Multi-column vertical axis wind heat storage energy electric heating furnace, control system and scheduling method

Abstract

This invention discloses a multi-column vertical axis wind-powered thermal energy storage electric furnace, a control system, and optimized scheduling. The electric furnace includes a wind-solar hybrid power generation system and a solid-state thermal energy storage system connected to it. The wind-solar hybrid power generation system includes wind turbine blades, a vertical axis, a multi-column tower, and photovoltaic modules. The wind turbine blades are connected to the vertical axis, the multi-column tower is fitted around the outer periphery of the vertical axis, and the photovoltaic modules are installed on the top of the wind turbine blades and around the multi-column tower. The solid-state thermal energy storage system includes at least one set of thermal energy storage devices, each set installed at the lower part of the multi-column tower. This electric furnace integrates multi-energy and spatial complementarity through a multi-column vertical axis wind power, photovoltaic curtain wall, and solid-state thermal energy storage system for both electricity and heat production, leveraging the complementary advantages of electrical and thermal energy.

Description

Technical Field

[0001] This invention belongs to the field of energy technology, and specifically relates to a multi-column vertical axis wind-powered thermal energy storage electric furnace, its control system, and its scheduling method. Background Technology

[0002] Faced with the dual crises of energy and the environment, the proportion of new energy power generation in my country is increasing. Thanks to the continuous advancement of wind and solar power technologies, wind and solar energy have become one of the most mainstream renewable energy sources globally, widely used in the power generation field. Modern wind turbines are classified into two main categories based on the topological geometry of the rotor shaft relative to the ground: vertical axis wind turbines and horizontal axis wind turbines. Horizontal axis wind turbines have high-speed blade rotation, generating high-frequency noise that impacts the surrounding environment and residents. The blades of horizontal axis wind turbines can also disturb or harm birds, damaging the ecosystem. For specific terrains, vertical axis wind turbines, with their simple structure, stable operation, and easy maintenance, are clearly more advantageous. Vertical axis wind turbines do not require yaw systems, pitch systems, braking systems, etc., only a simple support tower and a generator, reducing structural complexity and weight, and lowering manufacturing and maintenance costs and difficulties. Their blades experience uniform wind force during rotation, without generating periodic vibrations and stresses, greatly increasing operational stability and lifespan. Chinese invention patent (publication number: CN103742371A) discloses a multi-layered, double-bladed, vertical-axis wind turbine generator set, including a generator, at least two layers of wind turbines, and a frame mechanism, with the at least two layers of wind turbines sequentially mounted on the frame mechanism from bottom to top. Chinese invention patent (publication number: CN108397353A) discloses a novel vertical-axis wind turbine generator set. This design incorporates a rotating cylinder, blades, and a rotating shaft, ensuring the blades are vertically positioned. This allows for the collection of wind energy from different directions and wind speeds, eliminating the need for yaw or pitch control devices, resulting in a simpler overall structure, easier control, and a lower failure rate. Chinese invention patent (publication number: CN110873024A) discloses a vertical-axis wind turbine generator set. By stacking two or more generators on the outer periphery of a main shaft installed perpendicular to the horizontal plane, the power generation efficiency and output of the vertical-axis wind turbine generator set are improved.

[0003] Currently, due to the vigorous development of new energy sources, integrated new energy electric and thermal energy systems have emerged. For example, a Chinese utility model patent (publication number: CN205261707U) discloses an electric boiler thermal storage heating system utilizing curtailed wind and solar power. The high-pressure boiler subsystem is powered by wind power, solar power generation, and high-voltage power distribution backup power. Similarly, oil and gas stations have large demand for temperature maintenance in large tanks and pipelines. Currently, boilers using fossil fuels such as oil and natural gas produce large amounts of greenhouse gases such as CO2 after combustion, and electricity consumption is mainly based on ash electricity. Against this backdrop, the aforementioned patent does not focus on multi-energy complementarity, integration, and zero-fossil heating technologies. Therefore, how to match the design of vertical axis wind turbine power generation with thermal energy storage is becoming an increasingly urgent technical problem to be solved. Summary of the Invention

[0004] To address the aforementioned problems, the present invention aims to provide a multi-column vertical axis wind-powered thermal energy storage electric furnace, comprising a wind-solar hybrid power generation system and a solid-state electric thermal energy storage system connected thereto, wherein...

[0005] The wind-solar hybrid power generation system includes wind turbine blades, a vertical shaft, a multi-column tower, and photovoltaic modules. The wind turbine blades are connected to the vertical shaft, the multi-column tower is fitted around the outer periphery of the vertical shaft, and the photovoltaic modules are installed on the top of the wind turbine blades and around the multi-column tower.

[0006] The solid-state electric thermal energy storage system includes at least one set of thermal energy storage equipment, and each set of thermal energy storage equipment is installed at the bottom of a multi-column tower.

[0007] Furthermore, the wind-solar hybrid power generation system also includes a generator, converter, inverter, and wind-solar-thermal-power control cabinet, among which,

[0008] The generator is connected to the wind turbine blades and the converter respectively, and the photovoltaic module is connected to the inverter;

[0009] The converter and inverter are also connected to each group of thermal energy storage devices.

[0010] The wind, solar, thermal, and power control cabinets are connected to the generator, photovoltaic modules, and each set of thermal energy storage equipment, respectively.

[0011] Furthermore, each set of thermal energy storage equipment includes an electric heating element, a high-temperature heat storage body, a heat exchanger, a high-temperature circulating fan, and an insulation box.

[0012] The electric heating elements are connected to the converter, inverter, and heat exchanger, respectively.

[0013] The heat exchangers are connected to the high-temperature circulating fan and the high-temperature heat storage body, respectively.

[0014] The insulation box is installed on the outermost layer of each set of thermal energy storage equipment.

