行用电控制。
本实施例中根据确定的用电控制策略生成对应的用电控制指令，即，服务器获取用电控制策略中的用电总调整量、各个用电设备的用电优先级、用电设备的数量，各个用电设备的工作情况生成用电控制指令，并将用电控制指令发送至各个用电设备，用电设备根据接收到的用电控制指令调整用电设备的功率，以进行用电设备的用电控制。
本实施例中通过预设回归模型处理用电特征信息得到标准用电量，服务器根据计算得到标准用电量、实际用电量和用电特征信息，确定当前工作的用电设备的用电控制策略，并根据用电控制策略生成用电控制指令发送至各个用电设备，以使用电设备根据用电控制指令调节工作状态，本申请中实现了自动用电控制，使得用电控制更加智能灵活。
在本申请第一实施例的基础上，进一步提出了本申请基于电量预测的用电控制方法的本实施例。
本实施例是本申请第一实施例的中步骤S40的细化，所述基于电量预测的用电控制方法包括：
步骤S41，若所述实际用电量高于所述标准用电量，则将所述实际用电量与所述标准用电量的差值作为总调整量。
若所述实际用电量高于所述标准用电量，则服务器判定存在用电浪费的情况，服务器将所述实际用电量与所述标准用电量做差，并将差值作为总调整量，以将总调整量分配给不同的用电设备进行承担，例如，办公楼的标准用电量为40kwh实际用电量为53kwh，总用电调整量为13 kwh，服务器将总用电调整量分解给不同的用电设备进行分担，即，不同的用电设备的功率进行调整，使得实际用电量小于等于标准用电量。
步骤S42，将所述用电特征信息与预设用电优先级表格进行比对，确定各类设备的用电优先级。
服务器将所述用电特征信息与预设用电优先级表格进行比对，得到各类型设备的用电优先级，其中，预设用电优先级规则是指预先设置的不同用电特征信息对应的各类型设备的用电优先级表格，例如：表1，服务器根据预设用电优先级表格确定用电特征信息下各个类型设备的供电优先级。
用电特征信息/用电优先级 用电设备
空调 电脑 饮水机
室内温度26℃以上 高 中 低
工作日
室内温度26℃以上 低 高 中
节假日
室内温度20℃到26℃ 低 高 中
工作日
室内温度20℃到26℃ 低 高 中
节假日
室内温度低于20℃ 高 中 低
工作日
室内温度低于20℃ 低 高 中
节假日
表1
步骤S43，按所述总调整量和所述用电优先级确定各类所述设备的调整分量，生成用电控制策略。
服务器将按所述总调整量和所述用电优先级确定各类所述设备的调整分量，即，在确定各类型电设备的调整分量时，综合考虑实际用电情况，以生成用电控制策略，例如，总调整量为13kwh，空调的用电优先级低（用电优先级低对应总调整量的60%），空调的调整分量为6.5kwh；办公设备用电优先级高（用电优先级高对应总调整量的10%），办公设备的调整分量为1.3kwh；其他设备用电优先级中等（用电优先级高对应总调整量的30%），办公设备的调整分量为3.9kwh，并对应生成用电控制策略。
在上述实施例的基础上进一步地提出了本实施例，本实施例是第一实施例中步骤S50的细化，所述基于电量预测的用电控制方法包括：
步骤S51，确定当前工作的用电设备及所述用电设备的功率，并获取所述用电控制策略中各类所述设备的调整分量；
服务器与各个用电设备通信连接，服务器可以监测各个用电设备的工作情况，服务器获取当前处于工作状态的各个用电设备及用电设备的功率，服务器获取所述用电控制策略中各类所述设备的调整分量，以使服务器根据当前用电设备的功率和用电控制策略中各类所述设备的调整分量确定各个用电设备对应的调整量。
步骤S52，将所述调整分量按所述功率分配至各所述用电设备，并生成包含所述调整量的用电控制指令；
服务器将所述调整分量按用电设备的功率分配至各所述用电设备，即，服务器确定当前用电设备的空调、电脑、饮水机，服务器获取各类设备的调整分量，并将调整分量对应分配给各个用电设备，并生成包含所述调整量的用电控制指令，其中，用电控制指令可以根据具体的用电器设置，例如，针对空调可以调节工作频率，针对饮水机可以进行断电处理，针对电脑可以调整屏幕亮度等。
需要补充说明的是：在将调整分量按所述功率分配至各所述用电设备时还需要根据实际情况考虑各类用电设备的数量，例如，总调整量为13kwh，空调的用电优先级低，空调的调整分量为6.5kwh；办公设备用电优先级高，办公设备的调整分量为1.3kwh；其他设备用电优先级中，办公设备的调整分量为3.9kwh，服务器根据各个类型设备的功率和设备数量，将各个类型设备的调整分量对应分配给各个工作中的用电设备，生成用电控制指令。
步骤S53，将所述电控制指令发送至各所述用电设备，以使所述用电设备按所述用电控制指令进行用电控制。
服务器在生成用电控制指令后，服务器可以提示用户进行确认，以防止用电控制指令对用电设备工作的影响，在接收到用户授权之后，服务器将所述电控制指令发送至各所述用电设备，以使所述用电设备按所述用电控制指令进行用电控制。
在本实施例在进行用电控制时，综合考虑各个用电设备的实际工作情况，将用电的总调整量，分配给各个用电设备，使得用电调整更加科学。
进一步的，本申请基于电量预测的用电控制方法的第二实施例中，本实施例中还可以更加具体情况对用电设备的工作状态进行恢复，所述基于电量预测的用电控制方法包括：
步骤S60，当检测到所述用电量控制完成后，获取当前实际用电量。
用电设备按照用电控制指令调整用电量，在用电设备调整完成后发送反馈信息至服务器，服务器接收到用电设备的发送的反馈信息时，检测到所述用电量控制完成，服务器获取用电控制调整完成后实际用电量。
步骤S70，在检测到当前实际用电量与所述标准用电量的之差超过预设阈值时，按所述用电控制策略进行用电反向调控。
