Agricultural integrated energy park optimization control method considering environmental capacity constraint

Abstract

The invention discloses an agricultural integrated energy park optimization control method considering environmental capacity constraints, which optimizes a multi-energy scheduling strategy and improves energy utilization efficiency. The method comprises the following steps: firstly, constructing a multi-energy system operation control and pollution emission model, quantifying the influence of pollution emission on the environment, introducing environment capacity constraint, and evaluating and dynamically adjusting an energy scheduling strategy in real time; and then, proposing an optimization control model based on a fuzzy membership degree, and processing a nonlinear relationship between agricultural production requirements and energy supply by adopting a fuzzy theory. Secondly, providing a comprehensive planning method based on environmental capacity evaluation, and solving a long-term energy configuration scheme by adopting dynamic planning; and finally, proposing an optimization control model based on data driving, predicting an energy demand and a pollution emission trend by adopting a deep learning algorithm, dynamically adjusting an operation strategy, and ensuring efficient operation of the system under the constraint of the environmental capacity. According to the invention, energy-environment collaborative management can be realized, the operation efficiency is improved, and sustainable development is promoted.

Description

Technical Field

[0001] The present invention belongs to the field of power system regulation and control, and particularly relates to an optimized control method for an agricultural integrated energy park considering environmental capacity constraints. Background Art

[0002] With the rapid development of agricultural integrated energy parks, the energy demand is increasing day by day, and the requirements for environmental protection and sustainable development are also becoming increasingly strict. Traditional energy management methods mainly focus on the operating efficiency and economy of single energy systems, lacking comprehensive consideration of the collaborative optimization of multi-energy systems and environmental pollution control, resulting in problems such as low energy utilization efficiency and excessive pollution emissions, and it is difficult to meet the requirements of modern agricultural parks for high efficiency, environmental protection, and sustainable development.

[0003] The existing energy management methods for agricultural integrated energy parks have the following deficiencies: (1) The existing methods usually independently optimize single energy systems such as power, heat, and cold energy, lacking global optimization of the collaborative operation of multi-energy systems. The loads between various energy systems cannot be effectively balanced, the resource utilization efficiency is low, and it is difficult to achieve the efficient operation of the overall energy system. (2) The existing methods often ignore the impact of environmental pollution in energy scheduling and fail to incorporate environmental capacity constraints into the optimization model. This results in the system being unable to dynamically adjust the energy scheduling strategy during high pollution emission periods, making it difficult to effectively reduce pollution emissions and affecting the sustainability of the ecological environment. (3) Insufficient accuracy of energy demand prediction: The energy demand prediction of the existing methods is mainly based on simple historical data analysis, without fully considering the impact of agricultural meteorological data and park operation data. The obtained prediction results have large deviations and are difficult to support accurate energy scheduling and pollution control. (4) The existing methods often adopt static rules or fixed strategies in energy scheduling and pollution control, lacking the ability to dynamically adjust according to real-time data and environmental changes. The system cannot respond quickly to sudden load fluctuations or environmental capacity changes, affecting the stability and operation efficiency of the system. (5) The existing methods have limitations in data collection, processing, and analysis, and fail to make full use of advanced algorithms such as deep learning for real-time prediction and optimized control. The system is difficult to achieve intelligent management and adaptive optimization in a complex and changing operating environment, restricting the overall performance improvement of the energy system. (6) The existing methods often ignore the utilization of new energy and agricultural waste in energy planning and fail to give full play to their potential in reducing pollution emissions and lowering energy costs. The energy structure of agricultural integrated energy parks is not reasonable enough, and it is difficult to achieve the green and sustainable development of the park.

