Regional daily electric quantity intelligent monitoring method and device, storage medium and program product

Abstract

The invention discloses a regional daily electric quantity intelligent monitoring method and device, a storage medium and a program product, and relates to the technical field of electric quantity monitoring. The method comprises the following steps: acquiring historical weather data and daily electric quantity historical data of a region in the same period, and performing abnormal value processing and missing value completion on the daily electric quantity historical data to obtain corrected daily electric quantity historical data; based on the corrected daily electric quantity historical data and historical weather data, establishing a daily electric quantity prediction model by using a neural network algorithm; acquiring real-time weather data of the region, and inputting the real-time weather data into the daily electric quantity prediction model to obtain predicted daily electric quantity; and acquiring real-time daily electric quantity of the region, comparing the real-time daily electric quantity with the predicted daily electric quantity, and based on a comparison result, obtaining a conclusion and executing a corresponding countermeasure. According to the invention, intelligent monitoring of daily electric quantity is realized, dependence on personnel experience is not needed, personnel do not need to stick in front of a monitoring screen, and the use effect is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric quantity monitoring, and in particular to an intelligent regional daily electric quantity monitoring method and device, a storage medium and a program product. BACKGROUND

[0002] Electric power is an energy source that uses electric energy as power. The continuous emergence of new technologies has made electric power a necessity for people, providing energy security for people's life and production.

[0003] In order to ensure the balance of power supply in each region, the daily power consumption of each region needs to be monitored. The existing monitoring method is usually for a monitor to stay in a monitoring room and stare at a monitoring screen to obtain the daily power consumption of the region and then judge whether it is normal according to his own experience. This method needs to rely on the experience of the monitor and is prone to human judgment deviation. SUMMARY

[0004] The present application provides an intelligent regional daily electric quantity monitoring method, device, storage medium and program product to solve the problem of relying on the experience of the monitor and being prone to human judgment deviation in the existing daily electric quantity monitoring method. The intelligent monitoring of daily electric quantity is realized, and personnel experience is not needed, nor is personnel needed to stay in front of the monitoring screen, improving the use effect.

[0005] The present application is realized by the following technical solutions.

[0006] In a first aspect, an intelligent regional daily electric quantity monitoring method is provided, which comprises:

[0007] Obtain historical weather data and daily electric quantity historical data of the same period in the region, and perform outlier processing and missing value completion on the daily electric quantity historical data to obtain corrected daily electric quantity historical data;

[0008] Based on the corrected daily electric quantity historical data and the historical weather data, a daily electric quantity prediction model is established using a neural network algorithm;

[0009] Obtain real-time weather data of the region and input the daily electric quantity prediction model to obtain a predicted daily electric quantity;

[0010] Obtain real-time daily electric quantity of the region, compare the real-time daily electric quantity with the predicted daily electric quantity, and based on the comparison result, draw a conclusion and execute a corresponding countermeasure.

[0011] In some embodiments, based on the corrected daily electric quantity historical data and the historical weather data, a daily electric quantity prediction model is established using a neural network algorithm, which comprises:

[0012] The modified daily electricity consumption historical data and the historical weather data are randomly divided into a training set, a test set and a validation set;

[0013] Based on the training set, an initial model is obtained by using the neural network algorithm;

[0014] The test set is input into the initial model to adjust the parameters of the initial model, and an intermediate model is obtained.

[0015] The validation set is input into the intermediate model, and the intermediate model that passes the validation is determined as the daily electricity consumption prediction model.

[0016] In some embodiments, the neural network algorithm includes at least one of the following: a back propagation (BP) neural network algorithm, a convolutional neural network algorithm, and a recurrent neural network algorithm.

[0017] In some embodiments, the real-time daily electricity consumption is compared with the predicted daily electricity consumption, and based on the comparison result, a conclusion is drawn and a corresponding countermeasure is executed, including:

[0018] The result of subtracting the predicted daily electricity consumption from the real-time daily electricity consumption is divided by the predicted daily electricity consumption to obtain a daily electricity consumption difference ratio;

[0019] The daily electricity consumption difference ratio is compared with a preset threshold, and in the case that the daily electricity consumption difference ratio is not less than the preset threshold, it is determined that the daily electricity consumption is abnormal, and a corresponding countermeasure is executed.

[0020] In a second aspect, an intelligent monitoring device for regional daily electricity consumption is provided, and the device includes:

[0021] A historical data acquisition module is configured to acquire historical weather data and daily electricity consumption historical data of the same period of the region, and perform outlier processing and missing value completion on the daily electricity consumption historical data to obtain modified daily electricity consumption historical data.

