Capacity optimization configuration method of multi-energy complementary system and computer device

Abstract

The invention belongs to the technical field of energy optimization, and particularly relates to a capacity optimization configuration method of a multi-energy complementary system and a computer device. The method comprises the following steps: S1, constructing a capacity optimization configuration model of the multi-energy complementary system; decision variables of the capacity optimization configuration model comprise installed capacities of different energy types in the multi-energy complementary system; the target function of the capacity optimization configuration model comprises a target function constructed by minimizing the difference between the power supply quantity and the power consumption quantity of the system; s2, solving the capacity optimization configuration model to obtain an optimal decision variable; and S3, performing capacity optimization configuration of the multi-energy complementary system according to the optimal decision variable. The technical problem that the optimization result is unreasonable due to the fact that power supply balance is ignored in the prior art is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy optimization, and in particular relates to a capacity optimization configuration method and a computer device for a multi-energy complementary system. Background Art

[0002] In the current wave of socio-economic development, energy demand has been growing steadily. However, the scarcity of fossil fuels and growing environmental problems, including global climate change, make traditional energy unsuitable for sustainable development. The development of a green, low-carbon, and clean energy system has a positive and statistically significant impact on both developed and developing countries. In practical applications, power generation systems based on green and clean energy such as wind, solar, gas, and hydropower have shown unique advantages. However, solar and wind power generation are volatile and random, which poses challenges to the stability and security of the power grid. In order to meet these challenges, energy storage devices are often used in such power generation systems to smooth the output power and reduce the adverse effects of renewable energy generation on the power grid. Optimizing the capacity configuration of various energy sources in a multi-energy complementary system (MECS) is an important prerequisite for providing a reliable and stable power supply environment for the power grid.

[0003] The application of artificial intelligence in power systems and integrated energy systems has both opportunities and challenges. Reinforcement Learning is a branch of artificial intelligence that involves building intelligent agents and random environments. In the optimization of MECS capacity configuration, the capacity, battery status, and real-time system load of each energy source can be regarded as the environmental state in reinforcement learning, while the operating indicators of the multi-energy system are the rewards for actions taken in the environment. By promoting the interaction between the intelligent agent and the environment, the optimization of the energy capacity configuration in the system can be achieved.

[0004] The Chinese invention patent application with application publication number CN118917677A and application publication date 2024.11.08 discloses a multi-objective planning method for capacity configuration of an integrated energy system. In the planning stage, this method uses the minimum sum of the total carbon emissions and the total cost in each stage as the objective function to carry out planning and configuration, wherein the annual operating cost in the total cost is obtained by performing a lower-level optimization scheduling model with hourly optimization in the operation stage. This method comprehensively considers economic and environmental benefits, makes capacity configuration more reasonable, and balances economic and environmental benefits. However, the above scheme ignores the balance of supply and demand of energy, especially electricity, during optimization, resulting in unreasonable optimization results, unbalanced power supply, and energy waste or shortage. Summary of the invention

[0005] The purpose of the present invention is to provide a capacity optimization configuration method and a computer device for a multi-energy complementary system, so as to solve the technical problem in the prior art that power supply balance is neglected, resulting in unreasonable optimization results.

[0006] In order to solve the above technical problems, the present invention provides a technical solution for a capacity optimization configuration method of a multi-energy complementary system: a capacity optimization configuration method of a multi-energy complementary system, the method comprising:

[0007] S1. Construct a capacity optimization configuration model for a multi-energy complementary system;

[0008] The decision variables of the capacity optimization configuration model include the installed capacity of different energy types in the multi-energy complementary system;

[0009] The objective function of the capacity optimization configuration model includes an objective function constructed by minimizing the gap between the power supply and power consumption of the system;

[0010] S2. Solving the capacity optimization configuration model to obtain optimal decision variables;

[0011] S3. Optimize the capacity configuration of the multi-energy complementary system according to the optimal decision variables.

[0012] The beneficial effect of the above technical solution is that the technical solution of the capacity optimization configuration method of a multi-energy complementary system of the present invention belongs to an improved invention. On the basis of the prior art, the present invention improves the objective function in the optimization process and includes the power supply balance of electric energy in the optimization target, so that the final optimization result can minimize the energy waste or shortage caused by power supply imbalance, which is more in line with actual production and has greatly improved rationality. The present invention solves the technical problem that the prior art ignores the power supply balance and causes unreasonable optimization results.

