Building seasonal HVAC carbon emission actuarial system integrating big data and blockchain
Through a building seasonal HVAC carbon emission actuarial system that integrates big data and blockchain, the LSTM and regression model are used to predict the carbon emission data of HVAC equipment and upload it to the blockchain, solving the carbon of HVAC equipment in buildings The problem of difficulty in obtaining emission data accurately has achieved guidance on optimization of HVAC and energy-saving measures.
Patent Information
- Application Number
- CN202411296753.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-18
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-09-18
AI Technical Summary
The carbon emission data of HVAC equipment in buildings is difficult to accurately obtain, resulting in the inability to optimize the operating mode and energy-saving measures of HVAC system.
Adopt a building seasonal HVAC carbon emission actuarial system that integrates big data and blockchain, and combines LSTM model and regression prediction model to generate carbon emission prediction values for seasonal alternating periods, and upload data to the blockchain to ensure the data Accuracy and traceability.
Accurate prediction of HVAC carbon emission data during different seasons and seasonal alternating periods is achieved, and the optimization of HVAC systems and guidance on energy-saving measures are supported.
Smart Images

Figure CN118839152B_ABST
Abstract
Description
Background Art
[0002] Usually, carbon emissions in some buildings (such as residential and office buildings) mainly come from the HVAC equipment therein. Such as central air conditioners, split air conditioners, floor heating, wall-mounted boilers and other related equipment used to maintain indoor temperature. The carbon emissions of these equipment are mainly reflected in the fact that they consume a lot of electricity or burn a corresponding amount of coal or natural gas and other resources during their work. However, usually in buildings such as residential and office buildings, during the operation of HVAC equipment, there will be many other equipment working at the same time, so it is impossible to obtain more accurate data on the electricity and coal consumption of HVAC equipment. As a result, it is impossible to accurately obtain the HVAC carbon emissions corresponding to the building. It is not convenient to provide guidance for the subsequent optimization of the HVAC system operation mode, or it is not convenient to provide guidance for the subsequent optimization of energy-saving measures for buildings in the corresponding area. Summary of the invention
[0003] In view of the above technical problems, the technical solution adopted by the present invention is:
[0004] According to one aspect of the present invention, a building seasonal HVAC carbon emission actuarial system integrating big data and blockchain is provided, and the system includes:
[0005] Data collection module, carbon emission calculation module and data upload module; the carbon emission calculation module is respectively connected to the data collection module and the data upload module; the data collection module is used to collect HVAC characteristic data corresponding to the target building; the carbon emission calculation module is used to obtain the carbon emission value of the target building according to the HVAC characteristic data; the data upload module is used to upload the carbon emission value to the preset blockchain;
[0006] The data acquisition module operates in the following steps:
[0007] Obtain spring carbon emission prediction model A1, summer carbon emission prediction model A2, autumn carbon emission prediction model A3 and winter carbon emission prediction model A4 corresponding to the area where the target building is located; A1, A2, A3 and A4 are all LSTM models;
[0008] According to the model weight values P1, P2, P3 and P4 corresponding to A1, A2, A3 and A4 respectively in the seasonal transition period, the carbon emission value W of the target building in the seasonal transition period is generated; W satisfies the following conditions:
[0009] W=P1×result1+P2×result2+P3×result3+P4×result4;
[0010] Among them, result1, result2, result3 and result4 are the carbon emission prediction values generated by A1, A2, A3 and A4 according to the collected emission time series data of the target building;
[0011] Among them, the model weight values P1, P2, P3 and P4 are generated according to the following steps:
