A method, device, computer equipment and storage medium for optimizing carbon emissions

Abstract

The present invention provides a carbon emission optimization method, device, computer equipment and storage medium, which relates to the field of energy conservation and emission reduction. The method includes: according to the energy output model and energy output equipment, obtaining the actual energy output and the actual output carbon emissions in the time period; obtaining a multi-component time period reference quantity matching the actual energy output in the time period; according to the energy load model and the energy storage model, obtaining a group of reference carbon emissions corresponding to each component time period reference quantity; according to the actual output carbon emissions in the time period, the reference load carbon emissions and the reference storage carbon emissions, obtaining the optimized carbon emissions from the multi-component time period reference quantity; thereby obtaining the optimized energy output in the time period, the optimized energy load in the time period and the optimized energy storage in the time period. The present invention limits carbon emissions while also promoting economic development, taking into account environmental protection and economy, so as to achieve a balance between economic development and environmental protection.

Description

Technical Field

[0001] The present invention relates to the field of energy conservation and emission reduction, and in particular to a carbon emission optimization method, device, computer equipment and storage medium. Background Art

[0002] In the field of energy conservation and emission reduction, carbon emissions reflect the greenhouse gas emissions generated by industrial activities when producing, transporting, using and recycling a product. Therefore, carbon emissions are an inevitable by-product of economic development, but due to excessive carbon emissions, carbon emissions have become the main cause of global warming. If carbon emissions are completely banned, it will have a huge negative impact on human life and economic development. Therefore, it is necessary to find a balance between economy and environmental protection. Therefore, the optimization of carbon emissions has become an important means to ensure production and maintain the environment.

[0003] In the existing technology, carbon emission optimization is only limited in the fields of industry, daily use, etc., which affects industrial production capacity and daily life, and fails to find a balance between economic development, daily life and environmental protection. Summary of the invention

[0004] The main technical problem solved by the present invention is that the optimization of carbon emissions is too simple, which affects normal industrial production and daily life.

[0005] In order to solve the above problems, the present invention provides a carbon emission method, which comprises:

[0006] According to the energy output model and energy output equipment, obtain the actual energy output and carbon emissions in different time periods;

[0007] Acquire a plurality of time period reference quantities that match the actual energy output in the time period, each group of the time period reference quantities including a time period reference energy load and a time period reference energy storage;

[0008] According to the energy load model and the energy storage model, a group of reference carbon emissions corresponding to each group of the time period reference amounts is obtained, wherein the group of reference carbon emissions includes reference load carbon emissions and reference storage carbon emissions;

[0009] According to the actual output carbon emissions in different time periods, the reference load carbon emissions and the reference storage carbon emissions, obtaining the optimized carbon emissions from the multi-component time period reference amounts;

[0010] According to the optimized carbon emissions, the energy output model, the energy load model and the energy storage model, the time-phase optimized energy output, time-phase optimized energy load and time-phase optimized energy storage are obtained.

[0011] Optionally, before obtaining the actual energy output and the actual carbon emissions in different time periods, the carbon emissions optimization method further includes:

[0012] obtaining the energy output model;

[0013] The obtaining of the energy output model comprises:

[0014] Obtain the type and size of each energy production facility;

[0015] According to the type and scale of each energy production device, obtain the time-divided training energy output and time-divided training output carbon emissions of each energy production device;

[0016] The energy production model is obtained according to the time-phased training energy production and the time-phased training energy production carbon emissions of each energy production device.

[0017] Optionally, before obtaining the multi-component time period reference amount that matches the actual energy output in the time period, the carbon emission optimization method further includes:

[0018] obtaining the energy storage model;

[0019] The obtaining of the energy storage model comprises:

[0020] Obtain the type of each energy storage device;

[0021] Obtain the time-divided energy storage capacity of each energy storage device;

[0022] Obtain the time-divided contribution of each energy storage device to energy storage;

[0023] Obtain the carbon emissions of each energy storage device by time period;

[0024] The energy storage model is obtained according to the type of each energy storage device, the time-divided energy storage capacity of each energy storage device, the time-divided contribution of each energy storage device to energy storage, and the time-divided training carbon emissions of each energy storage device.

[0025] Optionally, obtaining the carbon emissions of each energy storage device by time period includes:

[0026] Obtaining the time-divided training carbon emissions corresponding to the storage capacity of each energy storage device;

[0027] Obtaining time-division training carbon emission information corresponding to the loss amount of each energy storage device;

[0028] The time-divided carbon emissions of each energy storage device are obtained according to the time-divided training carbon emissions corresponding to the storage capacity of each energy storage device and the time-divided training carbon emissions information corresponding to the loss of each energy storage device.

[0029] Optionally, before obtaining the multi-component time period reference amount that matches the actual energy output amount in the time period, the carbon emission optimization method further includes: obtaining the energy load model of the entire building;

[0030] The step of obtaining the energy load model of the entire building includes:

[0031] Get the types of each individual building contained in the overall building;

[0032] Obtaining a single load model of the type of each single building;

[0033] Obtain the arrangement of each individual building in the entire building complex;

[0034] The energy load model of the overall building is obtained according to the types of individual buildings included in the overall building, the arrangement of the individual buildings and the individual load models of the individual buildings.

