Green power consumption and carbon asset collaborative management system based on block chain

Abstract

The invention relates to a block chain-based green power consumption and carbon asset collaborative management system, provides a carbon emission transaction, and belongs to the field of purchasing, selling or leasing transactions. An intelligent joint prediction model of a set geographic area is adopted to intelligently predict green power supply data of a future time segment and carbon emission data of each electricity consumption enterprise; the upper chain evidence storage device writes the intelligent prediction data into the block chain network; and the contract generation device is used for automatically matching and forming a carbon transaction contract of each electricity consumption enterprise based on the intelligent prediction data. According to the invention, for the technical problems that the overall level of green power consumption and carbon asset collaborative management is insufficient and the performance is low, the same intelligent joint prediction model can be adopted to complete synchronous intelligent prediction of green power generation data and carbon emission data, and then automatic matching is carried out to form each carbon transaction contract. And meanwhile, the uplink evidence storage of the key data is executed, so that the technical problem is solved.

Description

TECHNICAL FIELD

[0001] The carbon emission transaction provided by the present application belongs to the field of purchase, sale or lease transaction, and particularly relates to a green power consumption and carbon asset collaborative management system based on a block chain. BACKGROUND

[0002] With the increasing scale of various types of new energy power generation, new energy power generation has begun to surpass coal power and become the largest clean energy power generation system, which can provide green power required by each power consumption enterprise. Under the background of large-scale development of new energy power generation, the importance of high-level consumption of large-scale renewable energy is increasingly highlighted. At the same time, how to realize carbon neutralization processing of carbon emissions of each power consumption enterprise while consuming large-scale renewable energy, such as designing carbon emission transactions matching carbon emissions of each power consumption enterprise to help achieve high-level carbon neutralization management goals, is also one of the important tasks to promote regional economic green and low-carbon transformation.

[0003] For example, the Chinese invention patent publication CN118115312A proposes a power system clearing method for promoting green power consumption and related device, which comprises: obtaining a day-ahead operation plan of a power system, a real-time prediction increment of green power, a green power overcharge curve willing to be sold by a power generation side, and a green power overcharge curve willing to be purchased by a user side; performing real-time clearing of the power system according to the day-ahead operation plan, the real-time prediction increment of green power, the green power overcharge curve willing to be sold by the power generation side, and the green power overcharge curve willing to be purchased by the user side, with the maximization of green power revenue as the optimization target, to obtain a real-time operation plan of the power system. Through the green power overcharge curve willing to be sold by the power generation side and the green power overcharge curve willing to be purchased by the user side, the real-time prediction increment of green power is reasonably distributed, the accurate matching of green power generation and load side power consumption is realized, the green power consumption and new type power system construction are better promoted, the carbon emissions are reduced, and the environmental pollution is reduced.

[0004] For example, the Chinese invention patent publication CN118036882A proposes a green power consumption certification and carbon emission monitoring and accounting linkage mechanism, which determines the carbon emission accounting range according to the logistics business activities of a power grid enterprise; establishes a carbon-green certificate joint transaction model considering the conditional value at risk; establishes a power equipment logistics space carbon emission total amount accounting model; and a green certificate management institution verifies the sampling data in the database by using a block chain, and issues a green certificate if the sampling data is true. After introducing high-load enterprise load as demand side response, the green certificate yield, wind power utilization rate and net income of the system have been improved to a certain extent.

[0005] Clearly, the aforementioned existing technologies primarily focus on the collaborative management of green electricity consumption and carbon assets from a commercial perspective. They do not address the high-level green electricity consumption and advanced carbon neutrality management within the same geographical region based on green electricity supply data and carbon emission data from electricity-consuming enterprises. Furthermore, the future segmentation of green electricity supply data and carbon emission data from electricity-consuming enterprises may involve different AI models for intelligent prediction, requiring numerous AI models. Additionally, the lack of secure and reliable network storage for the green electricity supply data and carbon emission data obtained through intelligent prediction raises concerns about the potential leakage of critical data. Finally, the signing of carbon trading contracts for green electricity consumption and carbon neutrality management by various electricity-consuming enterprises is generally done manually, consuming significant labor and time costs. Therefore, the overall level of collaborative management of green electricity consumption and carbon assets in existing technologies is insufficient and inefficient. Summary of the Invention

[0006] To address the technical problems in existing technologies, this invention provides a blockchain-based collaborative management system for green electricity consumption and carbon assets. For the same designated geographical area, a single intelligent joint prediction model with a customized structure for that area is used to synchronously and intelligently predict green power generation data from green power generation enterprises and carbon emission data from various household power companies, representing a future time segment. Based on the intelligent prediction data, carbon trading contracts are automatically matched and formed between the green power generation enterprises and each household power company. Equally important, the hash values ​​and compressed data of the green power generation data, carbon emission data, and carbon trading contracts are written into the blockchain network, forming verifiable and tamper-proof on-chain data. This improves the automation and intelligence levels of collaborative management of green electricity consumption and carbon assets in different geographical areas while ensuring the security and reliability of such management.

[0007] According to a first aspect of the present invention, a blockchain-based collaborative management system for green electricity consumption and carbon assets is provided, the system comprising: The directional acquisition device is used to collect power generation data curves and power generation configuration parameters of green power generation enterprises within a set geographical area in the most recent time segment based on 10-minute granularity, so as to serve as the directional acquisition data of green power generation enterprises within the set geographical area in the most recent time segment. Information analysis device, used to analyze the carbon asset association information of each household appliance enterprise within a specified geographical area in the most recent time segment; The joint prediction device is connected to the directional acquisition device and the information analysis device respectively. It is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the area of ​​the set geographical region, the duration of the most recent time segment, the directional acquisition data of green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment for a set geographical region. The on-chain evidence storage device, connected to the joint prediction device, is used to synchronously write the hash value and compressed data of the intelligent prediction data into the blockchain network, forming verifiable and tamper-proof on-chain prediction data. The contract generation device connects to the blockchain network to read on-chain prediction data from the blockchain network to obtain intelligent prediction data, and automatically matches and forms carbon trading contracts between green power generation companies and household electricity companies for the current time segment.

[0008] According to a second aspect of the present invention, a blockchain-based green electricity consumption and carbon asset collaborative management system is provided. The system includes a memory and multiple processors. The memory stores a computer program configured to be executed by the multiple processors to complete the following steps: Collect power generation data curves and power generation configuration parameters of green power generation enterprises within a set geographical area in the most recent time segment based on 10-minute granularity, so as to serve as the directional data collection data of green power generation enterprises within the set geographical area in the most recent time segment; Analyze the carbon asset association information of each household appliance enterprise within a specified geographical area in the most recent time segment; For a given geographical area, the intelligent joint prediction model corresponding to the given geographical area is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the area of ​​the given geographical area, the duration of the most recent time segment, the data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment. The hash value and compressed data of the intelligent prediction data are synchronously written into the blockchain network to form verifiable and tamper-proof on-chain prediction data. Intelligent prediction data is obtained by reading on-chain prediction data from the blockchain network, and based on the intelligent prediction data, carbon trading contracts are automatically matched and formed between green power generation companies and household electricity companies for the current time segment.

