Smart City Government Power Supply Regulation Method, Internet of Things System, Device and Medium

Abstract

An embodiment of this specification provides a method for government power supply regulation in a smart city, an Internet of Things system, a device, and a medium. This method is executed by a government power supply regulation management platform. The method includes: obtaining the weather characteristics of a target area in a future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period; based on the above characteristics, predicting the per capita living electricity consumption of the target area in the future time period through an electricity consumption prediction model; and determining the power supply strategy of the target area in the future time period based on the per capita living electricity consumption of the target area in the future time period. The Internet of Things system includes a user platform, a government service platform, a government power supply regulation management platform, a government sensing network platform, and an object platform that interact with each other in sequence. This method is implemented through a smart city government power supply regulation device. This method also runs after computer instructions stored in a computer-readable storage medium are read.

Description

Technical Field

[0001] This specification relates to the field of the Internet of Things and cloud platforms, and particularly to a government power supply regulation method, an Internet of Things system, a device and a medium for a smart city. Background Art

[0002] Under the combined effect of the green transformation at the energy supply end and the increase in the electrification ratio at the consumption end, the problem of insufficient power supply may persist for a long time. This requires accelerating the market-oriented reform of electricity, and guiding the better matching of supply and demand through the price mechanism. With the development of information science and technology, the concept of cloud platforms and their applications in the Internet of Things have been mentioned by more and more people. Therefore, an efficient and reasonable government power supply regulation method can be provided by using the Internet of Things platform.

[0003] Therefore, it is hoped that a government power supply regulation method, an Internet of Things system, a device and a medium for a smart city can be provided. By using the Internet of Things and cloud platforms, accurate power supply strategies can be determined and electricity subsidies can be reasonably distributed to citizens. To achieve more scientific government power supply regulation, encourage citizens to save energy, reduce the power supply gap, and relieve the pressure of power supply. Summary of the Invention

[0004] The summary of the invention includes a government power supply regulation method for a smart city. The government power supply regulation method for a smart city includes: obtaining the weather characteristics of a target area in a future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period; predicting the per capita domestic electricity consumption of the target area in the future time period through an electricity consumption prediction model based on the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period; and determining the power supply strategy of the target area in the future time period based on the per capita domestic electricity consumption of the target area in the future time period.

[0005] In some embodiments, the electricity consumption prediction model is obtained through a training process, and the training process includes: obtaining a plurality of training samples and their labels, the plurality of training samples including the weather characteristics of the target area in the historical future time period, the time event characteristics of the target area in the historical future time period, and the basic economic development characteristics of the target area in the historical current time period, and the labels including the actual per capita domestic electricity consumption in the historical future time period; and training an initial electricity consumption prediction model based on the plurality of training samples to obtain the electricity consumption prediction model.

[0006] In some embodiments, the input of the electricity consumption prediction model further includes the number of people quarantined due to the epidemic in the target area in the future time period.

[0007] In some embodiments, the method further includes determining a target power supply strategy for the target area in a future time period based on the per capita living power consumption in the future time period of the target area. The determining the target power supply strategy for the target area in the future time period based on the per capita living power consumption in the future time period of the target area includes: obtaining multiple groups of power supply strategies for the target area in the future time period as candidate power supply strategies; predicting the reduction rate corresponding to each group of the candidate power supply strategies through an effect prediction model based on each group of the candidate power supply strategies and the per capita living power consumption in the future time period of the target area; and determining the target power supply strategy for the target area in the future time period based on the reduction rate corresponding to each group of the candidate power supply strategies.

[0008] In some embodiments, the effect prediction model is obtained through a training process, and the training process includes: obtaining a plurality of training samples and their labels, where the plurality of training samples include power supply strategies in historical future time periods and the per capita living power consumption in the historical future time periods of the target area, and the labels include the actual reduction rate in the historical future time periods; and training an initial effect prediction model based on the plurality of training samples to obtain the effect prediction model.

[0009] In some embodiments, the input of the effect prediction model further includes the basic economic development characteristics of the target area in the current time period.

[0010] In some embodiments, the obtaining the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period includes: the government power supply regulation management platform obtaining the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period through the government sensing network platform based on the object platform; where the object platform is configured to include a smart meter and a terminal device.

[0011] The invention content includes a smart city government power supply regulation system, which includes a user platform, a government service platform, a government power supply regulation management platform, a government sensing network platform, and an object platform that interact with each other in sequence. The government power supply regulation management platform is configured to perform the following operations: obtaining the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period; predicting the per capita living power consumption of the target area in the future time period through a power consumption prediction model based on the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period; and determining the power supply strategy for the target area in the future time period based on the per capita living power consumption of the target area in the future time period.

[0012] The invention content includes a smart city government power supply regulation device, including a processor, and the processor is used to execute the smart city government power supply regulation method.

[0013] The invention content includes a computer-readable storage medium, and the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the smart city government power supply regulation method.

[0014] In order to overcome the problem of large power supply pressure caused by the shortage of power supply, the present invention determines the accurate preset maximum per capita living power consumption and the subsidy amount for saving unit power by predicting the per capita living power consumption in the future time period, and reasonably distributes power consumption subsidies to citizens. It realizes more scientific government power supply regulation, encourages citizens to save energy, reduces the power supply gap, and reduces the pressure of power supply. And, by using the effect prediction model to predict the reduction rate corresponding to each group of candidate power supply strategies, and then determining the target power supply strategy with the highest reduction rate within the threshold range of the total subsidy amount. It economically and efficiently reduces the pressure of power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] This specification will be further described in the form of exemplary embodiments, and these exemplary embodiments will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0016] Figure 1 is a schematic diagram of the application scenario of smart city government power supply regulation shown in some embodiments of this specification;

[0017] Figure 2 is an exemplary platform structure diagram of the smart city government power supply regulation system shown in some embodiments of this specification;

[0018] Figure 3 is an exemplary flowchart of the government power supply regulation method shown in some embodiments of this specification;

[0019] Figure 4 is an exemplary flowchart of the method for determining the target power supply strategy for the target area in the future time period shown in some embodiments of this specification;

[0020] Figure 5 is a schematic diagram of the structure of the power consumption prediction model shown in some embodiments of this specification;

[0021] Figure 6 is a schematic diagram of the structure of the epidemic prediction model shown in some embodiments of this specification;

[0022] Figure 7It is a schematic diagram of the effect prediction model structure shown in some embodiments of this specification;