[0035] Optionally, the obtaining of the single load model of the type of each single building includes:

[0036] Get the type of the single building;

[0037] Obtaining the appearance of the single building;

[0038] Obtaining the composition of the single building;

[0039] Obtaining the thermal insulation level of the single building;

[0040] Obtaining the time-divided training energy load of the single building, wherein the time-divided training energy load of the single building includes the time-divided training electricity load of the single building, the time-divided training cooling load of the single building, and the time-divided training heating load of the single building;

[0041] According to the type of the single building, the shape of the single building, the composition of the single building, the insulation level of the single building and the energy load of the training in different time periods of the single building, the carbon emission of the training in different time periods of the single building is obtained;

[0042] According to the obtained time-phased training energy load of the single building and the time-phased training carbon emission of the single building, a single load model of the type of each single building is obtained.

[0043] Optionally, after obtaining the time-divided optimized energy output, time-divided optimized energy load and time-divided optimized energy storage, the carbon emission optimization method further includes:

[0044] Carbon emissions are optimized according to the time-phase optimized energy output, the time-phase optimized energy load, and the time-phase optimized energy storage.

[0045] The carbon emission optimization method of the present invention predicts the energy parameters and carbon emission parameters of each time period through rapid automatic modeling and subdividing the model, predicts the energy load and optimizes the energy storage by time period, and reasonably optimizes the energy output, energy load and energy storage by time period, while limiting carbon emissions, it also promotes economic development and ensures normal life, takes into account environmental protection and economy, and achieves a balance between economic development and environmental protection.

[0046] The present invention provides a carbon emission optimization device, which comprises:

[0047] The output and emission acquisition unit is used to obtain the actual energy output and carbon emissions of each time period according to the energy output model and energy output equipment;

[0048] A load and storage acquisition unit, used to acquire a multi-group time period reference quantity that matches the actual energy output in the time period, each group of the time period reference quantity includes a time period reference energy load quantity and a time period reference energy storage quantity;

[0049] A reference carbon emission acquisition unit, used for acquiring a group of reference carbon emissions corresponding to each group of the time period reference amounts according to an energy load model and an energy storage model, wherein the group of reference carbon emissions includes reference load carbon emissions and reference storage carbon emissions;

[0050] An optimization unit, configured to obtain an optimized carbon emission amount from the multi-component time period reference amount according to the actual output carbon emission amount in the time period, the reference load carbon emission amount and the reference storage carbon emission amount;

[0051] The optimization unit is also used to obtain the time-divided optimized energy output, time-divided optimized energy load and time-divided optimized energy storage according to the optimized carbon emissions, the energy output model, the energy load model and the energy storage model.

[0052] The carbon emission optimization device of the present invention predicts the energy parameters and carbon emission parameters of each time period through rapid and automated modeling and subdividing the model, predicts the energy load and optimizes the energy storage by time period, and reasonably optimizes the energy output, energy load and energy storage by time period, thereby achieving carbon reduction while improving the flexibility of electricity consumption, limiting carbon emissions while also promoting economic development and ensuring normal life, taking into account both environmental protection and economy, and achieving a balance between economic development and environmental protection.

[0053] The present invention also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any one of the above-mentioned carbon emission optimization methods is implemented.

[0054] The computer equipment of the present invention predicts energy parameters and carbon emission parameters for each time period through rapid and automated modeling and subdividing the model, predicts energy load and optimizes energy storage by time period, and reasonably optimizes energy output, energy load and energy storage by time period, thereby achieving carbon reduction while improving electricity flexibility indicators, limiting carbon emissions while also promoting economic development and ensuring normal life, and achieving a balance between economic development and environmental protection.

[0055] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements any one of the above-mentioned carbon emission optimization methods when executed by a processor.

[0056] The computer-readable storage medium of the present invention predicts energy parameters and carbon emission parameters for each time period through rapid and automated modeling and subdividing the model, predicts energy load and optimizes energy storage by time period, and reasonably optimizes energy output, energy load and energy storage by time period, thereby achieving carbon reduction while improving electricity flexibility indicators, limiting carbon emissions while also promoting economic development and ensuring normal life, taking into account both environmental protection and economy, and achieving a balance between economic development and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a flow chart of the carbon emission optimization method in an embodiment of the present invention;

[0058] Figure 2 This is a flow chart of the carbon emission optimization method in an embodiment of the present invention;

[0059] Figure 3 This is a flow chart of the carbon emission optimization method in an embodiment of the present invention;

[0060] Figure 4 This is a flow chart of the carbon emission optimization method in an embodiment of the present invention;

[0061] Figure 5 This is a flow chart of the carbon emission optimization method in an embodiment of the present invention;

[0062] Figure 6 This is a flow chart of the carbon emission optimization method in an embodiment of the present invention;

[0063] Figure 7 This is a flow chart of the carbon emission optimization method in an embodiment of the present invention;

[0064] Figure 8 This is a schematic diagram of a carbon emission optimization device in an embodiment of the present invention;

[0065] Fig. 9 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0067] Combination Figure 1 As shown, the carbon emission optimization method of the present invention comprises:

[0068] S1: According to the energy output model and energy output equipment, obtain the actual energy output and carbon emissions in different time periods;

[0069] Specifically, the energy output model is used to predict the energy output equipment to be optimized, and the actual energy output and the actual output carbon emissions in different time periods are obtained. The prediction can be achieved through training based on a neural network.

