Oil and gas integrated management and control system based on renewable energy sources

Abstract

The invention discloses an oil-gas integrated management and control system based on renewable energy sources, belongs to the technical field of resource management, and aims to solve the problem that existing distributed energy sources are difficult to manage and control in a centralized manner. Through the hybrid energy system, the data acquisition module, the logic dynamic control module and the user terminal control module, real-time adjustment is carried out according to the environment where renewable energy is located and the output amount, the consumption amount is changed in a self-adaptive mode, and nearby timely consumption of redundant energy is achieved; under the current operation environment of the oil pumping unit, oil field exploitation can be carried out in a self-adaptive mode according to the energy supply condition of renewable energy sources, and the exploitation cost is greatly reduced. Meanwhile, the frequency of the motor can be manually adjusted through the upper computer, the control room and the mobile terminal, so that the actual operation requirement is met, and emergency situations are dealt with.

Description

Technical Field

[0001] The present invention relates to the technical field of resource management, and in particular to an integrated oil and gas management and control system based on renewable energy. Background Art

[0002] Renewable energy refers to naturally regenerated, inexhaustible energy sources that are utilized at a rate far lower than their natural replenishment rate. These sources typically come from natural processes such as solar energy, wind power, Earth's internal heat, tidal forces, and biological metabolism. They are characterized by low carbon emissions, environmental friendliness, and sustainable utilization.

[0003] Hybrid energy systems primarily powered by wind and solar often employ energy storage devices to stabilize output voltage and utilize hydrogen production as a means of timely energy consumption. However, as oil well and oilfield exploitation becomes increasingly challenging, the cost of energy supply required to operate the pumping units is also increasing. Furthermore, hybrid energy systems constructed with wind, solar, and storage suffer from high energy supply uncertainty and redundant energy that cannot be promptly consumed. The strong coupling between various hybrid energy devices and their subsystems makes accurate modeling impossible, and hybrid energy systems operate in harsh environments, with distributed energy resources not centrally managed.

[0004] To this end, we proposed an integrated oil and gas management and control system based on renewable energy. Summary of the Invention

[0005] The purpose of the present invention is to provide an integrated oil and gas management and control system based on renewable energy, which solves the problem in the background art that distributed energy is difficult to centrally manage.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an integrated oil and gas management and control system based on renewable energy, comprising:

[0007] Hybrid energy systems, which integrate wind power, photovoltaics, energy storage equipment, as well as pumping units and hydrogen production systems, optimize energy utilization, reduce extraction costs, and achieve coordinated management of renewable energy and oil and gas extraction;

[0008] Data acquisition module, used to monitor the operating status of the hybrid energy system in real time, track the parameters of the oil pumping unit and hydrogen production system, and ensure the quality of grid-connected power;

[0009] The logical dynamic control module is used to build a dynamic model by integrating multi-source data in real time. It combines reinforcement learning with model predictive control (MPC) strategies to adaptively optimize energy distribution and equipment coordination, ensuring the efficient and stable operation of the hybrid energy system under fluctuations in wind and solar power supply and complex constraints.

[0010] The user terminal control module is used to send control signals to the logic dynamic control module according to actual needs to implement manual adjustment of the hybrid energy system.

[0011] Furthermore, the data acquisition module includes renewable energy signal acquisition units, grid-connected voltage detection units, and pumping unit and hydrogen production system data acquisition units, wherein:

[0012] Renewable energy signal acquisition units are used to collect digital signals of wind, solar and energy storage output current, voltage, frequency and torque;

[0013] The data acquisition unit of the oil pumping unit and hydrogen production system is used to collect the operating load, stroke, stroke frequency signal, hydrogen production molar amount, and hydrogen production input current signal of the oil pumping unit and hydrogen production system;

[0014] The grid-connected voltage detection unit is used for DC voltage detection and collection of current and load signals.