[0022] A prediction model establishment module is configured to establish a daily electricity consumption prediction model based on the modified daily electricity consumption historical data and the historical weather data by using a neural network algorithm.

[0023] A daily electricity consumption prediction module is configured to acquire real-time weather data of the region and input the real-time weather data into the daily electricity consumption prediction model to obtain predicted daily electricity consumption.

[0024] An execution module is configured to acquire real-time daily electricity consumption of the region, compare the real-time daily electricity consumption with the predicted daily electricity consumption, and based on the comparison result, draw a conclusion and execute a corresponding countermeasure.

[0025] In some embodiments, the prediction model establishment module includes:

[0026] a dividing unit, configured to divide the modified daily electricity consumption history data and the historical weather data into a training set, a test set and a verification set randomly;

[0027] an initial model generating unit, configured to obtain an initial model based on the training set and by using the neural network algorithm;

[0028] an intermediate model generating unit, configured to input the test set into the initial model to adjust parameters of the initial model and obtain an intermediate model;

[0029] a verifying unit, configured to input the verification set into the intermediate model and determine the intermediate model that passes the verification as the daily electricity consumption prediction model.

[0030] In some embodiments, the execution module comprises:

[0031] a real-time daily electricity consumption obtaining unit, configured to obtain real-time daily electricity consumption of the region;

[0032] a calculating unit, configured to subtract the predicted electricity consumption from the real-time daily electricity consumption and divide the result by the predicted electricity consumption to obtain a daily electricity consumption difference ratio;

[0033] an execution unit, configured to compare the daily electricity consumption difference ratio with a preset threshold, and determine that daily electricity consumption is abnormal and execute a corresponding countermeasure if the daily electricity consumption difference ratio is not less than the preset threshold.

[0034] In a third aspect, an intelligent daily electricity consumption monitoring device for a region is provided, and the device comprises:

[0035] at least one processor;

[0036] at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions, when executed by the at least one processor, implementing the method according to any one of the preceding aspects.

[0037] In a third aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores instructions, which, when executed by a computer, cause the computer to perform the method according to any one of the preceding aspects.

[0038] In a fifth aspect, a computer program product is provided, and the computer program product comprises instructions, which, when executed by a computer, cause the computer to perform the method according to any one of the preceding aspects.

[0039] Compared with the prior art, the present application has the following advantages and beneficial effects: the historical weather data and daily power consumption history data of the same period of the region are acquired first, then the daily power consumption prediction model is established by using the historical weather data and daily power consumption history data, the predicted daily power consumption is obtained according to the real-time data and the daily power consumption prediction model, and then the predicted daily power consumption is compared with the real-time daily power consumption, so that the intelligent monitoring of the daily power consumption is realized, without relying on the experience of personnel and without requiring personnel to stay in front of the monitoring screen, thereby improving the use effect. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced as follows, and it should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0041] Figure 1 Flow chart of the regional daily power consumption intelligent monitoring method according to the embodiment of the present application.

[0042] Figure 2 Flow chart of the establishment of the daily power consumption prediction model according to the embodiment of the present application.

[0043] Figure 3 Flow chart of the comparison of the real-time daily power consumption with the predicted daily power consumption and the conclusion based on the comparison result according to the embodiment of the present application.

[0044] Figure 4 Structural block diagram of the regional daily power consumption intelligent monitoring device according to the embodiment of the present application.

[0045] Figure 5 Structural block diagram of the prediction model establishment module according to the embodiment of the present application.

[0046] Figure 6 Structural block diagram of the execution module according to the embodiment of the present application.

[0047] Figure 7 Structural schematic diagram of the regional daily power consumption intelligent monitoring device according to the embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the present application more clear and explicit, the present application will be further described in detail below with reference to the embodiments and drawings, and the exemplary embodiments of the present application and the description thereof are only used to explain the present application, and should not be regarded as a limitation on the present application.

[0049] In one aspect, the present application provides a regional daily power consumption intelligent monitoring method. Figure 1FIG. 1 is a flowchart of a method for intelligently monitoring regional daily power consumption according to an embodiment of the present application. Referring to FIG. 1, the method for intelligently monitoring regional daily power consumption includes S10 to S40. Figure 1 The method for intelligently monitoring regional daily power consumption includes S10 to S40.

[0050] In S10, historical weather data and historical daily power consumption data of the same period of a region are acquired, and the historical daily power consumption data is subjected to outlier processing and missing value completion to obtain corrected historical daily power consumption data.