[0004] In summary, the existing methods have obvious deficiencies in aspects such as collaborative optimization of multi-energy systems, environmental pollution control, energy demand prediction, dynamic optimization control, data-driven and intelligent management, and waste utilization, and it is difficult to meet the comprehensive requirements of modern agricultural integrated energy parks for high efficiency, environmental protection, and sustainable development. Summary of the Invention

[0005] In view of the above problems, the present invention proposes an optimized control method for an agricultural integrated energy park considering environmental capacity constraints, which is used to solve the problem of insufficient collaborative optimization of multi-energy systems in the agricultural integrated energy park, thereby improving the overall energy management efficiency and sustainable development level of the park.

[0006] The technical solution adopted by the present invention is as follows: An optimized control method for an agricultural integrated energy park considering environmental capacity constraints, comprising the following steps:

[0007] S1: Construct a multi-energy system operation control and pollution emission model: Establish a multi-energy system operation control model for the agricultural integrated energy park, and quantify the impact of pollution emissions on the environment on the basis of energy supply-demand balance; By introducing the established multi-energy system operation control model, add an atmospheric pollution environmental capacity constraint to the traditional unit commitment and economic dispatch, establish an atmospheric pollution environmental capacity model, including the pollutant contribution of the generator set and the pollution degree of the generator set to the park, quantify the calculation of the pollution emissions of the unit, and then evaluate the impact of energy use on the environmental capacity in real time, incorporate the ecological benefit accounting into the optimization control target, comprehensively consider the balance between economic benefits and ecological benefits, and achieve the dual goals of efficient operation of the energy system and environmental protection;

[0008] S2: Construct an optimized control model based on fuzzy membership: For the non-linear relationship between agricultural production demand and energy supply, use fuzzy theory for optimized control, construct a multi-objective optimization function and membership function model for the agricultural integrated energy park, take energy efficiency, economic cost and ecological benefits as optimization objectives, and quantify its constraint conditions through the membership function model, use a multi-objective optimization algorithm to solve the fuzzy optimization problem, balance the relationship between energy dispatch, production demand and environmental capacity, and obtain an optimized energy dispatch strategy to ensure the efficient operation of the multi-energy system under the premise of meeting the environmental capacity constraints;

[0009] S3: Construct a comprehensive planning method based on environmental capacity assessment: Quantify the environmental carrying capacity of the area where the park is located and clarify the upper limit of the environmental capacity; Incorporate the environmental capacity constraint into the park's energy planning and the operation strategy of the agricultural integrated energy park, construct a comprehensive planning model considering environmental capacity constraints, and use dynamic programming or mixed integer linear programming methods to solve the long-term energy allocation and a feasible solution optimized for the pollution distribution index;

[0010] S4: Construct a data-driven optimization control model based on agricultural meteorological data and park operation data: The agricultural meteorological data includes temperature, humidity, light, and precipitation data; the park operation data includes energy consumption, equipment status, and pollution emission data; use deep learning algorithms to predict energy demand and pollution emission trends in real time, and based on the prediction results, dynamically adjust the operation strategies of the multi-energy system and pollution control measures to ensure that the multi-energy system always operates efficiently under environmental capacity constraints.

[0011] Further, in step S1, the operation control model of the multi-energy system includes the electric power balance equation of the agricultural integrated energy park as shown in formula (1) and the thermal power balance equation of the agricultural integrated energy park as shown in formula (2), and the atmospheric pollution environmental capacity model includes the pollutant contribution equation of the generator set as shown in formula (3) and the pollution degree equation of the generator set to the park as shown in formula (4), and the atmospheric pollution environmental constraint model includes the quantification equation of different pollutants as shown in formula (5) and the environmental capacity constraint equation as shown in formula (6).

[0012]

[0013] In the formula: is the power generation power of the cogeneration unit; is the power generation power of the gas turbine; is the photovoltaic power generation power; is the energy storage discharge power; is the energy storage charging power; is the electric load of the agricultural integrated energy park; is the power consumption of electric heating; is the purchased electric power; is the flexible agricultural load; is the heat production power of the cogeneration unit; is the heating power; is the required heat load of the agricultural integrated energy park; is the contribution of unit i to the concentration of pollutant m at time t; is the pollution discharge function; G i (τ,t) is the gas diffusion function; is the pollution degree of atmospheric pollutant m contributed by coal-fired unit i at time t; is the boundary pollution concentration; E is the total pollution emission; P i is the supply of different energy types; F i is the emission factor; E imax is the upper limit of environmental capacity.

