A method and system for scheduling carbon emissions of a comprehensive energy system under variable working conditions

Abstract

The application discloses a kind of variable working condition under the scheduling method and system of comprehensive energy system carbon emission, method includes: obtaining the multi-energy coupling relationship of comprehensive energy system and the variable working condition characteristics of energy conversion equipment;According to the multi-energy coupling relationship of comprehensive energy system, establish energy hub model;Based on the variable working condition characteristics of energy conversion equipment, the efficiency parameter in the energy hub model is corrected using the efficiency correction model based on deep neural network constructed in advance, to obtain dynamic energy hub model;Based on dynamic energy hub model, construct the scheduling model of comprehensive energy system carbon emission under variable working condition, and the scheduling scheme of comprehensive energy system under variable working condition is obtained by solving.This application pays attention to the influence of equipment variable working condition characteristics on system carbon emission, can realize the low-carbon operation of comprehensive energy system, improve the solving speed and accuracy of scheduling model.

Description

Technical Field

[0001] This invention relates to a method and system for scheduling carbon emissions of an integrated energy system under varying operating conditions, belonging to the field of integrated energy technology for power systems. Background Technology

[0002] Currently, research on the optimization of integrated energy system (IES) operation mainly includes two aspects: system modeling and scheduling. The former focuses on equipment modeling and power flow calculation, while the latter mainly focuses on optimization algorithms and source-load uncertainty analysis. However, these studies often neglect the variable operating characteristics of equipment, simplifying the efficiency of energy conversion equipment to a constant. In reality, due to the fluctuation of load and environmental factors, equipment usually operates under variable operating conditions. Ignoring the variable operating characteristics of individual equipment can lead to power supply deviations that can propagate to the entire system, causing a shift in the system's energy conversion relationship and reducing the accuracy of optimized scheduling results. Therefore, accurate modeling of IES under variable operating conditions is of great significance for ensuring system supply-demand balance and optimized operation.

[0003] Research on the variable operating condition characteristics of equipment has made some progress. Reference: Huang Wujing, Zhang Ning, Wang Yi, et al. Matrix modeling of energy hub with variable energy efficiencies[J]. International Journal of Electrical Power & Energy Systems, 2020, 119. A piecewise linearization method is used to approximate the variable operating condition efficiency curve, but the prediction accuracy of this method is highly dependent on the accuracy of the linearization pieces. Reference: Li Hong, Du Shiqi. Optimal configuration of integrated energy system considering the variable operating condition characteristics of energy hubs[J]. Modern Electric Power, 2021, 39: 1-8. A dynamic function model of equipment variable operating conditions is established, and an IES mixed integer configuration optimization model is introduced for the variable operating condition characteristics of equipment, but this brings a large amount of computation. All the above studies have established functional models of equipment efficiency and load rate, but the large amount of complex mathematical calculations limits their practical application.

[0004] With the rapid development of emerging technologies such as big data and intelligent methods, deep neural networks (DNNs) have been widely used in IES, providing new solutions for prediction problems that are difficult to model accurately.

[0005] To fully realize the economic and environmental benefits of IES, carbon emission scheduling of IES has become a research hotspot. Reference: Wei Zhenbo, Wei Pingan, Guo Yi, et al. Decentralized low-carbon economic scheduling of power-gas interconnection network considering demand-side management and carbon trading [J]. High Voltage Technology, 2021, 47(01): 33-47. CO2 emission targets are introduced into the constraints of the power-gas interconnection network scheduling model. Reference: Wu Lei. Research on low-carbon economic scheduling of integrated energy system at multiple time scales [D]. Shenyang: Shenyang University of Technology, 2021. The optimization method of low-carbon scheduling of IES is studied to effectively achieve carbon emission reduction. Reference: Han Xiaoqing, Li Tingjun, Zhang Dongxia, et al. New problems and key technologies of new power system planning under dual carbon targets [J]. High Voltage Technology, 2021, 47(09): 3036-3046. Dynamic carbon emission factors are added to guide user electricity consumption behavior, and an optimization scheduling method with low carbon as the target is proposed. Reference: Li Yaowang, Zhang Ning, Du Ershun, et al. Research and benefit analysis of low-carbon demand response mechanism for power system based on carbon emission flow [J]. Proceedings of the CSEE, 2022, 42(08): 2830-2842. Based on demand-side management and carbon trading, load regulation is achieved through demand response, which further reduces system operating costs and carbon emissions.

[0006] However, existing research pays little attention to the impact of equipment's variable operating conditions on system carbon emissions. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a scheduling method and system for carbon emissions of integrated energy systems under varying operating conditions. This method focuses on the impact of equipment's varying operating characteristics on system carbon emissions, enabling low-carbon operation of integrated energy systems and improving the solution speed and accuracy of scheduling models. To achieve the above objectives, this invention employs the following technical solution:

[0008] In a first aspect, the present invention provides a method for scheduling carbon emissions of an integrated energy system under varying operating conditions, comprising:

[0009] To obtain the multi-energy coupling relationships of integrated energy systems and the variable operating condition characteristics of energy conversion equipment;

[0010] Based on the multi-energy coupling relationship of the integrated energy system, an energy hub model is established;

[0011] Based on the variable operating condition characteristics of the energy conversion equipment, the efficiency parameters in the energy hub model are corrected using a pre-built efficiency correction model based on a deep neural network to obtain a dynamic energy hub model.