[0051] The power consumption of a region on a certain day is related to the weather condition of the region on the day. When the weather is too hot, people will turn on air conditioners to cool down; when the weather is too cold, people will turn on heating devices (oil tincture, small sun, air conditioner, etc.) to heat; when the weather is too dry, people will turn on humidifiers to increase humidity; and when the weather is too humid, people will turn on the dehumidification model of the air conditioner to reduce humidity. Due to reasons such as device measurement, transmission or version, the acquired historical daily power consumption data may have missing values or outliers, and thus the historical daily power consumption data needs to be subjected to outlier processing and missing value completion to ensure the accuracy of subsequent data and thus the prediction accuracy of a subsequent prediction model.

[0052] In S20, a daily power consumption prediction model is established based on the corrected historical daily power consumption data and historical weather data by using a neural network algorithm.

[0053] After the historical daily power consumption data is subjected to outlier processing and missing value completion, the corrected historical daily power consumption data is obtained, and then the corrected historical daily power consumption data and historical weather data can be used to generate a daily power consumption prediction model by using a neural network algorithm.

[0054] In S30, real-time weather data of the region is acquired and input into the daily power consumption prediction model to obtain a predicted daily power consumption.

[0055] The real-time weather data can be input into the generated daily power consumption prediction model to obtain the predicted daily power consumption of the region on the day.

[0056] In S40, real-time daily power consumption of the region is acquired, and the real-time daily power consumption is compared with the predicted daily power consumption, and based on the comparison result, a conclusion is drawn and a corresponding countermeasure is executed.

[0057] The real-time daily power consumption is compared with the predicted daily power consumption to obtain the difference therebetween, and then the difference is compared with a preset threshold (obtained from historical data) to determine whether the daily power consumption of the region is normal. If the determination result is normal, no measure needs to be executed and no relevant personnel needs to be notified. If the determination result is abnormal, a corresponding countermeasure to be executed is queried from a countermeasure library and relevant personnel is notified to prevent a greater abnormality from occurring subsequently.

[0058] Figure 2A flowchart for establishing a daily power consumption prediction model according to an embodiment of the present application. Reference is made to Figure 2 , based on the corrected daily power consumption historical data and the historical weather data, a daily power consumption prediction model is established by using a neural network algorithm, including: S21 to S24.

[0059] In S21, the corrected daily power consumption historical data and the historical weather data are randomly divided into a training set, a test set and a validation set.

[0060] The corrected daily power consumption historical data and the historical weather data are used as samples for establishing a daily power consumption prediction model, and the samples are randomly divided into a training set, a test set and a validation set. The training set is used to generate a daily power consumption prediction model; the test set is used to adjust the parameters of the daily power consumption prediction model so that the accuracy of the daily power consumption prediction model is more optimal; and the validation set is used to verify whether the accuracy of the daily power consumption prediction model meets the requirements. Random division is to make the established daily power consumption prediction model more consistent with the general characteristics of all data. The ratio of the number of the training set, the test set and the validation set varies from person to person. Here, the ratio of the number of the training set, the test set and the validation set is set to 3:1:1.

[0061] In S22, based on the training set, an initial model is obtained by using a neural network algorithm. The initial neural network model and its parameters are set, the training set is output to the initial neural network model and trained to update the parameters of the initial neural network model, thereby obtaining the initial model. Exemplarily, the divided training set is substituted into the neural network algorithm and iterated for multiple times, and the initial model can be obtained. The neural network algorithm can be any one of a BP (back propagation) neural network algorithm, a convolutional neural network algorithm and a recurrent neural network algorithm. These three kinds of neural network algorithms are mature algorithms and can meet the requirements of power consumption prediction. Which one to use depends on the actual use.

[0062] In S23, the test set is input into the initial model to adjust the parameters of the initial model and obtain an intermediate model.

[0063] The initial model is only a model obtained according to the training set, and the initial model needs to be adjusted to make the performance of the model more excellent. At this time, the test set can be input into the initial model to adjust the initial model, so that the performance of the obtained model is more excellent, i.e., the intermediate model.

[0064] In S24, the validation set is input into the intermediate model, and the intermediate model that passes the verification is determined as the daily power consumption prediction model.

[0065] The performance of the intermediate model needs to be verified to see if it meets the requirements. At this time, the verification set needs to be substituted into the intermediate model. When the number of iterations reaches the required number or the generated result is accurate, it can be considered that the intermediate model meets the use requirements. At this time, the intermediate model is the daily power consumption prediction model.