[0070] S2: Obtain multiple groups of time period reference quantities that match the actual energy output in the time period, each group of the time period reference quantities includes a time period reference energy load and a time period reference energy storage;

[0071] Specifically, the actual energy output in each time period is obtained according to the prediction results, and the energy load and energy storage corresponding to the time period are obtained, wherein the energy load comes from various power infrastructures, including various buildings, and the energy load and energy storage obtained are obtained from various types of buildings.

[0072] S3: According to the energy load model and the energy storage model, a group of reference carbon emissions corresponding to each group of the time period reference amounts is obtained, wherein the group of reference carbon emissions includes reference load carbon emissions and reference storage carbon emissions;

[0073] Specifically, the reference load carbon emissions are predicted through the energy load model, and the reference storage carbon emissions are predicted through the energy storage model. The predictions are made simultaneously through the two models, and the two models can be deep learning network models. By training according to historical data, the output of reference load carbon emissions and reference storage carbon emissions is realized.

[0074] S4: according to the actual output carbon emissions in the time periods, the reference load carbon emissions and the reference storage carbon emissions, obtaining the optimized carbon emissions from the multi-component time period reference amounts;

[0075] Specifically, according to the above-obtained optimized energy output, optimized energy load and optimized energy storage in different time periods, the corresponding optimized carbon emissions are calculated by comparing with the reference amounts.

[0076] S5: Obtaining the optimized energy output amount, the optimized energy load amount and the optimized energy storage amount in different time periods according to the optimized carbon emissions, the energy output model, the energy load model and the energy storage model;

[0077] Specifically, according to the optimized carbon emissions and combined with the energy output model, the energy output equipment to be optimized is predicted to obtain the actual energy output in each time period and the actual output carbon emissions in each time period, and each optimized parameter is obtained respectively, namely the optimized energy output in each time period, the optimized energy load in each time period and the optimized energy storage in each time period.

[0078] In the optimization part, in the preferred embodiment of the invention, a genetic algorithm can be used for solving, and the optimized energy output, optimized energy load and optimized energy storage are taken as chromosomes, and the optimized energy output, optimized energy load and optimized energy storage of the same group are taken as an individual, and the optimized individuals are discarded with reference to the roulette rules, and the optimized energy output, optimized energy load and optimized energy storage within the individuals are randomly exchanged, and then any optimized energy output, optimized energy load and optimized energy storage in an individual are randomly changed. After that, it is determined whether the optimization times are met. If so, the best individual is output, that is, a set of parameters with the best carbon emission optimization effect.

[0079] In a preferred embodiment of the present invention, a particle algorithm may be used for calculation:

[0080] The optimized parameters are regarded as a population, where each parameter represents a particle;

[0081] The population is updated or optimized according to the results of the previous generation. When the number of optimization iterations is reached, the optimal population can be output, that is, a set of parameters with the best carbon emission optimization effect.

[0082] In an embodiment of the present invention, the population update formula may be:

[0083] x t,T =x t-1,T +q t-1,T ;

[0084] q t,T =wq t-1,T +r1(P bestt -x t-1,T )+r2(g best -x t-1,T );

[0085] Among them, x t,T represents the optimization parameters of the i-th particle in the time period from t to T, q t,T represents the optimized value in the time period from t to T, w represents the weight coefficient, and r1 and r2 represent random numbers between 0 and 1.

[0086] In an embodiment of the present invention, an energy output model is used to predict the energy output equipment to be optimized, and the actual energy output and the actual output carbon emissions in each time period are obtained. Then, a certain number of time period reference quantities corresponding to the actual energy output in each time period are obtained; each group of time period reference quantities is input into an energy load model and an energy storage model to obtain corresponding reference load carbon emissions and reference storage carbon emissions, and the carbon emissions to be optimized are obtained from multiple groups of time period reference quantities based on the obtained actual output carbon emissions in each time period, reference load carbon emissions and reference storage carbon emissions; and the carbon emissions are optimized based on the optimized energy output in each time period, the optimized energy load in each time period and the optimized energy storage in each time period. The method of the embodiment of the present invention obtains multiple groups of possible energy loads and energy storage amounts according to energy output, and obtains the optimal energy load and energy storage amount according to carbon emissions, which can not only meet the energy load required for production, but also optimize carbon emissions. In the embodiment of the present invention, the model used in the training process can adjust the parameters in the training data set according to local policies or other requirements during model training, so that the model outputs results according to specific requirements. For example, adjustable parameters are set in the training data set, and the parameters are adjusted with the energy level to change the actual function of the model.

[0087] In a preferred embodiment of the present invention, a large number of energy load curves can be generated through the load model, based on different scenarios and according to the common points of the reference quantities in the time period at the load law characteristic level, and the reference load carbon emissions and reference storage carbon emissions can be calibrated through the Bayesian calibration method; the optimized carbon emissions are obtained based on the genetic algorithm model, and then the optimized energy output, energy load and energy storage are obtained through deep reinforcement learning.

[0088] In one embodiment of the present invention, a time period can be a day, a month, a quarter or a year; or it can be a working day in a week as a time period, and a non-working day in a week as a time period; or it can be every hour of a day as a time period; or it can be a time period divided according to needs in a day, such as 8 am to 12 noon as a time period, 12 noon to 2 pm as a time period, etc., which will not be repeated here.