[0009] Therefore, it can be seen that the present invention has at least the following prominent substantive features: Substantial Feature A: It replaces the two sets of artificial intelligence models that perform separate intelligent predictions for green power generation data and carbon emission data, and adopts the same set of artificial intelligence models, namely the intelligent joint prediction model, to complete the synchronous intelligent prediction of green power generation data of green power generation enterprises and carbon emission data of household power generation enterprises in the same geographical area. This fully utilizes the correlation of power generation and consumption data and the consistency of basic information in the same geographical area, reduces the number and redundancy of artificial intelligence models, and improves the speed and accuracy of intelligent prediction. Substantive Feature B: The system uses green power generation data from green power generation companies and carbon emission data from household appliance companies within the same geographical area, obtained through intelligent forecasting, as intelligent forecasting data. The hash value and compressed data of the intelligent forecasting data are synchronously written into the blockchain network to form verifiable and tamper-proof on-chain forecasting data. Furthermore, when carbon trading contracts are automatically matched and formed between green power generation companies and household appliance companies based on the intelligent forecasting data, the hash value and compressed data of each carbon trading contract are also synchronously written into the blockchain network to form verifiable and tamper-proof on-chain transaction data. This enhances the security of green power generation data, carbon emission data, and carbon trading contracts. Substantive Feature C: After completing the synchronous intelligent prediction of green power supply data of green power generation enterprises in the same geographical area for the current time segment (which is a future time segment) and carbon emission data of each household power enterprise for the current time segment, the green power supply data and carbon emission data obtained by intelligent prediction are automatically matched and formed into carbon trading contracts between green power generation enterprises and each household power enterprise respectively. Specifically, for each household power enterprise, in the automatically matched carbon trading contract for the current time segment, the green power consumption data allocated to the power enterprise is equal to the carbon emission data of the power enterprise in the current time segment. Before each carbon trading contract is automatically matched and formed, it is determined based on the intelligent prediction data whether green power for the current time segment needs to be called from green power generation enterprises in the nearby geographical area, thereby improving the automation and intelligence level of green power consumption and carbon asset collaborative management in different geographical areas. Substantive Feature D: To achieve synchronous intelligent prediction of green power generation data from green power generation enterprises and carbon emission data from household appliance enterprises within the same geographical region, different intelligent joint prediction models with customized structures for different geographical regions are introduced. Specifically, the intelligent joint prediction model with customized structure for a given geographical region is a convolutional neural network that has undergone multiple learning iterations, and the number of learning iterations is positively correlated with the area of ​​the given geographical region. The convolutional neural network includes a single input layer, multiple convolutional layers, multiple pooling layers, and a single fully connected layer. The convolutional layers of the convolutional neural network use the ReLU activation function, and the number of convolutional layers in the convolutional neural network has the same numerical trend as the number of household appliance enterprises within the given geographical region. The customized structural design of the above-mentioned intelligent joint prediction model ensures the effectiveness and stability of the intelligent prediction results. Substantive Feature E: In each learning iteration of the convolutional neural network, the green power supply data of green power generation enterprises in a certain historical time segment and the carbon emission data of each household power enterprise in the same historical time segment are used as two outputs of the convolutional neural network. The area of ​​the set geographical region, the duration of the time segment preceding the historical time segment, the directional data collected by green power generation enterprises in the time segment preceding the historical time segment, and the carbon asset association information of each household power enterprise in the time segment preceding the historical time segment are used as multiple inputs of the convolutional neural network to complete the learning process, thereby ensuring the learning effectiveness of each convolutional neural network iteration. Substantive Feature F: To achieve synchronized intelligent prediction of green power generation data from green power generation enterprises and carbon emission data from household appliance enterprises within the same geographical area, several basic information elements are introduced, including the geographical area, the duration of the most recent time segment, the data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household appliance enterprise in the most recent time segment. The targeted screening of these basic information elements further ensures the effectiveness and stability of the intelligent prediction results. Substantive Feature G: Specifically, the data collected from green power generation enterprises within a geographic area in the most recent time segment is defined as three power generation data curves based on 10-minute granularity for photovoltaic, wind power, and hydropower respectively within the most recent time segment of the geographic area, as well as three sets of power generation configuration parameters corresponding to photovoltaic power generation equipment, wind power generation equipment, and hydropower generation equipment respectively. The carbon asset association information of each household electricity enterprise within a geographic area in the most recent time segment is defined as each household electricity enterprise within a geographic area in the most recent time segment, based on 10-minute granularity carbon emission data curve and each household electricity enterprise in the most recent time segment, thereby providing a customized data structure for multiple basic information for intelligent prediction. Attached Figure Description

[0010] The embodiments of the present invention will now be described with reference to the accompanying drawings, wherein: Figure 1 This is a schematic diagram illustrating the working principle of a blockchain-based collaborative management system for green electricity consumption and carbon assets according to the present invention.

[0011] Figure 2 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to a first embodiment of the present invention.

[0012] Figure 3 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to a second embodiment of the present invention.

[0013] Figure 4 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to a third embodiment of the present invention.

[0014] Figure 5 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to a fourth embodiment of the present invention.

[0015] Figure 6 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to the fifth embodiment of the present invention.

[0016] Figure 7 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to the sixth embodiment of the present invention. Detailed Implementation

[0017] like Figure 1 The diagram illustrates the working principle of a blockchain-based collaborative management system for green electricity consumption and carbon assets, as presented in this invention. The carbon emission trading proposed in this invention falls under the category of purchase, sale, or lease transactions.