[0015] Another object of the present invention is to provide a multi-column vertical axis wind power thermal energy storage control system, comprising a central control unit, a wind power controller, an energy management module, and any of the above-described electric furnaces, wherein,

[0016] The central control unit is used to issue control commands to the energy management module, wind power controller, converter and each group of thermal energy storage devices, and to receive feedback information;

[0017] The energy management module is used to control the converter to output electrical energy to the power grid and / or at least one set of thermal energy storage devices according to control commands, and to control at least one set of thermal energy storage devices to release the stored thermal energy or continue to store thermal energy.

[0018] Another object of the present invention is to provide a scheduling method for the above-described multi-column vertical axis wind-powered thermal energy storage electric furnace, comprising,

[0019] Establish a real-time optimization scheduling model for wind, solar, and thermal systems containing solid thermal energy storage, with the goal of minimizing wind and solar curtailment;

[0020] Establish a real-time optimization scheduling model for wind, solar, and thermal systems with solid thermal energy storage based on a Markov reward process within a reinforcement learning framework;

[0021] The scheduling model of the wind, solar and thermal system containing solid thermal energy storage is trained using a near-end strategy optimization algorithm to obtain the scheduling model of the wind, solar and thermal system containing solid thermal energy storage.

[0022] Furthermore, establishing a real-time optimal scheduling model for wind, solar, and thermal systems with solid thermal energy storage, aiming to minimize wind and solar curtailment, includes determining the objective function and constraints of the optimal scheduling model, whereby...

[0023] The objective function of optimizing the scheduling model satisfies:

[0024] minP wt,real +P pv,real -P wt,grid -P pv,grid -P wt,heat -P pv,heat +P bt,heat (1)

[0025] In the formula, P wt,real and P pv,real These represent the power output of wind power and solar power at each moment, P. wt,grid and P pv,grid These represent the actual power supplied to the electrical load by wind power and solar power at each moment; P wt,heat and P pv,heatThese represent the actual power supplied by wind power and solar power to the heat load at each moment; P bt,heat It is the output power of solid thermal energy storage, P bt,heat A value greater than zero indicates that solid-state thermal energy storage releases heat, P bt,heat A value less than zero indicates solid thermal energy storage.

[0026] The constraints include the electrical power balance constraint of the wind, solar and thermal system containing solid thermal energy storage, the thermal power balance constraint of the wind, solar output constraint, electrothermal coupling constraint, solid thermal energy storage heat storage and release constraint, and SOC constraint.

[0027] Furthermore, the power balance constraint of a wind, solar, and thermal system containing solid thermal energy storage satisfies:

[0028] P wt,grid +P pv,grid =P load (2)

[0029] In the formula, P load It is the power load of the wind and solar power storage station;

[0030] The thermal power balance constraints of wind, solar, and thermal systems containing solid thermal energy storage include,

[0031] Q wt,heat +Q pv,heat +Q bt,heat =Q load (3)

[0032] In the formula, Q wt,heat and Q pv,heat These are the heat generated by wind power and solar power, respectively, Q. bt,heat Q is the amount of heat stored or released in solid thermal energy storage. load It is the demand for heat load;

[0033] Wind and solar power output constraints include,

[0034]

[0035] In the formula, P wt,real and P pv,real These represent the power output of wind power and solar power at each moment, P. wt,grid and P pv,grid These represent the actual power supplied to the electrical load by wind power and solar power at each moment; P wt,heat and P pv,heat These represent the actual power supplied by wind power and solar power to the heat load at each moment;

[0036] The electrothermal coupling constraint satisfies:

[0037] Q wt,heat =ηeh P wt,heat (5)

[0038] Q pv,heat =η eh P pv,heat (6)

[0039] Q bt,heat =η eh P bt,heat (7)

[0040] In the formula, η eh It is the electrothermal conversion efficiency;

[0041] Solid-state thermal energy storage charge and discharge constraints are satisfied:

[0042] -P bt,heat,max ≤P bt,heat ≤P bt,heat,max (8)

[0043] In the formula, P bt,heat,max P bt,heat These represent the maximum heat storage and heat release power of the solid thermal energy storage device.

[0044] Solid-state thermal energy storage SOC constraints are satisfied:

[0045] SOC bt,heat =(1-ρ)SOC bt,heat,last -ΔSOC bt,heat (9)

[0046]

[0047] SOC btheat，min ≤SOC bt，heat ≤SOC bt，heat,max (11)

[0048] In the formula, SOCb t,heat,max and SOCb t,heat,min ΔSOC represents the upper and lower limits of the state of charge (SOC) for solid-state thermal energy storage, respectively, where ρ is the self-sustaining discharge rate of the energy storage battery; bt,heat Ebt represents the change in charge of a solid thermal energy storage device, which depends on the thermal state of the storage device and the thermal power released / stored. t,heat,max ηc represents the maximum capacity of the solid thermal energy storage device; ηd represents the charging efficiency of the solid thermal energy storage device; and ηd represents the discharging efficiency of the solid thermal energy storage device.

[0049] Furthermore, the Markov reward process includes a quadruple array {S,A,γ,R}; S, A, γ, and R represent the state space, action space, discount factor, and reward function, respectively.

[0050] The state space S is shown below:

[0051] S={S wt,real ,S pv.real ,S soc,heat,last ,S pload ,S qload} (12)

[0052] In the formula, S wt,real and S pv,real S represents the real-time power output sets of wind power and solar power, respectively. soc,heat,last It is the SOC of solid thermal energy storage at the previous moment, S pload S is the real-time output aggregation of electrical loads in wind, solar, and thermal systems containing solid thermal energy storage. qload It is a collection of real-time heat load outputs for wind, solar, and thermal systems containing solid thermal energy storage.

