Flue Gas Emission Prediction Method and Device Based on Federated Learning

Abstract

The present invention discloses a method and device for predicting flue gas emissions based on federated learning. The method includes: training a local energy data measurement model according to local energy data; based on a federated learning framework, training the local energy data measurement model according to test data and energy data of a target energy device to obtain a test data prediction model and a target energy data prediction model; calculating a first sample transfer weight and a second sample transfer weight based on the local energy data prediction model, the test data prediction model and the target energy data prediction model; using the local energy data and the first sample transfer weight, and the test data and the second sample transfer weight to train a local energy data network model and a test data network model; receiving a federated learning prediction model obtained by aggregating and training the local energy data network model and the test data network model by a central node; and predicting the flue gas emissions of the target energy device by using the federated learning prediction model.

Description

Technical Field

[0001] The present disclosure relates to the field of energy technologies, and in particular, to a method and device for predicting flue gas emissions based on federated learning. Background Art

[0002] Currently, zirconia oxygen analyzers are commonly used to measure the oxygen content in flue gas. However, the measurement and maintenance costs of such zirconia oxygen analyzers are relatively high. For example, in the field of distributed energy, small gas boilers generally abandon installation in order to save costs, resulting in the inability to achieve closed-loop control and optimal operation of thermal efficiency. Especially in scenarios where the calorific value of gas is unstable, it is impossible to accurately measure the oxygen content in flue gas. Therefore, there is an urgent need for a measurement method at present. Summary of the Invention

[0003] In view of this, embodiments of the present disclosure provide a method, device, electronic device, and computer-readable storage medium for predicting flue gas emissions based on federated learning to solve the problem in the prior art that due to the different distributions of devices, the measurement of flue gas emissions is inaccurate.

[0004] In the first aspect of the embodiments of the present disclosure, a method for predicting flue gas emissions based on federated learning is provided, including:

[0005] Training a local energy data measurement model according to local energy data;

[0006] Based on a federated learning framework, training the local energy data measurement model according to test data and the energy data of the target energy device to obtain a test data prediction model and a target energy data prediction model respectively;

[0007] Calculating a first sample transfer weight and a second sample transfer weight based on the local energy data prediction model, the test data prediction model, and the target energy data prediction model, where the first sample transfer weight is the sample transfer weight of the local energy data for the energy data of the target energy device, and the second sample transfer weight is the sample transfer weight of the test data for the energy data of the target energy device;

[0008] Training a local energy data network model and a test data network model respectively using the local energy data and the first sample transfer weight, and the test data and the second sample transfer weight;

[0009] Receiving a federated learning prediction model obtained by aggregating and training the local energy data network model and the test data network model from a central node;

[0010] Predicting the flue gas emissions of the target energy device according to the federated learning prediction model.

[0011] In the second aspect of the embodiments of the present disclosure, a device for predicting flue gas emissions based on federated learning is provided, including:

[0012] The first training module is used to train a local energy data measurement model according to local energy data;

[0013] The second training module is used to train a local energy data measurement model based on a federated learning framework according to test data and energy data of a target energy device, and respectively obtain a test data prediction model and a target energy data prediction model;

[0014] The calculation module is used to calculate a first sample transfer weight and a second sample transfer weight based on the local energy data prediction model, the test data prediction model, and the target energy data prediction model, where the first sample transfer weight is the sample transfer weight of the local energy data for the energy data of the target energy device, and the second sample transfer weight is the sample transfer weight of the test data for the energy data of the target energy device;

[0015] The third training module is used to train a local energy data network model and a test data network model by using the local energy data and the first sample transfer weight, and the test data and the second sample transfer weight respectively;

[0016] The establishment module is used to receive a federated learning prediction model after aggregating and training the local energy data network model and the test data network model from a central node;

[0017] The prediction module is used to predict the flue gas emission of the target energy device according to the federated learning prediction model.