[0013] Furthermore, when the power supply is higher than the power consumption, the gap is the surplus power; when the power supply is lower than the power consumption, the gap is the power shortage.

[0014] Furthermore, the objective function of the capacity optimization configuration model also includes an objective function constructed with the goal of minimizing the total cost of the multi-energy complementary system over its entire life cycle and an objective function constructed with the goal of minimizing the carbon emissions of the multi-energy complementary system.

[0015] Furthermore, the multi-energy complementary system includes a gas turbine that consumes natural gas to generate electricity, and the carbon emission CE is obtained according to the following formula:

[0016]

[0017] Among them, μ c,g is the carbon emission factor of natural gas combustion; V pgu，Tis the amount of natural gas consumed by the gas turbine at time T; max The maximum operating time of the system.

[0018] Furthermore, the total annual cost over the entire life cycle includes initial investment cost, operation and maintenance cost, equipment replacement cost and purchased energy cost.

[0019] Furthermore, the multi-energy complementary system includes wind power generation equipment, photovoltaic power generation equipment, hydropower generation equipment, energy storage batteries, ground source heat pumps and gas turbines that consume natural gas to generate electricity; the decision variables include the installed capacity of wind power generation equipment, the installed capacity of photovoltaic power generation equipment, the installed capacity of hydropower generation equipment, the installed capacity of energy storage batteries, the installed capacity of ground source heat pumps and the installed capacity of gas turbines.

[0020] Furthermore, the constraints of the capacity optimization configuration model include: installed capacity constraints of wind power generation equipment, installed capacity constraints of photovoltaic power generation equipment, output constraints of hydropower generation equipment, capacity constraints of energy storage batteries, heating constraints of ground source heat pumps, and output constraints of gas turbines:

[0021] The installed capacity constraint of the wind power generation equipment is:

[0022] C w ≤C w,max

[0023] Among them, C w and C w,max They are the installed capacity of wind power generation equipment and the maximum installed capacity of wind power generation equipment that can be planned and constructed in the region;

[0024] The installed capacity constraint of the photovoltaic power generation equipment is:

[0025] C pv ≤C pv,max

[0026] Among them, C pv and C pv,max They are the installed capacity of photovoltaic power generation equipment and the maximum installed capacity of photovoltaic power generation equipment that can be planned and constructed in the region;

[0027] The output constraint of the hydroelectric power generation equipment is:

[0028] P h,min ≤P h ≤P h,max

[0029] Among them, P h is the output power of the hydroelectric power generation equipment; P h，min and P h，max They are the upper and lower output limits of the hydroelectric power generation equipment respectively;

[0030] The capacity constraint of the energy storage battery is:

[0031]

[0032] Among them, C bat and C bat,max are the installed capacity of energy storage batteries and the maximum installed capacity of energy storage batteries that can be planned and constructed; P ch，min and P dis，max are the maximum charging power and maximum discharging power of the energy storage battery respectively; S bat，min and S bat，max are the lower and upper limits of the real-time capacity of the energy storage battery respectively; S bat is the real-time capacity of the energy storage battery; P bat is the charging and discharging power of the energy storage battery, P bat >0 means discharge, P bat <0 means charging;

[0033] The heating constraints of the ground source heat pump are:

[0034] P hph ≤P hph,max

[0035] Among them, P hph and P hph,max They are the heating power of the ground source heat pump and the upper limit of the heating power of the ground source heat pump respectively;

[0036] The output constraint of the gas turbine is:

[0037] P gt,min ≤P gt ≤P gt,max

[0038] Among them, P gt is the output power of the gas turbine; P gt，min and P gt，max They are the upper and lower output limits of the gas turbine respectively.

[0039] Furthermore, in S2, the capacity optimization configuration model is solved by a deep reinforcement learning algorithm.

[0040] The present invention also provides a technical solution for a computer device: a computer device comprising a processor, wherein the processor is used to execute a computer program to implement the steps of the capacity optimization configuration method of the multi-energy complementary system as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A method flow chart of an embodiment of the method of the present invention;

[0042] Figure 2 A structural diagram of a multi-energy complementary system according to an embodiment of the method of the present invention;

[0043] Figure 3 A flow chart of the DDPG algorithm of an embodiment of the method of the present invention;

[0044] Figure 4 This is a flow chart of the control strategy of a multi-energy complementary system according to an embodiment of the method of the present invention. DETAILED DESCRIPTION

[0045] Based on the prior art, the present invention improves the objective function in the optimization process and includes the power supply balance of electric energy in the optimization target, so that the final optimization result can minimize the energy waste or shortage caused by power supply imbalance, is more in line with actual production, and is much more reasonable. The present invention solves the technical problem that the prior art ignores the power supply balance, resulting in unreasonable optimization results.