[0012] According to the historical data corresponding to the seasonal alternation period, the emission verification time series data set B=(B1、B2、…、Bi、…、Bf(n)) corresponding to the seasonal alternation period is generated; where Bi is the i-th emission verification time series data in the seasonal alternation period, Bi=(B i 1, Ti), B i 1 is the HVAC characteristic data corresponding to the target building in the preset collection period during the seasonal transition period; Ti is B i 1 is the actual carbon emission value of the target building corresponding to 1; f(n) is the total number of emission verification time series data during the seasonal transition period, f(n)=1, 2, …, f(n);
[0013] Input B into A1, A2, A3 and A4 in sequence to generate four corresponding prediction sequences C1, C2, C3 and C4; among them, C1 is the prediction result sequence generated after inputting each emission verification time series data in B into A1 (T 1 1. T 1 2. ..., T 1 i, …, T 1 f(n)); C2 is the prediction result sequence generated after each emission verification time series data in B is input into A2 (T 2 1. T 2 2. ..., T 2 i, …, T 2 f(n)); C3 is the prediction result sequence generated after inputting each emission verification time series data in B into A3 (T 3 1. T 3 2. ..., T 3 i, …, T 3 f(n)); C4 is the prediction result sequence generated after each emission verification time series data in B is input into A4 (T 4 1. T 4 2. ..., T 4 i, …, T 4 f(n));
[0014] According to the carbon emission value in B and the predicted emission values in C1, C2, C3, and C4, the model weight values P1, P2, P3, and P4 corresponding to the seasonal transition period are generated; among which, P1, P2, P3, and P4 respectively meet the following conditions:
[0015] ; ; ; ;
[0016] ; ;
[0017] ; ;
[0018] in, , and They are the prediction deviation values corresponding to A1, A2, A3 and A4 respectively.
[0019] Furthermore, the emission time series data is a two-dimensional time series feature table; each line in the two-dimensional time series feature table obtains a feature sequence at a collection time in the collection period, and the feature sequence includes data of multiple feature dimensions; the two-dimensional time series feature table includes multiple feature sequences.
[0020] Furthermore, multiple feature dimensions include:
[0021] The indoor temperature value of the target building, the set temperature value of the HVAC equipment in the target building, and the outdoor temperature of the area to which the target building belongs.
[0022] Furthermore, the multiple feature dimensions also include:
[0023] Equipment type label, energy-saving grade, working mode label of HVAC equipment, practical area of the target building, location orientation, lighting area and number of indoor occupants.
[0024] Furthermore, the two-dimensional time series feature table is feature data acquired within a 24-hour collection period, and the collection cycle is 1 hour.
[0025] Furthermore, the spring carbon emission prediction model A1 corresponding to the area where the target building is located is obtained, including:
[0026] Generate training samples based on the emission time series data and corresponding carbon emission data collected during the spring period in the area where the target building is located;
[0027] The initial LSTM model is trained using the training samples to generate A1.
[0028] Furthermore, the spring period includes the period between the Beginning of Spring and the Spring Equinox.
[0029] Furthermore, after generating the corresponding four prediction sequences C1, C2, C3 and C4, the data acquisition module also operates according to the following steps:
[0030] Generate training samples based on the prediction results of the target building in C1, C2, C3 and C4 and the actual carbon emission value in B. The i-th training sample includes the sample sequence (T1 i. T 2 i. T 3 i. T 4 i) and sample label Ti;
[0031] Using the training samples, the initial feedforward neural network is trained to generate the corresponding regression prediction model.
[0032] Furthermore, the data acquisition module also operates according to the following steps:
[0033] The characteristic sequence formed by result1, result2, result3 and result4 is input into the regression prediction model to generate the carbon emission value W of the target building in the seasonal transition period.
[0034] Furthermore, the data upload module operates as follows:
[0035] The carbon emission value of the target building generated during each data collection period is encrypted, stored in the target storage system and a corresponding data ID is generated;
[0036] Generate a hash value corresponding to the encrypted carbon emission value of the target building, and upload the hash value and data ID to the preset blockchain.