[0018] In a third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0019] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0020] The beneficial effects of the embodiments of the present disclosure compared with the prior art are as follows: By training a local energy data measurement model based on local energy data; based on a federated learning framework, training the local energy data measurement model according to test data and the energy data of the target energy device to obtain a test data prediction model and a target energy data prediction model respectively; calculating a first sample transfer weight and a second sample transfer weight based on the local energy data prediction model, the test data prediction model and the target energy data prediction model, where the first sample transfer weight is the sample transfer weight of the local energy data for the energy data of the target energy device, and the second sample transfer weight is the sample transfer weight of the test data for the energy data of the target energy device; using the local energy data and the first sample transfer weight, the test data and the second sample transfer weight to train a local energy data network model and a test data network model respectively; receiving a federated learning prediction model obtained by aggregating and training the local energy data network model and the test data network model from a central node; and predicting the flue gas emission of the target energy device according to the federated learning prediction model. The embodiments of the present disclosure solve the problem in the prior art that the flue gas emission measurement is inaccurate due to the different distributions of devices, thereby saving the resource cost of actual sensor installation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0022] Figure 1 is a schematic diagram of the architecture of a federated learning in the embodiments of the present disclosure;

[0023] Figure 2 is a schematic flowchart of a method for predicting flue gas emission based on federated learning provided by the embodiments of the present disclosure;

[0024] Figure 3 is a schematic diagram of the structure of a device for predicting flue gas emission based on federated learning provided by the embodiments of the present disclosure;

[0025] Figure 4 is a schematic diagram of the structure of an electronic device provided by the embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0027] Federated learning refers to comprehensively utilizing various AI (Artificial Intelligence) technologies on the premise of ensuring data security and user privacy, jointly cooperating with multiple parties to jointly explore data value, and giving birth to new intelligent business forms and models based on joint modeling. Federated learning has at least the following characteristics:

[0028] (1) A weakly centralized joint training mode in which participating nodes control their own data, ensuring data privacy and security in the process of co-creating intelligence.

[0029] (2) In different application scenarios, by using screening and / or combining AI algorithms and privacy-preserving computing, establish various model aggregation and optimization strategies to obtain high-level and high-quality models.

[0030] (3) On the premise of ensuring data security and user privacy, based on various model aggregation and optimization strategies, obtain methods to improve the efficiency of federated learning, where the efficiency methods can be to improve the overall efficiency of federated learning by solving problems including computing architecture parallelism, information interaction under large-scale cross-domain networks, intelligent perception, and exception handling mechanisms.

[0031] (4) Obtain the needs of multi-party users in each scenario, and through a mutual trust mechanism, determine a reasonable evaluation of the true contribution of each participating party in the federation and conduct distribution incentives.

[0032] Based on the above methods, an AI technology ecosystem based on federated learning can be established, giving full play to the value of industry data and promoting the implementation of scenarios in vertical fields.

[0033] Next, a method and device for predicting flue gas emissions based on federated learning according to an embodiment of the present disclosure will be described in detail with reference to the accompanying drawings.

[0034] Figure 1 It is a schematic diagram of the architecture of federated learning according to an embodiment of the present disclosure. As Figure 1 shown, the architecture of federated learning may include a server (central node) 101 and participating parties 102, 103, and 104. The participating parties can be composed of one or more clients.

[0035] During the federated learning process, the basic model can be established by the server 101, and the server 101 sends the model to the participating parties 102, 103, and 104 that have established communication connections with it. The basic model can also be established by any participating party and uploaded to the server 101, and the server 101 sends the model to other participating parties that have established communication connections with it. The participating parties 102, 103, and 104 construct models according to the downloaded basic structure and model parameters, use local data to train the models, obtain updated model parameters, and encrypt and upload the updated model parameters to the server 101. The server 101 aggregates the model parameters sent by the participating parties 102, 103, and 104 to obtain global model parameters, and sends the global model parameters back to the participating parties 102, 103, and 104. The participating parties 102, 103, and 104 iterate their respective models according to the received global model parameters until the models finally converge, thereby realizing the training of the models. During the federated learning process, the data uploaded by the participating parties 102, 103, and 104 are model parameters, and the local data will not be uploaded to the server 101, and all participating parties can share the final model parameters, so common modeling can be realized on the basis of ensuring data privacy. It should be noted that the number of participating parties is not limited to the three mentioned above, but can be set as needed, and the embodiments of the present disclosure do not limit this.

[0036] Figure 2 It is a schematic flow chart of a flue gas emission prediction method based on federated learning provided by an embodiment of the present disclosure. Figure 2 The flue gas emission prediction method based on federated learning can be executed by Figure 1 the participating parties. As Figure 2 shown, the flue gas emission prediction method based on federated learning includes:

[0037] S201, training a local energy data measurement model according to local energy data.