[0046] Capacity optimization configuration method embodiment of multi-energy complementary system:

[0047] A capacity optimization configuration method for a multi-energy complementary system, such as Figure 1 Said method comprises the following steps:

[0048] S1. Construct a capacity optimization configuration model for a multi-energy complementary system.

[0049] The multi-energy complementary system of this embodiment is composed of wind energy, solar energy, hydropower, energy storage battery, natural gas energy, ground source heat pump WSHBG (Wind-Solar-Hydro-Battery-Gas) controller and power load. The system structure is as follows: Figure 2 shown.

[0050] Therefore, the capacity optimization configuration model includes six installed capacity of wind power equipment, installed capacity of photovoltaic power equipment, installed capacity of hydropower equipment, installed capacity of energy storage batteries, installed capacity of ground source heat pumps and installed capacity of gas turbines.

[0051] First, it is necessary to establish output models of various types of equipment as constraints for the subsequent solution of the capacity optimization configuration model.

[0052] Building a wind power generation model: The energy generated by a wind turbine depends mainly on the wind speed at the hub of the turbine. By obtaining the wind speed at the hub, the actual output power of the wind turbine can be determined according to the wind speed power curve:

[0053]

[0054] Where v is the wind speed at the fan hub, m / s; v iis the wind speed at the start of the fan, m / s, also known as the cut-in wind speed; v r is the rated wind speed, m / s; v c is the wind speed when the fan stops, m / s, also known as the cut-out wind speed; P w is the actual output power of the wind turbine, MW; P rw is the rated power of the wind turbine, MW; η rw It is the coefficient for converting the rated power of the fan into actual power when the wind speed is between the cut-in wind speed and the rated wind speed.

[0055] Constructing a photovoltaic power generation model: The main component of photovoltaic power generation is the solar panel. The power generated by the solar panel is calculated using the following formula:

[0056] P pν =RSη pν

[0057] Where R is the solar radiation intensity at a certain moment, MW / m 2 ; S is the area of ​​solar panels used for power generation, m 2 ;P pv is the actual output power of the solar photovoltaic power generation system, MW; η pv is the conversion efficiency of photovoltaic power generation.

[0058] Constructing a hydroelectric power generation model: Hydroelectric power generation uses the potential energy of water to convert into electrical energy by using the water level drop. Compared with wind power and solar photovoltaic power generation, hydroelectric power generation is relatively stable. During the flood season, hydroelectric power generation is usually used as the base load. The power generated by hydroelectric power generation is calculated by the following formula:

[0059] P h =QHgη h / 1000

[0060] Among them, P h is the actual output power of the hydropower generation system at a certain moment, MW; Q is the water flow at the same moment, m3 / s; H is the height of the water head, m; g is the acceleration of gravity; η h For hydroelectric efficiency.

[0061] Constructing energy storage battery model: In the multi-energy complementary system, energy storage batteries are used to solve the instability and imbalance of wind and solar power generation. The real-time capacity of the energy storage battery is calculated by the following formula:

[0062] S bat (t+△t)=S bat (t)-P bat △t

[0063] Where: S bat (t) is the battery capacity at time t, MWh; P batis the charging and discharging power of the energy storage battery, P bat >0 means discharge, P bat <0 means charging; S bat (t+Δt) is the battery capacity at the next moment, MWh; Δt is the time interval, which is 1 hour.

[0064] Constructing a gas-fired power generation model: Gas-fired power generation is easy to operate, quick to start, and emits significantly less pollutants than thermal power. In a multi-energy complementary energy system, when there is a shortage of solar and wind energy resources, hydropower cannot meet the load, and the capacity of the energy storage battery is at the lower limit, gas-fired power generation is used to ensure the operation of the load. This situation often occurs during peak hours, so gas-fired power generation is mostly used for peak load regulation.

[0065] The gas turbine uses natural gas as fuel to generate electricity. At the same time, the heat loss generated by power generation can be recovered and utilized through the waste heat recovery device. The power generation power of the gas turbine is calculated by the following formula:

[0066] P gt =F gt η gt

[0067] Q gt =F gt (1-η gt -η glos )

[0068] Among them, F gt is the natural gas consumption of gas turbine; η gt is the power generation efficiency of the gas turbine; Q gt Recover waste heat power for gas turbine; η glos Heat dissipation loss for gas turbine.