[0015] Furthermore, the logic dynamic control module includes a coupled reference model unit, a logic dynamic control algorithm unit and a signal transmission unit, wherein:

[0016] The coupled benchmark model unit is used to use the data signal collected by the data acquisition module as input, couple it with the mathematical model to establish the state space equation, perform processing and calculation according to the model, and pass the calculation results to the logic dynamic control algorithm unit;

[0017] The logic dynamic control algorithm unit is used to adaptively and dynamically update the logic judgment model in the controller in real time according to the uncertainty of wind and solar energy supply, and adopts the MPC control strategy based on reinforcement learning for update and optimization.

[0018] Furthermore, the signal transmission unit is used to remotely send the signal of the data acquisition module and the signal adjusted by the control algorithm to the user terminal control module.

[0019] Furthermore, the user terminal control module includes a host computer, a main control room and a mobile terminal, which sends control signals to the logic dynamic control algorithm unit according to actual needs to implement manual adjustment of the integrated system.

[0020] Furthermore, the hybrid energy system consists of four main parts:

[0021] The first part is to build a dynamic optimization scheduling strategy for each device in the hybrid renewable energy system;

[0022] The second part is to establish the integration constraints of distributed hybrid renewable energy systems;

[0023] The third part is to design the objective function of the distributed hybrid renewable energy system;

[0024] The fourth part is to integrate the dynamic coordinated control strategy of distributed hybrid renewable energy systems based on the basic expressions given in the first three parts.

[0025] Furthermore, in the first part, the dynamic optimization scheduling strategy takes power as the main optimization scheduling object, and integrates the constraints of wind turbines, photovoltaics, and energy storage into a hybrid logical inequality equation, so that the optimization scheduling strategy can ensure its own stable operation. After the dynamic model of each device is established, the integrated hybrid logical dynamic model of the entire hybrid energy system is as follows:

[0026]

[0027] in, A w , A pv , A bat , B w , B pv , B bat is the coefficient matrix of wind turbine, photovoltaic and energy storage in the state equation; C w , C pv , D w , D pv , D bat , D grid is the coefficient matrix of wind turbine, photovoltaic, energy storage and power grid in the output equation; E k，w , E k，pw , E k，bat , E k，grid (k=1,2,3) is the coefficient matrix of wind turbine, photovoltaic, energy storage and power grid of the logical inequality equation; δ w , δ pv , δ bat , δ grid They are auxiliary logic variables for wind turbines, photovoltaics, energy storage and power grids respectively.

[0028] Furthermore, in the second part, the integrated constraints mainly include distributed spatiotemporal complementarity constraints, physical property constraints, and power balance constraints. At the same time, these three constraints affect each other, thus providing basic conditions for the centralized control of various devices in the distributed hybrid renewable energy system.

[0029] The distributed spatiotemporal complementarity constraint is expressed as:

[0030]

[0031] Among them, P w (t), P pv (t) are the output power of wind power and photovoltaic power, P bat，cha (t) The power used to charge the energy storage device, δ w，t , δ pv，t , δ w，l , δ pv，lare independent temporal and spatial complementary logical variables. If the photovoltaic power generation is in daytime and the light intensity is high at the geographical location, then δ pv，t =1,δ pv，l =1, otherwise δ pv，t =0,δ pv，l = 0, if wind power is generated at night and the wind field density is high, then δ w，t =0,δ w，l =0, η represents the storage system efficiency factor;

[0032] The power balance constraint is expressed as:

[0033] P w (t)+P pv (t)+P bat，cha (t)+P grid (t)+S sc (t) = P s (t)+P bat，dis (t);

[0034] Among them, P w (t), P pv (t), P grid (t) are the output power of wind power, photovoltaic power and grid interaction, P bat，cha (t), P bat，dis (t) are the charging and discharging powers of the energy storage device, P s (t) is the available power and total electrical load of the system, and the left side of the equation represents the output power of the hybrid energy system, and the right side of the equation represents the available power of the hybrid energy system. When the energy storage power is greater than zero, it is in the charging state. For the system, P bat，dis (t) is regarded as an energy consuming device and is therefore placed on the right side of the equation. When the energy storage power is less than zero, it is in a discharging state. For the system, P bat，cha (t) is considered as a production equipment and is therefore placed on the left side of the equation;

[0035] Variables that need to be considered are affected by spatiotemporal complementarity:

[0036]