[0038] Specifically, the local energy data may refer to the flue gas temperature, flue gas flow rate, equipment inlet pressure, etc. of local equipment, such as the flue gas temperature of a steam boiler, the outlet temperature of an economizer, the instantaneous value of flue gas flow, the gas temperature of a steam boiler, the standard condition flow of flue gas of a steam boiler, the inlet pressure of natural gas of a steam boiler, the flue gas flow rate of a steam boiler, the inlet flue gas temperature of a condenser of a steam boiler, the exhaust gas temperature of a steam boiler, the flue gas pressure of a steam boiler, the inlet pressure of a condenser of a steam boiler, the instantaneous flow of main steam of a steam boiler, the operating state of a steam boiler, the instantaneous flow of natural gas inlet of a steam boiler, etc.

[0039] Further, before training the local energy data measurement model based on the local energy data, the local energy data, the test data, and the energy data of the target energy device can also be sorted or screened by the following method: First, select a sample data set; label the data in the sample data set to obtain the label data corresponding to the data in the sample data set; respectively determine the label data corresponding to the local energy data, the test data, and the energy data of the target energy device.

[0040] S202. Based on the federated learning framework, train the local energy data measurement model according to the test data and the energy data of the target energy device to obtain a test data prediction model and a target energy data prediction model respectively.

[0041] Among them, the test data can be selected from the local energy data or the energy data extracted by other related devices; the energy data of the target energy device can be the energy data of the device to be predicted.

[0042] Specifically, it can be implemented by the following method: Based on the federated learning framework, the participating party sends the local energy data prediction model to the central node; in response to the feedback information of the central node, train the local energy data test model according to the test data and the energy data of the target energy device to obtain a test data prediction model and a target energy data prediction model respectively.

[0043] S203. Calculate the first sample transfer weight and the second sample transfer weight based on the local energy data prediction model, the test data prediction model, and the target energy data prediction model; where the first sample transfer weight is the sample transfer weight of the local energy data for the energy data of the target energy device, and the second sample transfer weight is the sample transfer weight of the test data for the energy data of the target energy device.

[0044] Specifically, in the federated learning framework, first, the participating party sends the local energy data prediction model, the test data prediction model, and the target energy data prediction model to the central node; the central node can sort or adjust the local energy data prediction model, the test data prediction model, and the target energy data prediction model according to the target requirements of the participating party (or the demanding party), and then send them to the relevant participating parties; then, in response to the feedback information of the central node, based on the local energy data prediction model, the test data prediction model, and the target energy data prediction model, respectively perform target classification on the local energy data, the test data, and the energy data of the target energy device; finally, calculate the first sample transfer weight and the second sample transfer weight according to the target classification.

[0045] S204. Use the local energy data and the first sample transfer weight, the test data and the second sample transfer weight to train the local energy data network model and the test data network model respectively.

[0046] Specifically, it is preferable to establish an application data set by using local energy data and the first sample transfer weight; then, according to the established application data set, train the local energy data network model; then, use the test data and the second sample transfer weight to establish an expected data set; and then, according to the expected data set, train the test data network model. The training of the local energy data network model and the test data network model can be carried out in parallel, or one of the two models can be trained first. The present invention does not limit this.

[0047] S205, receive the joint learning prediction model after the central node aggregates and trains the local energy data network model and the test data network model.

[0048] Specifically, the local energy data network model and the test data network model can be uploaded to the central node; the central node aggregates and trains the local energy data network model and the test data network model. Then, receive the joint learning prediction model after the central node aggregates and trains the local energy data network model and the test data network model.

[0049] Furthermore, the prediction model of the joint learning can be optimized according to the prediction conditions, where the prediction conditions include: the predicted value of the model parameters and the judgment of the fitness of the model parameters.

[0050] S206, predict the flue gas emission of the target energy device according to the joint learning prediction model.