[0066] Figure 3 A flowchart for comparing real-time daily power consumption with predicted daily power consumption according to an embodiment of the present application and drawing conclusions based on the comparison results. Referring to Figure 3 , the real-time daily power consumption is compared with the predicted daily power consumption, and conclusions are drawn based on the comparison results and corresponding countermeasures are executed, including S41 and S42.

[0067] In S41, the result of subtracting the predicted power consumption from the real-time daily power consumption is divided by the predicted power consumption to obtain the daily power consumption difference ratio.

[0068] In S42, the daily power consumption difference ratio is compared with a preset threshold. In the case where the daily power consumption difference ratio is not less than the preset threshold, it is determined that the daily power consumption is abnormal, and corresponding countermeasures are executed. Illustratively, when the difference percentage between the real-time daily power consumption and the predicted power consumption exceeds a certain percentage (i.e., the power consumption suddenly increases or decreases a lot), it is considered that the power consumption in the region is abnormal.

[0069] The daily power consumption difference ratio is compared with a preset threshold. If the daily power consumption difference ratio is greater than or equal to the preset threshold, it is determined that the daily power consumption is abnormal, and corresponding countermeasures are executed. The preset threshold is pre-stored in the server and is summarized from historical data. When the difference percentage between the real-time daily power consumption and the predicted power consumption exceeds the threshold, it is determined that the daily power consumption is abnormal. The corresponding countermeasures are queried from the countermeasure library and notified to the relevant personnel to prevent larger abnormalities from occurring subsequently. When the difference percentage between the real-time daily power consumption and the predicted power consumption does not exceed the threshold, it is determined that the daily power consumption is normal, and no measures need to be executed or notified to the relevant personnel.

[0070] In the present application, historical weather data and daily power consumption historical data of the same period in the region are first obtained, and then a daily power consumption prediction model is established using the historical weather data and the daily power consumption historical data. The predicted daily power consumption is obtained according to real-time data and the daily power consumption prediction model. The predicted daily power consumption is compared with the real-time daily power consumption to realize intelligent monitoring of the daily power consumption. No personnel experience is required, and personnel do not need to stay in front of the monitoring screen, thereby improving the use effect.

[0071] On the other hand, an intelligent regional daily power consumption monitoring device is provided. Figure 4 A structural block diagram of the intelligent regional daily power consumption monitoring device according to an embodiment of the present application. Referring to Figure 4 The device includes a historical data acquisition module, a prediction model establishment module, a daily power consumption prediction module, and an execution module.

[0072] a historical data acquisition module, configured to acquire historical weather data and historical daily electricity consumption data of a region, and perform outlier processing and missing value completion on the historical daily electricity consumption data to obtain corrected historical daily electricity consumption data.

[0073] a prediction model establishment module, configured to establish a daily electricity consumption prediction model based on the corrected historical daily electricity consumption data and the historical weather data by using a neural network algorithm.

[0074] a daily electricity consumption prediction module, configured to acquire real-time weather data of the region and input the daily electricity consumption prediction model to obtain a predicted daily electricity consumption.

[0075] an execution module, configured to acquire a real-time daily electricity consumption of the region, compare the real-time daily electricity consumption with the predicted daily electricity consumption, and determine a conclusion and perform a corresponding countermeasure based on a comparison result.

[0076] In some embodiments, with reference to Figure 5 The prediction model establishment module comprises a division unit, an initial model generation unit, an intermediate model generation unit, and a verification unit.

[0077] The division unit is configured to randomly divide the corrected historical daily electricity consumption data and the historical weather data into a training set, a test set, and a verification set.

[0078] The initial model generation unit is configured to obtain an initial model based on the training set by using a neural network algorithm.

[0079] The intermediate model generation unit is configured to input the test set into the initial model to adjust parameters of the initial model and obtain an intermediate model.

[0080] The verification unit is configured to input the verification set into the intermediate model, and determine the intermediate model that passes the verification as the daily electricity consumption prediction model.

[0081] In some embodiments, with reference to Figure 6 The execution module comprises a real-time daily electricity consumption acquisition unit, a calculation unit, and an execution unit.

[0082] The real-time daily electricity consumption acquisition unit is configured to acquire a real-time daily electricity consumption of the region.

[0083] The calculation unit is configured to subtract the predicted daily electricity consumption from the real-time daily electricity consumption, divide the result by the predicted daily electricity consumption, and obtain a daily electricity consumption difference ratio.