[0037] in, Is a logical variable. If the photovoltaic is in daytime and the light intensity is high at the location, then otherwise P sc，pv To compensate for the power of wind power by photovoltaic power, if the wind power is generated at night and the wind field density is high in the geographical location, then Otherwise, 0, P sc，w Compensate for photovoltaic power with wind power;

[0038] The physical property constraints are expressed as:

[0039]

[0040] in, is the maximum and minimum constraint of wind power, is the maximum and minimum constraints of photovoltaic power, soc min , soc max is the maximum and minimum constraint of the energy storage state of charge, and δ is an auxiliary logical variable affected by the spatiotemporal complementarity.

[0041] Furthermore, in the third part, this part consists of the operating cost function of each device and the cost function between each device. These two cost functions are affected by the number of devices, operating costs and power factors. The operating cost functions for each device and between devices are expressed as follows:

[0042]

[0043] in, The integrated representation of the cost function representing each device, is the operating cost of each device, C req (k+j) is the minimum operating cost standard required for each device, is the power output of each device, P req (k+j) is the power standard required by each device, N represents the number of distributed renewable energy devices, and i represents the interaction between each device;

[0044] The overall objective function is expressed as:

[0045]

[0046] Among them, ω grid ,ω pv ,ω bat ,ω grid ,ω i It is the weight that is adaptively adjusted according to the situation.

[0047] Furthermore, in the fourth part, the control strategy uses MPC as the basic framework and incorporates reinforcement learning into this framework to optimize the objective function to obtain a more accurate model and solve the cumulative error. Based on the above basic conditions, the model predictive control problem of the hybrid energy system is transformed into the following form:

[0048]

[0049] Among them, U represents the optimization quantity, which is composed of real continuous variables and binary logical variables. V(k) represents the value function. Reinforcement learning can obtain a strategy π by approximating the value function V(k), thereby minimizing the future cumulative cost.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The proposed integrated renewable energy-based oil and gas management and control system utilizes a hybrid energy system, a data acquisition module, a logic dynamic control module, and a user terminal control module to perform real-time adjustments based on the renewable energy environment and output, adaptively changing the amount of energy consumed to achieve the immediate and local consumption of redundant energy. Under the current operating conditions of the pumping unit, oilfield production can be adaptively adjusted based on the renewable energy supply, significantly reducing production costs. Furthermore, the motor frequency can be manually adjusted by the host computer, control room, or mobile terminal to meet actual operating needs and respond to emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A roadmap for realizing the oil and gas integrated management and control system based on renewable energy of the present invention;

[0053] Figure 2 This is a structural diagram of the hybrid energy system in the oil and gas integrated management and control system based on renewable energy of the present invention. DETAILED DESCRIPTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0055] In order to solve the technical problem of how to improve the centralized control effect of distributed energy, such as Figure 1-Figure 2 As shown, the following preferred technical solutions are provided:

[0056] The integrated oil and gas management and control system based on renewable energy includes:

[0057] Hybrid energy systems, which integrate wind power, photovoltaics, energy storage equipment, as well as pumping units and hydrogen production systems, optimize energy utilization, reduce extraction costs, and achieve coordinated management of renewable energy and oil and gas extraction;

[0058] Data acquisition module, used to monitor the operating status of the hybrid energy system in real time, track the parameters of the oil pumping unit and hydrogen production system, and ensure the quality of grid-connected power;

[0059] The logical dynamic control module is used to build a dynamic model by integrating multi-source data in real time. It combines reinforcement learning with model predictive control (MPC) strategies to adaptively optimize energy distribution and equipment coordination, ensuring the efficient and stable operation of the hybrid energy system under fluctuations in wind and solar power supply and complex constraints.

[0060] The user terminal control module is used to send control signals to the logic dynamic control module according to actual needs to implement manual adjustment of the hybrid energy system.

[0061] The data acquisition module includes renewable energy signal acquisition units, grid-connected voltage detection units, and pumping unit and hydrogen production system data acquisition units, including:

[0062] Renewable energy signal acquisition units are used to collect digital signals of wind, solar and energy storage output current, voltage, frequency and torque;

[0063] The data acquisition unit of the oil pumping unit and hydrogen production system is used to collect the operating load, stroke, stroke frequency signal, hydrogen production molar amount, and hydrogen production input current signal of the oil pumping unit and hydrogen production system;

[0064] The grid-connected voltage detection unit is used for DC voltage detection and collection of current and load signals.