[0023] In the figure, 100 is an application scenario, 110 is a processing device, 120 is a network, 130 is a storage device, 140 is a smart meter, 150 is a power supply enterprise, 160 is a terminal device, 160-1 is a smart phone, 160-2 is a tablet computer, 160-3 is a laptop computer, 200 is a smart city government power supply regulation system, 210 is a user platform, 220 is a government service platform, 230 is a government power supply regulation management platform, 240 is a government sensor network platform, 250 is an object platform, 500 is an electricity consumption prediction model structure, 510-1 is the weather characteristics of the target area in the future time period, 510-2 is the time event characteristics of the target area in the future time period, 510-3 is the basic economic development characteristics of the target area in the current time period, 510-4 is the number of people quarantined due to the epidemic in the target area in the future time period, 520 is an electricity consumption prediction model, 530 is the per capita living electricity consumption of the target area in the future time period, 540 is the first training sample, 550 is an initial electricity consumption prediction model, 600 is an epidemic prediction model structure, 610-1 is the number of people tested positive for the etiology of the new coronavirus, 610-2 is the number of asymptomatic infections, 610-3 is the number of symptomatic infections, 610-4 is the number of medium and high-risk areas, 610-5 is the epidemic prevention and control measures, 620 is an epidemic prediction model, 620-1 is an epidemic feature extraction layer, 620-2 is an isolation number prediction layer, 630 is an epidemic feature vector, 640 is the second training sample, 650 is an initial epidemic prediction model, 700 is an effect prediction model structure, 710-1 is a group of candidate power supply strategies, 710-2 is the per capita living electricity consumption of the target area in the future time period, 720 is an effect prediction model, 730 is the reduction rate corresponding to this group of candidate power supply strategies, 740 is the third training sample, 750 is an initial effect prediction model. Detailed implementation manners

[0024] To more clearly illustrate the technical solutions of the embodiments of this specification, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

[0025] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0026] Unless the context clearly indicates otherwise, words such as "a", "an", "one", and / or "the" are not specific to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. A method or device may also include other steps or elements.

[0027] Flowcharts are used in this specification to illustrate the operations performed by the systems according to the embodiments of this specification. It should be understood that the operations before or after may not be precisely executed in sequence. On the contrary, the steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or more steps can be removed from these processes.

[0028] Figure 1 It is a schematic diagram of the application scenario of the power supply regulation of the smart city government shown in some embodiments of this specification.

[0029] In some embodiments, the application scenario 100 may include a processing device 110, a network 120, a storage device 130, a smart meter 140, a power supply enterprise 150, and a terminal device 160. In some embodiments, the components in the application scenario 100 can be connected to each other and / or communicate via the network 120 (such as a wireless connection, a wired connection, or a combination thereof). For example, the processing device 110 can be connected to the storage device 130 through the network 120. Again, for example, the smart meter 140 can be connected to the processing device 110 and the storage device 130 through the network 120.

[0030] The processing device 110 can be used to process information and / or data related to the application scenario 100. For example, the weather characteristics of the target area in a future time period, the time event characteristics of the target area in a future time period, the basic economic development characteristics of the target area in the current time period, the target power supply strategy of the target area in a future time period, etc. The processing device 110 can process the data, information, and / or processing results obtained from other devices or system components. And based on these data, information, and / or processing results, execute program instructions to perform one or more functions described in this specification.

[0031] The network 120 can connect the components of the application scenario 100 and / or connect the application scenario 100 with external resource parts. The network enables communication between the components and between the application scenario 100 and other parts outside, and promotes the exchange of data and / or information. The network can be a local area network, a wide area network, the Internet, etc., and can be a combination of multiple network structures.

[0032] The storage device 130 can be used to store data and / or instructions. In some embodiments, the storage device 130 can store the data and / or instructions that the processing device 110 uses to execute or utilize to complete the exemplary methods described in this specification. In some embodiments, the storage device 130 can be connected to the network 120 to communicate with one or more components of the application scenario 100 (e.g., the processing device 110, the smart meter 140, the power supply company 150, and the terminal device 160).

[0033] The smart meter 140 can be used to collect power consumption data and / or information. For example, the actual per capita domestic electricity consumption in the target area for historical and future time periods, etc. In some embodiments, the smart meter 140 can send the collected data and / or information to the processing device 110 via the network.

[0034] The power supply company 150 can be used to supply and / or dispatch electric energy. For example, the power supply company can supply electric energy to the public. Exemplary power supply companies can include the municipal power supply companies under State Grid or China Southern Power Grid.

[0035] In some embodiments, the terminal device 160 can be used to query power supply strategies and the corresponding subsidy amounts. For example, citizens can query the subsidy amount for the current month through the terminal device. The terminal device 160 can also be used to obtain the weather characteristics in the future time period of the target area, the time event characteristics in the future time period of the target area, and the basic economic development characteristics in the current time period of the target area. Exemplarily, the terminal device 160 can include a smart phone 160-1, a tablet computer 160-2, a laptop computer 160-3, etc.

[0036] It should be noted that the application scenario is provided only for illustrative purposes and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various modifications or changes can be made according to the description of this specification. For example, the application scenario can also include a database. Also, for example, the application scenario can be implemented on other devices to achieve similar or different functions. However, the changes and modifications will not deviate from the scope of this specification.

[0037] The Internet of Things system is an information processing system that includes some or all of the object platform, sensing network platform, management platform, service platform, and user platform. The management platform can coordinate and manage the connections and collaborations between various functional platforms (such as the sensing network platform and the object platform). The management platform aggregates the information of the Internet of Things operation system and can provide perception management and control management functions for the Internet of Things operation system. The sensing network platform can connect the management platform and the object platform and play the functions of sensing communication for perception information and sensing communication for control information. The object platform is a functional platform that executes the generated perception information and control information. The service platform refers to a platform that provides input and output services for users. The user platform refers to a user-led platform, including a platform that obtains user needs and feeds back information to users.

[0038] The processing of information in the Internet of Things system can be divided into the processing flow of perception information and the processing flow of control information. The control information can be information generated based on the perception information. Among them, the processing of perception information is that the object platform obtains the perception information and transmits it to the management platform through the sensing network platform. The control information is sent by the management platform to the object platform through the sensing network platform, so as to realize the control of the corresponding object.

[0039] In some embodiments, when the Internet of Things system is applied to urban management, it can be called a smart city Internet of Things system.

[0040] Figure 2 It is an exemplary platform structure diagram of the smart city government power supply regulation system shown in some embodiments of this specification. As Figure 2 shown, the smart city government power supply regulation system 200 can be implemented based on the Internet of Things system. The smart city government power supply regulation system 200 includes a user platform 210, a government service platform 220, a government power supply regulation management platform 230, a government sensing network platform 240, and an object platform 250. In some embodiments, the smart city government power supply regulation system 200 can be a part of the processing device 110 or implemented by the processing device 110.