[0051] According to the technical solution provided by the embodiments of the present disclosure, by training the local energy data measurement model according to the local energy data; based on the joint learning framework, training the local energy data measurement model according to the test data and the energy data of the target energy device to obtain the test data prediction model and the target energy data prediction model respectively; based on the local energy data prediction model, the test data prediction model and the target energy data prediction model, calculate the first sample transfer weight and the second sample transfer weight, where the first sample transfer weight is the sample transfer weight of the local energy data for the energy data of the target energy device, and the second sample transfer weight is the sample transfer weight of the test data for the energy data of the target energy device; use the local energy data and the first sample transfer weight, the test data and the second sample transfer weight to train the local energy data network model and the test data network model respectively; receive the joint learning prediction model after the central node aggregates and trains the local energy data network model and the test data network model; predict the flue gas emission of the target energy device according to the joint learning prediction model. To solve the problem in the prior art that the measurement of flue gas emissions is inaccurate due to the different distributions of devices. Furthermore, the resource cost of actual sensor installation is saved.

[0052] Any combination of the above optional technical solutions can form an optional embodiment of the present application, which will not be elaborated herein one by one.

[0053] The following is an embodiment of the disclosed device, which can be used to execute the method embodiment of the present disclosure. For details not disclosed in the embodiment of the disclosed device, please refer to the method embodiment of the present disclosure.

[0054] Figure 3 It is a schematic diagram of a flue gas emission prediction device based on federated learning provided by an embodiment of the present disclosure. As Figure 3 shown, the flue gas emission prediction device based on federated learning includes:

[0055] A first training module 301, configured to train a local energy data measurement model according to local energy data;

[0056] A second training module 302, configured to train the local energy data measurement model based on a federated learning framework according to test data and energy data of a target energy device, and respectively obtain a test data prediction model and a target energy data prediction model;

[0057] A calculation module 303, configured to calculate a first sample transfer weight and a second sample transfer weight based on the local energy data prediction model, the test data prediction model, and the target energy data prediction model, where the first sample transfer weight is the sample transfer weight of the local energy data for the energy data of the target energy device, and the second sample transfer weight is the sample transfer weight of the test data for the energy data of the target energy device;

[0058] A third training module 304, configured to use the local energy data and the first sample transfer weight, and the test data and the second sample transfer weight to train a local energy data network model and a test data network model respectively;

[0059] A building module 305, configured to receive a federated learning prediction model after aggregated training of the local energy data network model and the test data network model from a central node;

[0060] A prediction module 306, configured to predict the flue gas emission of a target energy device according to the federated learning prediction model.

[0061] According to the technical solution provided by the embodiments of the present disclosure, by training a local energy data measurement model based on local energy data; based on a federated learning framework, training the local energy data measurement model according to test data and the energy data of a target energy device to obtain a test data prediction model and a target energy data prediction model respectively; based on the local energy data prediction model, the test data prediction model and the target energy data prediction model, calculating a first sample transfer weight and a second sample transfer weight, where the first sample transfer weight is the sample transfer weight of the local energy data for the energy data of the target energy device, and the second sample transfer weight is the sample transfer weight of the test data for the energy data of the target energy device; using the local energy data and the first sample transfer weight, and the test data and the second sample transfer weight, training a local energy data network model and a test data network model respectively; receiving a federated learning prediction model after aggregating and training the local energy data network model and the test data network model from a central node; and predicting the flue gas emission of the target energy device according to the federated learning prediction model. To solve the problem in the prior art that due to the different distributions of devices, the measurement of flue gas emissions is inaccurate. Furthermore, the resource cost of actual sensor installation is saved.

[0062] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution is prior or posterior. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present disclosure.

[0063] Figure 4 is a schematic diagram of the electronic device 4 provided by the embodiments of the present disclosure. As Figure 4 shown, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned various method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of each module / unit in the above-mentioned various device embodiments are implemented.

[0064] Exemplarily, the computer program 403 can be divided into one or more modules / units. The one or more modules / units are stored in the memory 402 and executed by the processor 401 to complete the present disclosure. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 403 in the electronic device 4.

[0065] The electronic device 4 can be a desktop computer, a notebook, a palm computer, a cloud server and other electronic devices. The electronic device 4 may include, but is not limited to, the processor 401 and the memory 402. Those skilled in the art can understand, Figure 4These are merely examples of the electronic device 4 and do not constitute a limitation thereto. It may include more or fewer components than shown in the figures, or combine certain components, or have different components. For example, the electronic device may further include input / output devices, network access devices, buses, etc.

[0066] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc.

[0067] The memory 402 may be an internal storage unit of the electronic device 4. For example, the hard disk or memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4. For example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. Further, the memory 402 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device. The memory 402 may also be used to temporarily store data that has been output or is to be output.