[0065] The logic dynamic control module includes a coupling benchmark model unit, a logic dynamic control algorithm unit and a signal transmission unit, wherein:

[0066] The coupled benchmark model unit is used to use the data signal collected by the data acquisition module as input, couple it with the mathematical model to establish the state space equation, perform processing and calculation according to the model, and pass the calculation results to the logic dynamic control algorithm unit;

[0067] The logic dynamic control algorithm unit is used to adaptively and dynamically update the logic judgment model in the controller in real time according to the uncertainty of wind and solar energy supply, and adopts the MPC control strategy based on reinforcement learning for update and optimization.

[0068] The signal transmission unit is used to remotely send the signal from the data acquisition module and the signal adjusted by the control algorithm to the user terminal control module.

[0069] The user terminal control module includes a host computer, a main control room and a mobile terminal. According to actual needs, it sends control signals to the logic dynamic control algorithm unit to implement manual adjustment of the integrated system.

[0070] Furthermore, the hybrid energy system consists of four main parts:

[0071] The first part is to build a dynamic optimization scheduling strategy for each device in the hybrid renewable energy system;

[0072] The second part is to establish the integration constraints of distributed hybrid renewable energy systems;

[0073] The third part is to design the objective function of the distributed hybrid renewable energy system;

[0074] The fourth part is to integrate the dynamic coordinated control strategy of distributed hybrid renewable energy systems based on the basic expressions given in the first three parts.

[0075] In the first part, the dynamic optimization scheduling strategy takes power as the main optimization scheduling object and integrates the constraints of wind turbines, photovoltaics, and energy storage into a hybrid logical inequality equation to ensure that the optimization scheduling strategy can ensure its own stable operation. After establishing the dynamic model of each device, the integrated hybrid logical dynamic model of the entire hybrid energy system is as follows:

[0076]

[0077] in, A w , A pv , A bat , B w , B pv , B bat is the coefficient matrix of wind turbine, photovoltaic and energy storage in the state equation; C w , C pv , D w , D pv , D bat , D grid is the coefficient matrix of wind turbine, photovoltaic, energy storage and power grid in the output equation; E k，w , E k，pw , E k，bat , E k，grid (k=1,2,3) is the coefficient matrix of wind turbine, photovoltaic, energy storage and power grid of the logical inequality equation; δ w , δ pv , δ bat , δ grid They are auxiliary logic variables for wind turbines, photovoltaics, energy storage and power grids respectively.

[0078] In the second part, the integrated constraints mainly include distributed spatiotemporal complementarity constraints, physical property constraints, and power balance constraints. At the same time, these three constraints affect each other, thus providing the basic conditions for the centralized control of various devices in the distributed hybrid renewable energy system.

[0079] The distributed spatiotemporal complementarity constraint is expressed as:

[0080]

[0081] Among them, P w (t), P pv (t) are the output power of wind power and photovoltaic power, P bat，cha (t) The power used to charge the energy storage device, δ w，t , δ pv，t , δ w，l , δ pv，l are independent temporal and spatial complementary logical variables. If the photovoltaic power generation is in daytime and the light intensity is high at the geographical location, then δ pv，t =1,δ pv，l =1, otherwise δ pv，t =0,δ pv，l = 0, if wind power is generated at night and the wind field density is high, then δ w，t =0,δ w，l =0, η represents the storage system efficiency factor;

[0082] The power balance constraint is expressed as:

[0083] P w (t)+P pv (t)+P bat，cha (t)+P grid (t)+S sc (t) = P s (t)+P bat，dis (t);