[0041] In some embodiments, the smart city government power supply regulation system 200 can be applied to various scenarios of government power supply regulation. In some embodiments, the smart city government power supply regulation system 200 can respectively obtain power consumption-related data in various scenarios to obtain government power supply regulation strategies for each scenario. In some embodiments, the smart city government power supply regulation system 200 can obtain the government power supply regulation strategy for the entire region (such as the entire city) based on the power consumption-related data obtained in each scenario.

[0042] Multiple scenarios of government power supply regulation may include scenarios such as industrial power supply, agricultural power supply, and civilian power supply. For example, it may include civilian power supply regulation. It should be noted that the above scenarios are only examples and do not limit the specific application scenarios of the smart city government power supply regulation system 200. Those skilled in the art can, based on the content disclosed in this embodiment, apply the smart city government power supply regulation system 200 to any other suitable scenarios.

[0043] In some embodiments, the smart city government power supply regulation system 200 can be applied to civilian power supply regulation. When applied to civilian power supply regulation, the object platform 250 can be used to collect data related to power supply prediction. For example, the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period, etc.; the object platform 250 can upload the collected data related to power supply prediction to the government sensing network platform 240. The government sensing network platform 240 can perform summary processing on the collected data. The government sensing network platform 240 then uploads the further summarized data to the government power supply regulation management platform 230. The government power supply regulation management platform 230 makes power supply prediction-related strategies or instructions, such as power supply strategies, based on the processing of the collected data.

[0044] For those skilled in the art, after understanding the principle of the system, it may be possible to transfer the system to any other suitable scenario without departing from this principle.

[0045] The following will specifically describe the smart city government power supply regulation system 200 by taking the scenario where the smart city government power supply regulation system 200 is applied to civilian power supply as an example.

[0046] It should be noted that a sub-platform refers to a part of the platform divided according to the task type. In some embodiments, the government service platform 220, the government power supply regulation management platform 230, the government sensing network platform 240, and the object platform 250 can all be set with multiple sub-platforms as needed. The sub-platforms can assist the platform to complete information processing more efficiently and solve the problem of insufficient computing power of the platform.

[0047] A database refers to a collection of stored data. For example, the management platform database can store data information such as the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period.

[0048] A sub-database refers to a part of the data collection divided from the database according to the data type. In some embodiments, the service platform database, the management platform database, and the sensing network platform database can all be set with multiple sub-databases as needed.

[0049] The user platform 210 can be a citizen-led platform, including a platform for obtaining the needs of citizens and feeding back information to citizens. For example, the user platform 210 can obtain the input instructions of citizens through a terminal device (e.g., the terminal device 160) and query the power supply strategy of the target area. For another example, the user platform 210 can feed back the information of the subsidy plan to citizens.

[0050] The government service platform 220 can be a platform that provides input and output services for citizens. For example, the government service platform 220 can obtain the query instructions issued by citizens through the user platform 210, query the electricity subsidy plan, and feed back the electricity subsidy plan to citizens.

[0051] The government power supply regulation and management platform 230 can refer to a platform in a smart city that manages the government power supply regulation. In some embodiments, the government power supply regulation and management platform 230 can belong to the management platform. The government power supply regulation and management platform 230 can be configured to obtain the weather characteristics of the target area in a future time period, the time event characteristics of the target area in a future time period, and the basic economic development characteristics of the target area in the current time period based on the object platform 250 through the government sensing network platform 240.

[0052] In some embodiments, the government power supply regulation and management platform 230 can include a management information comprehensive management platform and multiple management sub-platforms.

[0053] In some embodiments, the government power supply regulation and management platform 230 can include one or more management sub-platforms such as a power supply regulation sub-platform and a financial management sub-platform. Different management sub-platforms can independently provide information for the management information comprehensive management platform through different management platform sub-databases. For example, the power supply regulation sub-platform can provide government power supply regulation information for the management information comprehensive management platform through the power supply regulation database. The financial management sub-platform can provide financial management information for the management information comprehensive management platform through the financial management database. The management information comprehensive management platform comprehensively manages the received information and sends it to the government service platform 220 according to the needs of citizens.

[0054] In some embodiments, the management platform database can obtain the weather characteristics of the target area in a future time period, the time event characteristics of the target area in a future time period, and the basic economic development characteristics of the target area in the current time period based on the object platform 250, and the management sub-platform database can obtain the weather characteristics of the target area in a future time period, the time event characteristics of the target area in a future time period, and the basic economic development characteristics of the target area in the current time period based on the management platform database.

[0055] In some embodiments, the government power supply regulation and management platform 230 may also be configured to determine the total subsidy amount corresponding to the target power supply strategy for the target area in a future time period based on the target power supply strategy for the target area in the future time period, and send the total subsidy amount corresponding to the target power supply strategy for the target area in the future time period to the financial management sub-platform.

[0056] For more information about the government power supply regulation and management platform 230, reference can be made to other parts of this specification (e.g., Figures 3 - 4 and its related descriptions), which will not be elaborated here.

[0057] The government sensing network platform 240 may refer to a platform for unified management of sensing communication, which may also be referred to as a sensing network management platform or a sensing network management server. In some embodiments, the government sensing network platform 240 may be connected to the government power supply regulation and management platform 230 and the object platform 250 to implement the functions of sensing communication of sensing information and sensing communication of control information. In some embodiments, the government sensing network platform 240 may be configured as an IoT gateway. It can be used to establish channels for uploading sensing information and downloading control information between terminal devices (e.g., terminal device 160) and / or smart meters (e.g., smart meter 140) and the management platform (e.g., the government power supply regulation and management platform 230). In some embodiments, the government sensing network platform 240 may include multiple sensing network sub-platforms. The sensing network sub-platforms may be sensing network sub-platforms corresponding to different object platforms 250 (e.g., a terminal device sub-platform and a smart meter sub-platform). It can process and store the data uploaded by the terminal devices and smart meters into the sensing network platform database, and then distribute it to different sensing network platform sub-databases for processing and storage. After being processed, the data is summarized and stored in the sensing network platform database and then transmitted to the sensing information integrated management platform, and is uniformly transmitted to the government power supply regulation and management platform 230 by the sensing information management integrated management platform and stored in the management platform database.

[0058] The object platform 250 may refer to a functional platform for generating sensing information and finally executing control information, which is the final platform for the realization of the will of the citizens. In some embodiments, the object platform 250 may obtain information. The obtained information may be used as the information input of the entire Internet of Things.

[0059] Sensing information may refer to the information obtained by physical entities. For example, the information obtained by a smart meter. Control information may refer to the control information formed after processing such as identifying, verifying, parsing, and converting sensing information, such as a control instruction.