[0018] The specific technical process of this invention is as follows: Technical Process 1: A customized intelligent joint prediction model is designed for a specific geographical area to simultaneously and intelligently predict green power generation data from green power generation enterprises and carbon emission data from various household appliance manufacturers within that area. Figure 1 As shown; There are two key points here: First, replace the two separate AI models that perform separate intelligent predictions for green power generation data and carbon emission data, and adopt the same AI model, namely the intelligent joint prediction model, to complete the synchronous intelligent prediction of green power generation data of green power generation enterprises and carbon emission data of household power generation enterprises in the same geographical area; Second, design intelligent joint prediction models with different customized structures for different geographical areas to ensure the effectiveness and stability of the synchronous intelligent prediction results of green power generation data and carbon emission data. Specifically, regarding the first key point, the operation mode of a single artificial intelligence model can make full use of the correlation between power generation and consumption data and the consistency of basic information within the same geographical area, thereby reducing the number and redundancy of artificial intelligence models and improving the speed and accuracy of intelligent prediction. Specifically, regarding the second key point, an intelligent joint prediction model is set up for the corresponding geographical region, and the structural customization is mainly reflected in the following aspects: Aspect A: The intelligent joint prediction model corresponding to the set geographical area is a convolutional neural network that has been trained multiple times, and the number of training times is positively correlated with the area of ​​the set geographical area. For example, when the geographical area is set to 1000 square kilometers, the number of times of learning is selected is 500; when the geographical area is set to 1200 square kilometers, the number of times of learning is selected is 600; when the geographical area is set to 1400 square kilometers, the number of times of learning is selected is 700; when the geographical area is set to 1600 square kilometers, the number of times of learning is selected is 800, and so on. Aspect B: The convolutional neural network used includes a single input layer, multiple convolutional layers, multiple pooling layers, and a single fully connected layer. The convolutional layers of the convolutional neural network use the ReLU activation function, and the number of convolutional layers in the convolutional neural network has the same numerical trend as the number of household appliance companies in the set geographical area. For example, if the number of household appliance companies in a geographical area is set to 500, the number of convolutional layers in the convolutional neural network is 1; if the number of household appliance companies in a geographical area is set to 1000, the number of convolutional layers in the convolutional neural network is 2; if the number of household appliance companies in a geographical area is set to 1500, the number of convolutional layers in the convolutional neural network is 3; if the number of household appliance companies in a geographical area is set to 2000, the number of convolutional layers in the convolutional neural network is 4, and so on. Aspect C: In each learning process of the convolutional neural network, the green power supply data of green power generation enterprises in a certain historical time segment and the carbon emission data of each household power enterprise in the same historical time segment are used as two output contents of the convolutional neural network. The area of ​​the set geographical region, the duration of the time segment before the specified historical time segment, the directional data collected by green power generation enterprises in the time segment before the specified historical time segment, and the carbon asset association information of each household power enterprise in the time segment before the specified historical time segment are used as multiple input contents of the convolutional neural network to complete the learning process, thereby ensuring the learning effect of the convolutional neural network in each learning process. Specifically, carbon assets refer to tradable resources generated under the carbon emission trading mechanism that can directly or indirectly affect greenhouse gas emissions. They mainly include two categories: carbon emission allowances allocated by the government and carbon credits obtained by enterprises through emission reduction projects. In this invention, carbon assets refer to the carbon emission data of various household electricity companies, which are generally controlled below the carbon emission allowances of the management department. When implementing carbon neutrality and management, these carbon emission data belong to the neutralization target of green power consumption. Therefore, they are a kind of carbon asset in the sense of green power consumption. In this way, the effectiveness and stability of the intelligent prediction results are guaranteed through the customized structural design of various aspects of the intelligent joint prediction model. Technical Process 2: To achieve synchronized intelligent prediction of green power generation data from green power generation enterprises and carbon emission data from various household appliance enterprises within the same geographical area, several basic information items were introduced; Specifically, such as Figure 1 As shown, the various basic information includes the area of ​​the set geographical region, the duration of the most recent time segment, the data collected by green power generation companies in the most recent time segment, and the carbon asset association information of each household power company in the most recent time segment. More specifically, the data collected from green power generation enterprises within a geographical area in the most recent time segment is defined as three power generation data curves based on 10-minute granularity for photovoltaic, wind power, and hydropower respectively within the most recent time segment of the geographical area, as well as three power generation configuration parameters corresponding to photovoltaic power generation equipment, wind power generation equipment, and hydropower generation equipment respectively. The carbon asset association information of each household electricity enterprise within a geographical area in the most recent time segment is defined as each household electricity enterprise within a geographical area in the most recent time segment, based on 10-minute granularity carbon emission data curve and each household electricity enterprise in the most recent time segment, thereby providing a customized data structure for multiple basic information for intelligent prediction. In this way, the effectiveness and stability of the intelligent prediction results are further guaranteed through targeted screening of the above-mentioned basic information. Technical Process Three: Using the intelligent joint prediction model with a customized structure designed for the specified geographical area in Technical Process One, and based on multiple basic information selectively selected in Technical Process Two, synchronous intelligent prediction is completed for the green power generation data of green power generation enterprises and the carbon emission data of various household power generation enterprises within the specified geographical area in the current time segment, which is considered a future time segment. Figure 1 As shown; Specifically, the most recent time segment ends at the current time and its duration is a multiple of 10 minutes, while the current time segment begins at the current time and its duration is equal to the duration of the most recent time segment. Technical Process 4: The green power generation data of green power generation enterprises and the carbon emission data of each household appliance enterprise within the designated geographical area obtained by intelligent prediction in Technical Process 3 are used as intelligent prediction data. The hash value and compressed data of the intelligent prediction data are synchronously written into the blockchain network to form verifiable and tamper-proof on-chain prediction data. Technical Process Five: Access the blockchain network to decrypt and obtain the intelligent prediction data stored on-chain in Technical Process Four, and automatically match and merge the corresponding carbon trading contracts between green power generation companies and various household electricity companies based on the intelligent prediction data. Figure 1 As shown; Specifically, for each electricity consumer, in the carbon trading contract automatically matched and formed for the current time segment, the green electricity consumption data allocated to the electricity consumer is equal to the carbon emission data of the electricity consumer in the current time segment, and before each carbon trading contract is automatically matched and formed, it is determined based on intelligent prediction data whether it is necessary to call green electricity from green power generation enterprises in the nearby geographical area to serve the current time segment. This improves the automation and intelligence levels of green electricity consumption and carbon asset collaborative management in different geographical regions; Technical Process Six: Simultaneously write the hash values ​​and compressed data of each carbon trading contract obtained in Technical Process Five into the blockchain network to form verifiable and tamper-proof on-chain transaction data. In this way, while improving the automation and intelligence level of green power consumption and carbon asset collaborative management in different geographical regions, the safety and reliability of green power consumption and carbon asset collaborative management in different geographical regions are also improved. Therefore, through the collaboration of the above-mentioned technical processes, a single artificial intelligence model can be used to complete the synchronous intelligent prediction of green power generation data from green power generation enterprises and carbon emission data from various household power enterprises. Based on the synchronous intelligent prediction results, carbon trading contracts for each household power enterprise that meet the needs of green power consumption and carbon neutrality and management requirements can be automatically generated. Furthermore, the synchronous intelligent prediction results and the carbon trading contracts of each household power enterprise can be stored on the blockchain for evidence, thereby improving the automation, intelligence, security, and reliability of green power consumption and carbon asset collaborative management in different geographical regions.

[0019] The key points of this invention are: the effective replacement of two separate artificial intelligence models for the simultaneous intelligent prediction of green power generation data and carbon emission data by the same artificial intelligence model; the automatic generation of carbon trading contracts based on the results of simultaneous intelligent prediction that simultaneously meet the needs of green power consumption and carbon neutrality and management requirements; the on-chain storage of key data on the blockchain; and the separate design of artificial intelligence models with different customized structures for different geographical regions.

[0020] The following will describe in detail an embodiment of the blockchain-based green power consumption and carbon asset collaborative management system of the present invention. Example

[0021] Figure 2 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to a first embodiment of the present invention.