[0037] The present invention has at least the following beneficial effects:
[0038] In actual use, the same area will have different temperatures in different seasons, and different HVAC equipment will be used accordingly. Based on this, the present invention sets different prediction models for different seasons, so that the carbon emission data of HVAC equipment in different seasons can be more accurately and carefully predicted according to the temperature characteristics of different seasons in the corresponding area.
[0039] In addition, during the seasonal transition period (such as the transition between spring and summer, summer and autumn, and autumn and winter), there are often large temperature changes, and the weather performance jumps back and forth between multiple seasons. Usually, the HVAC equipment used during this period is not a single device, and there may be a mixture of cooling and heating equipment. At this time, the corresponding single prediction model cannot capture the corresponding HVAC usage characteristics more accurately. In this embodiment, in order to more accurately predict the carbon emissions of HVAC equipment during the seasonal transition period, multiple prediction models are used to jointly predict, and then each prediction result is weighted and summed to obtain the final prediction result. Therefore, by combining the advantages of different models in capturing different HVAC characteristics, a more accurate carbon emission prediction result can be obtained. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0041] Figure 1 A structural block diagram of a building seasonal HVAC carbon emission actuarial system integrating big data and blockchain provided in an embodiment of the present invention;
[0042] Figure 2 A flow chart of the operation steps of the data acquisition module provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0044] As a possible embodiment of the present invention, Figure 1 As shown, a building seasonal HVAC carbon emission actuarial system integrating big data and blockchain is provided, and the system includes:
[0045] Data acquisition module, carbon emission calculation module and data upload module. The carbon emission calculation module is respectively connected to the data acquisition module and the data upload module. The data acquisition module is used to collect HVAC characteristic data corresponding to the target building. The data acquisition module can be connected to the control panel of the HVAC equipment in the target building by wired or wireless means to collect real-time operation data of the corresponding equipment. Alternatively, it can also be connected to the background server of the control APP of the existing HVAC equipment to collect the corresponding data. Alternatively, the corresponding data can be collected according to the corresponding sensors.
[0046] The carbon emission calculation module is used to obtain the carbon emission value of the target building based on the HVAC characteristic data. The data upload module is used to upload the carbon emission value to the preset blockchain.
[0047] Specifically, the data upload module operates as follows:
[0048] S400: After encrypting the carbon emission value of the target building generated in each data collection period, the carbon emission value is stored in the target storage system and a corresponding data ID is generated. Specifically, the data collection period (ie, the data collection cycle) may be one day.
[0049] S500: Generate a hash value corresponding to the encrypted carbon emission value of the target building, and upload the hash value and data ID to the preset blockchain.
[0050] Specifically, the data ID stored on the blockchain can be used to retrieve the corresponding carbon emission value data in the target storage system more quickly. In addition, the hash value on the blockchain can be matched with the hash value of the corresponding carbon emission value retrieved from the target storage system to verify whether the carbon emission value has been tampered with. This can ensure the accuracy of the carbon emission data.
[0051] In addition, since the carbon emission values obtained in each collection cycle may be data from multiple buildings and multiple collection cycles, the amount of data to be stored will be extremely large, so the size of the data on the chain can be reduced by storing hash values on the chain.
[0052] like Figure 2 As shown, the data acquisition module runs according to the following steps:
[0053] S100: Obtain spring carbon emission prediction model A1, summer carbon emission prediction model A2, autumn carbon emission prediction model A3 and winter carbon emission prediction model A4 corresponding to the area where the target building is located. A1, A2, A3 and A4 are all LSTM models.
[0054] Specifically, A1, A2, A3 and A4 can all be obtained by training using the operating data of HVAC equipment in the corresponding seasons and the corresponding carbon emission data to form corresponding training samples.
[0055] Taking the spring carbon emission prediction model A1 corresponding to the area where the target building is located as an example, the specific steps include:
[0056] S101: Generate training samples based on the emission time series data and corresponding carbon emission data collected during the spring period in the area where the target building is located. Specifically, the spring period can be the period between the beginning of spring and the spring equinox. Of course, the period can also be divided into corresponding periods according to the local climate characteristics.