[0060] In some embodiments, the object platform 250 may be configured as a terminal device and a smart meter. In some embodiments, the object platform 250 may be classified into multiple object sub-platforms based on the types of different sensing devices. For example, the object platform 250 may be classified as a terminal device platform based on the terminal device, including one or more terminal devices; the object platform 250 may be classified as a smart meter platform based on the smart meter, including one or more smart meters.

[0061] It should be noted that the above description of the system and its components is only for convenience of description and does not limit this specification within the scope of the examples given. It can be understood that for those skilled in the art, after understanding the principle of the system, they may, without departing from this principle, make any combination of the components, or form a subsystem and connect it with other components. For example, the components may share a storage device, or each component may have its own storage device. Such variations are all within the protection scope of this specification.

[0062] Implementing smart city government power supply regulation through the IoT functional architecture of five platforms completes the closed-loop of the information process and makes the IoT information processing more smooth and efficient.

[0063] Figure 3 It is an exemplary flowchart of the government power supply regulation method shown in some embodiments of this specification. As Figure 3 shown, process 300 includes the following steps. In some embodiments, process 300 may be executed by the government power supply regulation management platform 230.

[0064] Step 310, obtain the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period.

[0065] The target area refers to the area where the government intends to conduct power supply regulation. In some embodiments, the target area may include a city, a district, etc. For example, the target area may be Beijing. Another example is that the target area may be Chaoyang District, Beijing.

[0066] The current time period refers to the time period from a certain past moment to the current moment. The future time period refers to the time period from the current moment to a certain future moment. For example, if the current moment is 24:00 on June 30, 2032, the current time period may be from 24:00 on May 31, 2032 to 24:00 on June 30, 2032. The future time period may be from 24:00 on June 30, 2032 to 24:00 on July 31, 2032.

[0067] The weather characteristics of the target area in the future time period refer to the average values of the temperature and rainfall in the predicted future time period of the target area. For example, if the current time is 24:00 on June 30, 2032, the weather characteristics of the target area in the future time period can be the average values of the temperature and rainfall in the target area from 24:00 on June 30, 2032 to 24:00 on July 31, 2032.

[0068] In some embodiments, the object platform 250 can obtain the weather characteristics of the target area in the future time period based on the terminal device.

[0069] The time event characteristics of the target area in the future time period refer to the important events that affect the power consumption in the future time period of the target area. In some embodiments, the time event characteristics of the target area in the future time period can be the holiday characteristics (i.e., the total number of holidays in the future time period). For example, during holidays, most people will be at home, and the power consumption in the urban area may increase. Therefore, the total number of holidays in the future time period of the target area can be used as the time event characteristics in the future time period. In some embodiments, the time event characteristics of the target area in the future time period can be the regional event characteristics (i.e., the events that may cause changes in power consumption in the future time period of the area). For example, if a new policy is introduced in the target area and the electricity price will decrease next month, the power consumption in the area may increase next month. Therefore, such regional events that affect the power consumption can be quantified as a power consumption impact value as the time event characteristics of the target area in the future time period.

[0070] The power consumption impact value refers to the degree of impact on power consumption. In some embodiments, the power consumption impact value can be a numerical value that can reflect the degree of impact on power consumption. For example, the power consumption impact value can be a value between -10 and 10. A positive value can be taken for events that cause an increase in power consumption, and a negative value can be taken for events that cause a decrease in power consumption. The larger the absolute value of the power consumption impact value, the higher the degree of impact on power consumption. In some embodiments, the power consumption impact value can be determined based on human experience.

[0071] In some embodiments, the object platform 250 can obtain the time event characteristics of the target area in the future time period based on the terminal device.

[0072] The basic economic development characteristics of the current time period refer to the basic data of the economic development of the target area in the current time period. For example, if the current time is 24:00 on June 30, 2032, the basic economic development characteristics of the target area in the current time period can be the total GDP, per capita GDP, education level, per capita tax, etc. of the target area from 24:00 on May 31, 2032 to 24:00 on June 30, 2032.

[0073] In some embodiments, the object platform 250 may obtain the basic economic development characteristics of the target area for the current time period based on the terminal device.

[0074] Step 320: Based on the weather characteristics of the target area for the future time period, the time event characteristics of the target area for the future time period, and the basic economic development characteristics of the target area for the current time period, predict the per capita domestic electricity consumption of the target area for the future time period through an electricity consumption prediction model.

[0075] The per capita domestic electricity consumption of the target area for the future time period refers to the average domestic electricity consumption per person in the target area for the future time period. For example, if the current time is 24:00 on June 30, 2032, the per capita domestic electricity consumption of the target area for the future time period may be the predicted average domestic electricity consumption per person in the target area from 24:00 on June 30, 2032 to 24:00 on July 31, 2032.

[0076] In some embodiments, the government power supply regulation and management platform 230 may predict the per capita domestic electricity consumption of the target area for the future time period through an electricity consumption prediction model based on the weather characteristics of the target area for the future time period, the time event characteristics of the target area for the future time period, and the basic economic development characteristics of the target area for the current time period.

[0077] In some embodiments, after inputting the weather characteristics of the target area for the future time period, the time event characteristics of the target area for the future time period, and the basic economic development characteristics of the target area for the current time period into the electricity consumption prediction model, the electricity consumption prediction model may predict the per capita domestic electricity consumption of the target area for the future time period. In some embodiments, the input of the electricity consumption prediction model may further include the number of people quarantined in the target area due to the epidemic during the future time period.

[0078] The electricity consumption prediction model may be a Deep Neural Networks (DNN), a Recurrent Neural Network (RNN), a Convolutional Neural Networks (CNN), etc. For more information about the electricity consumption prediction model, reference may be made to other parts of this specification (e.g., Figure 5 and its related descriptions), which will not be elaborated here.

[0079] Step 330: Determine the power supply strategy for the target area for the future time period based on the per capita domestic electricity consumption of the target area for the future time period.

[0080] The power supply strategy for the target area in the future time period refers to the power supply plan for the target area in the future time period. In some embodiments, the power supply strategy for the target area in the future time period may include a preset maximum per capita living power consumption and the subsidy amount for saving a unit of power (for example, the subsidy amount for saving one degree of power). Among them, the preset maximum per capita living power consumption is a threshold set artificially. When the per capita living power consumption of a certain household in the target area in the future time period is lower than the preset maximum per capita living power consumption, the subsidy amount is determined based on the difference between the actual value of the per capita living power consumption of the household and the preset maximum per capita living power consumption (for example, for every degree of power saved, the household is subsidized with the subsidy amount for saving one degree of power). For example, the power supply strategy for the target area in the future time period may be that the preset maximum per capita living power consumption is 300 degrees, and for every degree of power saved in the actual per capita living power consumption compared to the preset maximum per capita living power consumption, a subsidy of 20 cents is provided.