[0022] like Figure 2 As shown, the blockchain-based green electricity consumption and carbon asset collaborative management system includes the following components: The directional acquisition device is used to collect power generation data curves and power generation configuration parameters of green power generation enterprises within a set geographical area in the most recent time segment based on 10-minute granularity, so as to serve as the directional acquisition data of green power generation enterprises within the set geographical area in the most recent time segment. Specifically, the most recent time segment ends at the current time and the duration of the most recent time segment is a multiple of 10 minutes. This ensures that the obtained power generation data curve based on 10-minute granularity is the complete power generation data for each time interval, and the duration of each time interval is 10 minutes. Specifically, the division of geographical regions can be based on the administrative division of cities or the predefined division of city clusters. A city cluster generally consists of a central city and multiple satellite cities, with the satellite cities surrounding the central city. Specifically, carbon assets refer to tradable resources generated under the carbon emission trading mechanism that can directly or indirectly affect greenhouse gas emissions. They mainly include two categories: carbon emission allowances allocated by the government and carbon credits obtained by enterprises through emission reduction projects. In this invention, carbon assets refer to the carbon emission data of various household electricity companies, which are generally controlled below the carbon emission allowances of the management department. When implementing carbon neutrality and management, these carbon emission data belong to the neutralization target of green power consumption. Therefore, they are a kind of carbon asset in the sense of green power consumption. Information analysis device, used to analyze the carbon asset association information of each household appliance enterprise within a specified geographical area in the most recent time segment; Specifically, each household appliance enterprise within a geographical region is defined as an electricity-consuming enterprise within that geographical region that has carbon neutrality and management needs and that emits carbon. The joint prediction device is connected to the directional acquisition device and the information analysis device respectively. It is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the area of ​​the set geographical region, the duration of the most recent time segment, the directional acquisition data of green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment for a set geographical region. Here, a single artificial intelligence model, namely the intelligent joint prediction model, can be used to complete the synchronous intelligent prediction of green power supply data and carbon emission data, thereby reducing the number and redundancy of artificial intelligence models and improving the speed and accuracy of intelligent prediction. The on-chain evidence storage device, connected to the joint prediction device, is used to synchronously write the hash value and compressed data of the intelligent prediction data into the blockchain network, forming verifiable and tamper-proof on-chain prediction data. Here, the on-chain evidence storage mechanism of the blockchain network enhances the security and reliability of key data for green power consumption and carbon asset collaborative management; The contract generation device connects to the blockchain network and is used to read on-chain prediction data from the blockchain network to obtain intelligent prediction data. Based on the intelligent prediction data, it automatically matches and forms carbon trading contracts between green power generation companies and various household electricity companies for the current time segment. Specifically, the automatic matching and formation of various carbon trading contracts is the core inventive point of this application. It replaces the manual formulation and signing mode in the prior art, and improves the automation and intelligence level of green power consumption and carbon asset collaborative management while meeting the needs of green power consumption and corporate carbon neutrality and management requirements. The carbon trading contracts between green power generation companies and household electricity companies that are automatically matched and formed based on intelligent forecast data for the current time segment include: the intelligent forecast data are the green power supply data of green power generation companies in the current time segment and the carbon emission data of household electricity companies in the current time segment; and for each household electricity company, the green power consumption data allocated to the electricity company in the automatically matched carbon trading contract for the current time segment is equal to the carbon emission data of the electricity company in the current time segment. Obviously, the above steps are based on the premise that the green power supply data of green power generation enterprises in the current time segment meets the carbon neutrality and management requirements of each household power generation enterprise in the current time segment. If the green power supply data is insufficient relative to the carbon neutrality and management requirements, it is necessary to call up green power from green power generation enterprises in nearby geographical areas in advance. Among them, the most recent time segment ends at the current time and its duration is a multiple of 10 minutes, while the current time segment starts at the current time and its duration is equal to the duration of the most recent time segment. For example, if the current time is 11:00 AM, then the most recent time segment is from 10:10 AM to 11:00 AM, and the current time segment is from 11:00 AM to 11:50 AM. The duration of both the most recent time segment and the current time segment is 50 minutes, which is a multiple of 10 minutes. The process of collecting power generation data curves and power generation configuration parameters of green power generation enterprises within a designated geographical area in the most recent time segment, based on a 10-minute granularity, and serving as the directional data collection for green power generation enterprises within the designated geographical area in the most recent time segment, includes: collecting three sets of power generation data curves based on a 10-minute granularity for photovoltaic, wind power, and hydropower respectively, and three sets of power generation configuration parameters for photovoltaic power generation equipment, wind power generation equipment, and hydropower generation equipment respectively, for green power generation enterprises within the designated geographical area in the most recent time segment; For example, three different parameter acquisition units can be used to collect three sets of power generation configuration parameters corresponding to photovoltaic power generation equipment, wind power generation equipment and hydropower generation equipment respectively; Among them, the analysis of carbon asset association information of each household appliance enterprise in the set geographical area in the most recent time segment includes: collecting carbon emission data curves based on 10-minute granularity for each household appliance enterprise in the set geographical area in the most recent time segment, as well as electricity configuration parameters for each household appliance enterprise, to serve as carbon asset association information of each household appliance enterprise in the set geographical area in the most recent time segment. Among them, the on-chain evidence storage device is also used to synchronously write the hash value and compressed data of each carbon trading contract into the blockchain network to form verifiable and tamper-proof on-chain transaction data. Among them, the intelligent joint prediction model corresponding to the set geographical area is a convolutional neural network that has been learned multiple times, and the number of learning times is positively correlated with the area of ​​the set geographical area. The convolutional neural network includes a single input layer, multiple convolutional layers, multiple pooling layers and a single fully connected layer. For example, the intelligent joint prediction model corresponding to the set geographical area is a convolutional neural network that has been trained multiple times, and the number of training times is positively correlated with the area of ​​the set geographical area, including: when the area of ​​the set geographical area is 1000 square kilometers, the number of training times is 500; when the area of ​​the set geographical area is 1200 square kilometers, the number of training times is 600; when the area of ​​the set geographical area is 1400 square kilometers, the number of training times is 700; when the area of ​​the set geographical area is 1600 square kilometers, the number of training times is 800, and so on. In the convolutional neural network, a single input layer, multiple convolutional layers, multiple pooling layers, and a single fully connected layer are sequentially connected. The convolutional layers of the convolutional neural network use the ReLU activation function, and the number of convolutional layers in the convolutional neural network has the same numerical trend as the number of household appliance companies in the set geographical area. For example, the number of convolutional layers in a convolutional neural network having the same numerical trend as the number of household appliance companies in a given geographical area includes: 1 convolutional layer for 500 household appliance companies in the given geographical area; 2 convolutional layers for 1000 household appliance companies in the given geographical area; 3 convolutional layers for 1500 household appliance companies in the given geographical area; 4 convolutional layers for 2000 household appliance companies in the given geographical area; and so on. In each learning iteration of the convolutional neural network, the green power supply data of green power generation enterprises in a certain historical time segment and the carbon emission data of each household power enterprise in the same historical time segment are used as two outputs of the convolutional neural network. The area of ​​the set geographical region, the duration of the time segment preceding the specified historical time segment, the directional data collected by green power generation enterprises in the time segment preceding the specified historical time segment, and the carbon asset association information of each household power enterprise in the time segment preceding the specified historical time segment are used as multiple inputs of the convolutional neural network to complete this learning process.