[0014] Further, in step S2, the optimization control model based on fuzzy membership includes the multi-objective optimization function of the agricultural integrated energy park as shown in formula (7) and the membership function model as shown in formula (8). Based on the various optimization target requirements of the agricultural integrated energy park, weights are assigned to the energy efficiency, economic cost, and ecological benefits of the system operation. By quantifying the constraints through membership, the flexibility of the system is improved, ensuring that the optimization targets form fuzzy constraints.

[0015] minZ=w1·f1+w2·f2+w3·f3 (7)

[0016]

[0017] Where: w1, w2, and w3 are the membership functions of the energy efficiency target, economic cost target, and ecological benefit target respectively; f1, f2, and f3 are the energy efficiency target, economic cost target, and ecological benefit target respectively; t inf 、t ker 、t sup are the three boundaries of the membership function respectively.

[0018] Further, in step S3, the comprehensive planning model considering environmental capacity constraints includes the energy allocation cost target as shown in formula (9), the biogas production volume of the agricultural integrated energy park by biomass pyrolysis as shown in formula (10), the solid production volume of biomass pyrolysis in the agricultural integrated energy park as shown in formula (11), and the controlled biogas output volume as shown in formula (12). By using the dynamic programming method to solve the long-term energy allocation problem, where modeling is carried out for the biomass added to the gas storage tank, considering agricultural constraints and biomass cost constraints, the effectiveness and economy in the park planning process are improved.

[0019] V(t,S)=min(C(t,x)+V(t+1,S′)) (9)

[0020]

[0021] m PG,t =δ PG m PG,0 (11)

[0022]

[0023] Where: V(t,S) is the optimal cost at time t in state S; C(t,x) is the cost of decision x at time t; S′ is the new state after transfer; V PG,t is the gas production volume of the pyrolysis gasifier in the t period; η PG is the gasification efficiency; Q1 is the lower calorific value of the biogas; Q s is the lower calorific value of the biomass; m PG,0is the consumption of biomass in the t period; δ PG is the yield of solid produced by biomass gasification; m PG,t is the solid output of biomass gasification.

[0024] Furthermore, in step S4, the data-driven optimal control model includes a long short-term memory network model as shown in formula (13), an energy scheduling result based on a prediction model as shown in formula (14), and a data-driven adaptive learning and updating model as shown in formula (15). The long short-term memory network model is used to predict the trends of energy demand and pollution emissions, the energy scheduling strategy is dynamically adjusted based on the energy scheduling result of the prediction model, and then the model parameters are adaptively learned and updated according to historical data and real-time operation, so as to realize the data-driven optimal control of the agricultural integrated energy park.

[0025]

[0026] u * (t) = arg min(w1·f1 + w2·f2 + w3·f3) (14)

[0027]

[0028] In the formula: is the predicted value at time t; X(t) is the input historical data; n is the time window size; u * (t) is the optimal control strategy at time t; θ t is the model parameter at time t; χ is the learning rate; L(θ t ) is the loss function.

[0029] Another object of the present invention is to provide an optimization control system for an agricultural integrated energy park considering environmental capacity constraints, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it realizes an optimization control method for an agricultural integrated energy park considering environmental capacity constraints as described above.