[0069] Constructing a heat pump heating model: A ground source heat pump (GSHP) is a heat pump that uses shallow geothermal resources such as rocks, soil, and groundwater to provide heating and cooling with electricity as the power source. Compared with electric boilers, the conversion efficiency of a ground source heat pump is greater than 4, which means that it consumes 1MWh of electricity and generates more than 4MWh of heat. At the same time, a ground source heat pump does not emit waste gas or wastewater, and is a green heating technology.

[0070] Due to the uncertainty of wind and solar energy, the electricity generated usually exceeds the load. When the energy storage battery is fully charged, it cannot store excess electricity. At this time, the use of ground source heat pumps can make full use of this excess electricity and improve energy efficiency. The heating power of the ground source heat pump is calculated by the following formula:

[0071] P hph =η hp P hp

[0072] Among them, P hph is the heating power of GSHP, MW; P ph is the input power of GSHP, MW; η ph is the heating efficiency of GSHP.

[0073] The objective function of the capacity optimization configuration model is constructed. In this embodiment, the objective function is formulated using economy, carbon emissions, and system energy efficiency as calculation indicators.

[0074] This embodiment evaluates the economic benefits of the system by minimizing the annual system total cost. The costs involved in the multi-energy complementary energy system throughout its life cycle include: initial capital investment in energy supply and energy storage devices, annual operation and maintenance costs, equipment replacement costs, and additional costs incurred by purchasing energy from outside (such as natural gas). The annual total cost C sys As shown below:

[0075] C sys =C a +C o +C re +C e

[0076] Among them, C a is the initial investment cost of the system; C o is the annual operation and maintenance cost of the system; C re is the replacement cost of damaged equipment during its life cycle; C e The cost of purchasing energy for the system.

[0077] For the initial investment cost, the initial investment cost of the system is the purchase cost of the relevant equipment. The initial investment cost is converted into each year according to the system life cycle, as shown in the following formula:

[0078]

[0079] Among them, F a is the capital recovery coefficient; r is the discount rate; m is the full life cycle of the multi-energy complementary system; C a，k (k=1,2,..,6) represent the investment costs of wind power, photovoltaic power, hydropower, energy storage battery, gas power generation and ground source heat pump respectively.

[0080] As for the operation and maintenance cost, the annual operation and maintenance cost of the system is mainly the maintenance cost of each device in the system, as shown in the following formula:

[0081]

[0082] Among them, C o，kis the unit operation and maintenance cost of the kth type of equipment in the system; D is the total number of days in a year; T is the time of day; W d，t，k is the output level of the kth type of equipment at time t on the dth day.

[0083] As for the equipment replacement cost, in the entire life cycle, the equipment replacement cost is determined by the initial investment cost and the service life of the equipment. In view of the uncertainty of equipment damage, this embodiment calculates this cost based on the expected life of the system, as shown in the following formula:

[0084]

[0085] Among them, C a，k represents the initial investment cost of the kth type of equipment; F r，k is the capital recovery factor of the k-th type of equipment; m_k is the service life of the k-th type of equipment.

[0086] Regarding the cost of purchased energy, in this embodiment, the gas turbine is the main mode of gas consumption. Therefore, the cost of purchased energy for the system is mainly the purchase cost of the gas required by the gas turbine, as shown in the following formula:

[0087]

[0088] Among them, C fuel is the unit price of natural gas; F d，t is the natural gas consumption at time t on the dth day.

[0089] This example evaluates the environmental friendliness of the multi-energy complementary energy system by minimizing the system's annual carbon emissions. Carbon emissions mainly come from the carbon emissions generated by the multi-energy complementary system through natural gas combustion for power generation, as shown in the following formula:

[0090]

[0091] Among them, CE (Carbon Emissions) is the annual carbon emissions of the multi-energy complementary system, μ c,g is the carbon emission factor of natural gas combustion; V pgu，T is the amount of natural gas consumed by the gas turbine at time T; max The maximum annual operating time of the system is usually 8760 hours.