服务器将当前实际用电量与标准用电量进行比较，在检测到当前实际用电量与所述标准用电量的之差超过预设阈值（预设阈值是指预先设置的用电差值，可根据具体情况设置）时，按所述用电控制策略进行用电反向调控，即，若调整后当前实际用电量偏低，则可能影响实际的工作情况，服务器还可以根据用电控制策略进行用电反向调控，使得用电设备的工作恢复至初始状态。在本实施例中既保证了用电设备的用电控制，又结合实际用电使用情况，使得用电控制更加优化。
此外，参照图3，本申请实施例还提出基于电量预测的用电控制装置，所述基于电量预测的用电控制装置包括：
接收模块10，用于接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息；
输入模块20，用于将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量；
获取比较模块30，用于获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较；
策略确定模块40，用于若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略；
控制模块50，用于基于所述用电控制策略生成用电控制指令，以调整用电设备的工作状态进行用电控制。
可选地，基于电量预测的用电控制装置，包括：
样本获取模块，用于从预设电量样本集中获取电量样本，将各所述电量样本按预设分类规则进行分类，得到n个电量样本子集；
训练模块，用于针对每一个所述电量样本子集执行如下步骤：将所述电量样本子集作为目标电量样本子集，基于所述目标电量样本子集生成初始回归模型，获取所述n个电量样本子集中去除所述目标电量样本子集的其他电量样本子集，利用所述其他电量样本子集对所述初始回归模型进行迭代训练，得到所述目标电量样本子集对应的回归子模型；
模型生成模块，用于将每个所述目标电量样本子集对应的所述回归子模型进行封装，生成预设回归模型。
可选地，所述输入模块20，包括：
信息输入单元，用于将所述用电特征信息输入至预设回归模型的各回归子模型中，通过各所述回归子模型处理所述用电特征信息，得到各所述回归子模型对应的基础用电量；
确定单元，用于将各所述基础用电量累加后求取平均值，并将所述平均值作为所述当前时间信息对应的标准用电量。
可选地，所述接收模块10，包括：
指令接收单元，用于接收用电监测指令，确定当前时间信息及当前时间信息对应的节假日信息；
确定单元，用于通过预设检测装置获取当前时间信息对应的温度信息，将所述温度信息和所述节假日信息作为所述当前时间信息关联的用电特征信息。
可选地，所述策略确定模块40，包括：
调整量确定单元，用于若所述实际用电量高于所述标准用电量，则将所述实际用电量与所述标准用电量的差值作为总调整量；
优先级确定单元，用于将所述用电特征信息与预设用电优先级表格进行比对，确定各类设备的用电优先级；
策略生成单元，用于按所述总调整量和所述用电优先级确定各类所述设备的调整分量，生成用电控制策略。
可选地，所述控制模块50，包括：
确定获取单元，用于确定当前工作的用电设备及所述用电设备的功率，并获取所述用电控制策略中各类所述设备的调整分量；
指令生成单元，用于将所述调整分量按所述功率分配至各所述用电设备，并生成包含所述调整量的用电控制指令；
发送控制单元，用于将所述电控制指令发送至各所述用电设备，以使所述用电设备按所述用电控制指令进行用电控制。
可选地，基于电量预测的用电控制装置，包括：
检测获取模块，用于当检测到所述用电量控制完成后，获取当前实际用电量；
反向控制模块，用于在检测到当前实际用电量与所述标准用电量的之差超过预设阈值时，按所述用电控制策略进行用电反向调控。
其中，基于电量预测的用电控制装置的各个功能模块实现的步骤可参照本申请基于电量预测的用电控制方法的各个实施例，此处不再赘述。
此外，本申请实施例还提出一种计算机存储介质。
所述计算机存储介质上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现上述实施例提供的基于电量预测的用电控制方法中的操作。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他关联的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种基于电量预测的用电控制方法，其特征在于，所述基于电量预测的用电控制方法包括以下步骤：
    接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息；
    将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量；
    获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较；
    若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略；
    基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制。
  2. 如权利要求1所述的基于电量预测的用电控制方法，其特征在于，所述接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息的步骤之前，包括：
    从预设电量样本集中获取电量样本，将各所述电量样本按预设分类规则进行分类，得到n个电量样本子集；
    针对每一个所述电量样本子集执行如下步骤：
    将所述电量样本子集作为目标电量样本子集，基于所述目标电量样本子集生成初始回归模型，获取所述n个电量样本子集中去除所述目标电量样本子集的其他电量样本子集，利用所述其他电量样本子集对所述初始回归模型进行迭代训练，得到所述目标电量样本子集对应的回归子模型；