[0030] Advantages and beneficial effects of the present invention: The present invention can improve the dynamic control ability of environmental pollution, optimize the prediction accuracy of energy demand and the scheduling strategy, achieve the dual goals of efficient operation of the multi-energy system and environmental protection, and improve the energy utilization efficiency and regulation ability in the agricultural integrated energy park. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flowchart of an optimization control method for an agricultural integrated energy park considering environmental capacity constraints of the present invention. DETAILED DESCRIPTION

[0032] To make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0033] Embodiment 1

[0034] An optimized control method for an agricultural integrated energy park considering environmental capacity constraints, comprising the following steps:

[0035] S1: Construct a multi-energy system operation control and pollution emission model: First, establish a multi-energy system operation control model for the agricultural integrated energy park. This model quantifies the impact of pollution emissions on the environment based on the balance between energy supply and demand. By introducing the established multi-energy collaborative operation control model, environmental capacity constraints are added to the traditional unit commitment and economic dispatch. Establish an atmospheric pollution environmental capacity model, which can evaluate the impact of energy use on environmental capacity in real time, so as to dynamically adjust strategies during the energy dispatch process, reduce pollution emissions, and improve ecological benefits. In addition, ecological benefit accounting is incorporated into the optimization control objective, comprehensively considering the balance between economic benefits and ecological benefits, providing a scientific basis for subsequent optimization control, and achieving the dual goals of efficient operation of the energy system and environmental protection;

[0036] Among them, the multi-energy system operation control model includes the electric power balance equation of the agricultural integrated energy park as shown in formula (1) and the thermal power balance equation of the agricultural integrated energy park as shown in formula (2). The atmospheric pollution environmental capacity model includes the pollutant contribution equation of the generator set as shown in formula (3) and the pollution degree equation of the generator set to the park as shown in formula (4). The atmospheric pollution environmental capacity model includes the quantification equation of different pollutants as shown in formula (5) and the environmental capacity constraint equation as shown in formula (6).

[0037]

[0038] In the formula: is the power generation power of the cogeneration unit; is the power generation power of the gas turbine; is the photovoltaic power generation power; is the energy storage discharge power; is the energy storage charging power; is the electrical load of the agricultural integrated energy park; is the power consumption of electric heating; is the purchased power; is the flexible agricultural load; is the heat production power of the cogeneration unit; is the heating power; is the thermal load required by the agricultural integrated energy park; is the contribution of unit i to the concentration of pollutant m at time period t; is the pollutant discharge function; G i (τ, t) is the gas diffusion function; is the pollution degree of atmospheric pollutant m contributed by coal-fired unit i at time period t; is the boundary pollution concentration; E is the total pollution emission; P i is the supply quantity of different energy types; F i is the emission factor; E imax is the upper limit of environmental capacity.

[0039] S2: Construct an optimization control model based on fuzzy membership: For the non-linear relationship between agricultural production demand and energy supply, fuzzy theory is used for optimization control. Construct a multi-objective optimization function and membership function model for the agricultural integrated energy park, taking energy efficiency, economic cost, and ecological benefits as optimization objectives, and quantifying their constraint conditions through the membership function model. Use multi-objective optimization algorithms (such as NSGA-II, MOPSO) to solve the fuzzy optimization problem and balance the relationship between energy scheduling, production demand, and environmental capacity. By solving this problem, an optimized energy scheduling strategy is obtained to ensure the efficient operation of the system under the premise of meeting the environmental capacity constraint. Design a multi-energy system optimization control scheme based on fuzzy membership, which can effectively cope with the uncertainties in agricultural production and improve the flexibility and robustness of the system.

[0040] Among them, the optimization control model based on fuzzy membership includes the multi-objective optimization function of the agricultural integrated energy park as shown in formula (7) and the membership function model as shown in formula (8). Based on the various optimization objective requirements of the agricultural integrated energy park, weights are assigned to the energy efficiency, economic cost, and ecological benefits of system operation, and the flexibility of the system is improved by quantifying the constraints through membership, ensuring that the optimization objectives form fuzzy constraints.