[0053] Action space A is shown below:

[0054] A={A wt,grid A pv,grid A wt,heat A pv,heat A bt,heat} (13)

[0055] In the formula, A wt,grid A pv,grid A wt,heat and A pv,heat A represents the electrical output and thermal conversion output of wind power and solar power respectively. bt,heat It is the real-time output of thermal energy storage;

[0056] The reward function R is shown below:

[0057]

[0058] In the formula, γ is the discount factor, and r t For instant rewards, instant reward r t satisfy:

[0059] r t =-(P wt,real +P pv,real -P wt,grid -P pv,grid -P wt,heat -P pv,heat +P bt (15).

[0060] Furthermore, training the scheduling model of the wind, solar, and thermal system containing solid thermal energy storage using a near-end strategy optimization algorithm includes,

[0061] Step S1: Randomly initialize the current policy network parameters θQ and value network parameters θ π We determine the training period K = 1,000,000, the scheduling period T = 24, and the target network update frequency C = 100, and set the number of training iterations k = 0.

[0062] Step S2: Initialize the initial state s of the wind, solar and thermal system from the state space. t And let t = 0;

[0063] Step S3: Based on state s in the current value network t Output action a t ;

[0064] Step S4: Execute action a in the energy management system of the wind, solar, and thermal system. t And obtain the next state s t+1 Reward r t Let t = t + 1, then proceed to step S3 until the time series sample {A} is learned. T， S T R T S T+1};

[0065] Step S5: Transfer the learned time series samples {A} T ,S T ,R T ,S T+1 The data is stored in the sample experience pool as a dataset for training the network.

[0066] Step S6: Randomly collect m time series samples {A} from the experience pool. T ,S T ,R T ,S T+1}, and calculate the loss function L(θ) of the value network. Q );

[0067] L(θ Q )=E(y t -Q(s t ,a t |θ Q )) 2 (16)

[0068] In the formula, Q(s) t ,a t |θ Q () represents the Q-value output by the current network at time t; E represents the mean function;

[0069] y t For the target Q value y t As shown below:

[0070] yt =r t +γQ′(s t+1 ,π′(s t+1 |θ π′ )|θ Q′ (17)

[0071] In the formula, r t The instantaneous reward at time t, extracted from the experience pool; π′(s t+1 |θ π′ ) is the target policy network in parameter θ π′ Input state variable s t+1 The action variable output at that time; Q′(s) t+1 ,π′(s t+1 |θ π′ )|θ Q′ ) is the target network in parameter θ Q′ Next input state s t+1 and action variable π′(s) t+1 |θ π′ Input Q value under ) ;

[0072] Step S7: Update the gradient of the value network according to the following formula:

[0073]

[0074] In the formula, θ Q μ represents the current value network parameters. Q The learning rate of the current value network. The loss function L(θ) Q For parameter θ Q gradient; π θ (a t |s t ) and πθ old (a t |s t (A) represents two different policies in the policy network: the old policy and the new policy. t ε is the advantage function; ε is the boundary value of the loss function, with a value of 0.1; E t It is a mean function;

[0075] Step S8: Update the parameters θ of the policy network. π ',Right now:

[0076]

[0077] In the formula, θ π μ represents the current policy network parameters. π is the learning rate of the policy network, with a value of 0.00001; Let Q be the Q-value Q(s,a|θ).Q The gradient of action a; For policy gradient;

[0078] Step S9: Determine if k%C=1 holds true. If so, update the policy network parameter θ based on formula (19). Q′ and value network parameters θ π′ If the condition is met, proceed to step S10; otherwise, proceed directly to step S10.

[0079]

[0080] In the formula, θ Q′ and θ π′ are the parameters of the target value network and the target policy network, respectively, and τ is the soft update coefficient;

[0081] Step S10: Determine whether the training count k>K is true. If yes, output the scheduling model of the wind, solar and thermal system containing solid thermal energy storage. Otherwise, let k = k+1 and return to step S2.

[0082] This invention's electric furnace integrates multi-energy and spatial complementary systems using multi-column vertical axis wind power, photovoltaic curtain walls, and solid thermal storage for production electricity and heat consumption. Through the complementary advantages of electricity and heat energy, it can significantly increase the absorption rate of wind and solar power. Interactive control of source and load enables refined management and control of oilfield energy consumption, promoting the economical and safe operation of the integrated electric and thermal energy system. By integrating with oil and gas stations, it forms a green alternative technology for grey electricity and fossil fuel heating in oil and gas stations, helping oil and gas companies achieve green and low-carbon development.

[0083] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0084] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0085] Figure 1 A schematic diagram of a multi-column vertical axis wind-powered thermal energy storage electric furnace is shown in an embodiment of the present invention.

[0086] Figure 2A schematic diagram of a multi-column vertical axis wind power thermal energy storage control system according to an embodiment of the present invention is shown.

[0087] Figure 3 A schematic flowchart of a scheduling method for a multi-column vertical axis wind-powered thermal energy storage electric furnace according to an embodiment of the present invention is shown.

[0088] Figure 4 To provide power to various devices in the electrical system under typical daytime conditions;

[0089] Figure 5 It provides power to various devices in a typical daytime thermal system. Detailed Implementation

[0090] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0091] like Figure 1 As shown in the illustration, this invention introduces a multi-column vertical axis wind-powered thermal energy storage electric furnace. The electric furnace includes a wind-solar hybrid power generation system and a solid-state electric thermal energy storage system connected thereto. The wind-solar hybrid power generation system includes wind turbine blades, a vertical axis, a multi-column tower, and photovoltaic modules. The wind turbine blades are connected to the vertical axis, the multi-column tower is fitted around the outer periphery of the vertical axis, and the photovoltaic modules are installed on the top of the wind turbine blades and around the multi-column tower. The solid-state electric thermal energy storage system includes at least one set of thermal energy storage devices, each set installed at the lower part of the multi-column tower. This multi-column vertical axis wind power, photovoltaic curtain wall, and solid-state thermal energy storage system achieves a multi-energy and spatial complementary integrated system to replace electricity and heat used in oil and gas production. Through the complementary advantages of electricity and heat energy, the wind and solar energy absorption ratio can be significantly increased. Through interactive control of source and load, refined management and control of oilfield energy consumption can be achieved, promoting the economical and safe operation of the integrated electric and thermal energy system. By integrating with oil and gas stations, green alternative technologies for gray electricity and fossil fuel heating at oil and gas stations can be developed, helping oil and gas companies achieve green and low-carbon development.