[0084] The execution unit is configured to compare the daily electricity consumption difference ratio with a preset threshold, and determine that the daily electricity consumption is abnormal and perform a corresponding countermeasure in a case where the daily electricity consumption difference ratio is not less than the preset threshold.

[0085] Details of the regional daily power consumption intelligent monitoring device refer to the description of the regional daily power consumption intelligent monitoring method, which will not be repeated here.

[0086] In the case of implementing the functions of the above-mentioned integrated modules in the form of hardware, the embodiments of the present application provide a structure of the regional daily power consumption intelligent monitoring device involved in the above-mentioned embodiments. Figure 7 FIG. 1 is a structure diagram of a regional daily power consumption intelligent monitoring device according to an embodiment of the present application. Referring to FIG. 1, Figure 7 The regional daily power consumption intelligent monitoring device includes at least one processor and at least one memory. The at least one memory is coupled to the at least one processor and stores instructions for execution by the at least one processor, which, when executed by the at least one processor, implement the above-mentioned method.

[0087] As an implementation manner, the memory can exist independently of the processor, and the memory can be connected to the processor through a bus for storing instructions or program codes. When the processor invokes and executes the instructions or program codes stored in the memory, the method provided by the embodiments of the present application can be implemented. In another implementation manner, the memory can also be integrated with the processor.

[0088] On the other hand, the present application also provides a computer readable storage medium (for example, a non-transitory computer readable storage medium) having computer program instructions stored therein, which, when executed on a computer, cause the computer to execute the method of any one of the above-mentioned embodiments.

[0089] Exemplarily, the above-mentioned computer readable storage medium can include, but is not limited to, a magnetic storage device (for example, a hard disk, a floppy disk or a magnetic tape, etc.), an optical disk (for example, a compact disk (CD), a digital versatile disk (DVD), etc.), a smart card and a flash memory device (for example, an erasable programmable read only memory (EPROM), a card, a stick or a key drive, etc.). The various computer readable storage media described in the present application can represent one or more devices and / or other machine readable storage media for storing information. The term "machine readable storage medium" can include, but is not limited to, a wireless channel and various other media capable of storing, containing and / or carrying instructions and / or data.

[0090] The embodiments of the present application provide a computer program, which, when executed on a computer, causes the computer to execute the method of any one of the above-mentioned embodiments.

[0091] The embodiment of the present application provides a computer program product containing instructions, when the computer program product runs on a computer, the computer is caused to execute the method in any of the above embodiments.

[0092] The processor fetches instructions from the memory one by one, analyzes the instructions, and then completes corresponding operations according to the instructions, generates a series of control commands, and makes each part of the computer automatically, continuously and coordinately act, becomes an organic whole, realizes the input of the program, the input of the data and the operation and the output of the result, and the arithmetic operation or the logical operation generated in the process is completed by the operation unit; the memory includes a read-only memory (Read-Only Memory, ROM), and the read-only memory is used to store a computer program, and the memory is externally provided with a protection device.

[0093] Exemplarily, the computer program can be divided into one or more modules, the one or more modules are stored in the memory and executed by the processor to complete the present application. The one or more modules can be a series of computer program instruction segments capable of completing a specific function, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0094] Those skilled in the art can understand that the description of the service device above is only an example, and does not constitute a limitation on the terminal device, and can include more or less components than the above description, or combine certain components, or different components, for example, can include an input and output device, a network access device, a bus and the like.

[0095] The processor can be a central processing unit (Central Processing Unit, CPU), and can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), ready programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The above processor is the control center of the terminal device, and is connected with each part of the terminal device through various interfaces and lines.

[0096] The memory can be used to store computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as an information collection template display function, a product information publishing function, etc.), etc.; and the data storage area can store data created according to the use of the berth state display system (such as product information collection templates corresponding to different product categories, product information to be published by different product providers, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0097] If the modules / units integrated in the terminal device are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the modules / units in the above-mentioned embodiment system can also be instructed by a computer program to complete the related hardware. The computer program can be stored in a computer-readable storage medium, and when the processor executes the computer program, the functions of the above-mentioned various system embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium can include any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0098] It should be noted that in this document, the term "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0099] The above merely describes the preferred embodiments of the present application, and is not intended to limit the patent scope of the present application, and any equivalent structure or equivalent process conversion, or direct or indirect application in other related technical fields, which are made by using the content of the present application specification and drawings, are also included in the patent protection scope of the present application.