[0092] This embodiment evaluates the stability and energy utilization rate of the multi-energy complementary energy system through the power balance loss index, thereby evaluating the energy efficiency level of the system. With the goal of minimizing the power balance loss caused by wind energy, solar energy and hydropower storage, gas power is used when there is a power shortage, and ground source heat pumps are used for heating when there is surplus power. The power balance loss consists of two parts, one is the power shortage PS, and the other is the surplus SP.

[0093] When the combined power supply of wind energy, solar energy, hydropower and energy storage batteries cannot meet the load demand, the power shortage at this time is calculated by the following formula:

[0094] PS(t)=P load -P w -P pv -P h -P bat

[0095] When the system's wind, solar, and hydroelectric power generation exceeds the load, and the real-time battery capacity S bat Reach the maximum permissible battery capacity S bat，max When the system uses ground source heat pump for heating, the surplus electricity is calculated by the following formula:

[0096] SP(t)=P w +P pv +P h -P load

[0097] In the system optimization simulation, the system has different states at each moment. The power and load information are calculated and read to determine the power shortage or surplus power situation. One of PS and SP is used as the optimization target. By simulating 8760h and setting different simulation conditions, the optimal configuration of multi-objective capacity of the multi-energy system will be achieved.

[0098] In addition to the output models of the above-mentioned various types of equipment, the constraints of the capacity optimization configuration model of this embodiment also include:

[0099] (1) The installed capacity constraint of wind power generation equipment is:

[0100] C w ≤C w,max

[0101] Among them, C w and C w,max They are respectively the installed capacity of wind power generation equipment and the maximum installed capacity of wind power generation equipment that can be planned and constructed in a region.

[0102] (2) The installed capacity constraint of photovoltaic power generation equipment is:

[0103] C pv ≤C pv,max

[0104] Among them, C pv and C pv,max They are respectively the installed capacity of photovoltaic power generation equipment and the maximum installed capacity of photovoltaic power generation equipment that can be planned and constructed in a region.

[0105] (3) The output constraints of hydropower generation equipment are:

[0106] P h,min ≤P h ≤P h,max

[0107] Among them, P h is the output power of the hydroelectric power generation equipment; P h，min and P h，max They are the upper and lower output limits of the hydropower equipment respectively.

[0108] (4) The capacity constraint of the energy storage battery is:

[0109]

[0110] Among them, C bat and C bat,max are the installed capacity of energy storage batteries and the maximum installed capacity of energy storage batteries that can be planned and constructed; P ch，min and P dis，max are the maximum charging power and maximum discharging power of the energy storage battery respectively; S bat，min and S bat，max are the lower and upper limits of the real-time capacity of the energy storage battery respectively; S bat is the real-time capacity of the energy storage battery; P bat is the charging and discharging power of the energy storage battery, P bat >0 means discharge, P bat <0 means charging.

[0111] (5) The heating constraints of the ground source heat pump are:

[0112]

[0113] Among them, P hph and P hph,max They are the heating power of the ground source heat pump and the upper limit of the heating power of the ground source heat pump respectively.

[0114] (6) The output constraint of the gas turbine is:

[0115] P gt,min ≤P gt ≤P gt,max

[0116] Among them, P gt is the output power of the gas turbine; P gt，min and P gt，max They are the upper and lower output limits of the gas turbine respectively.

[0117] S2. Solve the capacity optimization configuration model to obtain the optimal decision variables.

[0118] This embodiment uses the Deep Deterministic Policy Gradient (DDPG) algorithm to solve the capacity optimization configuration model.

[0119] First, the DDPG algorithm framework is constructed. This embodiment uses the DDPG algorithm to train an intelligent agent, which can find the optimal capacity configuration of the multi-energy complementary energy system including wind-solar-water-storage-gas in this embodiment. The Actor-Critic network of DDPG consists of four networks, namely, the actor network μ(s|θ μ ), critic network Q(s,a|θ Q ), target actor network μ′(s|θ μ′ ) and the target critic network Q′(s,a|θ Q′ ). s represents the state; a represents the action; θ μ ,θ Q ,θ μ′ ,θ Q′ are the weights of the four networks.

[0120] The weights of the actor and critic networks are randomly initialized, and the initial weights of the target actor and target critic networks are set to θ μ and θ Q .

[0121] DDPG contains a total of 4 neural networks for approximate representation of Q-value functions and strategies. The target critic network is used to approximate the Q-value function Q′(s,a|θ) of the state-action at the next moment. Q′ ), where the next action value is estimated by the target actor network approximation μ′(s|θ μ′ ). So the target value of the Q-value function in the current state is:

[0122] y i =r i +γQ′(s i+1 ,μ′(S i+1 |θ μ′ )|θ Q′ )

[0123] Among them, y i is the objective function value; r i is the reward value corresponding to each action; γ is the discount rate.