[0012] Based on the dynamic energy hub model, a scheduling model for carbon emissions of the integrated energy system under varying operating conditions is constructed, and the scheduling scheme of the integrated energy system under varying operating conditions is obtained by solving the problem.

[0013] In conjunction with the first aspect, the pre-constructed efficiency correction model based on deep neural networks is further expressed by the following formula:

[0014] (1)

[0015] In equation (1), i represents the energy conversion device; η i,t Let T be the efficiency of energy conversion device i at time t; i,t F represents the ambient temperature of the energy conversion device i at time t. i,t The atmospheric pressure of the operating environment of energy conversion device i at time t; N i,t Let the load power of energy conversion device i at time t be expressed by the following formula:

[0016] (2)

[0017] In equation (2), P i,t Let P be the output power of energy conversion device i at time t, in kW. i,cap Let i be the capacity of the energy conversion device, in kW.

[0018] In conjunction with the first aspect, the matrix form of the energy hub model is further expressed by the following equation:

[0019] (3)

[0020] In equation (3), L e,t Let L be the electrical load of the integrated energy system at time t. h,t Let η be the heat load of the integrated energy system at time t; CHP For the power generation efficiency of the combined heat and power (CHP) unit, η CHP,h For the heating efficiency of the combined heat and power (CHP) unit, η GB The heating efficiency of gas-fired boilers (GB); P e,t Let P be the power supplied by the electrical energy at time t. g,t η is the gas energy supply power at time t; C For battery charging efficiency (BAT), η D For battery BAT discharge efficiency; W e,t Let BAT be the energy stored in the battery at time t; v t The ratio of natural gas consumed by the combined heat and power (CHP) unit at time t to the natural gas supply at time t is given by the coefficient of proportion.

[0021] In conjunction with the first aspect, the matrix form of the dynamic energy hub model is further expressed by the following equation:

[0022] (4)

[0023] In equation (4), η CHP,t Let η be the power generation efficiency of the combined heat and power (CHP) unit at time t. CHP,h,t Let η be the heating efficiency of the combined heat and power unit CHP at time t. GB,t Let GB be the heating efficiency of the gas-fired boiler at time t.

[0024] In conjunction with the first aspect, the scheduling model for carbon emissions of the integrated energy system under varying operating conditions takes the minimum energy cost of the integrated energy system as its objective function, and is expressed by the following formula:

[0025] (5)

[0026] In equation (5), f c The energy cost of a comprehensive energy system; f ope Energy purchase cost, including electricity purchase cost f e Gas purchase cost f g It can be expressed by the following formula:

[0027] (6)

[0028] In equation (6), T is the scheduling period, and ∆t is the unit scheduling time period; e,t Let c be the electricity purchase price at time t. g The unit price for gas purchase; P e,t Let P be the power purchased at time t. g,t Let t be the gas purchase power.

[0029] In equation (5), f env Environmental costs, including the cost of purchasing electricity from the grid for CO2 emissions. Costs of CO2 emissions from combined heat and power (CHP) units Costs of CO2 emissions from gas-fired boilers (GB standard) It can be expressed by the following formula:

[0030] (7)

[0031] In equation (7), T is the scheduling period, and ∆t is the unit scheduling time period; The environmental cost per unit of CO2 emitted; Carbon emission calculation factor for supplying electricity to the power grid. Calculation factor for carbon emissions per unit output power of combined heat and power (CHP) units. P is the carbon emission calculation factor per unit output power of a gas-fired boiler (GB standard). e,t Let P be the power purchased at time t. CHP,t P represents the output power of the combined heat and power unit (CHP) at time t. GB,tLet GB be the output power of the gas-fired boiler at time t.

[0032] In conjunction with the first aspect, the constraints of the scheduling model for carbon emissions of the integrated energy system under varying operating conditions further include: power balance constraints, tie-line power constraints, energy conversion equipment operation constraints, and energy storage equipment operation constraints.

[0033] The power balance constraint satisfies the multi-energy coupling relationship described by the dynamic energy hub model. The efficiency of the energy conversion equipment in the integrated energy system is calculated by a pre-built efficiency correction model based on a deep neural network.

[0034] The tie-line power constraint ensures that the interaction power between the integrated energy system and the upstream power grid is within a safe range, expressed by the following formula:

[0035] (8)

[0036] In equation (8), P grid,t Let P be the power purchased at time t. grid,cap This is the upper limit of the tie line power.