    将每个所述目标电量样本子集对应的所述回归子模型进行封装，生成预设回归模型。
  3. 如权利要求1所述的基于电量预测的用电控制方法，其特征在于，所述将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量的步骤，包括：
    将所述用电特征信息输入至预设回归模型的各回归子模型中，通过各所述回归子模型处理所述用电特征信息，得到各所述回归子模型对应的基础用电量；
    将各所述基础用电量累加后求取平均值，并将所述平均值作为所述当前时间信息对应的标准用电量。
  4. 如权利要求1所述的基于电量预测的用电控制方法，其特征在于，所述接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息的步骤，包括：
    接收用电监测指令，确定当前时间信息及当前时间信息对应的节假日信息；
    通过预设检测装置获取当前时间信息对应的温度信息，将所述温度信息和所述节假日信息作为所述当前时间信息关联的用电特征信息。
  5. 如权利要求1所述的基于电量预测的用电控制方法，其特征在于，所述若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略的步骤，包括：
    若所述实际用电量高于所述标准用电量，则将所述实际用电量与所述标准用电量的差值作为总调整量；
    将所述用电特征信息与预设用电优先级表格进行比对，确定各类设备的用电优先级；
    按所述总调整量和所述用电优先级确定各类所述设备的调整分量，生成用电控制策略。
  6. 如权利要求1所述的基于电量预测的用电控制方法，其特征在于，所述基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制的步骤，包括：
    确定当前工作的用电设备及所述用电设备的功率，并获取所述用电控制策略中各类所述设备的调整分量；
    将所述调整分量按所述功率分配至各所述用电设备，并生成包含所述调整量的用电控制指令；
    将所述电控制指令发送至各所述用电设备，以使所述用电设备按所述用电控制指令进行用电控制。
  7. 如权利要求1所述的基于电量预测的用电控制方法，其特征在于，所述基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制的步骤之后，包括：
    当检测到所述用电量控制完成后，获取当前实际用电量；
    在检测到当前实际用电量与所述标准用电量的之差超过预设阈值时，按所述用电控制策略进行用电反向调控。
  8. 一种基于电量预测的用电控制装置，其特征在于，所述基于电量预测的用电控制装置包括：
    接收模块，用于接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息；
    输入模块，用于将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量；
    获取比较模块，用于获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较；
    策略确定模块，用于若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略；
    控制模块，用于基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制。
  9. 如权利要求8所述的基于电量预测的用电控制装置，其特征在于，所述基于电量预测的用电控制装置，包括：
    样本获取模块，用于从预设电量样本集中获取电量样本，将各所述电量样本按预设分类规则进行分类，得到n个电量样本子集；
    训练模块，用于针对每一个所述电量样本子集执行如下步骤：将所述电量样本子集作为目标电量样本子集，基于所述目标电量样本子集生成初始回归模型，获取所述n个电量样本子集中去除所述目标电量样本子集的其他电量样本子集，利用所述其他电量样本子集对所述初始回归模型进行迭代训练，得到所述目标电量样本子集对应的回归子模型；
    模型生成模块，用于将每个所述目标电量样本子集对应的所述回归子模型进行封装，生成预设回归模型。
  10. 如权利要求9所述的基于电量预测的用电控制装置，其特征在于，所述输入模块，包括：
    信息输入单元，用于将所述用电特征信息输入至预设回归模型的各回归子模型中，通过各所述回归子模型处理所述用电特征信息，得到各所述回归子模型对应的基础用电量；
    确定单元，用于将各所述基础用电量累加后求取平均值，并将所述平均值作为所述当前时间信息对应的标准用电量。
  11. 如权利要求8所述的基于电量预测的用电控制装置，其特征在于，所述接收模块，包括：
    指令接收单元，用于接收用电监测指令，确定当前时间信息及当前时间信息对应的节假日信息；
    确定单元，用于通过预设检测装置获取当前时间信息对应的温度信息，将所述温度信息和所述节假日信息作为所述当前时间信息关联的用电特征信息。
  12. 如权利要求8所述的基于电量预测的用电控制装置，其特征在于，所述策略确定模块，包括：
    调整量确定单元，用于若所述实际用电量高于所述标准用电量，则将所述实际用电量与所述标准用电量的差值作为总调整量；
    优先级确定单元，用于将所述用电特征信息与预设用电优先级表格进行比对，确定各类设备的用电优先级；
    策略生成单元，用于按所述总调整量和所述用电优先级确定各类所述设备的调整分量，生成用电控制策略。