[0081] In some embodiments, the government power supply regulation and management platform 230 may determine the power supply strategy for the target area in the future time period based on the per capita living power consumption of the target area in the future time period. For more content on determining the power supply strategy, reference can be made to other parts of this specification (for example, Figure 4 and its related descriptions), which will not be elaborated here.

[0082] Step 340, determine the target power supply strategy for the target area in the future time period based on the per capita living power consumption of the target area in the future time period.

[0083] The target power supply strategy refers to the finally determined power supply strategy.

[0084] In some embodiments, the government power supply regulation and management platform 230 may determine the target power supply strategy for the target area in the future time period based on the reduction rate corresponding to each group of the candidate power supply strategies. For more content on determining the target power supply strategy, reference can be made to other parts of this specification (for example, Figure 4 and its related descriptions), which will not be elaborated here.

[0085] By predicting the per capita living power consumption in the future time period, an accurate preset maximum per capita living power consumption and the subsidy amount for saving a unit of power are determined, and the electricity subsidy is reasonably distributed to the public. More scientific government power supply regulation is achieved, prompting the public to save energy, reducing the power supply gap, and alleviating the pressure on power supply.

[0086] Figure 4 is an exemplary flowchart of the method for determining the target power supply strategy for the target area in the future time period according to some embodiments of this specification. As Figure 4 shown, process 400 includes the following steps. In some embodiments, process 400 may be executed by the government power supply regulation and management platform 230.

[0087] Step 410: Obtain multiple sets of power supply strategies for the target area in the future time period as candidate power supply strategies.

[0088] A candidate power supply strategy refers to a strategy to be selected as the target power supply strategy. In some embodiments, there may be multiple sets of candidate power supply strategies. For example, candidate power supply strategy 1 may be that the preset maximum per capita living electricity consumption is 300 degrees, and for every degree saved in the actual per capita living electricity consumption compared to the preset maximum per capita living electricity consumption, a subsidy of 20 cents is given. Candidate power supply strategy 2 may be that the preset maximum per capita living electricity consumption is 290 degrees, and for every degree saved in the actual per capita living electricity consumption compared to the preset maximum per capita living electricity consumption, a subsidy of 20 cents is given. Candidate power supply strategy 1 may be that the preset maximum per capita living electricity consumption is 280 degrees, and for every degree saved in the actual per capita living electricity consumption compared to the preset maximum per capita living electricity consumption, a subsidy of 30 cents is given. Candidate power supply strategy 1 may be that the preset maximum per capita living electricity consumption is 270 degrees, and for every degree saved in the actual per capita living electricity consumption compared to the preset maximum per capita living electricity consumption, a subsidy of 30 cents is given.

[0089] In some embodiments, the government power supply regulation and management platform 230 may adjust the per capita living electricity consumption in the target area in the future time period based on multiple preset reduction amplitudes to determine the preset maximum per capita living electricity consumption.

[0090] The preset reduction amplitude refers to the pre-set reduction amplitude. For example, the preset reduction amplitude may be 10 degrees. When the predicted per capita living electricity consumption in the target area in the future time period is 300 degrees, the preset maximum per capita living electricity consumption may be 300 degrees, 290 degrees, 280 degrees, and 270 degrees (assuming that according to historical data, the number of people with an actual per capita living electricity consumption lower than 260 degrees is lower than a certain threshold (e.g., 5%), then if it is set below 260 degrees, it is almost impossible for citizens to reach, and thus it cannot achieve the purpose of encouraging citizens to save electricity). Another example, the preset reduction amplitude may be 5 degrees. When the predicted per capita living electricity consumption in the target area in the future time period is 300 degrees, the preset maximum per capita living electricity consumption may be 300 degrees, 295 degrees, 290 degrees, 285 degrees, 280 degrees, 275 degrees, 270 degrees, and 265 degrees.

[0091] In some embodiments, the government power supply regulation and management platform 230 may adjust a preset reduction amplitude based on the confidence level of the power consumption prediction model. The lower the confidence level of the power consumption prediction model, the greater the preset reduction amplitude can be, and the minimum value of the preset maximum per capita living power consumption can be appropriately reduced. For example, the predicted per capita living power consumption in the target area for a future time period by the power consumption prediction model is 300 degrees, but its confidence level is low (e.g., 60%). This indicates that there is likely to be a large deviation between the per capita power consumption in the next month and 300 degrees without implementing the power supply strategy. Therefore, when generating a candidate power supply strategy, the preset reduction amplitude can be increased, and the minimum value of the preset maximum per capita living power consumption can be appropriately reduced (e.g., when the predicted per capita living power consumption in the target area for a future time period is 300 degrees, the preset reduction amplitude can be 20 degrees, and the minimum value of the preset maximum per capita living power consumption is set to 240 degrees).

[0092] In some embodiments, assuming that the power consumption prediction model has just been trained, the accuracy rate of the power consumption prediction model on the training set can be used as the confidence level of the power consumption prediction model. In some embodiments, assuming that the power consumption prediction model has not just been trained, the average value of the prediction deviations in several previous time periods can be used as the confidence level of the power consumption prediction model. Among them, the prediction deviation in a certain time period is the difference between the predicted per capita living power consumption in that time period and the actual per capita living power consumption in that time period, accounting for the proportion of the predicted per capita living power consumption in that time period. For example, if the power consumption prediction model predicts that the per capita power consumption in a certain time period is 300 degrees, and the actual per capita living power consumption in that time period is 270 degrees, then the prediction deviation is (300 - 270) / 300 = 10%.

[0093] In some embodiments, the government power supply regulation and management platform 230 may determine the subsidy amount for saving a unit of power based on whether the target area is economically developed, the electricity price in the target area, and the set preset maximum per capita living power consumption. For example, the more economically developed the target area is (i.e., the relatively lower the importance attached to the subsidy amount), and the lower the electricity price is (i.e., the worse the awareness of saving electricity), the higher the subsidy amount for saving a unit of power can be. For another example, the lower the set preset maximum per capita living power consumption is (i.e., the more difficult it is to reach below the preset maximum per capita living power consumption), the higher the subsidy amount for saving a unit of power can be.

[0094] Step 420, based on each group of candidate power supply strategies and the per capita living power consumption in the target area for a future time period, predict the reduction rate corresponding to each group of candidate power supply strategies through an effect prediction model.

[0095] The reduction rate refers to the ratio of the reduction in per capita domestic electricity consumption in the target area during a future time period by implementing a candidate power supply strategy. For example, the predicted per capita domestic electricity consumption in the target area during a future time period through an electricity consumption prediction model is 300 degrees. The candidate power supply strategy implemented can be a preset maximum per capita domestic electricity consumption of 300 degrees, and for every degree of electricity saved in actual per capita domestic electricity consumption compared to the preset maximum per capita domestic electricity consumption, a subsidy of 20 cents is provided. After implementing this candidate power supply strategy, the actual per capita domestic electricity consumption during this time period is 270 degrees, then the reduction rate is: (300 - 270) / 300 = 10%.