[0092] Compared to horizontal-axis wind turbines, vertical-axis wind turbines possess numerous advantages due to their inherent structural design: Vertical-axis wind turbines can capture incoming wind from any direction, thus eliminating the need for complex yaw mechanisms, resulting in a simpler structure and lower installation costs. Important equipment such as generators and gearboxes can be housed on the ground or at the base of a tower, eliminating the need for maintenance and repairs on high-altitude platforms tens or even hundreds of meters above the ground, as is required for horizontal-axis wind turbines. This significantly reduces maintenance costs and eliminates the need for safe distances of hundreds of meters from oil and gas facilities. From the perspective of long-term operating costs for wind power generation, vertical-axis wind turbines demonstrate greater development potential.

[0093] Specifically, Figure 1 , 2 The wind-solar hybrid power generation system includes wind turbine blades, a vertical shaft (not shown in the figure), a permanent magnet generator, a multi-column tower, a converter, photovoltaic modules, an inverter, a wind-solar-thermal-electric control cabinet, and an energy management module (not shown in the figure). The wind-solar-thermal-electric control cabinet houses the system circuit breaker and protection circuit devices. Furthermore, the permanent magnet generator, converter, inverter, and energy management module are all housed within the wind-solar-thermal-electric control cabinet. The solid-state electric thermal energy storage system includes two sets of thermal energy storage devices, but is not limited to this; the number can be adjusted according to the application, and may include one, three, or four sets. The thermal energy storage devices include electric heating elements (not shown in the figure), a high-temperature heat storage body, a heat exchanger, a high-temperature circulating fan, and an insulation box. The high-temperature circulating fan includes a fan. Further, the photovoltaic module includes a photovoltaic panel. The fan turbine blades are connected to a vertical axis. A permanent magnet generator is connected to the fan turbine blades and a converter. The photovoltaic module is connected to an inverter. The converter and inverter are also connected to electric heating elements. The wind-solar-thermal-electric control cabinet is connected to the generator, photovoltaic module, and electric heating elements. The electric heating elements are also connected to a heat exchanger. The heat exchanger is connected to the high-temperature circulating fan and the high-temperature heat storage body. An insulation box is installed on the outermost layer of the thermal energy storage device. Further, the photovoltaic module is installed on the top of the fan turbine blades and around the multi-column tower. The multi-column structure provides a three-dimensional installation space for the photovoltaic cells, eliminating the need for separate space and the need for photovoltaic cell mounting brackets. Simultaneously, the multi-column tower is covered with photovoltaic panels on all four sides, serving as insulation walls for the solid-state electric thermal energy storage device. Each set of thermal energy storage equipment is installed at the bottom of the multi-column tower. Taking full advantage of the multi-column structure of the vertical axis wind turbine's lower support, photovoltaic modules are installed on the top of the turbine and under the rotor. Simultaneously, a solid-state electric thermal energy storage system, matching the power output of the vertical axis wind turbine, is designed using the space at its base, demonstrating universal applicability. Furthermore, the electric furnace also includes disc brakes and gearboxes, which will not be detailed here. Moreover, the electrical connections between components within the system should be fixed and reliable; plug-and-socket interconnections are not permitted.

[0094] Furthermore, the multi-column vertical axis wind turbine utilizes the turbine blades to convert wind energy into kinetic energy, which is then transmitted to a permanent magnet generator. The permanent magnet generator receives the kinetic energy and generates electrical energy. Photovoltaic modules are mounted on the multi-column tower around and on top of the multi-column vertical axis wind turbine. The installation location should ensure that no object or shadow obstructs the solar panels within the photovoltaic modules throughout the entire daylight hours. The excitation generator is connected to the inverter, and the photovoltaic modules are connected to the inverter, utilizing wind and solar energy to generate electricity and transmit it to at least one set of thermal energy storage devices. The aforementioned electric furnace considers the optimized matching of the system structure, fully leveraging structural and flexibility features to further improve the system's economic efficiency and promote wind and solar energy integration.

[0095] Each set of thermal energy storage devices can store the electrical energy generated by the wind-solar hybrid power generation system as thermal energy through electric heating elements. Specifically, the wind-solar-thermal-electric control cabinet controls the permanent magnet generator and photovoltaic modules to generate electricity, controls the electric heating elements to store thermal energy, and controls the heat to enter the heat exchanger for heat exchange, producing hot water to provide heat for the oil and gas field's heating equipment. When the heat reaches its upper limit, power supply to the thermal storage system stops, and surplus electricity is fed into the grid. Figure 2 As shown in the diagram. The process of controlling heat entering and exiting the heat exchanger to provide heat for oil and gas field heating equipment includes: a high-temperature circulating fan circulates the high-temperature air from the heat exchanger to the high-temperature heat storage medium for heating; and heat transfer pipelines transport the hot water or steam to the oil field heating scenario. Furthermore, an insulation box is located on the outermost layer of the electric heat storage unit to reduce heat loss from the high-temperature heat storage medium.

[0096] The multi-column vertical axis wind-powered thermal energy storage electric furnace can be applied to the new energy field where various types of oil and gas stations have electricity and heat demand, thereby improving the utilization efficiency and economic benefits of new energy.