[0037] The operational constraints of the energy conversion equipment include input and output power relationship constraints and upper and lower limits of the energy conversion equipment output constraints, which are expressed by the following formula:

[0038] (9)

[0039] In equation (9), P CHP,t η represents the output power of the combined heat and power unit (CHP) at time t. CHP,t Let P be the power generation efficiency of the combined heat and power unit CHP at time t. in,CHP,t Let P be the input power of the combined heat and power unit CHP at time t. CHP,cap The upper limit of the output power of the combined heat and power (CHP) unit; P GB,t Let η be the output power of the gas-fired boiler GB at time t. GB,t Let P be the heating efficiency of the gas-fired boiler GB at time t. in,GB,t Let P be the GB input power of the gas boiler at time t. GB,cap This refers to the upper limit of the output power of gas-fired boilers as defined in GB standards.

[0040] The operational constraints of the energy storage device include limitations on charging and discharging power and device capacity, expressed by the following formula:

[0041] (10)

[0042] In equation (10), W e,t For the energy stored in the battery before charging and discharging, W e,t+1The energy stored after the battery BAT is charged and discharged. For the self-discharge rate of battery BAT, P C,t Let η be the charging power of BAT at time t. C For battery charging efficiency (BAT), P D,t Let η be the power released by BAT at time t. D The battery's BAT discharge efficiency is given, and ∆t represents the unit scheduling time period; W cap This refers to the rated capacity of the battery BAT. This represents the maximum charging power of the battery BAT. This represents the maximum power output of the battery BAT; W start For the energy stored in the battery BAT at the beginning of the scheduling cycle; W end This refers to the energy stored in the battery BAT at the end of the scheduling cycle.

[0043] Secondly, the present invention provides a scheduling system for carbon emissions of an integrated energy system under varying operating conditions, comprising:

[0044] To obtain the multi-energy coupling relationships of integrated energy systems and the variable operating condition characteristics of energy conversion equipment;

[0045] Based on the multi-energy coupling relationship of the integrated energy system, an energy hub model is established;

[0046] Based on the variable operating condition characteristics of the energy conversion equipment, the efficiency parameters in the energy hub model are corrected using a pre-built efficiency correction model based on a deep neural network to obtain a dynamic energy hub model.

[0047] Based on the dynamic energy hub model, a scheduling model for carbon emissions of the integrated energy system under varying operating conditions is constructed, and the scheduling scheme of the integrated energy system under varying operating conditions is obtained by solving the problem.

[0048] Thirdly, the present invention provides a computing device, characterized in that it includes a processor and a storage medium;

[0049] The storage medium is used to store instructions;

[0050] The processor is configured to operate according to the instructions to perform the steps of the method described in the first aspect.

[0051] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that the program, when executed by a processor, implements the steps of the method described in the first aspect.

[0052] Compared with the prior art, the beneficial effects achieved by the carbon emission scheduling method and system of an integrated energy system under varying operating conditions provided by the embodiments of the present invention include:

[0053] This invention obtains the multi-energy coupling relationship of an integrated energy system and the variable operating condition characteristics of energy conversion equipment; based on the multi-energy coupling relationship of the integrated energy system, an energy hub model is established; based on the variable operating condition characteristics of the energy conversion equipment, a pre-constructed efficiency correction model based on deep neural networks is used to correct the efficiency parameters in the energy hub model, resulting in a dynamic energy hub model; this invention uses an efficiency correction model based on deep neural networks to model the relationship between the efficiency of energy conversion equipment and load rate, temperature, and air pressure, which helps to improve the problems of large computational load and low accuracy of traditional methods;

[0054] This invention is based on a dynamic energy hub model to construct a scheduling model for carbon emissions of an integrated energy system under varying operating conditions, and solves the scheduling scheme of the integrated energy system under varying operating conditions. This invention considers the strong nonlinearity of equipment efficiency changes, improves the accuracy of the equipment model, enables low-carbon operation of the integrated energy system, and improves the solution speed and accuracy of the scheduling model. Attached Figure Description

[0055] Figure 1 This is a flowchart of a method for scheduling carbon emissions of an integrated energy system under varying operating conditions, provided in Embodiment 1 of the present invention.

[0056] Figure 2 This is a schematic diagram of the structure of a typical integrated energy system in the carbon emission scheduling method of an integrated energy system under varying operating conditions provided in Embodiment 2 of the present invention;

[0057] Figure 3 This is a schematic diagram of the efficiency correction model based on a deep neural network in a carbon emission scheduling method for an integrated energy system under varying operating conditions, provided in Embodiment 2 of the present invention.

[0058] Figure 4 This is a schematic diagram of the dynamic energy hub model in a carbon emission scheduling method for an integrated energy system under varying operating conditions provided in Embodiment 2 of the present invention;

[0059] Figure 5 This is a schematic diagram of the electricity and heat load of a typical integrated energy system under a typical day in a method for scheduling carbon emissions of an integrated energy system under varying operating conditions, provided in Embodiment 2 of the present invention.