[0089] The carbon emission optimization method of the present invention predicts the energy parameters and carbon emission parameters of each time period through rapid automatic modeling and subdividing the model, predicts the energy load and optimizes the energy storage by time period, and reasonably optimizes the energy output, energy load and energy storage by time period, thereby reducing carbon emissions within the time period, achieving carbon reduction while improving the flexibility of electricity consumption, limiting carbon emissions while also promoting economic development and ensuring normal life, taking into account both environmental protection and economy, and achieving a balance between economic development and environmental protection.

[0090] Combination Figure 2 As shown, in the embodiment of the present invention, before obtaining the actual energy output and the actual output carbon emissions in different time periods, the carbon emission optimization method further includes:

[0091] obtaining the energy output model;

[0092] The obtaining of the energy output model comprises:

[0093] S11: Obtain the type and scale of each energy production equipment;

[0094] S12: according to the type and scale of each energy production device, obtaining the time-divided training energy output and time-divided training output carbon emission of each energy production device;

[0095] S13: Acquire the energy production model according to the time-phased training energy production of each energy production device and the time-phased training energy production carbon emission.

[0096] In this embodiment, before processing through the energy output model, it is necessary to construct an energy output model, adopt neural network learning, predict the energy output and carbon emissions within a time period, and obtain the time period training energy output and time period training output carbon emissions of each energy output equipment by the type and scale of each energy output equipment as the training data set to train the model. When the model can output the corresponding time period actual energy output and time period actual output carbon emissions through the time period training energy output and time period training output carbon emissions, wherein, when the deviation value between the time period actual energy output and time period actual output carbon emissions output during model training and the time period training energy output and time period training output carbon emissions in the training data set is less than or equal to the preset threshold value, it means that the model training is completed and the model can be used as an energy output model.

[0097] Among them, in the embodiment of the present invention, Among them, the impact of each energy output equipment type and scale on energy output and carbon emissions is abstracted as a coefficient F, t is the start time, T is the end time, and in the time period between t and T, it is necessary to synthesize the actual data of each device based on actual detection and integrate it into the energy output model.

[0098] In a preferred embodiment of the present invention, the type of energy production equipment can be civil equipment types such as power supply or heating, or industrial equipment types such as large-scale machinery production. Different equipment types correspond to different carbon emissions. Therefore, the carbon emissions of different equipment types are predicted, and the carbon emissions corresponding to different equipment in different time periods are output.

[0099] The carbon emission optimization method of the present invention can accurately and real-time output the actual energy output and the actual carbon emissions in different time periods by training the energy output model, so as to facilitate the subsequent precise optimization of carbon emissions, promote economic development while limiting carbon emissions, take into account both environmental protection and economy, and achieve a balance between economic development and environmental protection.

[0100] Combination Figure 3 As shown, in the embodiment of the present invention, before obtaining the multi-component time period reference quantity matching the actual energy output in the time period, the method further includes:

[0101] Obtain energy storage models;

[0102] The energy storage model includes:

[0103] S31: Obtain the type of each energy storage device;

[0104] S32: Obtaining the time-divided energy storage capacity of each energy storage device;

[0105] S33: Obtaining the time-divided contribution of each energy storage device to energy storage;

[0106] S34: Obtaining the carbon emissions of each energy storage device by time period;

[0107] S35: Acquire the energy storage model according to the type of each energy storage device, the time-divided energy storage capacity of each energy storage device, the time-divided contribution of each energy storage device to energy storage, and the time-divided training carbon emissions of each energy storage device.

[0108] In this embodiment, before obtaining a multi-component time period reference quantity that matches the actual energy output in each time period, it is necessary to first construct and train its energy storage model, and use the corresponding time period energy storage capacity of each energy storage device, the time period contribution of each energy storage device to energy storage, and the time period training carbon emissions of each energy storage device as training data sets, among which the contribution degree is selected as a reference for the greater contribution to energy storage, and the corresponding training data set is input into the model for training to obtain the corresponding time period reference quantity. When the model meets the conditions, it can be used as an energy storage model.

[0109] In a preferred embodiment of the present invention, the types of various energy production devices can generally be battery storage, water storage, etc. By considering the time-sharing energy storage capacity of each energy storage device, such as the electrical capacity corresponding to battery storage, the water storage capacity corresponding to water storage, safety performance, etc., the model is trained using the above data to obtain an energy storage model.

[0110] The carbon emission optimization method of the present invention can accurately and real-time output the actual energy output and the actual carbon emissions in different time periods by training the energy output model, so as to facilitate the subsequent precise optimization of carbon emissions, promote economic development while limiting carbon emissions, take into account both environmental protection and economy, and achieve a balance between economic development and environmental protection.

[0111] Combination Figure 4 As shown, in the embodiment of the present invention, the step of obtaining the carbon emissions of each energy storage device in different time periods includes:

[0112] S3401: Obtaining the time-divided training carbon emissions corresponding to the storage capacity of each energy storage device;

[0113] S3402: Obtaining time-divided training carbon emission information corresponding to the loss amount of each energy storage device;

[0114] S3403: Obtain the time-divided carbon emissions of each energy storage device according to the time-divided training carbon emissions corresponding to the storage capacity of each energy storage device and the time-divided training carbon emissions information corresponding to the loss of each energy storage device.