[0023] Second Embodiment Figure 3 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to a second embodiment of the present invention.

[0024] like Figure 3 As shown, compared to Figure 2 The blockchain-based green electricity consumption and carbon asset collaborative management system also includes: The dynamic calling device, connected to the blockchain network, is used to determine, based on intelligent predictive data, whether green electricity needs to be called from green power generation companies in the nearby geographical area to serve the current time segment before each carbon trading contract is automatically matched and formed. For example, an ASIC chip can be used to implement a dynamic calling device, which determines, based on intelligent forecast data, whether green electricity needs to be called from green power generation companies in the nearby geographic area to serve the current time segment before each carbon trading contract is automatically matched and formed. Before each carbon trading contract is automatically matched and formed, determining whether it is necessary to draw green electricity from green power generation enterprises in the nearby geographical area to serve the current time segment based on intelligent prediction data includes: accumulating the carbon emission data of each household electricity enterprise in the set geographical area for the current time segment to obtain the combined carbon emission data of the current time segment in the set geographical area, and determining that it is necessary to draw green electricity from green power generation enterprises in the nearby geographical area to serve the current time segment of each household electricity enterprise in the set geographical area when the combined carbon emission data of the current time segment in the set geographical area is greater than the green electricity supply data of green power generation enterprises in the set geographical area for the current time segment; Before each carbon trading contract is automatically matched and formed, determining whether green electricity needs to be drawn from green power generation companies in the nearby geographical area to serve the current time segment, based on intelligent forecast data, also includes: the supply data of the green electricity to be drawn is the difference between the combined carbon emission data of the current time segment in the set geographical area and the green electricity supply data of the green power generation companies in the set geographical area in the current time segment.

[0025] Third Embodiment Figure 4 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to a third embodiment of the present invention.

[0026] like Figure 4 As shown, compared to Figure 2 The blockchain-based green electricity consumption and carbon asset collaborative management system also includes: The object construction device is connected to the joint prediction device to perform multiple learning operations on the convolutional neural network to obtain the convolutional neural network after multiple learning operations and output it as the intelligent joint prediction model corresponding to the set geographical area. The object construction device also has a built-in model storage module, which is used to store the intelligent joint prediction model corresponding to the set geographical area. For example, the object construction device also has a built-in model storage module for storing the intelligent joint prediction model corresponding to the set geographical area. The model storage module uses multiple physical storage addresses to store the various model parameters of the intelligent joint prediction model corresponding to the set geographical area.

[0027] Fourth embodiment Figure 5 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to a fourth embodiment of the present invention.

[0028] like Figure 5 As shown, compared to Figure 2 The blockchain-based green electricity consumption and carbon asset collaborative management system also includes: The timing server is connected to the directional acquisition device and the information parsing device respectively, and is used to provide the timing service signals required by the directional acquisition device and the information parsing device respectively. The timing server device is connected to the directional acquisition device and the information analysis device respectively, and is used to provide the timing service signals required by the directional acquisition device and the information analysis device respectively. The timing server device has a built-in quartz oscillator unit, which is used to provide a reference pulse waveform for the generation of timing service signals. For example, the timing server device has a built-in quartz oscillator unit for providing a reference pulse waveform for the generation of the timing service signal, including: the reference pulse waveform is a square waveform of a preset frequency.

[0029] Fifth Embodiment Figure 6 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to the fifth embodiment of the present invention.

[0030] like Figure 6 As shown, compared to Figure 2 The blockchain-based green electricity consumption and carbon asset collaborative management system also includes: The regional management device is connected to the directional acquisition device and the information parsing device respectively, and is used to perform configuration management for green power generation enterprises and household power enterprises in each geographical area; Among them, the regional management device is connected to the directional acquisition device and the information parsing device respectively, and is used to perform configuration management of green power generation enterprises and household appliance enterprises in each geographical area. The regional management device has a built-in user input interface, which is used to complete the configuration operation of green power generation enterprises and household appliance enterprises in each geographical area under the user operation. For example, different area numbers can be set for different geographical regions to distinguish between them.

[0031] Next, various embodiments of the present invention will be further described.

[0032] Optionally, within the blockchain-based green electricity consumption and carbon asset collaborative management system described above: The power generation configuration parameters corresponding to photovoltaic power generation equipment include the number of photovoltaic panels, the surface area of ​​a single photovoltaic panel, the latitude and longitude of the installation location, the average sunshine duration, and the maximum incident light intensity. The power generation configuration parameters corresponding to wind power generation equipment include the number of generator sets, the rated output power of a single generator set, the latitude and longitude of the installation location, the average wind speed, and the maximum wind speed. The power generation configuration parameters corresponding to hydropower generation equipment include the number of generator sets, the rated output power of a single generator set, the latitude and longitude of the installation location, the average water level drop, and the maximum flow velocity. Specifically, the latitude and longitude of the installation location are represented by the longitude data and the latitude data of the installation location; Among them, the power configuration parameters corresponding to each household appliance enterprise are the number of electrical appliances of that household appliance enterprise, the daily power consumption duration, the average rated output power of each electrical appliance, and the maximum rated output power of each electrical appliance. The intelligent joint prediction model corresponding to the set geographical area is a convolutional neural network that has been trained multiple times, and the number of training times is positively correlated with the area of ​​the set geographical area. The convolutional neural network includes a single input layer, multiple convolutional layers, multiple pooling layers, and a single fully connected layer. The content transformation function is used to represent the content transformation relationship between the number of training times and the area of ​​the set geographical area. For example, the implementation process of the content conversion function can be simulated and tested using the MATLAB toolbox; The content conversion relationship, which uses a content conversion function to represent the positive correlation between the number of learning sessions and the area of ​​a set geographical region, includes: in the content conversion function, the area of ​​the set geographical region is the input content of the content conversion function, and the number of learning sessions that is positively correlated with the area of ​​the set geographical region is the output content of the content conversion function.

[0033] And, optionally, within the aforementioned embodiments, in the blockchain-based green electricity consumption and carbon asset collaborative management system: For a given geographical area, an intelligent joint prediction model corresponding to that geographical area is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the geographical area, the duration of the most recent time segment, the directional data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment. This includes: inputting the intelligent joint prediction model corresponding to the given geographical area in parallel with the geographical area, the duration of the most recent time segment, the directional data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment. For example, programmable logic devices can be used to implement a smart joint prediction model for a set geographical area based on the area of ​​the set geographical area, the duration of the most recent time segment, the data collected by green power generation companies in the most recent time segment, and the carbon asset association information of each household power company in the most recent time segment. Specifically, for a given geographical area, the intelligent joint prediction model corresponding to that geographical area is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the area of ​​the given geographical area, the duration of the most recent time segment, the directional data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment. This also includes: running the intelligent joint prediction model corresponding to the given geographical area to obtain the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment output by the intelligent joint prediction model corresponding to the given geographical area. The intelligent joint prediction model corresponding to the set geographical area includes multiple input ports and two output ports. The green power supply data of green power generation enterprises in the current time segment, the carbon emission data of each household power enterprise in the current time segment, the intelligent joint prediction model corresponding to the set geographical area based on the area of ​​the set geographical area, the duration of the most recent time segment, the directional data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment are all in a numerically normalized numerical representation. Specifically, the green power supply data of green power generation enterprises in the current time segment, the carbon emission data of each household power enterprise in the current time segment, the intelligent joint prediction model corresponding to the set geographical area, the duration of the most recent time segment, the directional data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment can all be represented in hexadecimal numerical form.