[0060] Figure 6 This is a schematic diagram of the temperature and air pressure of a typical integrated energy system operating environment in a method for scheduling carbon emissions of an integrated energy system under varying operating conditions, provided in Embodiment 2 of the present invention.

[0061] Figure 7a This is a schematic diagram of the scheduling results for scenario 1. Figure 7b This is a schematic diagram of the scheduling results for scenario 2. Figure 7c This is a schematic diagram of the scheduling results for scenario 3. Detailed Implementation

[0062] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0063] Example 1:

[0064] like Figure 1 As shown, this embodiment of the invention provides a method for scheduling carbon emissions of an integrated energy system under varying operating conditions, including:

[0065] To obtain the multi-energy coupling relationships of integrated energy systems and the variable operating condition characteristics of energy conversion equipment;

[0066] Based on the multi-energy coupling relationship of the integrated energy system, an energy hub model is established;

[0067] Based on the variable operating condition characteristics of the energy conversion equipment, the efficiency parameters in the energy hub model are corrected using a pre-built efficiency correction model based on a deep neural network to obtain a dynamic energy hub model.

[0068] Based on the dynamic energy hub model, a scheduling model for carbon emissions of the integrated energy system under varying operating conditions is constructed, and the scheduling scheme of the integrated energy system under varying operating conditions is obtained by solving the problem.

[0069] The specific steps are as follows:

[0070] Step 1: Construct an efficiency correction model based on deep neural networks, expressed by the following formula:

[0071] (1)

[0072] In equation (1), i represents the energy conversion device; η i,t Let T be the efficiency of energy conversion device i at time t; i,t F represents the ambient temperature of the energy conversion device i at time t. i,t The atmospheric pressure of the operating environment of energy conversion device i at time t; N i,t Let the load power of energy conversion device i at time t be expressed by the following formula:

[0073] (2)

[0074] In equation (2), P i,t Let P be the output power of energy conversion device i at time t, in kW. i,cap Let i be the capacity of the energy conversion device, in kW.

[0075] Step 2: Obtain the multi-energy coupling relationships of the integrated energy system and the variable operating condition characteristics of the energy conversion equipment. Based on the multi-energy coupling relationships of the integrated energy system, establish an energy hub model.

[0076] The matrix form of the energy hub model is expressed by the following equation:

[0077] (3)

[0078] In equation (3), L e,t Let L be the electrical load of the integrated energy system at time t. h,t Let η be the heat load of the integrated energy system at time t; CHP For the power generation efficiency of the combined heat and power (CHP) unit, η CHP,h For the heating efficiency of the combined heat and power (CHP) unit, η GB The heating efficiency of gas-fired boilers (GB); P e,t Let P be the power supplied by the electrical energy at time t. g,t η is the gas energy supply power at time t; C For battery charging efficiency (BAT), η D For battery BAT discharge efficiency; W e,t Let BAT be the energy stored in the battery at time t; v t The ratio of natural gas consumed by the combined heat and power (CHP) unit at time t to the natural gas supply at time t is given by the coefficient of proportion.

[0079] Step 3: Based on the variable operating condition characteristics of the energy conversion equipment, the efficiency parameters in the energy hub model are corrected using a pre-built efficiency correction model based on a deep neural network to obtain a dynamic energy hub model.

[0080] The matrix form of the dynamic energy hub model is expressed by the following equation:

[0081] (4)

[0082] In equation (4), η CHP,t Let η be the power generation efficiency of the combined heat and power (CHP) unit at time t. CHP,h,t Let η be the heating efficiency of the combined heat and power unit CHP at time t. GB,t Let GB be the heating efficiency of the gas-fired boiler at time t.

[0083] Step 4: Based on the dynamic energy hub model, construct a scheduling model for carbon emissions of the integrated energy system under varying operating conditions, and solve for the scheduling scheme of the integrated energy system under varying operating conditions.

[0084] Achieving low-carbon operation while meeting the constraints of the integrated energy system's operation. The scheduling model for carbon emissions of the integrated energy system under varying operating conditions, with the minimum energy cost of the integrated energy system as the objective function, is expressed by the following formula:

[0085] (5)

[0086] In equation (5), f c The energy cost of a comprehensive energy system; f ope Energy purchase cost, including electricity purchase cost f e Gas purchase cost f g It can be expressed by the following formula:

[0087] (6)

[0088] In equation (6), T is the scheduling period, and ∆t is the unit scheduling time period; e,t Let c be the electricity purchase price at time t. g The unit price for gas purchase; P e,t Let P be the power purchased at time t. g,t Let t be the gas purchase power.