[0084] Among them, P w (t), P pv (t), P grid (t) are the output power of wind power, photovoltaic power and grid interaction, P bat，cha (t), P bat，dis (t) are the charging and discharging powers of the energy storage device, P s (t) is the available power and total electrical load of the system, and the left side of the equation represents the output power of the hybrid energy system, and the right side of the equation represents the available power of the hybrid energy system. When the energy storage power is greater than zero, it is in the charging state. For the system, P bat，dis (t) is regarded as an energy consuming device and is therefore placed on the right side of the equation. When the energy storage power is less than zero, it is in a discharging state. For the system, P bat，cha (t) is considered as a production equipment and is therefore placed on the left side of the equation;

[0085] Variables that need to be considered are affected by spatiotemporal complementarity:

[0086]

[0087] in, Is a logical variable. If the photovoltaic is in daytime and the light intensity is high at the location, then otherwise P sc，pv To compensate for the power of wind power by photovoltaic power, if the wind power is generated at night and the wind field density is high in the geographical location, then Otherwise, 0, P sc，w Compensate for photovoltaic power with wind power;

[0088] The physical property constraints are expressed as:

[0089]

[0090] in, is the maximum and minimum constraint of wind power, is the maximum and minimum constraints of photovoltaic power, soc min , soc max is the maximum and minimum constraint of the energy storage state of charge, and δ is an auxiliary logical variable affected by the spatiotemporal complementarity.

[0091] In the third part, this part consists of the operating cost function of each device and the cost function between each device. These two cost functions are affected by the number of devices, operating costs and power factors. The operating cost functions of each device and between devices are expressed as follows:

[0092]

[0093] in, The integrated representation of the cost function representing each device, is the operating cost of each device, C req (k+j) is the minimum operating cost standard required for each device, is the power output of each device, P req (k+j) is the power standard required by each device, N represents the number of distributed renewable energy devices, and i represents the interaction between each device;

[0094] The overall objective function is expressed as:

[0095]

[0096] Among them, ω grid ,ω pv ,ω bat ,ω grid ,ω i It is the weight that is adaptively adjusted according to the situation.

[0097] In the fourth part, the control strategy uses MPC as the basic framework and incorporates reinforcement learning into the framework to optimize the objective function to obtain a more accurate model and solve the cumulative error. Based on the above basic conditions, the model predictive control problem of the hybrid energy system is transformed into the following form:

[0098]

[0099]

[0100] Among them, U represents the optimization quantity, which is composed of real continuous variables and binary logical variables. V(k) represents the value function. Reinforcement learning can obtain a strategy π by approximating the value function V(k), thereby minimizing the future cumulative cost.

[0101] The specific implementation steps of the integrated oil and gas management and control system based on renewable energy are as follows:

[0102] S1: Build a baseline model for wind turbines, photovoltaics, and energy storage, and simultaneously build a mathematical model for energy consumption by oil pumping units and electrolytic hydrogen production to simulate the operating mechanism and system structure of the integrated system.

[0103] S2: Build a dynamic optimization scheduling model, design the logical inequality constraints for each device in the hybrid renewable energy system, and unify it with the benchmark model in step 1 into a state space expression to form a hybrid logical dynamic system;

[0104] S3: Design the integration constraints of the oil and gas integrated system based on renewable energy. Design the integrated system under the three constraints of power balance, spatiotemporal complementarity, and physical characteristics to create conditions for subsequent updates and optimizations.

[0105] S4: Construct the objective function. According to the quantity, power and cost of the integrated system in the environment, the objective function is constructed to provide conditions for the subsequent model predictive control. The objective function formula is:

[0106]

[0107] S5: Establish a logical dynamic energy coordination control strategy, using the above-designed model and constraints as the optimization problem and basic conditions under the MPC framework. At the same time, reinforcement learning is used to further strengthen MPC, forming a model-based reinforcement learning control strategy, improving the accuracy of the control strategy and eliminating cumulative errors.

[0108] S6: If the difference between the value of the minimized objective function of the energy coordination control strategy and the expected value is small, fine-tune the parameters of each constraint in the hybrid logic dynamic model. If the difference is large, return to S4 and rebuild the model of the objective function.

[0109] Specifically, real-time adjustments are made based on the environment and output of renewable energy, adaptively changing the amount consumed to ensure timely and local consumption of redundant energy. Within the pumping unit's current operating environment, oilfield production can be adaptively tailored to the renewable energy supply, significantly reducing production costs. Furthermore, motor frequency can be manually adjusted by the host computer, control room, or mobile device to meet actual operational needs and respond to emergencies.