[0034] Sixth Embodiment Figure 7 This is an internal structure diagram of a blockchain-based green electricity consumption and carbon asset collaborative management system according to the sixth embodiment of the present invention.

[0035] like Figure 7 As shown, the multimedia content automatic generation and publishing system includes a memory and multiple processors. The memory stores a computer program, which is configured to be executed by the multiple processors to complete the following steps: Collect power generation data curves and power generation configuration parameters of green power generation enterprises within a set geographical area in the most recent time segment based on 10-minute granularity, so as to serve as the directional data collection data of green power generation enterprises within the set geographical area in the most recent time segment; Specifically, the most recent time segment ends at the current time and the duration of the most recent time segment is a multiple of 10 minutes. This ensures that the obtained power generation data curve based on 10-minute granularity is the complete power generation data for each time interval, and the duration of each time interval is 10 minutes. Specifically, the division of geographical regions can be based on the administrative division of cities or the predefined division of city clusters. A city cluster generally consists of a central city and multiple satellite cities, with the satellite cities surrounding the central city. Specifically, carbon assets refer to tradable resources generated under the carbon emission trading mechanism that can directly or indirectly affect greenhouse gas emissions. They mainly include two categories: carbon emission allowances allocated by the government and carbon credits obtained by enterprises through emission reduction projects. In this invention, carbon assets refer to the carbon emission data of various household electricity companies, which are generally controlled below the carbon emission allowances of the management department. When implementing carbon neutrality and management, these carbon emission data belong to the neutralization target of green power consumption. Therefore, they are a kind of carbon asset in the sense of green power consumption. Analyze the carbon asset association information of each household appliance enterprise within a specified geographical area in the most recent time segment; Specifically, each household appliance enterprise within a geographical region is defined as an electricity-consuming enterprise within that geographical region that has carbon neutrality and management needs and that emits carbon. For a given geographical area, the intelligent joint prediction model corresponding to the given geographical area is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the area of ​​the given geographical area, the duration of the most recent time segment, the data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment. Here, a single artificial intelligence model, namely the intelligent joint prediction model, can be used to complete the synchronous intelligent prediction of green power supply data and carbon emission data, thereby reducing the number and redundancy of artificial intelligence models and improving the speed and accuracy of intelligent prediction. The hash value and compressed data of the intelligent prediction data are synchronously written into the blockchain network to form verifiable and tamper-proof on-chain prediction data. Here, the on-chain evidence storage mechanism of the blockchain network enhances the security and reliability of key data for green power consumption and carbon asset collaborative management; The system reads on-chain prediction data from the blockchain network to obtain intelligent prediction data, and automatically matches and forms carbon trading contracts between green power generation companies and household electricity companies for the current time segment. Specifically, the automatic matching and formation of various carbon trading contracts is the core inventive point of this application. It replaces the manual formulation and signing mode in the prior art, and improves the automation and intelligence level of green power consumption and carbon asset collaborative management while meeting the needs of green power consumption and corporate carbon neutrality and management requirements. The carbon trading contracts between green power generation companies and household electricity companies that are automatically matched and formed based on intelligent forecast data for the current time segment include: the intelligent forecast data are the green power supply data of green power generation companies in the current time segment and the carbon emission data of household electricity companies in the current time segment; and for each household electricity company, the green power consumption data allocated to the electricity company in the automatically matched carbon trading contract for the current time segment is equal to the carbon emission data of the electricity company in the current time segment. Obviously, the above steps are based on the premise that the green power supply data of green power generation enterprises in the current time segment meets the carbon neutrality and management requirements of each household power generation enterprise in the current time segment. If the green power supply data is insufficient relative to the carbon neutrality and management requirements, it is necessary to call up green power from green power generation enterprises in nearby geographical areas in advance. Among them, the most recent time segment ends at the current time and its duration is a multiple of 10 minutes, while the current time segment starts at the current time and its duration is equal to the duration of the most recent time segment. For example, if the current time is 11:00 AM, then the most recent time segment is from 10:10 AM to 11:00 AM, and the current time segment is from 11:00 AM to 11:50 AM. The duration of both the most recent time segment and the current time segment is 50 minutes, which is a multiple of 10 minutes. The process of collecting power generation data curves and power generation configuration parameters of green power generation enterprises within a designated geographical area in the most recent time segment, based on a 10-minute granularity, and serving as the directional data collection for green power generation enterprises within the designated geographical area in the most recent time segment, includes: collecting three sets of power generation data curves based on a 10-minute granularity for photovoltaic, wind power, and hydropower respectively, and three sets of power generation configuration parameters for photovoltaic power generation equipment, wind power generation equipment, and hydropower generation equipment respectively, for green power generation enterprises within the designated geographical area in the most recent time segment; For example, three different parameter acquisition units can be used to collect three sets of power generation configuration parameters corresponding to photovoltaic power generation equipment, wind power generation equipment and hydropower generation equipment respectively; Among them, the analysis of carbon asset association information of each household appliance enterprise in the set geographical area in the most recent time segment includes: collecting carbon emission data curves based on 10-minute granularity for each household appliance enterprise in the set geographical area in the most recent time segment, as well as electricity configuration parameters for each household appliance enterprise, to serve as carbon asset association information of each household appliance enterprise in the set geographical area in the most recent time segment. Among them, the on-chain evidence storage device is also used to synchronously write the hash value and compressed data of each carbon trading contract into the blockchain network to form verifiable and tamper-proof on-chain transaction data. Among them, the intelligent joint prediction model corresponding to the set geographical area is a convolutional neural network that has been learned multiple times, and the number of learning times is positively correlated with the area of ​​the set geographical area. The convolutional neural network includes a single input layer, multiple convolutional layers, multiple pooling layers and a single fully connected layer. For example, the intelligent joint prediction model corresponding to the set geographical area is a convolutional neural network that has been trained multiple times, and the number of training times is positively correlated with the area of ​​the set geographical area, including: when the area of ​​the set geographical area is 1000 square kilometers, the number of training times is 500; when the area of ​​the set geographical area is 1200 square kilometers, the number of training times is 600; when the area of ​​the set geographical area is 1400 square kilometers, the number of training times is 700; when the area of ​​the set geographical area is 1600 square kilometers, the number of training times is 800, and so on. In the convolutional neural network, a single input layer, multiple convolutional layers, multiple pooling layers, and a single fully connected layer are sequentially connected. The convolutional layers of the convolutional neural network use the ReLU activation function, and the number of convolutional layers in the convolutional neural network has the same numerical trend as the number of household appliance companies in the set geographical area. For example, the number of convolutional layers in a convolutional neural network having the same numerical trend as the number of household appliance companies in a given geographical area includes: 1 convolutional layer for 500 household appliance companies in the given geographical area; 2 convolutional layers for 1000 household appliance companies in the given geographical area; 3 convolutional layers for 1500 household appliance companies in the given geographical area; 4 convolutional layers for 2000 household appliance companies in the given geographical area; and so on. In each learning iteration of the convolutional neural network, the green power supply data of green power generation enterprises in a certain historical time segment and the carbon emission data of each household power enterprise in the same historical time segment are used as two outputs of the convolutional neural network. The area of ​​the set geographical region, the duration of the time segment preceding the specified historical time segment, the directional data collected by green power generation enterprises in the time segment preceding the specified historical time segment, and the carbon asset association information of each household power enterprise in the time segment preceding the specified historical time segment are used as multiple inputs of the convolutional neural network to complete this learning process.