[0068] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In practical applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into a processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0069] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0070] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0071] In the embodiments provided by this disclosure, it should be understood that the disclosed device / electronic device and method can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. Multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the device or unit can be in electrical, mechanical or other forms.

[0072] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0073] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0074] When the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods, the present disclosure can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. The computer program can include computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice within the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0075] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present disclosure, and should all be included in the protection scope of the present disclosure.

Claims

1. A flue gas emission prediction method based on collaborative learning, characterized in that Including: Training a local energy data prediction model according to local energy data; Based on a federated learning framework, training a local energy data prediction model according to test data and energy data of a target energy device to obtain a test data prediction model and a target energy data prediction model respectively; Calculating a first sample transfer weight and a second sample transfer weight based on the local energy data prediction model, the test data prediction model, and the target energy data prediction model, where the first sample transfer weight is the sample transfer weight of the local energy data for the energy data of the target energy device, and the second sample transfer weight is the sample transfer weight of the test data for the energy data of the target energy device; Using the local energy data and the first sample transfer weight to establish an application data set; training a local energy data network model according to the application data set; using the test data and the second sample transfer weight to establish an expected data set; training a test data network model according to the expected data set; Receiving a federated learning prediction model obtained by aggregating and training the local energy data network model and the test data network model from a central node; Predicting the flue gas emissions of the target energy device according to the federated learning prediction model.

2. The method according to claim 1, characterized in that Before training the local energy data prediction model according to the local energy data, it includes: Selecting a sample data set; Labeling the data in the sample data set and obtaining the label data corresponding to the data in the sample data set; Respectively determining the label data corresponding to the local energy data, the test data, and the energy data of the target energy device.

3. The method according to claim 1, wherein Based on a federated learning framework, training a local energy data prediction model according to test data and energy data of a target energy device to obtain a test data prediction model and a target energy data prediction model respectively includes: Based on a federated learning framework, a participant sends the local energy data prediction model to a central node; In response to the feedback information from the central node, training a local energy data prediction model according to the test data and the energy data of the target energy device to obtain a test data prediction model and a target energy data prediction model respectively.

4. The method according to claim 1, wherein Calculating a first sample transfer weight and a second sample transfer weight based on the local energy data prediction model, the test data prediction model, and the target energy data prediction model includes: Based on a federated learning framework, a participant sends the local energy data prediction model, the test data prediction model, and the target energy data prediction model to a central node; In response to the feedback information from the central node, respectively performing target classification on the local energy data, the test data, and the energy data of the target energy device based on the local energy data prediction model, the test data prediction model, and the target energy data prediction model; Calculating the first sample transfer weight and the second sample transfer weight according to the target classification.

5. The method according to claim 1, wherein Receiving a federated learning prediction model obtained by aggregating and training the local energy data network model and the test data network model from a central node includes: Uploading the local energy data network model and the test data network model to a central node; Receiving a federated learning prediction model obtained by aggregating and training the local energy data network model and the test data network model from a central node.

6. The method according to claim 5, wherein It also includes: Optimize the collaborative learning prediction model according to the prediction conditions; The prediction conditions include: the predicted value of the model parameters and the judgment of the fitness of the model parameters.

7. A flue gas emission prediction device based on joint learning, characterized in that, It includes: A first training module for training a local energy data prediction model according to local energy data; A second training module for training a local energy data prediction model based on a collaborative learning framework according to test data and the energy data of the target energy device to obtain a test data prediction model and a target energy data prediction model respectively; A calculation module for calculating a first sample transfer weight and a second sample transfer weight based on the local energy data prediction model, the test data prediction model and the target energy data prediction model, where the first sample transfer weight is the sample transfer weight of the local energy data for the energy data of the target energy device, and the second sample transfer weight is the sample transfer weight of the test data for the energy data of the target energy device; A third training module for using the local energy data and the first sample transfer weight to establish an application data set; training a local energy data network model according to the application data set; using the test data and the second sample transfer weight to establish an expected data set; training a test data network model according to the expected data set; A building module for receiving the collaborative learning prediction model after aggregating and training the local energy data network model and the test data network model from the central node; A prediction module for predicting the flue gas emissions of the target energy device according to the collaborative learning prediction model.

8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.

Images