[0089] In equation (5), f env Environmental costs, including the cost of purchasing electricity from the grid for CO2 emissions. Costs of CO2 emissions from combined heat and power (CHP) units Costs of CO2 emissions from gas-fired boilers (GB standard) It can be expressed by the following formula:

[0090] (7)

[0091] In equation (7), T is the scheduling period, and ∆t is the unit scheduling time period; The environmental cost per unit of CO2 emitted; Carbon emission calculation factor for supplying electricity to the power grid. Calculation factor for carbon emissions per unit output power of combined heat and power (CHP) units. P is the carbon emission calculation factor per unit output power of a gas-fired boiler (GB standard). e,t Let P be the power purchased at time t. CHP,t P represents the output power of the combined heat and power unit (CHP) at time t. GB,t Let GB be the output power of the gas-fired boiler at time t.

[0092] The constraints of the scheduling model for carbon emissions of the integrated energy system under varying operating conditions include: power balance constraints, tie-line power constraints, energy conversion equipment operation constraints, and energy storage equipment operation constraints.

[0093] (1) The integrated energy system includes electric, heat and gas energy flow. The power balance constraint is to satisfy the multi-energy coupling relationship described by the dynamic energy hub model. The efficiency of the energy conversion equipment in the integrated energy system is calculated by the pre-constructed efficiency correction model based on deep neural network, as shown in equations (1) and (4).

[0094] (2) Tie-line power constraint: To ensure the safe operation of the integrated energy system, the interaction power between the integrated energy system and the upper-level power grid is within a safe range, expressed by the following formula:

[0095] (8)

[0096] In equation (8), P grid,t Let P be the power purchased at time t. grid,cap This is the upper limit of the tie line power.

[0097] (3) The operating constraints of the energy conversion equipment include the input and output power relationship constraints and the upper and lower limits of the energy conversion equipment output constraints, which are expressed by the following formula:

[0098] (9)

[0099] In equation (9), P CHP,t η represents the output power of the combined heat and power unit (CHP) at time t. CHP,t Let P be the power generation efficiency of the combined heat and power unit CHP at time t. in,CHP,t Let P be the input power of the combined heat and power unit CHP at time t. CHP,cap The upper limit of the output power of the combined heat and power (CHP) unit; P GB,t Let η be the output power of the gas-fired boiler GB at time t. GB,t Let P be the heating efficiency of the gas-fired boiler GB at time t. in,GB,t Let P be the GB input power of the gas boiler at time t. GB,cap This is the upper limit of the output power of the gas-fired boiler (GB).

[0100] (4) The operational constraints of energy storage equipment include limitations on charging and discharging power and equipment capacity, which are expressed by the following formula:

[0101] (10)

[0102] In equation (10), W e,t For the energy stored in the battery before charging and discharging, W e,t+1 The energy stored after the battery BAT is charged and discharged. For the self-discharge rate of battery BAT, P C,t Let η be the charging power of BAT at time t. C For battery charging efficiency (BAT), P D,t Let η be the power released by BAT at time t. D The battery's BAT discharge efficiency is given, and ∆t represents the unit scheduling time period; W cap This refers to the rated capacity of the battery BAT. This represents the maximum charging power of the battery BAT. This represents the maximum power output of the battery BAT; Wstart For the energy stored in the battery BAT at the beginning of the scheduling cycle; W end This refers to the energy stored in the battery BAT at the end of the scheduling cycle.

[0103] This invention employs an efficiency correction model based on deep neural networks to model the relationship between the efficiency of energy conversion equipment and load rate, temperature, and air pressure. This helps to improve the problems of large computational load and low accuracy of traditional methods. It also considers the strong nonlinearity of equipment efficiency changes, thereby improving the accuracy of the equipment model. This enables low-carbon operation of integrated energy systems and improves the solution speed and accuracy of scheduling models.

[0104] Example 2:

[0105] This embodiment is based on the carbon emission scheduling method of a comprehensive energy system under varying operating conditions provided in Embodiment 1, and selects, for example... Figure 2 The diagram illustrates the carbon emission scheduling of a typical integrated energy system in southern my country.

[0106] like Figure 5 , Figure 6 The figures shown are schematic diagrams of the electricity and heat loads of a typical integrated energy system in southern China on a typical day, and schematic diagrams of the temperature and air pressure of the operating environment.

[0107] Electricity purchase price, CO2 emission cost and tie-line power limit are shown in Table 1, and equipment rated parameters are shown in Table 2.

[0108] Table 1. Electricity purchase price, CO2 emission cost, and tie-line cross-connection power cap

[0109]

[0110] Table 2 Equipment Rated Parameters

[0111]

[0112] To verify the effectiveness of the method of the present invention, the following three scenarios were constructed for comparison:

[0113] Scenario 1: Based on the constant efficiency EH model, without considering the variable operating conditions of the equipment.

[0114] Scenario 2: DEH model based on polynomial fitting method.

[0115] Scenario 3: The proposed DNN-based DEH model. Furthermore, different iteration numbers (E) were set during neural network training, and multiple sub-scenarios were established accordingly. When E is sufficiently large (e.g., 500), the efficiency-corrected model based on the deep neural network fully converges, exhibiting high prediction accuracy, with the network loss function value approximating 0. At this point, the prediction result can be considered an accurate value and used as a reference for comparison and analysis of other scenarios.