[0041] minZ = w1·f1 + w2·f2 + w3·f3 (7)

[0042]

[0043] In the formula: w1, w2, and w3 are the membership functions of the energy efficiency objective, economic cost objective, and ecological benefit objective respectively; f1, f2, and f3 are the energy efficiency objective, economic cost objective, and ecological benefit objective respectively; t inf 、t ker 、t sup are the three boundaries of the membership function respectively;

[0044] S3: Construct a comprehensive planning method based on environmental capacity assessment: Quantify the environmental carrying capacity of the region where the park is located and clarify the upper limit of the environmental capacity. Incorporate the environmental capacity constraint into the energy planning of the park and the operation strategy of the agricultural integrated energy park, and construct a comprehensive planning model considering the environmental capacity constraint. Use dynamic programming or mixed integer linear programming methods to solve the long-term energy allocation and the feasible solutions optimized for the pollution distribution index. By encouraging the replacement of traditional energy with new energy, optimize the energy structure and improve the economic and environmental benefits of the system. During the planning process, the utilization of biomass energy in the agricultural integrated energy park is also considered. Agricultural waste straw and manure can be used as raw materials for pyrolysis fermentation to supply energy for the park, which not only reduces the waste treatment cost but also realizes the recycling of resources and ensures the sustainable development of the park.

[0045] Among them, the comprehensive planning model considering the environmental capacity constraint includes the energy allocation cost target as shown in formula (9), the biomass pyrolysis gas production in the agricultural integrated energy park as shown in formula (10), the biomass pyrolysis solid production in the agricultural integrated energy park as shown in formula (11), and the controlled biogas output as shown in formula (12). By using the dynamic programming method to solve the long-term energy allocation problem, where the biomass is modeled when added to the gas storage tank, considering the agricultural constraint and the biomass cost constraint, the effectiveness and economy in the park planning process are improved.

[0046] V(t,S)=min(C(t,x)+V(t+1,S′)) (9)

[0047]

[0048] m PG,t =δ PG m PG,0 (11)

[0049]

[0050] In the formula: V(t,S) is the optimal cost at time t in state S; C(t,x) is the cost of decision x at time t; S′ is the new state after the transfer; V PG,t is the gas production of the pyrolysis gasifier in the t period; η PG is the gasification efficiency; Q1 is the lower calorific value of the biomass gas; Q s is the lower calorific value of the biomass; m PG,0 is the consumption of biomass in the t period; δ PG is the yield of solid produced by biomass gasification; m PG,t is the biomass gasification solid production;

[0051] S4: Construct a data-driven optimization control model based on agricultural meteorological data and park operation data: The agricultural meteorological data includes temperature, humidity, light, and precipitation data; the park operation data includes energy consumption, equipment status, and pollution emission data; use deep learning algorithms to predict energy demand and pollution emission trends in real time, and based on the prediction results, dynamically adjust the operation strategies of the multi-energy system and pollution control measures to ensure that the system always operates efficiently under environmental capacity constraints. Through the data-driven dynamic optimization control strategy, the system can quickly respond to external environmental changes, improve the response speed and adaptability of the system. In addition, the model can also perform self-learning and optimization based on historical data and real-time data, further improving the intelligence level of the system, and realizing the efficient and environmentally friendly operation of the energy system.

[0052] Among them, the data-driven optimization control model includes a long short-term memory network model as shown in formula (13), an energy scheduling result based on the prediction model as shown in formula (14), and a data-driven adaptive learning update model as shown in formula (15). Use the long short-term memory network model to predict the trends of energy demand and pollution emissions, dynamically adjust the energy scheduling strategy based on the energy scheduling results of the prediction model, and then adaptively learn and update the model parameters according to historical data and real-time operation to achieve data-driven optimization control of the agricultural integrated energy park.

[0053]

[0054] u * (t) = arg min(w1·f1 + w2·f2 + w3·f3) (14)

[0055]

[0056] In the formula: is the predicted value at time t; X(t) is the input historical data; n is the time window size; u * (t) is the optimal control strategy at time t; θ t is the model parameter at time t; χ is the learning rate; L(θ t ) is the loss function.