[0097] like Figure 2 As shown in the illustration, this invention also introduces a multi-column vertical axis wind power thermal energy storage control system. The control system includes a central control unit, a wind power controller, an energy management module, and the aforementioned multi-column vertical axis wind power thermal energy storage electric furnace. The central control unit sends control commands to the energy management module, wind power controller, converter, and thermal energy storage device, and receives feedback information. The energy management module controls the converter to output electrical energy to the power grid and / or the thermal energy storage device through the wind power controller according to the control commands, and controls the thermal energy storage device to release stored thermal energy or continue storing thermal energy. The control system controls the vertical axis wind turbine and photovoltaic modules to generate electricity, controls the electric heating elements to store thermal energy, and controls the heat to enter the heat exchanger for heat exchange and steam output, providing heat for the oil and gas field heating system, reducing wind and solar energy curtailment, and improving the utilization rate of wind and solar energy.

[0098] Specifically, the converter can output electrical energy to the grid, thermal energy storage units, or oil pumping unit loads according to the instructions of the energy management module; it can switch between grid-connected and off-grid modes according to application requirements and control strategies. Furthermore, when the DC voltage of the system varies within 90% to 120% of the rated voltage, the AC output frequency of the system should be maintained within 50Hz ± 2.5Hz (Hertz), i.e., frequency stability of ±5%. In addition, the thermal energy storage equipment includes three operating states: minimum thermal margin, optimal thermal storage operating range, and limited thermal storage, distinguished by heat consumption. This comprehensively considers heat demand, and the control of any set of thermal energy storage equipment needs to maintain its capacity within the normal range, ensuring timely absorption of wind power while maintaining a certain level of heating. When any set of thermal energy storage equipment is at its minimum margin, electrical energy is preferentially supplied to the thermal energy storage equipment. In the optimal operating range, wind and solar power can be connected to the grid or supply power to oil field loads. For the grid, at least one set of thermal energy storage equipment can participate in dispatch as a load to accommodate wind power, improving the reliability of electricity use.

[0099] The control system also has undervoltage protection, overvoltage protection, overcurrent protection, and fan overspeed protection functions, which can be manually set.

[0100] like Figure 3 As shown in the embodiments of the present invention, a scheduling method for the aforementioned electric furnace is also introduced. The scheduling method includes: first, establishing a real-time optimization scheduling model for a wind, solar, and thermal system containing solid thermal energy storage with the objective of minimizing wind and solar curtailment; then, establishing a Markov reward process for the real-time optimization scheduling model of the wind, solar, and thermal system containing solid thermal energy storage under a reinforcement learning framework; and finally, training the scheduling model of the wind, solar, and thermal system containing solid thermal energy storage using a proximal policy optimization algorithm based on the Markov reward process to obtain the scheduling model of the wind, solar, and thermal system containing solid thermal energy storage.

[0101] Specifically, establishing a real-time optimal scheduling model for wind, solar, and thermal systems with solid thermal energy storage, aiming to minimize wind and solar curtailment, includes determining the objective function and constraints of the real-time optimal scheduling model for wind, solar, and thermal systems with solid thermal energy storage.

[0102] The objective function satisfies:

[0103] minP wt,real +P pv,real -P wt,grid -P pv,grid -P wt,heat -P pv,heat +P bt,heat (1)

[0104] In the formula, P wt,real and P pv,realThese represent the power output of wind power and solar power at each moment, P. wt,grid and P pv,grid These represent the actual power supplied to the electrical load by wind power and solar power at each moment; P wt,heat and P pv,heat These represent the actual power supplied by wind power and solar power to the heat load at each moment; P bt,heat It is the output power of solid thermal energy storage, P bt,heat A value greater than zero indicates that solid-state thermal energy storage releases heat, P bt,heat A value less than zero indicates solid thermal energy storage.

[0105] The constraints include the power balance constraints of the wind, solar, and thermal systems containing solid thermal energy storage, the thermal power balance constraints of the wind, solar, and thermal systems containing solid thermal energy storage, wind and solar power output constraints, electrothermal coupling constraints, solid thermal energy storage heat storage and release constraints, and SOC constraints. Among these, the power balance constraints of the wind, solar, and thermal systems containing solid thermal energy storage satisfy:

[0106] P wt,grid +P pv,grid =P load (2)

[0107] In the formula, P load It is the power load of the wind and solar power storage station;

[0108] The thermal power balance constraints of wind, solar, and thermal systems containing solid thermal energy storage include,

[0109] Q wt,heat +Q pv,heat +Q bt,heat =Q load (3)

[0110] In the formula, Q wt,heat and Q pv,heat These are the heat generated by wind power and solar power, respectively, Q. bt,heat Q is the amount of heat stored or released in solid thermal energy storage. load It is the heat load demand.

[0111] Wind and solar power output constraints include,

[0112]

[0113] In the formula, P wt,real and P pv,real These represent the power output of wind power and solar power at each moment, P. wt,grid and P pv,grid These represent the actual power supplied to the electrical load by wind power and solar power at each moment; P wt,heat and P pv,heat These represent the actual power supplied by wind power and solar power to the heat load at each moment;

[0114] The electrothermal coupling constraint satisfies:

[0115] Q wt,heat =η eh P wt,heat (5)

[0116] Q pv,heat =η eh P pv,heat (6)

[0117] Q bt,heat =η eh P bt,heat (7)

[0118] In the formula, η eh It is the electrothermal conversion efficiency;

[0119] Solid thermal energy storage charge and discharge constraints are satisfied:

[0120] -P bt,heat,max ≤P bt,heat ≤P bt,heat,max (8)

[0121] In the formula, P bt,heat,max P bt,heat These represent the maximum heat storage and heat release power of the solid thermal energy storage device.