[0116] The scheduling models for carbon emissions of integrated energy systems under three scenarios were solved, and the energy purchase cost, environmental cost, operating cost, relative error, and computation time were obtained, as shown in Table 3.

[0117] Table 3. Operating costs, relative errors, and computation time for the three scenarios.

[0118]

[0119] In Scenario 1, the relative error of operating costs reached 4.1824%, indicating that the constant efficiency energy hub model is difficult to achieve accurate modeling of integrated energy systems, affecting the accuracy of optimal scheduling.

[0120] In Scenario 2, the polynomial fitting method reduced the relative error of operating costs from 4.1824% to 0.6334%, but it still struggles to accurately describe the actual operating conditions of the integrated energy system. However, this method is computationally intensive and complex to solve, with a computation time approximately eight times that of Scenario 1.

[0121] In Scenario 3 (E=100-500), as E increases, the prediction accuracy of the deep neural network improves, as does the prediction accuracy of the efficiency correction model based on the deep neural network, and the relative errors of each sub-scenario gradually decrease. Scenario 3 (E=500) has the highest accuracy, and its scheduling scheme best matches the actual operation of the integrated energy system. This indicates that the carbon emission scheduling method for the integrated energy system under varying operating conditions provided in Example 1 can more accurately characterize the nonlinear changes in equipment efficiency and has superior prediction performance compared to the traditional polynomial fitting method in Scenario 2. Due to the high computational efficiency of deep neural networks, the model solution time in Scenario 3 is slightly increased compared to Scenario 1, but not exceeding 0.03 seconds. In addition, the energy purchase cost and environmental cost in Scenario 3 are higher than in Scenario 1 and 2. Changes in equipment load rate, temperature, and air pressure will cause the actual operating conditions of the equipment to deviate from the rated operating conditions, and the operating efficiency of CHP and GB will be lower than the rated efficiency, resulting in increased energy purchase costs. In order to meet load demand, the power supply from the grid increases, that is, the output of thermal power units with high carbon emission intensity increases, while the output of gas turbine units with low carbon emission intensity decreases, thereby increasing environmental costs. It is evident that considering the variable operating conditions of equipment can effectively improve the accuracy of scheduling schemes and carbon emission studies.

[0122] In scenario 3 (E=500), such as Figure 7cAs shown, electricity and heat loads are mostly supplied by the power grid and GB (Power Supply Unit), with CHP serving as a supplementary energy source. During peak electricity price periods (9:00-10:00 and 18:00-20:00), CHP acts as the primary heating unit to maintain its high-efficiency operation, while the power grid supplies the remaining electricity load. Furthermore, when heat load levels are low (4:00-5:00), the large rated capacity of GB results in lower efficiency; therefore, the heat load is entirely supplied by CHP during this time. When heat load levels exceed the rated capacity of GB (12:00-13:00), CHP acts as the primary heating unit to ensure its high-efficiency operation.

[0123] The scheduling results in Scenario 1 differ significantly from those in Scenario 3 (E=500), such as... Figure 7a As shown in the diagram. Scenario 1 ignores the variable operating conditions of the equipment, with the vast majority of the load being met by the CHP operating at low load levels. GB only participates in heating when the heat load exceeds the CHP capacity (12:00-13:00), and the grid compensates for the insufficient power supply from CHP. Therefore, the impact of the variable operating conditions of the equipment cannot be ignored, and a constant-efficiency scheduling model may lead to unreasonable scheduling schemes.

[0124] The carbon emission scheduling method for an integrated energy system under varying operating conditions provided in Example 1 has higher accuracy than the traditional polynomial fitting method used in Scenario 2, such as... Figure 7b As shown, although the scheduling schemes obtained in the two scenarios are quite similar, the scheduling scheme in scenario 2 still has some errors. During the 3:30-4:00 period, in scenario 2, the heat load is met by CHP instead of GB. During the 4:30-5:00 period, the start / stop states of CHP and GB are also drastically different in scenarios 2 and 3 (E=500). These results indicate that the polynomial fitting method is less accurate than neural networks in predicting equipment efficiency, which can cause significant biases in IES scheduling and may even alter the start / stop state of the equipment.

[0125] In summary, this invention proposes a method for scheduling carbon emissions of an integrated energy system under varying operating conditions, and the conclusions are as follows:

[0126] 1) The constant efficiency energy hub model will cause the energy conversion relationship of the system to deviate, affecting the accuracy of the integrated energy system scheduling scheme.

[0127] 2) Based on deep neural networks, an efficiency correction model is established, which can accurately and quickly predict the nonlinear changes in equipment efficiency. This model is then combined with an energy hub model to establish a dynamic energy hub model with variable efficiency, enabling accurate modeling of integrated energy systems under varying operating conditions.