[0096] In some embodiments, based on each group of candidate power supply strategies and the per capita domestic electricity consumption in the target area during a future time period, the reduction rate corresponding to each group of candidate power supply strategies can be predicted through an effect prediction model.

[0097] In some embodiments, after inputting each group of candidate power supply strategies and the per capita domestic electricity consumption in the target area during a future time period into the effect prediction model, the reduction rate corresponding to each group of candidate power supply strategies can be predicted by the effect prediction model. In some embodiments, the input of the effect prediction model can further include the basic economic development characteristics of the target area during the current time period.

[0098] The effect prediction model can be a neural network model (e.g., models such as CNN, RNN, DNN, etc.). For more content about the electricity consumption prediction model, reference can be made to other parts of this specification (e.g., Figure 7 and its related descriptions), which will not be elaborated here.

[0099] Step 430, based on the reduction rate corresponding to each group of candidate power supply strategies, determine the target power supply strategy for the target area during a future time period.

[0100] In some embodiments, the government power supply regulation and management platform 230 can determine the total subsidy amount corresponding to each group of candidate power supply strategies based on each group of candidate power supply strategies. Then, the plan with the total subsidy amount not exceeding the threshold of the total subsidy amount and the maximum reduction rate is used as the target power supply strategy for the target area during a future time period. Among them, the threshold of the total subsidy amount can be a threshold determined based on the financial situation of this area.

[0101] The total subsidy amount refers to the total amount of subsidies after implementing the power supply strategy in the target area during a future time period. In some embodiments, the total subsidy amount corresponding to the candidate power supply strategy can be determined based on the total subsidy electricity quantity corresponding to the candidate power supply strategy. For example, assume that the total subsidy electricity quantity after implementing a certain group of candidate power supply strategies in a certain city is 10,000 degrees, and assume that 1 yuan is subsidized for 1 degree of electricity, then the total subsidy amount after implementing the candidate power supply strategy in this city is 10,000 yuan.

[0102] In some embodiments, the government power supply regulation and management platform 230 may determine the total subsidized electricity quantity corresponding to the candidate power supply strategy based on the formula Q = (x - y) × n + Q1.

[0103] Where Q is the total subsidized electricity quantity corresponding to the candidate power supply strategy, x is the preset maximum per capita domestic electricity consumption corresponding to the candidate power supply strategy, y is the per capita domestic electricity consumption in the target area during the future time period, n is the number of people in the target area, and Q1 is the total electricity quantity exceeding the preset maximum per capita domestic electricity consumption corresponding to the candidate power supply strategy.

[0104] Where y can be obtained based on the reduction rate. For example, if the per capita domestic electricity consumption predicted by the electricity consumption prediction model in the target area during the future time period is 300 and the reduction rate predicted by the effect prediction model is 10%, then y = 300 * (1 - 10%) = 270. Q1 can be obtained based on historical data. For example, since people who exceed the preset maximum per capita domestic electricity consumption value attach relatively less importance to subsidies. Therefore, the average value of the total electricity quantity exceeding the preset maximum per capita domestic electricity consumption corresponding to the candidate power supply strategy in the same month in the past three years can be used as Q1.

[0105] Since the per capita domestic electricity consumption should decrease after the candidate power supply strategy is implemented, theoretically, x should be greater than y. In some embodiments, when the total electricity quantity Q1 exceeding the preset maximum per capita domestic electricity consumption corresponding to the candidate power supply strategy is 0, Q = (x - y) × n. Since Q1 = 0, the formula for the total subsidized electricity quantity corresponding to the candidate power supply strategy can be: Q = (x - y) × n + Q1. For example, assume n = 3, x = 280, y = 270 (the domestic electricity consumption of the first person in the future time period is 280 degrees, the domestic electricity consumption of the second person in the future time period is 260 degrees, and the domestic electricity consumption of the third person in the future time period is 270 degrees), then Q1 = 0, Q = (280 - 270) × 3 + 0 = 30 degrees.

[0106] In some embodiments, when the total power Q1 exceeding the preset maximum per capita living power consumption corresponding to the candidate power supply strategy is greater than 0, since the total power Q1 exceeding the preset maximum per capita living power consumption corresponding to the candidate power supply strategy offsets part of the power that should be subsidized. Therefore, the total subsidy power corresponding to the candidate power supply strategy calculated by Q = (x - y) × n is on the small side. The total subsidy power corresponding to the candidate power supply strategy should also be added with the total power Q1 exceeding the preset maximum per capita living power consumption corresponding to the candidate power supply strategy. That is, the formula for determining the total subsidy power corresponding to the candidate power supply strategy should be: Q = (x - y) × n + Q1. For example, assume n = 3, x = 280, y = 270 (the living power consumption of the first person in the future time period is 300 degrees, the living power consumption of the second person in the future time period is 310 degrees, and the living power consumption of the third person in the future time period is 200 degrees), then Q1 = (300 - 280) + (310 - 280) = 50 degrees, Q = (280 - 270) × 3 + 50 = 80 degrees.

[0107] Predict the reduction rate corresponding to each group of candidate power supply strategies through the effect prediction model, and then determine the target power supply strategy with the highest reduction rate within the threshold range of the total subsidy amount. Economically and efficiently reduces the pressure on power supply.

[0108] Figure 5 It is a schematic diagram of the power consumption prediction model structure 500 shown in some embodiments of this specification.

[0109] In some embodiments, such as Figure 5 shown, the input of the power consumption prediction model 520 may include the weather characteristics 510-1 of the target area in the future time period, the time event characteristics 510-2 of the target area in the future time period, and the basic economic development characteristics 510-3 of the target area in the current time period, and the output is the per capita living power consumption 530 of the target area in the future time period.

[0110] In some embodiments, such as Figure 5 shown, the input of the power consumption prediction model 520 may also include the number of people quarantined due to the epidemic in the target area in the future time period 510-4. Because people quarantined due to the epidemic stay at home for a long time, it will lead to an increase in power consumption. Therefore, the input of the power consumption prediction model should also consider the number of people quarantined due to the epidemic in the target area in the future time period.

[0111] In some embodiments, the power supply control and management platform can determine the number of people quarantined due to the epidemic in the target area in the future time period through the epidemic prediction model based on the number of positive cases of the new coronavirus etiology detection, the number of asymptomatic infections, the number of symptomatic infections, the number of medium and high-risk areas, and the epidemic prevention and control measures in the target area at the current time period. For more content about the epidemic prediction model, reference can be made to other parts of this specification (for example,Figure 6 and its related descriptions) will not be elaborated here.