[0110] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. An integrated oil and gas management and control system based on renewable energy, characterized by: include: Hybrid energy systems, which integrate wind power, photovoltaics, energy storage equipment, as well as pumping units and hydrogen production systems, optimize energy utilization, reduce extraction costs, and achieve coordinated management of renewable energy and oil and gas extraction; Data acquisition module, used to monitor the operating status of the hybrid energy system in real time, track the parameters of the oil pumping unit and hydrogen production system, and ensure the quality of grid-connected power; The logical dynamic control module is used to build a dynamic model by integrating multi-source data in real time. It combines reinforcement learning with model predictive control (MPC) strategies to adaptively optimize energy distribution and equipment coordination, ensuring the efficient and stable operation of the hybrid energy system under fluctuations in wind and solar power supply and complex constraints. The user terminal control module is used to send control signals to the logic dynamic control module according to actual needs to implement manual adjustment of the hybrid energy system.

2. The integrated oil and gas management and control system based on renewable energy according to claim 1, characterized in that: The data acquisition module includes renewable energy signal acquisition units, grid-connected voltage detection units, and pumping unit and hydrogen production system data acquisition units, including: Renewable energy signal acquisition units are used to collect digital signals of wind, solar and energy storage output current, voltage, frequency and torque; The data acquisition unit of the oil pumping unit and hydrogen production system is used to collect the operating load, stroke, stroke frequency signal, hydrogen production molar amount, and hydrogen production input current signal of the oil pumping unit and hydrogen production system; The grid-connected voltage detection unit is used for DC voltage detection and collection of current and load signals.

3. The integrated oil and gas management and control system based on renewable energy according to claim 2, characterized in that: The logic dynamic control module includes a coupling benchmark model unit, a logic dynamic control algorithm unit and a signal transmission unit, wherein: The coupled benchmark model unit is used to use the data signal collected by the data acquisition module as input, couple it with the mathematical model to establish the state space equation, perform processing and calculation according to the model, and pass the calculation results to the logic dynamic control algorithm unit; The logic dynamic control algorithm unit is used to adaptively and dynamically update the logic judgment model in the controller in real time according to the uncertainty of wind and solar energy supply, and adopts the MPC control strategy based on reinforcement learning for update and optimization.

4. The integrated oil and gas management and control system based on renewable energy according to claim 3, characterized in that: The signal transmission unit is used to remotely send the signal from the data acquisition module and the signal adjusted by the control algorithm to the user terminal control module.

5. The integrated oil and gas management and control system based on renewable energy according to claim 4, characterized in that: The user terminal control module includes a host computer, a main control room and a mobile terminal. According to actual needs, it sends control signals to the logic dynamic control algorithm unit to implement manual adjustment of the integrated system.

6. The integrated oil and gas management and control system based on renewable energy according to claim 5, characterized in that: The hybrid energy system consists of four main parts: The first part is to build a dynamic optimization scheduling strategy for each device in the hybrid renewable energy system; The second part is to establish the integration constraints of distributed hybrid renewable energy systems; The third part is to design the objective function of the distributed hybrid renewable energy system; The fourth part is to integrate the dynamic coordinated control strategy of distributed hybrid renewable energy systems based on the basic expressions given in the first three parts.

7. The integrated oil and gas management and control system based on renewable energy according to claim 6, characterized in that: In the first part, the dynamic optimization scheduling strategy takes power as the main optimization scheduling object and integrates the constraints of wind turbines, photovoltaics, and energy storage into a hybrid logical inequality equation to ensure that the optimization scheduling strategy can ensure its own stable operation. After establishing the dynamic model of each device, the integrated hybrid logical dynamic model of the entire hybrid energy system is as follows: ； in, A w , A pv , A bat , B w , B pv , B bat is the coefficient matrix of wind turbine, photovoltaic and energy storage in the state equation; C w , C pv , D w , D pv , D bat , D grid is the coefficient matrix of wind turbine, photovoltaic, energy storage and power grid in the output equation; E k，w , E k，pw , E k，bat , E k，grid (k=1,2,3) is the coefficient matrix of wind turbine, photovoltaic, energy storage and power grid of the logical inequality equation; δ w , δ pv , δ bat , δ grid They are auxiliary logic variables for wind turbines, photovoltaics, energy storage and power grids respectively.