[0128] 3) The carbon emission scheduling method of the integrated energy system under variable operating conditions provided in Example 1 can effectively alleviate the problem of insufficient accuracy of constant efficiency scheduling scheme, realize low-carbon operation of integrated energy system, improve the solution speed and accuracy of scheduling model, and help decision-makers accurately analyze the economics of low-carbon scheduling of integrated energy system.

[0129] Example 3:

[0130] This invention provides a carbon emission scheduling system for an integrated energy system under varying operating conditions, comprising:

[0131] To obtain the multi-energy coupling relationships of integrated energy systems and the variable operating condition characteristics of energy conversion equipment;

[0132] Based on the multi-energy coupling relationship of the integrated energy system, an energy hub model is established;

[0133] Based on the variable operating condition characteristics of the energy conversion equipment, the efficiency parameters in the energy hub model are corrected using a pre-built efficiency correction model based on a deep neural network to obtain a dynamic energy hub model.

[0134] Based on the dynamic energy hub model, a scheduling model for carbon emissions of the integrated energy system under varying operating conditions is constructed, and the scheduling scheme of the integrated energy system under varying operating conditions is obtained by solving the problem.

[0135] Example 4:

[0136] This invention provides a computing device, including a processor and a storage medium;

[0137] The storage medium is used to store instructions;

[0138] The processor is configured to operate according to the instructions to execute the steps of the method described in Embodiment 1.

[0139] Example 5:

[0140] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in Embodiment 1.

[0141] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0142] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0143] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0145] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for scheduling carbon emissions of a comprehensive energy system under variable operating conditions, characterized in that, The method comprises the following steps: obtaining a multi-energy coupling relationship of a comprehensive energy system and a variable working condition characteristic of an energy conversion device; establishing an energy hub model according to the multi-energy coupling relationship of the comprehensive energy system; based on the variable working condition characteristic of the energy conversion device, an efficiency parameter in the energy hub model is corrected by using a pre-constructed efficiency correction model based on a deep neural network to obtain a dynamic energy hub model; wherein the pre-constructed efficiency correction model based on the deep neural network is represented by the following formula: （1） In formula (1), i is an energy conversion device; η i,t is the efficiency of energy conversion device i at time t; T i,t is the air temperature of the operating environment of energy conversion device i at time t; F i,t is the air pressure of the operating environment of energy conversion device i at time t; N i,t is the load power of energy conversion device i at time t, which is represented by the following formula: （2） In formula (2), P i,t is the output power of the energy conversion device i at time t, kW; P i,cap is the device capacity of the energy conversion device i, kW; wherein a matrix form of the energy hub model is represented by the following formula: （3） In formula (3), L e,t is the electric load of the integrated energy system at time t, L h,t is the heat load of the integrated energy system at time t; η CHP is the power generation efficiency of the combined heat and power unit CHP, η CHP,h is the heat supply efficiency of the combined heat and power unit CHP, η GB is the heat supply efficiency of the gas boiler GB; P e,t is the electric energy supply power at time t, P g,t is the gas energy supply power at time t; η C is the charging efficiency of the battery BAT, η D is the discharging efficiency of the battery BAT; W e,t is the electric energy storage of the battery BAT at time t; v t is the proportion coefficient of the natural gas consumed by the combined heat and power unit CHP at time t to the natural gas supply at time t; wherein a matrix form of the dynamic energy hub model is represented by the following formula: （4） In formula (4), η CHP,t is the power generation efficiency of the combined heat and power unit CHP at time t, η CHP,h,t is the heat supply efficiency of the combined heat and power unit CHP at time t, η GB,t is the heat supply efficiency of the gas boiler GB at time t; based on the dynamic energy hub model, a scheduling model of carbon emission of the comprehensive energy system under a variable working condition is constructed, and a scheduling scheme of the comprehensive energy system under the variable working condition is solved.

2. The method of claim 1, wherein, The scheduling model of carbon emission of the comprehensive energy system under the variable working condition takes a minimum energy cost of the comprehensive energy system as an objective function and is represented by the following formula: （5） In formula (5), f c is the energy cost of the integrated energy system; f ope is the energy purchase cost, including the electricity purchase cost f e and the gas purchase cost f g , which is expressed by the following formula: （6） In equation (6), T is the scheduling period, and ∆t is the unit scheduling time period; e,t Let c be the electricity purchase price at time t. g The unit price for gas purchase; P e,t Let P be the power purchased at time t. g,t Let t be the gas purchase power. In formula (5), f env is the environmental cost, including CO2 emission cost from grid electricity purchase , CO2 emission cost from combined heat and power (CHP) unit , CO2 emission cost from gas boiler (GB) is represented by the following formula: （7） In formula (7), T is a scheduling period, and At is a unit scheduling period; is the environmental cost of discharging unit CO2; is a carbon emission calculation coefficient of the power grid power supply, is a carbon emission calculation coefficient of unit output power of the combined heat and power (CHP) unit, is a carbon emission calculation coefficient of unit output power of the gas boiler (GB); P e,t is the purchased power at time t, P CHP,t is the output power of the combined heat and power (CHP) unit at time t, P GB,t is the output power of the gas boiler (GB) at time t.