[0112] In some embodiments, as Figure 5 shown, the parameters of the electricity consumption prediction model 520 can be obtained by training with multiple sets of labeled first training samples 540. In some embodiments, multiple sets of first training samples 540 can be obtained, and each set of first training samples 540 can include multiple training data and the labels corresponding to the training data. The training data can include the weather characteristics of the target area in the historical future time period, the time event characteristics of the target area in the historical future time period, and the basic economic development characteristics of the target area in the historical current time period. The label of the training data can be the actual per capita living electricity consumption in the historical future time period. The parameters of the initial electricity consumption prediction model 550 can be updated through multiple sets of first training samples 540 to obtain the trained electricity consumption prediction model 520.

[0113] In some embodiments, the parameters of the initial electricity consumption prediction model 550 can be iteratively updated based on multiple first training samples 540 to make the loss function of the model meet the preset conditions. For example, the loss function converges, or the value of the loss function is less than the preset value. When the loss function meets the preset conditions, the model training is completed, and the trained initial electricity consumption prediction model 550 is obtained. Among them, the electricity consumption prediction model 520 and the trained initial electricity consumption prediction model 550 have the same model structure.

[0114] In some embodiments, when the input of the electricity consumption prediction model 520 further includes the number of people quarantined due to the epidemic in the future time period of the target area 510-4. Correspondingly, the first training samples 540 can further include the number of people quarantined due to the epidemic in the historical future time period of the target area.

[0115] Through the prediction of the per capita living electricity consumption in the future time period by the electricity consumption prediction model, the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period can be used as the input of the electricity consumption prediction model. And by combining the interrelated prediction results of the number of people quarantined due to the epidemic in the future time period of the target area, the prediction of the per capita living electricity consumption in the future time period by the electricity consumption prediction model is more accurate.

[0116] Figure 6 is a schematic diagram of the epidemic prediction model structure 600 shown in some embodiments of this specification.

[0117] In some embodiments, the epidemic prediction model can be a neural network model (for example, models such as CNN, RNN, DNN, etc.).

[0118] In some embodiments, as Figure 6As shown, the inputs of the epidemic prediction model 620 may include the number 610-1 of positive cases in the etiological detection of the novel coronavirus in the target area during the current time period, the number 610-2 of asymptomatic infections, the number 610-3 of symptomatic infections, the number 610-4 of medium- and high-risk areas, and the epidemic prevention and control measures 610-5, and the output is the number 510-4 of people quarantined due to the epidemic in the target area during the future time period.

[0119] In some embodiments, the epidemic prediction model 620 may include an epidemic feature extraction layer 620-1 and a quarantined population prediction layer 620-2.

[0120] In some embodiments, the epidemic feature extraction layer 620-1 may determine an epidemic feature vector 630 based on the number 610-1 of positive cases in the etiological detection of the novel coronavirus in the target area during the current time period, the number 610-2 of asymptomatic infections, the number 610-3 of symptomatic infections, the number 610-4 of medium- and high-risk areas, and the epidemic prevention and control measures 610-5. The epidemic feature vector 630 is a feature vector characterizing the epidemic features. In some embodiments, the epidemic feature extraction layer 620-1 may be a CNN.

[0121] In some embodiments, the quarantined population prediction layer 620-2 may predict the number 510-4 of people quarantined due to the epidemic in the target area during the future time period based on the epidemic feature vector 630. In some embodiments, the quarantined population prediction layer 620-2 may be a DNN.

[0122] In some embodiments, the epidemic feature extraction layer 620-1 and the quarantined population prediction layer 620-2 may be jointly trained based on training samples to update the parameters.

[0123] In some embodiments, the epidemic prediction model 620 may be obtained by training based on historical epidemic data. The historical epidemic data includes the number of positive cases in the etiological detection of the novel coronavirus, the number of asymptomatic infections, the number of symptomatic infections, the number of medium- and high-risk areas, and the epidemic prevention and control measures during the historical current time period. The number of positive cases in the etiological detection of the novel coronavirus, the number of asymptomatic infections, the number of symptomatic infections, the number of medium- and high-risk areas, and the epidemic prevention and control measures during the historical current time period may be used as training samples. The label of the training sample may be the actual number of people quarantined due to the epidemic in the historical future time period of the target area. Specifically, the second training sample 640 with a label is input into the initial epidemic prediction model 650, and the parameters of the initial epidemic prediction model 650 are updated through training. When the trained model meets the preset conditions, the training ends, and the trained epidemic prediction model 620 is obtained.

[0124] Predict the number of people quarantined due to the epidemic in the target area in the future time period through the epidemic prediction model, and obtain the parameters of the epidemic prediction model through the joint training method, which is beneficial to solving the problem of difficult to obtain labels when training the epidemic feature extraction layer alone. Secondly, jointly training the epidemic feature extraction layer and the quarantine population prediction layer can not only reduce the number of samples required, but also improve the training efficiency.

[0125] Figure 7 It is a schematic diagram of the effect prediction model structure 700 shown according to some embodiments of this specification.

[0126] In some embodiments, such as Figure 7 shown, the input of the effect prediction model 720 may include a set of candidate power supply strategies 710-1 and the per capita living electricity consumption 710-2 in the target area in the future time period, and the output is the reduction rate 730 corresponding to this set of candidate power supply strategies.

[0127] In some embodiments, such as Figure 7 shown, the input of the effect prediction model 720 may further include the basic economic development characteristics 510-3 of the target area in the current time period. Because if the basic economic development of the target area in the current time period is good, the emphasis on the subsidy amount is relatively low, which will lead to poor implementation effects of the power supply policy. Therefore, the input of the effect prediction model should also consider the basic economic development characteristics of the target area in the current time period.

[0128] In some embodiments, such as Figure 7 shown, the parameters of the effect prediction model 720 can be obtained through training with multiple sets of labeled third training samples 740. In some embodiments, multiple sets of third training samples 740 can be obtained, and each set of third training samples 740 may include multiple training data and the labels corresponding to the training data. The training data may include the power supply strategies in the historical future time period and the per capita living electricity consumption in the historical future time period of the target area. The label of the training data may be the actual reduction rate in the historical future time period. The parameters of the initial effect prediction model 750 can be updated through multiple sets of third training samples 740 to obtain the trained effect prediction model 720.

[0129] In some embodiments, the parameters of the initial effect prediction model 750 can be iteratively updated based on multiple third training samples 740 to make the loss function of the model meet the preset conditions. For example, the loss function converges, or the value of the loss function is less than the preset value. When the loss function meets the preset conditions, the model training is completed to obtain the trained initial effect prediction model 750. Among them, the effect prediction model 720 and the trained initial effect prediction model 750 have the same model structure.