Claims

1. A method for intelligent monitoring of regional daily electricity consumption, characterized in that, The method comprises: obtaining historical weather data and daily electricity consumption history data of the same period of the region, and performing outlier processing and missing value completion on the daily electricity consumption history data to obtain corrected daily electricity consumption history data; based on the corrected daily electricity consumption history data and the historical weather data, a daily electricity consumption prediction model is established by using a neural network algorithm; obtaining real-time weather data of the region and inputting the daily electricity consumption prediction model to obtain predicted daily electricity consumption; obtaining real-time daily electricity consumption of the region, comparing the real-time daily electricity consumption with the predicted daily electricity consumption, and based on the comparison result, drawing a conclusion and executing corresponding countermeasures.

2. The method for intelligent monitoring of daily electricity consumption in a region according to claim 1, characterized in that, Based on the corrected daily electricity consumption history data and the historical weather data, a daily electricity consumption prediction model is established by using a neural network algorithm, comprising: randomly dividing the corrected daily electricity consumption history data and the historical weather data into a training set, a test set and a validation set; based on the training set, the initial model is obtained by using the neural network algorithm; inputting the test set into the initial model to adjust the parameters of the initial model and obtaining an intermediate model; inputting the validation set into the intermediate model, and determining the intermediate model that passes the validation as the daily electricity consumption prediction model.

3. The method for intelligent monitoring of daily electricity consumption in a region according to claim 2, characterized in that, The neural network algorithm comprises at least one of the following: back propagation BP neural network algorithm, convolutional neural network algorithm, recurrent neural network algorithm.

4. The method for intelligent monitoring of regional daily electricity consumption according to claim 1, characterized in that, Comparing the real-time daily electricity consumption with the predicted daily electricity consumption, and based on the comparison result, drawing a conclusion and executing corresponding countermeasures, comprising: the result of subtracting the predicted electricity consumption from the real-time daily electricity consumption is divided by the predicted electricity consumption to obtain the daily electricity consumption difference ratio; comparing the daily electricity consumption difference ratio with a preset threshold, and in the case that the daily electricity consumption difference ratio is not less than the preset threshold, determining that the daily electricity consumption is abnormal, and executing corresponding countermeasures.

5. A smart monitoring device for regional daily electricity consumption, characterized in that, The device comprises: a historical data acquisition module, configured to: obtain historical weather data and daily electricity consumption history data of the same period of the region, and perform outlier processing and missing value completion on the daily electricity consumption history data to obtain corrected daily electricity consumption history data; a prediction model establishment module, configured to: based on the corrected daily electricity consumption history data and the historical weather data, a daily electricity consumption prediction model is established by using a neural network algorithm; a daily electricity consumption prediction module, configured to: obtain real-time weather data of the region and input the daily electricity consumption prediction model to obtain predicted daily electricity consumption; an execution module, configured to: obtain real-time daily electricity consumption of the region, compare the real-time daily electricity consumption with the predicted daily electricity consumption, and based on the comparison result, draw a conclusion and execute corresponding countermeasures.

6. The regional daily electricity consumption smart monitoring device according to claim 5, characterized in that, The prediction model establishment module comprises: a division unit, configured to: randomly divide the corrected daily electricity consumption history data and the historical weather data into a training set, a test set and a validation set; an initial model generation unit, configured to: based on the training set, the initial model is obtained by using the neural network algorithm; an intermediate model generation unit, configured to: input the test set into the initial model to adjust the parameters of the initial model and obtain an intermediate model; A verification unit is configured to input the verification set into the intermediate model and determine the intermediate model that passes the verification as the daily electricity consumption prediction model.

7. The regional daily electricity consumption smart monitoring device according to claim 5, characterized in that, The execution module comprises: A real-time daily electricity consumption acquisition unit is configured to acquire real-time daily electricity consumption of the region; A calculation unit is configured to subtract the predicted electricity consumption from the real-time daily electricity consumption and divide the result by the predicted electricity consumption to obtain a daily electricity consumption difference ratio; An execution unit is configured to compare the daily electricity consumption difference ratio with a preset threshold value, determine daily electricity consumption anomaly and execute corresponding countermeasures if the daily electricity consumption difference ratio is not less than the preset threshold value.

8. A district daily electricity consumption intelligent monitoring device, characterized in that, The device comprises: at least one processor; at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions, when executed by the at least one processor, implement the method according to any one of claims 1 to 4.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions, which, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 4.

10. A computer program product, characterised in that, The computer program product comprises instructions, which, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 4.

Images