3. The method of claim 2, wherein, constraint conditions of the scheduling model of carbon emission of the comprehensive energy system under the variable working condition include a power balance constraint, a tie-line power constraint, an energy conversion device operation constraint, and an energy storage device operation constraint, the power balance constraint is to satisfy the multi-energy coupling relationship described by the dynamic energy hub model, and the efficiency of the energy conversion device in the comprehensive energy system is calculated by the pre-constructed efficiency correction model based on the deep neural network; the tie-line power constraint is that interactive power of the comprehensive energy system and a superior power grid is within a safe range and is represented by the following formula: （8） In formula (8), P grid,t is the purchase power at time t, P grid,cap is the upper limit of tie-line power the energy conversion device operation constraint includes an input-output power relationship constraint and an upper and lower limit constraint of energy conversion device output and is represented by the following formula: （9） In formula (9), P CHP,t is the output power of the combined heat and power unit CHP at time t, η CHP,t is the power generation efficiency of the combined heat and power unit CHP at time t, P in,CHP,t is the input power of the combined heat and power unit CHP at time t, P CHP,cap is the upper limit of the output power of the combined heat and power unit CHP; P GB,t is the output power of the gas boiler GB at time t, η GB,t is the heat supply efficiency of the gas boiler GB at time t, P in,GB,t is the input power of the gas boiler GB at time t, P GB,cap is the upper limit of the output power of the gas boiler GB; the energy storage device operation constraint includes a charge-discharge power and a device capacity limit and is represented by the following formula: （10） In formula (10), W e,t is the energy storage of the battery BAT before charging and discharging, W e,t+1 is the energy storage of the battery BAT after charging and discharging, is the self-discharging rate of the battery BAT, P C,t is the charging power of the battery BAT at time t, η C is the charging efficiency of the battery BAT, P D,t is the discharging power of the battery BAT at time t, η D is the discharging efficiency of the battery BAT, Δt is a unit scheduling period; W cap is the rated capacity of the battery BAT; is the maximum charging power of the battery BAT; is the maximum discharging power of the battery BAT; W start is the energy storage of the battery BAT at the beginning of the scheduling period; W end is the energy storage of the battery BAT at the end of the scheduling period.

4. A scheduling system for carbon emissions of a comprehensive energy system under variable operating conditions, characterized in that, The method comprises the following steps: obtaining a multi-energy coupling relationship of a comprehensive energy system and a variable working condition characteristic of an energy conversion device; establishing an energy hub model according to the multi-energy coupling relationship of the comprehensive energy system; based on the variable working condition characteristic of the energy conversion device, an efficiency parameter in the energy hub model is corrected by using a pre-constructed efficiency correction model based on a deep neural network to obtain a dynamic energy hub model; wherein the pre-constructed efficiency correction model based on the deep neural network is represented by the following formula: （1） In formula (1), i is an energy conversion device; η i,t is the efficiency of energy conversion device i at time t; T i,t is the air temperature of the operating environment of energy conversion device i at time t; F i,t is the air pressure of the operating environment of energy conversion device i at time t; N i,t is the load power of energy conversion device i at time t, and is represented by the following formula: （2） In formula (2), P i,t is the output power of the energy conversion device i at time t, kW; P i,cap is the device capacity of the energy conversion device i, kW; wherein a matrix form of the energy hub model is represented by the following formula: （3） In formula (3), L e,t is the electric load of the integrated energy system at time t, L h,t is the heat load of the integrated energy system at time t; η CHP is the power generation efficiency of the combined heat and power unit CHP, η CHP,h is the heat supply efficiency of the combined heat and power unit CHP, η GB is the heat supply efficiency of the gas boiler GB; P e,t is the electric energy supply power at time t, P g,t is the gas energy supply power at time t; η C is the charging efficiency of the battery BAT, η D is the discharging efficiency of the battery BAT; W e,t is the electric energy storage of the battery BAT at time t; v t is the proportion coefficient of the natural gas consumed by the combined heat and power unit CHP at time t to the natural gas supply at time t; wherein a matrix form of the dynamic energy hub model is represented by the following formula: （4） In formula (4), η CHP,t is the power generation efficiency of the combined heat and power unit CHP at time t, η CHP,h,t is the heat supply efficiency of the combined heat and power unit CHP at time t, η GB,t is the heat supply efficiency of the gas boiler GB at time t; based on the dynamic energy hub model, a scheduling model of carbon emission of the comprehensive energy system under a variable working condition is constructed, and a scheduling scheme of the comprehensive energy system under the variable working condition is solved.

5. A computing device, comprising: The method comprises a processor and a storage medium. The storage medium is used to store instructions. The processor is used to operate according to the instructions to perform the steps of the method in any one of claims 1-3.

6. A computer readable storage medium having stored thereon a computer program, characterized in that The program is executed by the processor to implement the steps of the method in any one of claims 1-3.

Images