[0057] Specifically, the emission time series data is a two-dimensional time series feature table. Each line in the two-dimensional time series feature table obtains a feature sequence at a collection time in the collection period, and the feature sequence includes data of multiple feature dimensions. The two-dimensional time series feature table includes multiple feature sequences. For example, the two-dimensional time series feature table can be feature data obtained within a 24-hour collection period, and the collection cycle can be 1 hour. Therefore, the collected feature table is a two-dimensional table with 24 rows of feature sequences. Correspondingly, for the collection of carbon emission data (i.e., sample labels), if the HVAC equipment is an electrical appliance, the power consumption of the HVAC equipment corresponding to each collection time can be collected by using the existing smart sockets arranged in the corresponding building in advance, and then converted into the corresponding carbon emission value. If the HVAC equipment is a device that consumes coal or natural gas, the energy consumption of the corresponding HVAC equipment can be detected by the corresponding flow valve or weight meter, and then converted into the corresponding carbon emission value.
[0058] Of course, since it is difficult to separately collect the power consumption, coal consumption or gas consumption of the corresponding HVAC equipment, this embodiment provides a method of collecting other easily available feature data to form a corresponding feature sequence. For example, multiple feature dimensions in the feature sequence may include:
[0059] The indoor temperature value of the target building, the set temperature value of the HVAC equipment in the target building, and the outdoor temperature of the area to which the target building belongs.
[0060] The indoor temperature value of the target building can be collected in real time by setting up multiple temperature collectors. The set temperature value of the HVAC equipment in the target building can also be obtained through the corresponding equipment control panel installed. The outdoor temperature of the area where the target building belongs can be obtained based on the local real-time data disclosed by the meteorological service agency. At the same time, since the change of outdoor temperature is continuous, in order to improve the accuracy of the prediction results, the temperature change data of the prediction day and the two adjacent days before and after can also be obtained.
[0061] Therefore, by obtaining the data in the above three aspects, it can be reflected how much work the HVAC equipment has done in order to resist the influence of the external temperature and reach the preset temperature value in the building during the corresponding collection period.
[0062] In addition, in order to further accurately describe the heating or cooling capacity required by the building during the collection period (that is, the workmanship of the HVAC equipment), multiple feature dimensions can also include:
[0063] Equipment type label, energy-saving grade, working mode label of HVAC equipment, practical area of the target building, location orientation, lighting area and number of indoor occupants.
[0064] S102: Use the training samples to train the initial LSTM model to generate A1.
[0065] Since the prediction of carbon emissions is highly correlated with the corresponding time series features and has time series dependence, it is necessary to select a model that can better capture this dependency. The LSTM (Long Short-Term Memory) model is a special recurrent neural network (RNN) architecture. The design purpose of LSTM is to solve the long-term dependency problem encountered by traditional RNN when processing sequence data, especially the gradient disappearance or gradient explosion problem. Of course, in this embodiment, the initial LSTM model can also be trained by preparing different training samples so that it can have the ability to predict the carbon emission value of the target building in the future.
[0066] In actual use, the same area will have different temperatures in different seasons, and different HVAC equipment will be used accordingly. Based on this, the present invention sets different prediction models for different seasons, so that the carbon emission data of HVAC equipment in different seasons can be more accurately and carefully predicted according to the temperature characteristics of different seasons in the corresponding area.
[0067] S200: Generate a carbon emission value W of the target building in the seasonal alternation period according to the model weight values P1, P2, P3 and P4 corresponding to A1, A2, A3 and A4 respectively in the seasonal alternation period. In this embodiment, the values of P1, P2, P3 and P4 corresponding to each seasonal alternation period may be different.
[0068] W satisfies the following conditions:
[0069] W=P1×result1+P2×result2+P3×result3+P4×result4.