[0036] Furthermore, in a blockchain-based collaborative management system for green electricity consumption and carbon assets according to the present invention: In a convolutional neural network, a single input layer, multiple convolutional layers, multiple pooling layers, and a single fully connected layer are sequentially connected. The convolutional layers of the convolutional neural network use the ReLU activation function, and the number of convolutional layers in the convolutional neural network has the same numerical trend as the number of household appliance companies in a set geographical area. This includes: using a curve representing the number of companies to indicate the numerical trend of the number of household appliance companies in a set geographical area, and using a curve representing the number of layers to indicate the numerical trend of the number of convolutional layers in the convolutional neural network. Among them, the curve representing the change in the number of enterprises in a set geographical area is used to represent the numerical change trend of the number of household appliance enterprises, and the curve representing the change in the number of layers in a convolutional neural network is used to represent the numerical change trend of the number of convolutional layers in a convolutional neural network. This includes performing curve length normalization processing on the curve representing the change in the number of enterprises and the curve representing the change in the number of layers respectively, so as to obtain a normalized curve representing the number of enterprises and a normalized curve representing the number of layers of equal length. Among them, the use of the enterprise number change curve to represent the numerical change trend of the number of household appliance enterprises in the set geographical area, and the use of the layer number change curve to represent the numerical change trend of the number of convolutional layers in the convolutional neural network, also include: the enterprise number normalization processing curve and the layer number normalization processing curve of equal length completely overlap. For example, a GAL chip can be used to perform curve length normalization processing on the enterprise number change curve and the layer number change curve respectively, so as to obtain an equal-length enterprise number normalization curve and layer number normalization curve.

[0037] While the invention has been described in considerable detail, it should be understood that those skilled in the art can modify various devices therein without departing from the spirit and scope of the invention. It is believed that the system of the invention and its associated advantages will be understood from the foregoing description, and it will be clear that various changes can be made to its form, structure, and component arrangement without departing from the scope and spirit of the invention or sacrificing all its substantial advantages, and since the forms described above are merely illustrative embodiments of the invention, no other substantial changes are provided. The claims are intended to cover and include these changes.

Claims

1. A blockchain-based collaborative management system for green electricity consumption and carbon assets, characterized in that, The system includes: The directional acquisition device is used to collect power generation data curves and power generation configuration parameters of green power generation enterprises within a set geographical area in the most recent time segment based on 10-minute granularity, so as to serve as the directional acquisition data of green power generation enterprises within the set geographical area in the most recent time segment. Information analysis device, used to analyze the carbon asset association information of each household appliance enterprise within a specified geographical area in the most recent time segment; The joint prediction device is connected to the directional acquisition device and the information analysis device respectively. It is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the area of ​​the set geographical region, the duration of the most recent time segment, the directional acquisition data of green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment for a set geographical region. The on-chain evidence storage device, connected to the joint prediction device, is used to synchronously write the hash value and compressed data of the intelligent prediction data into the blockchain network, forming verifiable and tamper-proof on-chain prediction data. The contract generation device connects to the blockchain network to read on-chain prediction data from the blockchain network to obtain intelligent prediction data, and automatically matches and forms carbon trading contracts between green power generation companies and household electricity companies for the current time segment.

2. The blockchain-based green electricity consumption and carbon asset collaborative management system as described in claim 1, characterized in that: The carbon trading contracts automatically matched and formed based on intelligent forecast data between green power generation companies and household electricity companies for the current time segment include: the intelligent forecast data consists of green power supply data of green power generation companies for the current time segment and carbon emission data of household electricity companies for the current time segment; and for each household electricity company, the green power consumption data allocated to the electricity company in the automatically matched and formed carbon trading contract for the current time segment is equal to the carbon emission data of the electricity company for the current time segment. Among them, the most recent time segment ends at the current time and its duration is a multiple of 10 minutes, while the current time segment starts at the current time and its duration is equal to the duration of the most recent time segment. The process of collecting power generation data curves and power generation configuration parameters of green power generation enterprises within a designated geographical area in the most recent time segment, based on a 10-minute granularity, and serving as the directional data collection for green power generation enterprises within the designated geographical area in the most recent time segment, includes: collecting three sets of power generation data curves based on a 10-minute granularity for photovoltaic, wind power, and hydropower respectively, and three sets of power generation configuration parameters for photovoltaic power generation equipment, wind power generation equipment, and hydropower generation equipment respectively, for green power generation enterprises within the designated geographical area in the most recent time segment; Among them, the analysis of carbon asset association information of each household appliance enterprise in the set geographical area in the most recent time segment includes: collecting carbon emission data curves based on 10-minute granularity for each household appliance enterprise in the set geographical area in the most recent time segment, as well as electricity configuration parameters for each household appliance enterprise, to serve as carbon asset association information of each household appliance enterprise in the set geographical area in the most recent time segment. Among them, the on-chain evidence storage device is also used to synchronously write the hash value and compressed data of each carbon trading contract into the blockchain network, forming verifiable and tamper-proof on-chain transaction data.

3. The blockchain-based green electricity consumption and carbon asset collaborative management system as described in claim 2, characterized in that: The intelligent joint prediction model for the set geographical region is a convolutional neural network that has undergone multiple learning processes. The number of learning processes is positively correlated with the area of ​​the set geographical region. The convolutional neural network includes a single input layer, multiple convolutional layers, multiple pooling layers, and a single fully connected layer. In the convolutional neural network, a single input layer, multiple convolutional layers, multiple pooling layers, and a single fully connected layer are sequentially connected. The convolutional layers of the convolutional neural network use the ReLU activation function, and the number of convolutional layers in the convolutional neural network has the same numerical trend as the number of household appliance companies in the set geographical area. In each learning iteration of the convolutional neural network, the green power supply data of green power generation enterprises in a certain historical time segment and the carbon emission data of each household power enterprise in the same historical time segment are used as two outputs of the convolutional neural network. The area of ​​the set geographical region, the duration of the time segment preceding the specified historical time segment, the directional data collected by green power generation enterprises in the time segment preceding the specified historical time segment, and the carbon asset association information of each household power enterprise in the time segment preceding the specified historical time segment are used as multiple inputs of the convolutional neural network to complete this learning process.