  13. 如权利要求8所述的基于电量预测的用电控制装置，其特征在于，所述控制模块，包括：
    确定获取单元，用于确定当前工作的用电设备及所述用电设备的功率，并获取所述用电控制策略中各类所述设备的调整分量；
    指令生成单元，用于将所述调整分量按所述功率分配至各所述用电设备，并生成包含所述调整量的用电控制指令；
    发送控制单元，用于将所述电控制指令发送至各所述用电设备，以使所述用电设备按所述用电控制指令进行用电控制。
  14. 如权利要求8所述的基于电量预测的用电控制装置，其特征在于，所述基于电量预测的用电控制装置，还包括：
    检测获取模块，用于当检测到所述用电量控制完成后，获取当前实际用电量；
    反向控制模块，用于在检测到当前实际用电量与所述标准用电量的之差超过预设阈值时，按所述用电控制策略进行用电反向调控。
  15. 一种基于电量预测的用电控制设备，其特征在于，所述基于电量预测的用电控制设备包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机可读指令，其中：
    所述计算机可读指令被所述处理器执行时实现以下的步骤：
    接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息；
    将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量；
    获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较；
    若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略；
    基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制。
  16. 如权利要求15所述的基于电量预测的用电控制设备，其特征在于，所述计算机可读指令被所述处理器执行时实现以下的步骤：
    从预设电量样本集中获取电量样本，将各所述电量样本按预设分类规则进行分类，得到n个电量样本子集；
    针对每一个所述电量样本子集执行如下步骤：
    将所述电量样本子集作为目标电量样本子集，基于所述目标电量样本子集生成初始回归模型，获取所述n个电量样本子集中去除所述目标电量样本子集的其他电量样本子集，利用所述其他电量样本子集对所述初始回归模型进行迭代训练，得到所述目标电量样本子集对应的回归子模型；
    将每个所述目标电量样本子集对应的所述回归子模型进行封装，生成预设回归模型。
  17. 如权利要求16所述的基于电量预测的用电控制设备，其特征在于，所述计算机可读指令被所述处理器执行时实现将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量的步骤，包括：
    将所述用电特征信息输入至预设回归模型的各回归子模型中，通过各所述回归子模型处理所述用电特征信息，得到各所述回归子模型对应的基础用电量；
    将各所述基础用电量累加后求取平均值，并将所述平均值作为所述当前时间信息对应的标准用电量。
  18. 如权利要求15所述的基于电量预测的用电控制设备，其特征在于，所述计算机可读指令被所述处理器执行时实现接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息的步骤，包括：
    接收用电监测指令，确定当前时间信息及当前时间信息对应的节假日信息；
    通过预设检测装置获取当前时间信息对应的温度信息，将所述温度信息和所述节假日信息作为所述当前时间信息关联的用电特征信息。
  19. 如权利要求15所述的基于电量预测的用电控制设备，其特征在于，所述计算机可读指令被所述处理器执行时实现若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略的步骤，包括：
    若所述实际用电量高于所述标准用电量，则将所述实际用电量与所述标准用电量的差值作为总调整量；
    将所述用电特征信息与预设用电优先级表格进行比对，确定各类设备的用电优先级；
    按所述总调整量和所述用电优先级确定各类所述设备的调整分量，生成用电控制策略。
  20. 一种计算机存储介质，其特征在于，所述计算机存储介质上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现以下的步骤：
    接收用电监测指令，确定当前时间信息并获取所述当前时间信息关联的用电特征信息；
    将所述用电特征信息输入至预设回归模型，得到所述当前时间信息对应的标准用电量；
    获取所述当前时间信息对应的实际用电量，将所述实际用电量与所述标准用电量进行比较；
    若所述实际用电量高于所述标准用电量，则根据所述实际用电量、所述标准用电量和所述用电特征信息确定用电控制策略；
    基于所述用电控制策略是生成用电控制指令，以调整用电设备的工作状态进行用电控制。
PCT/CN2018/122805 2018-08-02 2018-12-21 基于电量预测的用电控制方法、装置、设备和存储介质 WO2020024534A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810876240.6A CN109727155A (zh) 2018-08-02 2018-08-02 基于电量预测的用电控制方法、装置、设备和存储介质
CN201810876240.6 2018-08-02