[0115] In this embodiment, the time-division training carbon emissions corresponding to the storage capacity of each energy storage device and the time-division training carbon emissions information corresponding to the loss of each energy storage device are calculated according to the system to obtain the time-division carbon emissions of each energy storage device.

[0116] In a preferred embodiment of the present invention, the carbon emissions of the corresponding storage devices in different time periods are obtained, including the carbon emissions and carbon emission information required for the water storage equipment to store water in the different time periods. The carbon emissions of the energy storage equipment in a certain period of time can be obtained based on the emissions and emission information.

[0117] The carbon emission optimization method of the present invention obtains the time-phased training carbon emissions corresponding to the storage capacity of each energy storage device, which is convenient for subsequent precise optimization of carbon emissions. It limits carbon emissions while also promoting economic development, taking into account both environmental protection and economy, and achieving a balance between economic development and environmental protection.

[0118] Combination Figure 5 As shown, in the embodiment of the present invention, before obtaining the multi-component time period reference quantity matching the actual energy output in the time period, combined with Figure 6 As shown, the carbon emission optimization method further includes: S2: obtaining an energy load model of the entire building;

[0119] The method of obtaining the energy load model of the entire building includes:

[0120] S21: Obtain the type of each individual building contained in the overall building;

[0121] S22: Obtaining a single load model of the type of each single building;

[0122] S23: Obtaining the arrangement of each individual building in the entire building complex;

[0123] S24: Acquire an energy load model of the overall building according to the types of individual buildings included in the overall building, the arrangement of the individual buildings, and the individual load models of the individual buildings.

[0124] In this embodiment, since the source of energy load comes from various power-consuming infrastructures, including various buildings, the energy load and energy storage are obtained from various types of buildings. Therefore, based on the clustering method, the arrangement of each single building in the overall building complex is mined. Through the single load model of each single building type and the single building sorting method of the overall building complex, random sampling is performed through the Monte Carlo sampling method for the attribute characteristics of typical industrial communities. The attribute characteristics of the detected community and other industrial parks are taken as expectations to comprehensively obtain the corresponding overall building energy load model. According to the type of single buildings in the overall building and the energy load model corresponding to each single building, the energy load model of the detected overall building is generated. The energy load model can calculate the loads of various types of power generation, cold sources, heat sources, and energy storage equipment in the overall buildings in the area.

[0125] Specifically, in a preferred embodiment of the present invention, the above-mentioned single building can be an industrial building, commercial building or civil building such as a hospital, school, residential building, office building and factory. Different single buildings correspond to different loads. Industrial buildings such as factories and commercial buildings have relatively fixed working hours, resulting in a higher load during the day, and civil buildings such as residential buildings have a higher load at night; and the sorting method of the corresponding buildings is obtained, wherein industrial buildings can be arranged in the form of industrial park building complexes, using centralized cooling or centralized heating, resulting in a higher overall load and a lower average load, while commercial buildings such as office buildings have a higher average load. The above data can be used to form a training data set to train the model, and finally a load model corresponding to the single building is obtained.

[0126] The carbon emission optimization method of the present invention generates a large number of energy load models of different buildings and simulates the models to dig out the energy load laws of typical buildings and their corresponding building attribute characteristics.

[0127] Combination Figure 7 As shown, in the embodiment of the present invention, the step of obtaining the single load model of the type of each single building includes:

[0128] S2201: Obtain the type of the single building;

[0129] S2202: Obtaining the appearance of the single building;

[0130] S2203: Obtaining the composition of the single building;

[0131] S2204: Obtain the thermal insulation level of the single building;

[0132] S2205: Obtain the time-divided training energy load of the single building, where the time-divided training energy load of the single building includes the time-divided training electricity load of the single building, the time-divided training cooling load of the single building, and the time-divided training heating load of the single building;

[0133] S2206: Obtain the time-divided training carbon emissions of the single building according to the type of the single building, the shape of the single building, the composition of the single building, the insulation level of the single building, and the time-divided training energy load of the single building;

[0134] S2207: Acquire a single load model of the type of each single building according to the obtained time-phased training energy load of the single building and the time-phased training carbon emission of the single building.

[0135] Specifically, in this embodiment, by taking the type of single building, the appearance of single building, the composition of single building, the insulation level of single building and the time period training energy load of single building as the training data set, when the type, appearance and composition of single building are acquired, detection equipment such as drones can be used to identify and detect the target single building, and then modeling is performed according to the grid method to represent the target single building in a three-dimensional manner, and then the existing data corresponding to the single building, that is, the corresponding time period energy load model, is used to train the load model of the actual single building to be detected.

[0136] In the embodiment of the present invention, the single load model can be obtained according to the formula: m(t)A1(t)+nB1+jC1+kD1, wherein the type A of the single building is abstractly calculated to obtain Abstractly calculate the shape B to get The composition of the single building is abstractly calculated to obtain C1; m, n, j, k are all weight coefficients of the corresponding parameters.