[0122] Solid-state thermal energy storage SOC constraints are satisfied:

[0123] SOC bt,heat =(1-ρ)SOC bt,heat,last -ΔSOC bt,heat (9)

[0124]

[0125] SOC bt,heat,min ≤SOC bt,heat ≤SOC bt,heat,max (11)

[0126] In the formula, SOC bt,heat,max and SOC bt,heat,min ΔSOC represents the upper and lower limits of the state of charge (SOC) for solid-state thermal energy storage, respectively, where ρ is the self-sustaining discharge rate of the energy storage battery; bt,heat E represents the change in charge of a solid thermal energy storage device, which depends on the thermal storage state and the thermal power released / stored by the device. bt,heat,max η is the maximum capacity of the solid thermal energy storage device. c The charging efficiency of solid thermal energy storage devices; η d The discharge efficiency of solid thermal energy storage devices.

[0127] The Markov reward process includes a quaternion {S, A, γ, R}; S, A, γ, and R represent the state space, action space, discount factor, and reward function, respectively.

[0128] The state space S is shown below:

[0129] S={S wt,real ,S pv.real ,S soc,heat,last ,S pload ,S qload}(12)

[0130] In the formula, S wt,real and S pv,real S represents the real-time power output sets of wind power and solar power, respectively. soc,heat,last It is the SOC of solid thermal energy storage at the previous moment, S pload S is the real-time output aggregation of electrical loads in wind, solar, and thermal systems containing solid thermal energy storage. qload It is a collection of real-time heat load outputs for wind, solar, and thermal systems containing solid thermal energy storage.

[0131] Action space A is shown below:

[0132] A={A wt,grid A pv,grid A wt,heat A pv,heat A bt,heat}(13)

[0133] In the formula, A wt,grid A pv,grid A wt,heat and A pv,heat A represents the electrical output and thermal conversion output of wind power and solar power respectively. bt,heat It is the real-time output of thermal energy storage;

[0134] The reward function R is shown below:

[0135]

[0136] In the formula, γ is the discount factor, and r t For instant rewards,

[0137] Instant rewards t satisfy:

[0138] r t =-(P wt,real +P pv,real -P wt,grid -P pv,grid -P wt,heat -P pv,heat +P bt (15)

[0139] Based on the Markov reward process, a near-end policy optimization algorithm is used to train the scheduling model of the wind, solar, and thermal system containing solid thermal energy storage.

[0140] Step S1: Randomly initialize the current policy network parameters θ Q and value network parameters θ π We determine the training period K = 1,000,000, the scheduling period T = 24, and the target network update frequency C = 100, and set the number of training iterations k = 0.

[0141] Step S2: Initialize the initial state s of the wind, solar and thermal system from the state space. t And let t = 0;

[0142] Step S3: Based on state s in the current value network t Output action a t ;

[0143] Step S4: Execute action a in the energy management system of the wind, solar, and thermal system. t And obtain the next state s t+1 Reward r t Let t = t + 1, then proceed to step S3 until the time series sample {A} is learned. T S T R T S T+1};

[0144] Step S5: Transfer the learned time series samples {A} T S T R T S T+1 The data is stored in the sample experience pool as a dataset for training the network.

[0145] Step S6: Randomly collect m time series samples {A} from the experience pool. T ,S T ,R T ,S T+1}, and calculate the loss function L(θ) of the value network. Q );

[0146] L(θ Q )=E(y t -Q(s t ,a t |θ Q )) 2 (16)

[0147] In the formula, Q(s) t ,a t |θQ ) represents the Q-value output by the current network at time t; E represents the mean function; y t Let y be the target Q value. t As shown below:

[0148] y t =r t +γQ′(s t+1 ,π′(s t+1 |θ π′ )|θ Q′ (17)

[0149] In the formula, r t The instantaneous reward at time t, extracted from the experience pool; π′(s t+1 |θ π′ ) is the target policy network in parameter θ π Input state variable s t+1 The action variable output at that time; Q′(s) t+1 ,π′(s t+1 |θ π′ )|θ Q′ ) is the target network in parameter θ Q′ Next input state s t+1 and action variable π′(s) t+1 |θ π′ Input Q value under ) ;

[0150] Step S7: Update the gradient of the value network according to the following formula:

[0151]

[0152] In the formula, θ Q μ represents the current value network parameters. Q The learning rate of the current value network. The loss function L(θ) Q For parameter θ Q gradient; π θ (a t |s t ) and π θold (a t |s t (A) represents two different policies in the policy network: the old policy and the new policy. t ε is the advantage function; ε is the boundary value of the loss function, with a value of 0.1; E t It is a mean function;

[0153] Step S8: Update the parameters θ of the policy network. π ',Right now:

[0154]

[0155] In the formula, θ π μ represents the current policy network parameters. π is the learning rate of the policy network, with a value of 0.00001; Let Q be the Q-value Q(s,a|θ). Q The gradient of action a; For policy gradient;

[0156] Step S9: Determine if k%C=1 holds true. If so, update the policy network parameter θ based on formula (19). Q′ and value network parameters θ π′ If the condition is met, proceed to step S10; otherwise, proceed directly to step S10.

[0157]

[0158] In the formula, θ Q′ and θ π′ are the parameters of the target value network and the target policy network, respectively, and τ is the soft update coefficient with a value of 0.001;

[0159] Step S10: Determine whether the training count k>K is true. If yes, output the scheduling model of the wind, solar and thermal system containing solid thermal energy storage. Otherwise, let k = k+1 and return to step S2.

[0160] For example, to verify the adaptability and superiority of the scheduling method proposed in this paper, the following comparative examples are set up:

[0161] Case 1: The particle swarm optimization algorithm is used to solve the scheduling model of the wind, solar, and thermal system containing solid thermal energy storage.

[0162] Case 2: The scheduling method proposed in this paper is used to train a real-time scheduling network for a wind, solar and thermal system containing solid thermal energy storage.