[0124] The critic network outputs the Q-value function Q(s,a|θ) of the current state-action Q ), which is used to evaluate the current strategy. In order to increase the agent's exploration in the environment, DDPG adds a Gaussian noise function to the behavior strategy. The goal of the critic network is defined as:

[0125] y i -Q(s i ,a i ∣θ Q )

[0126] The parameters of the critic network are updated by minimizing the loss value (mean square error loss). The loss function of the critic network when updating is:

[0127]

[0128] The target actor network is used to provide the strategy for the next state, while the actor network provides the strategy for the current state. Combined with the Q-value function of the critic network, the policy gradient of the actor network during parameter update is obtained:

[0129]

[0130] Where J represents the objective function of the DDPG algorithm; Represents a gradient operation.

[0131] After updating the actor network and the critic network for a certain number of steps, the target actor network and the target critic network are updated using the following formula:

[0132] θ μ′ ←τθ μ +(1-τ)θ μ′

[0133] θ Q′ ←τθ Q +(1-τ)θ Q′

[0134] Among them, τ is the soft update coefficient (0<τ01), and τ is used to update the target network to minimize the parameter changes of the target network and make the algorithm more stable. The process of the DDPG algorithm is as follows Figure 3 shown.

[0135] Based on the established wind-solar-water-storage-gas multi-energy complementary energy system model, the multi-objective optimization problem is formulated as a reinforcement learning optimization problem.

[0136] The state space includes wind power installed capacity C w 、Solar photovoltaic power generation installed capacity C pv 、Real-time hydropower capacity P h , real-time capacity Sbat(t) of energy storage battery and real-time load P load The action space includes adjusting the wind power installed capacity a w and adjust the installed capacity of solar photovoltaic power generationa pvThe installed capacity of the battery is set at the beginning. The simulation time of the system is 8760 hours, with a time step of 1 hour.

[0137] The reward function is designed according to the optimization goal to ensure that the intelligent agent explores in the direction of low power shortage, low surplus, low cost and low carbon emission.

[0138] The control strategy of wind-solar-water-storage-gas multi-energy complementary energy system is as follows Figure 4 As shown. wsh Represents the combined output power of wind, solar and hydropower; P n Indicates the difference between load and output power. n =0 means the system power is balanced; P n >0 means that energy storage batteries are needed to supplement power; P n <0 means there is excess power generation and the battery can be charged. max is a finite step length. Through the DDPG model, the optimal configuration scheme of the multi-energy system capacity (i.e., the optimal decision variable) is solved.

[0139] S3. Configure the capacity of the multi-energy complementary system according to the optimal configuration scheme of the capacity of the multi-energy complementary system (i.e., the optimal decision variable).

[0140] Computer device embodiment:

[0141] A computer device includes a processor, the processor is used to execute a computer program to implement the steps of the capacity optimization configuration method of the multi-energy complementary system as described above. The specific capacity optimization configuration method of the multi-energy complementary system has been introduced in detail in the embodiment of the capacity optimization configuration method of the multi-energy complementary system, and will not be repeated here.

[0142] The present invention has the following characteristics:

[0143] The present invention provides a method for optimizing the capacity configuration of a multi-energy system based on deep reinforcement learning, establishes a wind-solar-water-storage-gas multi-energy complementary energy system model, comprehensively considers multiple optimization objectives such as economy, carbon emissions and system energy efficiency, and obtains the optimal capacity configuration scheme for peak power, photovoltaics, hydropower, energy storage batteries, and gas turbines through a deep reinforcement learning algorithm, so as to achieve a multi-energy system planning and design scheme with the characteristics of low power shortage, low surplus, low cost, and low carbon emissions, support the generation of comprehensive energy planning and design schemes for the green economy, and promote the high-quality development of comprehensive energy.

[0144] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention is described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments without creative work, or replace some of the technical features therein with equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A capacity optimization configuration method for a multi-energy complementary system, characterized in that: The method includes: S1. Construct a capacity optimization configuration model for a multi-energy complementary system; The decision variables of the capacity optimization configuration model include the installed capacity of different energy types in the multi-energy complementary system; The objective function of the capacity optimization configuration model includes an objective function constructed by minimizing the gap between the power supply and power consumption of the system; S2. Solving the capacity optimization configuration model to obtain optimal decision variables; S3. Optimize the capacity configuration of the multi-energy complementary system according to the optimal decision variables.