[0137] In a preferred embodiment of the present invention, the above-mentioned single building can be an industrial building, commercial building or civil building such as a hospital, school, residential building, office building and factory. Among them, civil buildings such as residential buildings are concentratedly distributed and require a high insulation level. Due to seasonal reasons, their load is greater than other buildings. At the same time, the electricity consumption time of civil buildings is relatively fixed, resulting in huge carbon emissions within a fixed time period. Therefore, the energy load and carbon emissions of the corresponding building in different time periods can be obtained according to its building type, building composition and insulation level.

[0138] The carbon emission optimization method of the present invention constructs a single-unit compliance model for a single building, which is convenient for subsequent precise optimization of carbon emissions. It limits carbon emissions while also promoting economic development, taking into account both environmental protection and economy, and achieving a balance between economic development and environmental protection.

[0139] In the embodiment of the present invention, after obtaining the time-divided optimized energy output, time-divided optimized energy load and time-divided optimized energy storage, the carbon emission optimization method further includes:

[0140] Carbon emissions are optimized according to the time-phase optimized energy output, the time-phase optimized energy load, and the time-phase optimized energy storage.

[0141] In this embodiment, when the time-phase optimized energy output, the time-phase optimized energy load and the time-phase optimized energy storage are obtained, the carbon emissions can be optimized in different time periods according to the parameters given by the model.

[0142] The carbon emission optimization method of the present invention predicts the carbon emission optimization and predicts the optimization through a model, so that the optimization parameters are no longer fixed thresholds, but flexibly optimize carbon emissions according to different carbon emissions and energy output equipment, thereby limiting carbon emissions while also promoting economic development, taking into account both environmental protection and economy, and achieving a balance between economic development and environmental protection.

[0143] In a specific application scenario of the present invention, according to the energy output model and the actual energy output entity, the energy output for the period is obtained to be 1000 units, and the output carbon emissions is 200 units.

[0144] The obtained matched multi-component time period reference quantities are described below in terms of energy load quantity and energy storage quantity for the convenience of description.

[0145] The basic principle for matching is energy output ≥ energy load + energy storage, and the optimal matching principle is energy output = energy load + energy storage.

[0146] According to the models of the above embodiments, the energy load and the corresponding load carbon emissions obtained in different time periods are:

[0147] (1) Load 900, load carbon emission 300; storage capacity 100, storage carbon emission 200;

[0148] (2) Load 900, load carbon emission 300; storage capacity 80, storage carbon emission 200;

[0149] (3) Load 700, load carbon emission 200; storage capacity 300, storage carbon emission 400;

[0150] (4) Load 600, load carbon emission 180; storage 400, storage carbon emission 500;

[0151] (5) Load 1000, load carbon emission 400. Storage 0, storage carbon emission 100.

[0152] Calculating the carbon emissions of each group, we get: (1) 500, (2) 500, (3) 600, (4) 680, (5) 500.

[0153] The carbon emissions of the above groups (1)(2)(5) are all minimal, but in (2), the load plus storage is less than the output, that is, there is a large energy loss, so (1) and (5) can be used as the optimized carbon emissions.

[0154] The choice between (1) and (5) can be made based on more specific application scenarios. For example, if the expected energy output in the next period is insufficient, but the expected load is large, then (1) can be preferred. If the expected load in the next period is large relative to the expected energy output, or the expected energy storage is small, then (5) can be preferred.

[0155] After obtaining the optimized carbon emissions, the optimized time-divided energy output, the optimized time-divided energy load and the optimized time-divided energy storage can be obtained according to the optimized carbon emissions, energy output model, energy load model and energy storage model.

[0156] Combination Figure 8 As shown, the present invention also provides a carbon emission optimization device 100, the device comprising:

[0157] The output and emission acquisition unit 110 is used to acquire the actual energy output and the actual carbon emission in different time periods according to the energy output model and energy output equipment;

[0158] The load and storage acquisition unit 120 is used to acquire a multi-group time period reference quantity that matches the actual energy output in the time period, each group of the time period reference quantity includes a time period reference energy load quantity and a time period reference energy storage quantity;

[0159] A reference carbon emission acquisition unit 130 is used to acquire a group of reference carbon emissions corresponding to each group of the time-divided reference amounts according to an energy load model and an energy storage model, wherein the group of reference carbon emissions includes reference load carbon emissions and reference storage carbon emissions;

[0160] The optimization unit 140 is used to obtain the optimized carbon emissions from the multi-component time period reference amount according to the actual output carbon emissions in the time period, the reference load carbon emissions and the reference storage carbon emissions;

[0161] The optimization unit 140 is also used to obtain the time-divided optimized energy output, time-divided optimized energy load and time-divided optimized energy storage according to the optimized carbon emissions, the energy output model, the energy load model and the energy storage model.

[0162] In one embodiment of the present invention, the carbon emission optimization device 100 further includes a model training unit 150;

[0163] The model training unit 150 is used to obtain the energy production model; obtain the type and scale of each energy production device; obtain the time period training energy production and time period training output carbon emissions of each energy production device according to the type and scale of each energy production device; obtain the energy production model according to the time period training energy production and time period training energy output carbon emissions of each energy production device.