[0163] Based on the proposed real-time dispatch network for wind, solar, and thermal systems incorporating solid thermal energy storage, the dispatch scheme for the electric and thermal systems can be obtained as follows: Figure 4 and Figure 5 As shown in Table 1 below, the results for two different cases demonstrate that the proposed scheduling method achieves less wind and solar power abandonment and shorter computation time compared to the particle swarm optimization algorithm.

[0164] Table 1 Performance indicators under different schemes

[0165]

[0166] As can be seen from Table 1 above, the scheduling method proposed in this paper has excellent performance and speed. Its overall wind and solar curtailment is reduced by 43.55% compared with the particle swarm optimization algorithm. It only takes 0.98s to generate a scheduling plan, which is 96.95% lower than the conventional particle swarm optimization algorithm. Furthermore, the network has good applicability and can adapt to different wind, solar and thermal loads and energy storage inputs.

[0167] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-column vertical axis wind-powered thermal energy storage electric furnace, characterized in that, This includes a wind-solar hybrid power generation system and a solid-state thermal energy storage system connected to it, wherein, The wind-solar hybrid power generation system includes wind turbine blades, a vertical shaft, a multi-column tower, and photovoltaic modules. The wind turbine blades are connected to the vertical shaft, the multi-column tower is fitted around the outer periphery of the vertical shaft, and the photovoltaic modules are installed on the top of the wind turbine blades and around the multi-column tower. The solid-state electric thermal energy storage system includes at least one set of thermal energy storage equipment, and each set of thermal energy storage equipment is installed at the bottom of a multi-column tower.

2. The multi-column vertical axis wind-powered thermal energy storage electric furnace according to claim 1, characterized in that, A wind-solar hybrid power generation system also includes a generator, converter, inverter, and wind-solar-thermal-power control cabinet, among which, The generator is connected to the wind turbine blades and the converter respectively, and the photovoltaic module is connected to the inverter; The converter and inverter are also connected to each group of thermal energy storage devices. The wind, solar, thermal, and power control cabinets are connected to the generator, photovoltaic modules, and each set of thermal energy storage equipment, respectively.

3. The multi-column vertical axis wind-powered thermal energy storage electric furnace according to claim 1, characterized in that, Each set of thermal energy storage equipment includes electric heating elements, high-temperature heat storage medium, heat exchanger, high-temperature circulating fan, and insulation box. The electric heating elements are connected to the converter, inverter, and heat exchanger, respectively. The heat exchangers are connected to the high-temperature circulating fan and the high-temperature heat storage body, respectively. The insulation box is installed on the outermost layer of each set of thermal energy storage equipment.

4. A multi-column vertical axis wind power thermal energy storage control system, characterized in that, Includes a central control unit, a wind power controller, an energy management module, and an electric furnace as described in any one of claims 1-3, wherein, The central control unit is used to issue control commands to the energy management module, wind power controller, converter and each group of thermal energy storage devices, and to receive feedback information; The energy management module is used to control the converter to output electrical energy to the power grid and / or at least one set of thermal energy storage devices according to control commands, and to control at least one set of thermal energy storage devices to release the stored thermal energy or continue to store thermal energy.

5. A scheduling method for a multi-column vertical axis wind-powered thermal energy storage electric furnace as described in any one of claims 1-3, characterized in that, include, Establish a real-time optimization scheduling model for wind, solar, and thermal systems containing solid thermal energy storage, with the goal of minimizing wind and solar curtailment; Establish a real-time optimization scheduling model for wind, solar, and thermal systems with solid thermal energy storage based on a Markov reward process within a reinforcement learning framework; The scheduling model of the wind, solar and thermal system containing solid thermal energy storage is trained using a near-end strategy optimization algorithm to obtain the scheduling model of the wind, solar and thermal system containing solid thermal energy storage.

6. The scheduling method according to claim 5, characterized in that, Establishing a real-time optimal scheduling model for wind, solar, and thermal systems with solid thermal energy storage, aiming to minimize wind and solar curtailment, includes determining the objective function and constraints of the real-time optimal scheduling model for wind, solar, and thermal systems with solid thermal energy storage. The objective function satisfies: minP wt,real +P pv,real -P wt,grid -P pv,grid -P wt,heat -P pv,heat +P bt,heat (1) In the formula, P wt,real and P pv,real These represent the power output of wind power and solar power at each moment, P. wt,grid and P pv,grid These represent the actual power supplied to the electrical load by wind power and solar power at each moment; P wt,heat and P pv,heat These represent the actual power supplied by wind power and solar power to the heat load at each moment; P bt,heat These are the output power of solid thermal energy storage, P bt,heat A value greater than zero indicates that solid-state thermal energy storage releases heat, P bt,heat A value less than zero indicates solid thermal energy storage. The constraints include the electrical power balance constraint of the wind, solar and thermal system containing solid thermal energy storage, the thermal power balance constraint of the wind, solar output constraint, electrothermal coupling constraint, solid thermal energy storage heat storage and release constraint, and SOC constraint.