[0070] Among them, result1, result2, result3 and result4 are the carbon emission prediction values generated by A1, A2, A3 and A4 according to the collected emission time series data of the target building.
[0071] In addition, during the seasonal transition period (such as the transition between spring and summer, summer and autumn, and autumn and winter), there are often large temperature changes, and the weather performance jumps back and forth between multiple seasons. Usually, the HVAC equipment used during this period is not a single device, and there may be a mixture of cooling and heating equipment. At this time, the corresponding single prediction model cannot capture the corresponding HVAC usage characteristics more accurately. In this embodiment, in order to more accurately predict the carbon emissions of HVAC equipment during the seasonal transition period, multiple prediction models are used to jointly predict, and then each prediction result is weighted and summed to obtain the final prediction result. Therefore, by combining the advantages of different models in capturing different HVAC characteristics, a more accurate carbon emission prediction result can be obtained.
[0072] Among them, the model weight values P1, P2, P3 and P4 are generated according to the following steps:
[0073] S201: Generate an emission verification time series data set B=(B1、B2、…、Bi、…、Bf(n)) corresponding to the seasonal alternation period according to the historical data corresponding to the seasonal alternation period. Where Bi is the ith emission verification time series data in the seasonal alternation period, Bi=(B i 1, Ti), B i 1 is the HVAC characteristic data corresponding to the target building in the preset collection period during the seasonal transition period. Ti is B i The actual carbon emission value of the target building corresponding to 1. f(n) is the total number of emission verification time series data during the seasonal transition period, f(n) = 1, 2, ..., f(n).
[0074] S202: Input B into A1, A2, A3 and A4 in sequence to generate four corresponding prediction sequences C1, C2, C3 and C4. C1 is the prediction result sequence (T 1 1. T 1 2. ..., T 1 i, …, T 1 f(n)). C2 is the prediction result sequence generated after each emission verification time series data in B is input into A2 (T 2 1. T 2 2. ..., T 2 i, …, T 2 f(n)). C3 is the prediction result sequence generated after inputting each emission verification time series data in B into A3 (T 3 1. T 3 2. ..., T 3 i, …, T 3f(n)). C4 is the prediction result sequence generated after each emission verification time series data in B is input into A4 (T 4 1. T 4 2. ..., T 4 i, …, T 4 f(n)).
[0075] S203: Generate model weight values P1, P2, P3 and P4 corresponding to the seasonal transition period according to the carbon emission value in B and the predicted emission values in C1, C2, C3 and C4. Among them, P1, P2, P3 and P4 meet the following conditions respectively:
[0076] ; ; ; .
[0077] ; ;
[0078] ; .
[0079] in, , and They are the prediction deviation values corresponding to A1, A2, A3 and A4 respectively.
[0080] In this embodiment, the emission verification time series data of the seasonal transition period is input into A1, A2, A3 and A4 in sequence, and then the deviation between the predicted value and the actual value of each model is calculated respectively, and the weight of each model is formed according to the inverse of the calculated deviation. In this way, the model results with greater prediction deviation are less considered in the final calculation results.
[0081] In addition, even in the period of seasonal transition, the operating characteristics of the HVAC equipment in this period usually do not involve all four characteristics of A1, A2, A3 and A4. More often, they involve the models corresponding to the two alternating seasons. Therefore, in order to more accurately mix the prediction results of the corresponding models, a deviation threshold can be set according to the actual situation. If the prediction deviation degree of any model (that is, , , or ) is greater than the threshold, then the corresponding , , or The value of is set to 0. This allows for more appropriate selection of model results for mixing.
[0082] In another possible embodiment of the present invention, after S202: generating the corresponding four prediction sequences C1, C2, C3 and C4, the data acquisition module further operates according to the following steps:
[0083] S204: Generate training samples according to the prediction results of the target building in C1, C2, C3 and C4 and the actual carbon emission value in B. The i-th training sample includes a sample sequence (T 1 i. T 2 i. T 3 i. T 4 i) and sample label Ti.