[0164] The model training unit 150 is also used to obtain an energy storage model; obtain the type of each energy storage device; obtain the time-divided energy storage capacity of each energy storage device; obtain the time-divided contribution of each energy storage device to energy storage; obtain the time-divided carbon emissions of each energy storage device; and obtain the energy storage model based on the type of each energy storage device, the time-divided energy storage capacity of each energy storage device, the time-divided contribution of each energy storage device to energy storage, and the time-divided training carbon emissions of each energy storage device.

[0165] The production and emission acquisition unit 110 is also used to obtain the time period trained carbon emissions corresponding to the storage capacity of each energy storage device; obtain the time period trained carbon emission information corresponding to the loss of each energy storage device; and obtain the time period carbon emissions of each energy storage device based on the time period trained carbon emissions corresponding to the storage capacity of each energy storage device and the time period trained carbon emission information corresponding to the loss of each energy storage device.

[0166] The model training unit 150 is also used to obtain the type of each individual building included in the overall building; obtain the individual load model of the type of each individual building; and obtain the arrangement of each individual building in the overall building complex.

[0167] The model training unit 150 is also used to obtain the energy load model of the overall building according to the types of individual buildings included in the overall building, the arrangement of the individual buildings and the individual load models of the individual buildings; obtain the types of the individual buildings; obtain the appearance of the individual buildings; obtain the composition of the individual buildings; obtain the insulation level of the individual buildings; obtain the time-divided training energy load of the individual buildings, the time-divided training energy load of the individual buildings includes the time-divided training electricity load of the individual buildings, the time-divided training cooling load of the individual buildings and the time-divided training heating load of the individual buildings; obtain the time-divided training carbon emissions of the individual buildings according to the types of the individual buildings, the appearance of the individual buildings, the composition of the individual buildings, the insulation level of the individual buildings and the time-divided training energy load of the individual buildings; obtain the individual load models of the types of the individual buildings according to the time-divided training energy load of the individual buildings and the time-divided training carbon emissions of the individual buildings.

[0168] The optimization unit 140 is further used to optimize carbon emissions according to the time-divided optimized energy output, the time-divided optimized energy load, and the time-divided optimized energy storage.

[0169] The carbon emission optimization device of the present invention predicts the energy parameters and carbon emission parameters of each time period through rapid and automated modeling and subdividing the model, predicts the energy load and optimizes the energy storage by time period, and reasonably optimizes the energy output, energy load and energy storage by time period, thereby reducing carbon emissions during this period, limiting carbon emissions while also promoting economic development, taking into account both environmental protection and economy, and achieving a balance between economic development and environmental protection.

[0170] Combination Fig. 9 As shown, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0171] According to the energy output model and energy output equipment, obtain the actual energy output and carbon emissions in different time periods;

[0172] Acquire a plurality of time period reference quantities that match the actual energy output in the time period, each group of the time period reference quantities including a time period reference energy load and a time period reference energy storage;

[0173] According to the energy load model and the energy storage model, a group of reference carbon emissions corresponding to each group of the time period reference amounts is obtained, wherein the group of reference carbon emissions includes reference load carbon emissions and reference storage carbon emissions;

[0174] According to the actual output carbon emissions in different time periods, the reference load carbon emissions and the reference storage carbon emissions, obtaining the optimized carbon emissions from the multi-component time period reference amounts;

[0175] According to the optimized carbon emissions, the energy output model, the energy load model and the energy storage model, the time-phase optimized energy output, time-phase optimized energy load and time-phase optimized energy storage are obtained.

[0176] The computer equipment of the present invention predicts the energy parameters and carbon emission parameters of each time period through rapid and automated modeling and subdividing the model, predicts the energy load and optimizes the energy storage by time period, and reasonably optimizes the energy output, energy load and energy storage by time period, thereby reducing carbon emissions within the time period, achieving carbon reduction while improving the flexibility index of electricity consumption, and promoting economic development and ensuring normal life while limiting carbon emissions, thereby achieving a balance between economic development and environmental protection.

[0177] The present invention also provides a computer-readable storage medium, wherein a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0178] According to the energy output model and energy output equipment, obtain the actual energy output and carbon emissions in different time periods;

[0179] Acquire a plurality of time period reference quantities that match the actual energy output in the time period, each group of the time period reference quantities including a time period reference energy load and a time period reference energy storage;

[0180] According to the energy load model and the energy storage model, a group of reference carbon emissions corresponding to each group of the time period reference amounts is obtained, wherein the group of reference carbon emissions includes reference load carbon emissions and reference storage carbon emissions;

[0181] According to the actual output carbon emissions in different time periods, the reference load carbon emissions and the reference storage carbon emissions, obtaining the optimized carbon emissions from the multi-component time period reference amounts;

[0182] According to the optimized carbon emissions, the energy output model, the energy load model and the energy storage model, the time-phase optimized energy output, time-phase optimized energy load and time-phase optimized energy storage are obtained.

[0183] The computer-readable storage medium of the present invention predicts energy parameters and carbon emission parameters for each time period through rapid and automated modeling and subdividing the model, predicts energy load and optimizes energy storage by time period, and reasonably optimizes energy output, energy load and energy storage by time period, thereby achieving carbon reduction while improving electricity flexibility indicators, limiting carbon emissions while also promoting economic development and ensuring normal life, taking into account both environmental protection and economy, and achieving a balance between economic development and environmental protection.