[0057] The method proposed by the present invention can solve the problem of energy-environment collaborative management, effectively improve the operation efficiency of the park energy system, realize the intelligence of energy management, and promote low-carbon environmental protection and sustainable development.

Claims

1. An optimization control method for an agricultural comprehensive energy park considering environmental capacity constraints, characterized in that: The steps include: S1: Constructing multi-energy system operation control and pollution emission model: Establishing the multi-energy system operation control model of agricultural comprehensive energy park, quantifying the impact of pollution emission on the environment on the basis of energy supply and demand balance; by introducing the established multi-energy system operation control model, adding air pollution environmental capacity constraints to the traditional unit combination and economic dispatch, establishing an air pollution environmental capacity model, including the pollutant contribution of the generator set and the pollution degree of the generator set to the park, and quantitatively calculating the unit emission pollution, and then evaluating the impact of energy use on environmental capacity in real time, incorporating ecological benefit accounting into the optimization control target, comprehensively considering the balance between economic and ecological benefits, and achieving the dual goals of efficient operation of the energy system and environmental protection; S2: Construct an optimization control model based on fuzzy membership: Aiming at the nonlinear relationship between agricultural production demand and energy supply, fuzzy theory is used for optimization control, and a multi-objective optimization function and membership function model of the agricultural comprehensive energy park are constructed. Energy efficiency, economic cost and ecological benefit are taken as optimization goals, and their constraints are quantified through the membership function model. The multi-objective optimization algorithm is used to solve the fuzzy optimization problem, balance the relationship between energy scheduling, production demand and environmental capacity, and obtain the optimized energy scheduling strategy to ensure that the multi-energy system can achieve efficient operation under the premise of meeting the environmental capacity constraints; S3: Construct a comprehensive planning method based on environmental capacity assessment: quantify the environmental carrying capacity of the area where the park is located and clarify the upper limit of environmental capacity; Incorporate environmental capacity constraints into the park energy planning and agricultural comprehensive energy park operation strategy, build a comprehensive planning model that takes environmental capacity constraints into account, and use dynamic programming or mixed integer linear programming methods to solve long-term energy configuration and feasible solutions for optimizing pollution distribution indicators; S4: Construct a data-driven optimization control model based on agricultural meteorological data and park operation data: the agricultural meteorological data include temperature, humidity, light and precipitation data; the park operation data include energy consumption, equipment status and pollution emission data; use deep learning algorithms to predict energy demand and pollution emission trends in real time, and dynamically adjust the operation strategies and pollution control measures of the multi-energy system based on the prediction results to ensure that the multi-energy system always operates efficiently under environmental capacity constraints.

2. The method for optimizing and controlling an agricultural comprehensive energy park considering environmental capacity constraints according to claim 1 is characterized in that: In step S1, the multi-energy system operation control model includes the electric power balance equation of the agricultural comprehensive energy park as shown in formula (1) and the thermal power balance equation of the agricultural comprehensive energy park as shown in formula (2), the atmospheric pollution environment capacity model includes the pollutant contribution equation of the generator set as shown in formula (3) and the pollution degree equation of the generator set to the park as shown in formula (4), the atmospheric pollution environment capacity model includes the quantification equation for different pollutants as shown in formula (5) and the environmental capacity constraint equation as shown in formula (6), Where: is the power generation capacity of the cogeneration unit; is the power generated by the gas turbine; is the photovoltaic power generation power; is the energy storage discharge power; is the energy storage charging power; It is the electricity load of the agricultural comprehensive energy park; is the power consumed by electric heating; is the purchased power; It is a flexible agricultural load; is the heat production power of the cogeneration unit; is the heating power; It is the heat load required by the agricultural comprehensive energy park; is the contribution of unit i to the concentration of pollutant m in period t; is the sewage discharge function; G i (τ,t) is the gas diffusion function; is the pollution degree of atmospheric pollutants m contributed by coal-fired unit i in time period t; is the boundary pollution concentration; E is the total pollution emission; P i is the supply of different energy types; F i is the emission factor; E imax The upper limit of environmental capacity.