8. The integrated oil and gas management and control system based on renewable energy according to claim 7, characterized in that: In the second part, the integrated constraints mainly include distributed spatiotemporal complementarity constraints, physical property constraints, and power balance constraints. At the same time, these three constraints affect each other, thus providing the basic conditions for the centralized control of various devices in the distributed hybrid renewable energy system. The distributed spatiotemporal complementarity constraint is expressed as: Among them, P w (t), P pv (t) are the output power of wind power and photovoltaic power, P bat，cha (t) The power used to charge the energy storage device, δ w，t , δ pv，t , δ w，l , δ pv，l are independent temporal and spatial complementary logical variables. If the photovoltaic power generation is in daytime and the light intensity is high at the geographical location, then δ pv，t =1,δ pv，l =1, otherwise δ pv，t =0,δ pv，l = 0, if wind power is generated at night and the wind field density is high, then δ w，t =0,δ w，l =0, η represents the storage system efficiency factor; The power balance constraint is expressed as: P w (t)+P pv (t)+P bat，cha (t)+P grid (t)+S sc (t)=P s (t)+P bat，dis (t); Among them, P w (t), P pv (t), P grid (t) are the output power of wind power, photovoltaic power and grid interaction, P bat，cha (t), P bat，dis (t) are the charging and discharging powers of the energy storage device, P s (t) is the available power and total electrical load of the system, and the left side of the equation represents the output power of the hybrid energy system, and the right side of the equation represents the available power of the hybrid energy system. When the energy storage power is greater than zero, it is in the charging state. For the system, P bat，dis (t) is regarded as an energy consuming device and is therefore placed on the right side of the equation. When the energy storage power is less than zero, it is in a discharging state. For the system, P bat，cha (t) is considered as a production equipment and is therefore placed on the left side of the equation; Variables that need to be considered are affected by spatiotemporal complementarity: in, Is a logical variable. If the photovoltaic is in daytime and the light intensity is high at the location, then otherwise P sc，pv To compensate for the power of wind power by photovoltaic power, if the wind power is generated at night and the wind field density is high in the geographical location, then Otherwise, it is 0. sc，w Compensate for photovoltaic power with wind power; The physical property constraints are expressed as: in, is the maximum and minimum constraint of wind power, is the maximum and minimum constraints of photovoltaic power, soc min , soc max is the maximum and minimum constraint of the energy storage state of charge, and δ is an auxiliary logical variable affected by the spatiotemporal complementarity.

9. The integrated oil and gas management and control system based on renewable energy according to claim 8, characterized in that: In the third part, this part consists of the operating cost function of each device and the cost function between each device. These two cost functions are affected by the number of devices, operating costs and power factors. The operating cost functions of each device and between devices are expressed as follows: in, The integrated representation of the cost function representing each device, is the operating cost of each device, C req (k+j) is the minimum operating cost standard required for each device, is the power output of each device, P req (k+j) is the power standard required by each device, N represents the number of distributed renewable energy devices, and i represents the interaction between each device; The overall objective function is expressed as: Among them, ω grid ,ω pv ,ω bat ,ω grid ,ω i It is the weight that is adaptively adjusted according to the situation.

10. The integrated oil and gas management and control system based on renewable energy according to claim 9, characterized in that: In the fourth part, the control strategy uses MPC as the basic framework and incorporates reinforcement learning into the framework to optimize the objective function to obtain a more accurate model and solve the cumulative error. Based on the above basic conditions, the model predictive control problem of the hybrid energy system is transformed into the following form: Among them, U represents the optimization quantity, which is composed of real continuous variables and binary logical variables. V(k) represents the value function. Reinforcement learning can obtain a strategy π by approximating the value function V(k), thereby minimizing the future cumulative cost.

Images