[0084] S205: Using the training samples, the initial feedforward neural network is trained to generate a corresponding regression prediction model.
[0085] Correspondingly, the data acquisition module can also be run according to the following steps:
[0086] S300: Input the characteristic sequence formed by result1, result2, result3 and result4 into the regression prediction model to generate the carbon emission value W of the target building in the seasonal transition period.
[0087] In this embodiment, after having a large amount of carbon emission prediction data and actual data, the training samples formed by these data can also be used to train a regression prediction model of a feedforward neural network. Subsequently, result1, result2, result3 and result4 can be directly input into the regression prediction model to obtain the corresponding carbon emission prediction results. Of course, the corresponding model weight values P1, P2, P3 and P4 can also be generated after extracting the parameters of each neuron in the feedforward neural network.
[0088] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.
[0089] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.
[0090] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.
[0091] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".
[0092] The electronic device according to this embodiment of the present invention is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0093] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).
[0094] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.
[0095] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).
[0096] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
[0097] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.
[0098] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may communicate with one or more devices that enable a user to interact with the electronic device, and / or may communicate with any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input / output (I / O) interface. In addition, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter. The network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.
[0099] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.
[0100] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.
[0101] The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.
[0102] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0103] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.
[0104] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).
[0105] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.
[0106] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.
[0107] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims
1. Building seasonal HVAC carbon emission actuarial system integrating big data and blockchain, It is characterized in that The system comprises: Data collection module, carbon emission calculation module and data upload module; the carbon emission calculation module is respectively connected to the data collection module and the data upload module; the data collection module is used to collect HVAC characteristic data corresponding to the target building; the carbon emission calculation module is used to obtain the carbon emission value of the target building according to the HVAC characteristic data; the data upload module is used to upload the carbon emission value to a preset blockchain; The data acquisition module operates according to the following steps: Obtain spring carbon emission prediction model A1, summer carbon emission prediction model A2, autumn carbon emission prediction model A3 and winter carbon emission prediction model A4 corresponding to the area where the target building is located; A1, A2, A3 and A4 are all LSTM models; According to the model weight values P1, P2, P3 and P4 corresponding to A1, A2, A3 and A4 respectively in the seasonal transition period, the carbon emission value W of the target building in the seasonal transition period is generated; W satisfies the following conditions: W=P1×result1+P2×result2+P3×result3+P4×result4; Among them, result1, result2, result3 and result4 are the carbon emission prediction values generated by A1, A2, A3 and A4 according to the collected emission time series data of the target building; Among them, the model weight values P1, P2, P3 and P4 are generated according to the following steps: According to the historical data corresponding to the seasonal alternation period, the emission verification time series data set B=(B1、B2、…、Bi、…、Bf(n)) corresponding to the seasonal alternation period is generated; wherein Bi is the i-th emission verification time series data in the seasonal alternation period, Bi=(B i 1, Ti), B i 1 is the HVAC characteristic data corresponding to the target building in the preset collection period during the seasonal transition period; Ti is B i 1 is the actual carbon emission value of the target building corresponding to 1; f(n) is the total number of emission verification time series data in the seasonal transition period, f(n)=1, 2, …, f(n); Input B into A1, A2, A3 and A4 in sequence to generate four corresponding prediction sequences C1, C2, C3 and C4; among them, C1 is the prediction result sequence generated after inputting each emission verification time series data in B into A1 (T 1 1. T 1 2. ..., T 1 i, …, T 1 f(n)); C2 is the prediction result sequence generated after each emission verification time series data in B is input into A2 (T 2 1. T 2 2. ..., T 2 i, …, T 2 f(n)); C3 is the prediction result sequence generated after inputting each emission verification time series data in B into A3 (T 3 1. T 3 2. ..., T 3 i, …, T 3 f(n)); C4 is the prediction result sequence generated after each emission verification time series data in B is input into A4 (T 4 1. T 4 2. ..., T 4 i, …, T 4 f(n)); According to the carbon emission value in B and the predicted emission values in C1, C2, C3, and C4, the model weight values P1, P2, P3, and P4 corresponding to the seasonal transition period are generated; wherein P1, P2, P3, and P4 respectively meet the following conditions: ; ; ; ; ; ; ; ; in, , and They are the prediction deviation values corresponding to A1, A2, A3 and A4 respectively.