3. The method for optimizing and controlling an agricultural comprehensive energy park considering environmental capacity constraints according to claim 2 is characterized in that: In step S2, the optimization control model based on fuzzy membership includes a multi-objective optimization function of the agricultural comprehensive energy park as shown in formula (7) and a membership function model as shown in formula (8). Based on the various optimization target requirements for the agricultural comprehensive energy park, the energy efficiency, economic cost and ecological benefit of the system operation are weighted, and the flexibility of the system is improved by quantifying the constraints through the membership, ensuring that the optimization target forms a fuzzy constraint. minZ=w1·f1+w2·f2+w3·f3 (7) Where: w1, w2, w3 are the membership functions of energy efficiency target, economic cost target and ecological benefit target respectively; f1, f2, f3 are the energy efficiency target, economic cost target and ecological benefit target respectively; t inf ,t ker ,t sup They are the three boundaries of the membership function.

4. The method for optimizing and controlling an agricultural comprehensive energy park considering environmental capacity constraints according to claim 3 is characterized in that: In step S3, the comprehensive planning model considering environmental capacity constraints includes the energy allocation cost target as shown in formula (9), the biomass pyrolysis gas production of the agricultural comprehensive energy park as shown in formula (10), the solid output of biomass pyrolysis of the agricultural comprehensive energy park as shown in formula (11) and the controlled biogas output as shown in formula (12). The long-term energy allocation problem is solved by adopting a dynamic programming method, wherein a model is built for the addition of biomass to a gas storage tank, agricultural constraints and biomass cost constraints are considered, and the effectiveness and economy of the park planning process are improved. V(t,S)=min(C(t,x)+V(t+1,S′)) (9) m PG,t =d PG m PG,0 (11) Where: V(t,S) is the optimal cost in state S at time t; C(t,x) is the cost of decision x at time t; S′ is the new state after the transfer; V PG,t is the gas production of the pyrolysis gasifier in period t; η PG is the gasification efficiency; Q1 is the lower calorific value of biomass gas; Q s is the lower calorific value of biomass; m PG,0 is the consumption of biomass in period t; δ PG is the yield of solid produced by biomass gasification; m PG,t is the solid yield of biomass gasification.

5. The method for optimizing and controlling an agricultural comprehensive energy park considering environmental capacity constraints according to claim 4 is characterized in that: In step S4, the data-driven optimization control model includes a long short-term memory network model as shown in formula (13), an energy scheduling result based on a prediction model as shown in formula (14), and a data-driven adaptive learning update model as shown in formula (15). The long short-term memory network model is used to predict the trend of energy demand and pollution emissions, and the energy scheduling strategy is dynamically adjusted based on the energy scheduling result of the prediction model. Then, the model parameters are updated based on historical data and real-time operation adaptive learning to achieve data-driven optimization control of the agricultural comprehensive energy park. <h2 style=";text-align:left;direction:ltr">u<h2 style=";text-align:left;direction:ltr"> * <h2 style=";text-align:left;direction:ltr"> (t) = arg min(w1·f1+w2·f2+w3·f3) (14) i t+1 =θ t -x▽ θ L(θ t ) (15) Where: is the predicted value at time t; X(t) is the input historical data; n is the time window size; u * (t) is the optimal control strategy at time t; θ t is the model parameter at time t; χ is the learning rate; L(θ t ) is the loss function.

6. An agricultural comprehensive energy park optimization control system considering environmental capacity constraints, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements an agricultural comprehensive energy park optimization control method taking into account environmental capacity constraints as described in any one of claims 1 to 5.

Images