[0184] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0185] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0186] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A carbon emission optimization method, characterized in that: The carbon emission optimization method comprises: According to the energy output model and energy output equipment, obtain the actual energy output and carbon emissions in different time periods; Acquire a plurality of time period reference quantities that match the actual energy output in the time period, each group of the time period reference quantities including a time period reference energy load and a time period reference energy storage; According to the energy load model and the energy storage model, a group of reference carbon emissions corresponding to each group of the time period reference amounts is obtained, wherein the group of reference carbon emissions includes reference load carbon emissions and reference storage carbon emissions; According to the actual output carbon emissions in different time periods, the reference load carbon emissions and the reference storage carbon emissions, obtaining the optimized carbon emissions from the multi-component time period reference amounts; According to the optimized carbon emissions, the energy output model, the energy load model and the energy storage model, obtaining the time-divided optimized energy output, the time-divided optimized energy load and the time-divided optimized energy storage; Carbon emissions are optimized according to the time-phase optimized energy output, the time-phase optimized energy load, and the time-phase optimized energy storage.

2. The carbon emission optimization method according to claim 1, characterized in that: Before obtaining the actual energy output and the actual carbon emissions by time period, the carbon emissions optimization method further includes: obtaining the energy output model; The obtaining of the energy output model comprises: Obtain the type and size of each energy production facility; According to the type and scale of each energy production device, obtain the time-divided training energy output and time-divided training output carbon emissions of each energy production device; The energy production model is obtained according to the time-phased training energy production and the time-phased training energy production carbon emissions of each energy production device.

3. The carbon emission optimization method according to claim 1, characterized in that: Before obtaining the multi-component time period reference amount that matches the actual energy output amount in the time period, the carbon emission optimization method further includes: obtaining the energy storage model; The obtaining of the energy storage model comprises: Obtain the type of each energy storage device; Obtain the time-divided energy storage capacity of each energy storage device; Obtain the time-divided contribution of each energy storage device to energy storage; Obtain the carbon emissions of each energy storage device by time period; The energy storage model is obtained according to the type of each energy storage device, the time-divided energy storage capacity of each energy storage device, the time-divided contribution of each energy storage device to energy storage, and the time-divided training carbon emissions of each energy storage device.

4. The carbon emission optimization method according to claim 3, characterized in that: The step of obtaining the carbon emissions of each energy storage device by time period includes: Obtaining the time-divided training carbon emissions corresponding to the storage capacity of each energy storage device; Obtaining time-division training carbon emission information corresponding to the loss amount of each energy storage device; The time-divided carbon emissions of each energy storage device are obtained according to the time-divided training carbon emissions corresponding to the storage capacity of each energy storage device and the time-divided training carbon emissions information corresponding to the loss of each energy storage device.

5. The carbon emission optimization method according to claim 1, characterized in that: Before obtaining the multi-component time period reference quantity that matches the actual energy output quantity in the time period, the carbon emission optimization method further includes: obtaining the energy load model of the entire building; The step of obtaining the energy load model of the entire building includes: Get the types of each individual building contained in the overall building; Obtaining a single load model of the type of each single building; Obtain the arrangement of each individual building in the entire building complex; The energy load model of the overall building is obtained according to the types of individual buildings included in the overall building, the arrangement of the individual buildings and the individual load models of the individual buildings.

6. The carbon emission optimization method according to claim 5, characterized in that: The step of obtaining the single load model of each single building type includes: Get the type of the single building; Obtaining the appearance of the single building; Obtaining the composition of the single building; Obtaining the thermal insulation level of the single building; Obtaining the time-divided training energy load of the single building, wherein the time-divided training energy load of the single building includes the time-divided training electricity load of the single building, the time-divided training cooling load of the single building, and the time-divided training heating load of the single building; According to the type of the single building, the shape of the single building, the composition of the single building, the insulation level of the single building and the energy load of the training in different time periods of the single building, the carbon emission of the training in different time periods of the single building is obtained; According to the obtained time-phased training energy load of the single building and the time-phased training carbon emission of the single building, a single load model of the type of each single building is obtained.

7. A carbon emission optimization device, characterized in that: The device comprises: The output and emission acquisition unit is used to obtain the actual energy output and carbon emissions of each time period according to the energy output model and energy output equipment; A load and storage acquisition unit, used to acquire a multi-group time period reference quantity that matches the actual energy output in the time period, each group of the time period reference quantity includes a time period reference energy load quantity and a time period reference energy storage quantity; A reference carbon emission acquisition unit, used for acquiring a group of reference carbon emissions corresponding to each group of the time period reference amounts according to an energy load model and an energy storage model, wherein the group of reference carbon emissions includes reference load carbon emissions and reference storage carbon emissions; An optimization unit, configured to obtain an optimized carbon emission amount from the multi-component time period reference amount according to the actual output carbon emission amount in the time period, the reference load carbon emission amount and the reference storage carbon emission amount; The optimization unit is also used to obtain the time-divided optimized energy output, the time-divided optimized energy load and the time-divided optimized energy storage according to the optimized carbon emissions, the energy output model, the energy load model and the energy storage model; and optimize carbon emissions according to the time-divided optimized energy output, the time-divided optimized energy load and the time-divided optimized energy storage.

8. A computer 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, the carbon emission optimization method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the carbon emission optimization method according to any one of claims 1 to 6 is implemented.

Images