2. According to the building seasonal HVAC carbon emission actuarial system integrating big data and blockchain according to claim 1, It is characterized in that The emission time series data is a two-dimensional time series feature table; each line in the two-dimensional time series feature table obtains a feature sequence at a collection time in a collection period, and the feature sequence includes data of multiple feature dimensions; the two-dimensional time series feature table includes multiple feature sequences.
3. According to claim 2, the building seasonal HVAC carbon emission actuarial system integrating big data and blockchain, It is characterized in that The plurality of characteristic dimensions include: The indoor temperature value of the target building, the set temperature value of the HVAC equipment in the target building, and the outdoor temperature of the area to which the target building belongs.
4. According to claim 3, the building seasonal HVAC carbon emission actuarial system integrating big data and blockchain, It is characterized in that The plurality of characteristic dimensions also include: Equipment type label, energy-saving grade, working mode label of HVAC equipment, practical area of the target building, location orientation, lighting area and number of indoor occupants.
5. According to claim 2, the building seasonal HVAC carbon emission actuarial system integrating big data and blockchain, It is characterized in that The two-dimensional time series feature table is feature data acquired within a 24-hour collection period, and the collection cycle is 1 hour.
6. The building seasonal HVAC carbon emission actuarial system integrating big data and blockchain according to claim 1, It is characterized in that Obtaining the spring carbon emission prediction model A1 corresponding to the area where the target building is located, including: Generate training samples based on the emission time series data and corresponding carbon emission data collected during the spring period in the area where the target building is located; The initial LSTM model is trained using the training samples to generate A1.
7. The building seasonal HVAC carbon emission actuarial system integrating big data and blockchain according to claim 6, It is characterized in that The spring period includes the period between the Beginning of Spring and the Spring Equinox.
8. The building seasonal HVAC carbon emission actuarial system integrating big data and blockchain according to claim 1, It is characterized in that After generating the corresponding four prediction sequences C1, C2, C3 and C4, the data acquisition module further operates according to the following steps: Generate training samples based on the prediction results of the target building in C1, C2, C3 and C4 and the actual carbon emission values in B; Among them, the i-th training sample includes the sample sequence (T 1 i. T 2 i. T 3 i. T 4 i) and sample label Ti; Using the training samples, the initial feedforward neural network is trained to generate the corresponding regression prediction model.
9. The building seasonal HVAC carbon emission actuarial system integrating big data and blockchain according to claim 8, It is characterized in that The data acquisition module also operates according to the following steps: The characteristic sequence formed by result1, result2, result3 and result4 is input into the regression prediction model to generate the carbon emission value W of the target building in the seasonal transition period.
10. The building seasonal HVAC carbon emission actuarial system integrating big data and blockchain according to claim 1, It is characterized in that The data upload module operates as follows: The carbon emission value of the target building generated during each data collection period is encrypted, stored in the target storage system and a corresponding data ID is generated; Generate a hash value corresponding to the encrypted carbon emission value of the target building, and upload the hash value and data ID to a preset blockchain.
Citation Information
Patent Citations
Building body heating carbon emission prediction method and system
CN115293461A
Carbon emission checking method and system
CN116596196A
Carbon emission prediction method based on energy data
CN117634693A
Electric power carbon emission early warning and response system
CN118336930A
Carbon emission accounting method and device for fire-fighting building
CN118521220A