[0130] In some embodiments, when the input of the effect prediction model 720 further includes the basic economic development characteristics 510-3 of the target area in the current time period, correspondingly, the third training sample 740 may further include the basic economic development characteristics of the target area in the historical current time period.

[0131] Through the prediction of the reduction rate corresponding to each group of the candidate power supply strategies by the effect prediction model, each group of candidate power supply strategies and the per capita domestic electricity consumption in the future time period of the target area can be used as the input of the effect prediction model. Combining the prediction results related to the basic economic development characteristics of the target area in the current time period can make the effect prediction model predict the reduction rate corresponding to each group of the candidate power supply strategies more accurately.

[0132] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

[0133] Meanwhile, this specification uses specific terms to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification is not necessarily the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0134] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numbers, letters, or other names in this specification is not used to limit the order of the processes and methods in this specification. Although some currently useful invention embodiments are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0135] Similarly, it should be noted that, in order to simplify the description disclosed in this specification and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, sometimes multiple features are incorporated into one embodiment, drawing or description thereof. However, this disclosure method does not mean that the features required by the object of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0136] In some embodiments, numbers are used to describe components and the quantity of attributes. It should be understood that such numbers used to describe the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the said numbers allow a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and such approximate values may vary according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their scope are approximate values, in specific embodiments, such numerical settings are as precise as possible within the feasible range.

[0137] For each patent, patent application, patent application publication and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification by reference. Except for the application history documents that are inconsistent with or conflict with the content of this specification, and except for the documents that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0138] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered to be consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for predicting electricity consumption in a smart city, characterized in that, The method is executed by a government power supply regulation and management platform, and the method includes: Obtaining the weather characteristics of the target area in a future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period; Based on the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period, predicting the per capita domestic electricity consumption of the target area in the future time period through an electricity consumption prediction model, where the electricity consumption prediction model is at least one of a deep neural network, a recurrent neural network, and a convolutional neural network; the per capita domestic electricity consumption of the target area in the future time period is used to determine the power supply strategy of the target area in the future time period; where The electricity consumption prediction model is obtained through a training process, and the training process includes: Obtaining a plurality of training samples and their labels, where the plurality of training samples include the weather characteristics of the target area in the historical future time period, the time event characteristics of the target area in the historical future time period, and the basic economic development characteristics of the target area in the historical current time period, and the labels include the actual per capita domestic electricity consumption in the historical future time period; and Training an initial electricity consumption prediction model based on the plurality of training samples to obtain the electricity consumption prediction model; The method further includes: Determining the target power supply strategy of the target area in the future time period based on the per capita domestic electricity consumption of the target area in the future time period; The determining the target power supply strategy of the target area in the future time period based on the per capita domestic electricity consumption of the target area in the future time period includes: Obtaining multiple groups of power supply strategies of the target area in the future time period as candidate power supply strategies; Based on each group of the candidate power supply strategies and the per capita domestic electricity consumption of the target area in the future time period, predicting the reduction rate corresponding to each group of the candidate power supply strategies through an effect prediction model; Based on each group of the candidate power supply strategies, determining the total subsidy amount corresponding to each group of the candidate power supply strategies; Determining the candidate power supply strategy with the largest reduction rate and a total subsidy amount less than the subsidy amount threshold among the multiple groups of the candidate power supply strategies as the target power supply strategy of the target area in the future time period; the effect prediction model is obtained through a training process, and the training process includes: Obtaining a plurality of training samples and their labels, where the plurality of training samples include the power supply strategies in the historical future time period and the per capita domestic electricity consumption of the target area in the historical future time period, and the labels include the actual reduction rate in the historical future time period; and Training an initial effect prediction model based on the plurality of training samples to obtain the effect prediction model.

2. The method according to claim 1, wherein The input of the electricity consumption prediction model further includes the number of people quarantined due to the epidemic in the target area in the future time period.

3. The method according to claim 1, characterized in that, The input of the effect prediction model further includes the basic economic development characteristics of the target area in the current time period.

4. The method according to claim 1, wherein The obtaining the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period includes: The government power supply regulation and management platform obtains the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period through the government sensing network platform based on the object platform; wherein, the object platform is configured to include a smart meter and a terminal device.

5. An electricity consumption prediction system for a smart city, characterized in that, The system includes a user platform, a government service platform, a government power supply regulation and management platform, a government sensing network platform, and an object platform that interact in sequence. The government power supply regulation and management platform is configured to perform the following operations: Obtain the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period; Based on the weather characteristics of the target area in the future time period, the time event characteristics of the target area in the future time period, and the basic economic development characteristics of the target area in the current time period, predict the per capita living electricity consumption of the target area in the future time period through an electricity consumption prediction model, where the electricity consumption prediction model is at least one of a deep neural network, a recurrent neural network, and a convolutional neural network; the per capita living electricity consumption of the target area in the future time period is used to determine the power supply strategy of the target area in the future time period; wherein The electricity consumption prediction model is obtained through a training process, and the training process includes: Obtain a plurality of training samples and their labels. The plurality of training samples include the weather characteristics of the target area in the historical future time period, the time event characteristics of the target area in the historical future time period, and the basic economic development characteristics of the target area in the historical current time period. The labels include the actual per capita living electricity consumption in the historical future time period; and Based on the plurality of training samples, train the initial electricity consumption prediction model to obtain the electricity consumption prediction model; The government power supply regulation and management platform is further configured to perform the following operations: Based on the per capita living electricity consumption of the target area in the future time period, determine the target power supply strategy of the target area in the future time period; The government power supply regulation and management platform is further configured to perform the following operations: Obtain multiple sets of power supply strategies for the target area in the future time period as candidate power supply strategies; Based on each set of the candidate power supply strategies and the per capita living electricity consumption of the target area in the future time period, predict the reduction rate corresponding to each set of the candidate power supply strategies through an effect prediction model; Based on each set of the candidate power supply strategies, determine the total subsidy amount corresponding to each set of the candidate power supply strategies; Determine the candidate power supply strategy with the largest reduction rate and a total subsidy amount less than the subsidy amount threshold among the multiple sets of candidate power supply strategies as the target power supply strategy of the target area in the future time period; the government power supply regulation and management platform is further configured to perform the following operations: Obtain a plurality of training samples and their labels. The plurality of training samples include the power supply strategies in the historical future time period and the per capita living electricity consumption of the target area in the historical future time period. The labels include the actual reduction rate in the historical future time period; and Train an initial effect prediction model based on the multiple training samples to obtain the effect prediction model.

6. An electricity consumption prediction device for a smart city, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least some of the computer instructions to implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 4.

Images