7. The scheduling method according to claim 6, characterized in that, The power balance constraints of wind, solar, and thermal systems containing solid thermal energy storage satisfy: P wt,grid +P pv,grid =P load (2) In the formula, P load It is the power load of the wind and solar power storage station; The thermal power balance constraints of wind, solar, and thermal systems containing solid thermal energy storage include, Q wt,heat +Q pv,heat +Q bt,heat =Q load (3) In the formula, Q wt,heat and Q pv,heat These are the heat generated by wind power and solar power, respectively, Q. bt,heat Q is the amount of heat stored or released in solid thermal energy storage. load It is the demand for heat load; Wind and solar power output constraints include, In the formula, P wt,real and P pv,real These represent the power output of wind power and solar power at each moment, P. wt,grid and P pv,grid These represent the actual power supplied to the electrical load by wind power and solar power at each moment; P wt,heat and P pv,heat These represent the actual power supplied by wind power and solar power to the heat load at each moment; The electrothermal coupling constraint satisfies: Q wt,heat =η eh P wt,heat (5) Q pv,heat =η eh P pv,heat (6) Q bt,heat =η eh P bt,heat (7) In the formula, η eh It is the electrothermal conversion efficiency; Solid-state thermal energy storage charge and discharge constraints are satisfied: -P bt,heat,max ≤P bt,heat ≤P bt,heat,max (8) In the formula, P bt,heat,max P bt,heat These represent the maximum heat storage and heat release power of the solid thermal energy storage device. Solid-state thermal energy storage SOC constraints are satisfied: SOCIETY bt,heat =(1-ρ)SOC bt,heat,last -ΔSOC bt,heat (9) SOC bt,heat,min ≤SOC bt,heat ≤SOC bt,heat,max (11) In the formula, SOC bt,heat,max and SOC bt,heat,min ΔSOC represents the upper and lower limits of the state of charge (SOC) for solid-state thermal energy storage, respectively, where ρ is the self-sustaining discharge rate of the energy storage battery; bt,heat E represents the change in charge of a solid thermal energy storage device, which depends on the thermal storage state and the thermal power released / stored by the device. bt,heat,max This is the maximum capacity of the solid thermal energy storage device. η c The charging efficiency of solid thermal energy storage devices; η d The discharge efficiency of solid thermal energy storage devices.

8. The scheduling method according to claim 6, characterized in that, The Markov reward process includes a quadruple array {S,A,γ,R}; S, A, γ, and R represent the state space, action space, discount factor, and reward function, respectively. The state space S is shown below: S={S wt,real ,S pv.real ,S soc,heat,last ,S pload ,S qload }(12) In the formula, S wt,real and S pv,real S represents the real-time power output sets of wind power and solar power, respectively. soc,heat,last It is the SOC of solid thermal energy storage at the previous moment, S pload S is the real-time output aggregation of electrical loads in wind, solar, and thermal systems containing solid thermal energy storage. qload It is a collection of real-time heat load outputs for wind, solar, and thermal systems containing solid thermal energy storage. Action space A is shown below: A={A wt,grid ,A pv,grid ,A wt,heat ,A pv,heat A bt,heat }(13) In the formula, A wt,grid A pv,grid , A wt,heat and A pv,heat A represents the electrical output and thermal conversion output of wind power and solar power respectively. bt,heat It is the real-time output of thermal energy storage; The reward function R is shown below: In the formula, γ is the discount factor, and r t For instant rewards, instant reward r t satisfy: r t =-(P wt,real +P pv,real -P wt,grid -P pv,grid -P wt,heat -P pv,heat +P bt )(15)。 9. The scheduling method according to claim 8, characterized in that, The training of the scheduling model for the wind, solar, and thermal system containing solid thermal energy storage using a near-end strategy optimization algorithm includes... Step S1: Randomly initialize the current policy network parameters θ Q and value network parameters θ π We determine the training period K = 1,000,000, the scheduling period T = 24, and the target network update frequency C = 100, and set the number of training iterations k = 0. Step S2: Initialize the initial state s of the wind, solar and thermal system from the state space. t And let t = 0; Step S3: Based on state s in the current value network t Output action a t ; Step S4: Execute action a in the energy management system of the wind, solar, and thermal system. t And obtain the next state s t+1 Reward r t Let t = t + 1, then proceed to step S3 until the time series sample {A} is learned. T， S T R T S T+1 }; Step S5: Transfer the learned time series samples {A} T ,S T ,R T ,S T+1 The data is stored in the sample experience pool as a dataset for training the network. Step S6: Randomly collect m time series samples {A} from the experience pool. T ,S T ,R T ,S T+1 }, and calculate the loss function L(θ) of the value network. Q ); L(θ Q )=E(y t -Q(s t ,a t |θ Q )) 2 (16) In the formula, Q(s) t ,a t |θ Q () represents the Q-value output by the current network at time t; E represents the mean function; y t For the target Q value y t As shown below: y t =r t +γQ′(s t+1 ,π′(s t+1 |θ π′ )|θ Q′ ) (17) In the formula, r t The instantaneous reward at time t, extracted from the experience pool; π′(s t+1 |θ π′ ) is the target policy network in parameter θ π′ Input state variable s t+1 The action variable output at that time; Q′(s) t+1 ,π′(s t+1 |θ π′ )|θ Q′ ) is the target network in parameter θ Q′ Next input state s t+1 and action variable π′(s) t+1 |θ π′ Input Q value under ) ; Step S7: Update the gradient of the value network according to the following formula: In the formula, θ Q μ represents the current value network parameters. Q The learning rate of the current value network. The loss function L(θ) Q For parameter θ Q gradient; π θ (a t |s t ) and πθ old (a t |s t A represents two different policies in the policy network: the old policy and the new policy. t ε is the advantage function; ε is the boundary value of the loss function, with a value of 0.1; E t It is a mean function; Step S8: Update the parameters θ of the policy network. π ',Right now: In the formula, θ π μ represents the current policy network parameters. π is the learning rate of the policy network, with a value of 0.00001; Let Q be the Q-value Q(s,a|θ). Q The gradient of action a; For policy gradient; Step S9: Determine if k%C=1 holds true. If so, update the policy network parameter θ based on formula (19). Q′ and value network parameters θ π′ If the condition is met, proceed to step S10; otherwise, proceed directly to step S10. In the formula, θ Q′ and θ π′ are the parameters of the target value network and the target policy network, respectively, and τ is the soft update coefficient; Step S10: Determine whether the training count k>K is true. If yes, output the scheduling model of the wind, solar and thermal system containing solid thermal energy storage. Otherwise, let k = k+1 and return to step S2.

Images