Publications (1)

Publication Number Publication Date
WO2020024534A1 true WO2020024534A1 (zh) 2020-02-06

Family

ID=66294577

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/122805 WO2020024534A1 (zh) 2018-08-02 2018-12-21 基于电量预测的用电控制方法、装置、设备和存储介质

Country Status (2)

Country Link
CN (1) CN109727155A (zh)
WO (1) WO2020024534A1 (zh)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110595547B (zh) * 2019-10-24 2022-02-22 重庆小富农康农业科技服务有限公司 一种猪场运行异常监测装置
CN111090684B (zh) * 2019-12-17 2023-11-03 国网数字科技控股有限公司 一种用电数据的处理方法及系统
CN111597194B (zh) * 2020-04-30 2023-05-05 广东良实机电工程有限公司 设备能耗控制方法、装置、终端设备及存储介质
CN111401667B (zh) * 2020-06-03 2021-01-08 广东电网有限责任公司东莞供电局 一种工厂的用电调度方法、装置、计算机设备和存储介质
CN114576827B (zh) * 2020-11-30 2024-04-09 广东美的制冷设备有限公司 一种空调用电标准值确定方法、用电控制方法、装置和空调
CN112766797B (zh) * 2021-01-30 2023-12-22 新华建集团(广东)建设有限公司 光电一体化建筑供能方法及系统
CN113780600A (zh) * 2021-11-11 2021-12-10 滨州学院 电力设备工作状态管理方法、系统及电子设备
TWI825844B (zh) * 2022-07-13 2023-12-11 緯創資通股份有限公司 工廠用電的節能預估方法及電子裝置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104348150A (zh) * 2013-07-31 2015-02-11 国家电网公司 电力负荷管控方法、服务器、终端及系统
CN106096778A (zh) * 2016-06-03 2016-11-09 合肥工业大学 一种基于分时电价和阶梯电价形式的家庭用电规划系统与方法
CN107703854A (zh) * 2017-10-26 2018-02-16 国网黑龙江省电力有限公司信息通信公司 电力负荷监控系统及方法
CN107907759A (zh) * 2017-10-26 2018-04-13 国网黑龙江省电力有限公司信息通信公司 电力设备的电量监控系统及方法