4. The blockchain-based green electricity consumption and carbon asset collaborative management system as described in claim 3, characterized in that, The system also includes: The dynamic calling device, connected to the blockchain network, is used to determine, based on intelligent predictive data, whether green electricity needs to be called from green power generation companies in the nearby geographical area to serve the current time segment before each carbon trading contract is automatically matched and formed. Before each carbon trading contract is automatically matched and formed, determining whether it is necessary to draw green electricity from green power generation enterprises in the nearby geographical area to serve the current time segment based on intelligent prediction data includes: accumulating the carbon emission data of each household electricity enterprise in the set geographical area for the current time segment to obtain the combined carbon emission data of the current time segment in the set geographical area, and determining that it is necessary to draw green electricity from green power generation enterprises in the nearby geographical area to serve the current time segment of each household electricity enterprise in the set geographical area when the combined carbon emission data of the current time segment in the set geographical area is greater than the green electricity supply data of green power generation enterprises in the set geographical area for the current time segment; Before each carbon trading contract is automatically matched and formed, determining whether green electricity needs to be drawn from green power generation companies in the nearby geographical area to serve the current time segment, based on intelligent forecast data, also includes: the supply data of the green electricity to be drawn is the difference between the combined carbon emission data of the current time segment in the set geographical area and the green electricity supply data of the green power generation companies in the set geographical area in the current time segment.

5. The blockchain-based green electricity consumption and carbon asset collaborative management system as described in claim 3, characterized in that, The system also includes: The object construction device is connected to the joint prediction device to perform multiple learning operations on the convolutional neural network to obtain the convolutional neural network after multiple learning operations and output it as the intelligent joint prediction model corresponding to the set geographical area. The object construction device also has a built-in model storage module, which is used to store the intelligent joint prediction model corresponding to the set geographical area.

6. The blockchain-based green electricity consumption and carbon asset collaborative management system as described in claim 3, characterized in that, The system also includes: The timing server is connected to the directional acquisition device and the information parsing device respectively, and is used to provide the timing service signals required by the directional acquisition device and the information parsing device respectively. The timing server device is connected to the directional acquisition device and the information analysis device respectively, and is used to provide the timing service signals required by the directional acquisition device and the information analysis device respectively. The timing server device has a built-in quartz oscillator unit to provide a reference pulse waveform for the generation of timing service signals.

7. The blockchain-based green electricity consumption and carbon asset collaborative management system as described in claim 3, characterized in that, The system also includes: The regional management device is connected to the directional acquisition device and the information parsing device respectively, and is used to perform configuration management for green power generation enterprises and household power enterprises in each geographical area; The regional management device is connected to the directional acquisition device and the information parsing device, respectively, and is used to perform configuration management of green power generation enterprises and household appliance enterprises in each geographical area. The regional management device has a built-in user input interface, which is used to complete the configuration operation of green power generation enterprises and household appliance enterprises in each geographical area under the user's operation.

8. A blockchain-based green electricity consumption and carbon asset collaborative management system as described in any one of claims 3-7, characterized in that: The power generation configuration parameters corresponding to photovoltaic power generation equipment include the number of photovoltaic panels, the surface area of ​​a single photovoltaic panel, the latitude and longitude of the installation location, the average sunshine duration, and the maximum incident light intensity. The power generation configuration parameters corresponding to wind power generation equipment include the number of generator sets, the rated output power of a single generator set, the latitude and longitude of the installation location, the average wind speed, and the maximum wind speed. The power generation configuration parameters corresponding to hydropower generation equipment include the number of generator sets, the rated output power of a single generator set, the latitude and longitude of the installation location, the average water level drop, and the maximum flow velocity. Among them, the power configuration parameters corresponding to each household appliance enterprise are the number of electrical appliances of that household appliance enterprise, the daily power consumption duration, the average rated output power of each electrical appliance, and the maximum rated output power of each electrical appliance. The intelligent joint prediction model corresponding to the set geographical area is a convolutional neural network that has been trained multiple times, and the number of training times is positively correlated with the area of ​​the set geographical area. The convolutional neural network includes a single input layer, multiple convolutional layers, multiple pooling layers, and a single fully connected layer. The content transformation function is used to represent the content transformation relationship between the number of training times and the area of ​​the set geographical area. The content conversion relationship, which uses a content conversion function to represent the positive correlation between the number of learning sessions and the area of ​​a set geographical region, includes the following: In the content conversion function, the area of ​​the set geographical region is the input content of the content conversion function, and the number of learning sessions that is positively correlated with the area of ​​the set geographical region is the output content of the content conversion function.

9. A blockchain-based green electricity consumption and carbon asset collaborative management system as described in any one of claims 3-7, characterized in that: For a given geographical area, an intelligent joint prediction model corresponding to that geographical area is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the geographical area, the duration of the most recent time segment, the directional data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment. This includes: inputting the intelligent joint prediction model corresponding to the given geographical area in parallel with the geographical area, the duration of the most recent time segment, the directional data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment. Specifically, for a given geographical area, the intelligent joint prediction model corresponding to that geographical area is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the area of ​​the given geographical area, the duration of the most recent time segment, the directional data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment. This also includes: running the intelligent joint prediction model corresponding to the given geographical area to obtain the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment output by the intelligent joint prediction model corresponding to the given geographical area. The intelligent joint prediction model corresponding to the set geographical area includes multiple input ports and two output ports. The green power supply data of green power generation enterprises in the current time segment, the carbon emission data of each household power enterprise in the current time segment, the intelligent joint prediction model corresponding to the set geographical area based on the area of ​​the set geographical area, the duration of the most recent time segment, the directional data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment are all in a numerically normalized numerical representation.

10. A blockchain-based collaborative management system for green electricity consumption and carbon assets, the system comprising a memory and multiple processors, the memory storing a computer program configured to be executed by the multiple processors to complete the following steps: Collect power generation data curves and power generation configuration parameters of green power generation enterprises within a set geographical area in the most recent time segment based on 10-minute granularity, so as to serve as the directional data collection data of green power generation enterprises within the set geographical area in the most recent time segment; Analyze the carbon asset association information of each household appliance enterprise within a specified geographical area in the most recent time segment; For a given geographical area, the intelligent joint prediction model corresponding to the given geographical area is used to intelligently predict the green power supply data of green power generation enterprises in the current time segment and the carbon emission data of each household power enterprise in the current time segment based on the area of ​​the given geographical area, the duration of the most recent time segment, the data collected by green power generation enterprises in the most recent time segment, and the carbon asset association information of each household power enterprise in the most recent time segment. The hash value and compressed data of the intelligent prediction data are synchronously written into the blockchain network to form verifiable and tamper-proof on-chain prediction data. Intelligent prediction data is obtained by reading on-chain prediction data from the blockchain network, and based on the intelligent prediction data, carbon trading contracts are automatically matched and formed between green power generation companies and household electricity companies for the current time segment.

Images