2. The capacity optimization configuration method of the multi-energy complementary system according to claim 1 is characterized in that: When the power supply is higher than the power consumption, the gap is the surplus power; when the power supply is lower than the power consumption, the gap is the power shortage.

3. The capacity optimization configuration method of a multi-energy complementary system according to claim 1, characterized in that: The objective function of the capacity optimization configuration model also includes an objective function constructed with the goal of minimizing the total cost of the multi-energy complementary system over its entire life cycle and an objective function constructed with the goal of minimizing the carbon emissions of the multi-energy complementary system.

4. The capacity optimization configuration method of the multi-energy complementary system according to claim 3 is characterized in that: The multi-energy complementary system includes a gas turbine that consumes natural gas to generate electricity, and the carbon emission CE is obtained according to the following formula: Among them, μ c,g is the carbon emission factor of natural gas combustion; V pgu，T is the amount of natural gas consumed by the gas turbine at time T; max The maximum operating time of the system.

5. The capacity optimization configuration method of the multi-energy complementary system according to claim 3 is characterized in that: The total annual cost over the entire life cycle includes initial investment cost, operation and maintenance cost, equipment replacement cost and purchased energy cost.

6. The capacity optimization configuration method of the multi-energy complementary system according to claim 1 is characterized in that: The multi-energy complementary system includes wind power generation equipment, photovoltaic power generation equipment, hydropower generation equipment, energy storage batteries, ground source heat pumps and gas turbines that consume natural gas to generate electricity; the decision variables include the installed capacity of wind power generation equipment, the installed capacity of photovoltaic power generation equipment, the installed capacity of hydropower generation equipment, the installed capacity of energy storage batteries, the installed capacity of ground source heat pumps and the installed capacity of gas turbines.

7. The capacity optimization configuration method of the multi-energy complementary system according to claim 6 is characterized in that: The constraints of the capacity optimization configuration model include: installed capacity constraints of wind power generation equipment, installed capacity constraints of photovoltaic power generation equipment, output constraints of hydropower generation equipment, capacity constraints of energy storage batteries, heating constraints of ground source heat pumps and output constraints of gas turbines: The installed capacity constraint of the wind power generation equipment is: C w ≤C w,max Among them, C w and C w,max They are the installed capacity of wind power generation equipment and the maximum installed capacity of wind power generation equipment that can be planned and constructed in the region; The installed capacity constraint of the photovoltaic power generation equipment is: C pv ≤C pv,max Among them, C pv and C pv,max They are the installed capacity of photovoltaic power generation equipment and the maximum installed capacity of photovoltaic power generation equipment that can be planned and constructed in the region; The output constraint of the hydroelectric power generation equipment is: P h,min ≤P h ≤P h,max Among them, P h is the output power of the hydroelectric power generation equipment; P h，min and P h，max They are the upper and lower output limits of the hydroelectric power generation equipment respectively; The capacity constraint of the energy storage battery is: Among them, C bat and C bat,max are the installed capacity of energy storage batteries and the maximum installed capacity of energy storage batteries that can be planned and constructed; P ch，min and P dis，max are the maximum charging power and maximum discharging power of the energy storage battery respectively; S bat，min and S bat，max are the lower and upper limits of the real-time capacity of the energy storage battery respectively; S bat is the real-time capacity of the energy storage battery; P bat is the charging and discharging power of the energy storage battery, P bat >0 means discharge, P bat <0 means charging; The heating constraints of the ground source heat pump are: P hph ≤P hph,max Among them, P hph and P hph,max They are the heating power of the ground source heat pump and the upper limit of the heating power of the ground source heat pump respectively; The output constraint of the gas turbine is: P gt,min ≤P gt ≤P gt,max Among them, P gt is the output power of the gas turbine; P gt，min and P gt，max They are the upper and lower output limits of the gas turbine respectively.

8. The capacity optimization configuration method of a multi-energy complementary system according to claim 1, characterized in that: In S2, the capacity optimization configuration model is solved by a deep deterministic policy gradient algorithm.

9. A computer device comprising a processor, characterized in that: The processor is used to execute a computer program to implement the steps of the capacity optimization configuration method of a multi-energy complementary system as claimed in any one of claims 1 to 8.

Images