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104881718B (zh) * 2015-06-02 2018-06-12 国家电网公司 基于多尺度经济先行指标的区域电力景气指数构建方法
CN107273998B (zh) * 2016-06-30 2024-02-13 国网江苏省电力公司南通供电公司 一种用于台区日用电量预测的气温修正方法
CN106934500B (zh) * 2017-03-15 2021-02-23 国网山东省电力公司经济技术研究院 一种基于非参数模型对地区饱和电量进行预测的方法
CN107730059A (zh) * 2017-11-29 2018-02-23 成都思晗科技股份有限公司 基于机器学习的变电站电量趋势预测分析的方法
CN108280462A (zh) * 2017-12-11 2018-07-13 北京三快在线科技有限公司 一种模型训练方法及装置，电子设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104348150A (zh) * 2013-07-31 2015-02-11 国家电网公司 电力负荷管控方法、服务器、终端及系统
CN106096778A (zh) * 2016-06-03 2016-11-09 合肥工业大学 一种基于分时电价和阶梯电价形式的家庭用电规划系统与方法
CN107703854A (zh) * 2017-10-26 2018-02-16 国网黑龙江省电力有限公司信息通信公司 电力负荷监控系统及方法
CN107907759A (zh) * 2017-10-26 2018-04-13 国网黑龙江省电力有限公司信息通信公司 电力设备的电量监控系统及方法

Also Published As

Publication number Publication date
CN109727155A (zh) 2019-05-07

Similar Documents

Publication Publication Date Title
WO2020024534A1 (zh) 基于电量预测的用电控制方法、装置、设备和存储介质
WO2020015060A1 (zh) 用电量异常评估方法、装置、设备和计算机存储介质
WO2020019403A1 (zh) 用电量异常检测方法、装置、设备及可读存储介质
WO2019037196A1 (zh) 任务分配方法、装置及计算机可读存储介质
WO2014098481A1 (ko) 홈 네트워크 시스템에서 에너지 소비를 관리하는 방법 및 장치
WO2016105020A1 (en) Apparatus and method for charging electronic device having battery
WO2020224246A1 (zh) 基于区块链的数据管理方法、装置、设备和存储介质
WO2018070768A1 (ko) 모니터링 시스템 제어 방법 및 이를 지원하는 전자 장치
WO2016111540A1 (en) Method and apparatus for processing sensor information
WO2020098075A1 (zh) 金融数据处理方法、装置、设备和存储介质
WO2020253116A1 (zh) 数据跑批方法、装置、存储介质及集群中的成员主机
WO2020147264A1 (zh) 多系统日志数据的监控方法、装置、设备及可读存储介质
WO2016195327A1 (ko) 전력 공급을 제어하는 방법 및 장치
WO2016089077A1 (en) Apparatus and method for executing task of electronic device
WO2021000507A1 (zh) 空调温度调节异常的控制方法、空调器及存储介质
WO2020019405A1 (zh) 数据库监控方法、装置、设备及可读存储介质
WO2020119115A1 (zh) 数据审核方法、装置、设备及存储介质
WO2022065623A1 (en) Method of implementing self-organizing network for plurality of access network devices and electronic device for performing the same
WO2016186417A1 (ko) 공조 기기의 기동 제어 방법 및 장치
WO2018090465A1 (zh) 视频监控方法、系统以及监控装置
WO2021012508A1 (zh) Ai影像识别方法、装置、设备及存储介质
WO2020107591A1 (zh) 重复投保限制方法、装置、设备及可读存储介质
WO2020258672A1 (zh) 网络访问的异常检测方法和装置
WO2015093902A1 (ko) 스마트 홈 시스템의 피 제어 장치 검색 및 제어 방법과 장치
WO2019114587A1 (zh) 虚拟现实终端的信息处理方法、装置及可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18928546

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18928546

Country of ref document: EP

Kind code of ref document: A1