New energy power plant output power intelligent allocation method and system

Abstract

The invention relates to the technical field of new energy, and discloses a new energy power plant output power intelligent allocation method, which comprises the steps of establishing a power output and energy storage capacity model of a new energy power plant; decomposing the whole power allocation problem into a plurality of sub-problems by using a distributed computing technology; solving each sub-problem based on a particle swarm optimization algorithm; updating the particles by each computing node according to a speed updating formula and a position updating formula of a particle swarm optimization algorithm; summarizing local optimization results by each computing node; and according to the global optimal allocation scheme, generating a control instruction for each power generation device and energy storage device of the new energy power plant. Through the particle swarm optimization algorithm, the sum of the output power income and the energy storage capacity income is maximized, the energy utilization efficiency of the new energy power plant is effectively improved, and the distributed computing architecture is adopted, so that the computing efficiency is improved, and the stability and reliability of the system are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of new energy technology, and in particular to a method and system for intelligently allocating output power of a new energy power plant. Background Art

[0002] As the global demand for renewable energy continues to increase, the construction and development of new energy power plants has received more and more attention. Solar energy and wind energy, as two major renewable energy sources, have the advantages of being clean, pollution-free, and renewable. However, their power generation capacity is greatly affected by environmental factors and is intermittent and unstable. In order to improve the reliability and stability of new energy power plants, they are usually equipped with energy storage equipment to store excess energy and release it when needed.

[0003] However, the existing output power allocation methods of renewable energy power plants often have the following problems: lack of intelligence. Traditional power allocation methods are usually based on fixed rules and experience, and cannot be adaptively adjusted according to real-time environmental changes and equipment status, which easily leads to energy waste and unstable supply, reducing the efficiency and reliability of the system; low computing efficiency. For large-scale renewable energy power plants, power allocation problems are usually very complex and require a lot of calculations and optimizations. Traditional centralized computing methods often find it difficult to meet real-time requirements and have low computing efficiency, which affects the response speed and performance of the system. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method and system for intelligently allocating the output power of a new energy power plant, which solves the problem in the prior art that power allocation lacks intelligence, resulting in low reliability and efficiency.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method and system for intelligently adjusting the output power of a new energy power plant, comprising the following steps:

[0006] S1. Establish a power output and energy storage capacity model for a new energy power plant, which includes but is not limited to the power output function of solar power generation equipment:

[0007] P s =η s ×A×I, where η s is the solar cell efficiency, A is the panel area, and I is the light intensity;

[0008] Power output function of wind turbine:

[0009] P w =0.5×ρ×A rotor ×C p ×V 3 , where ρ is the air density, Arotor is the swept area of ​​the wind wheel, C p is the power coefficient, V is the wind speed;

[0010] Energy storage capacity function of energy storage equipment:

[0011] E s (t) = E s (0)+∫0 t (P charge -P discharge )dt, represents the energy storage capacity E at any time t s (t) and initial energy storage capacity E s (0) and the charging power P from the initial time 0 to time t charge and discharge power P discharge the relationship between;

[0012] S2. Use distributed computing technology to decompose the entire power allocation problem into multiple sub-problems, each of which is assigned to a different computing node for processing. Each computing node collects real-time data on new energy power generation equipment and energy storage equipment in the corresponding area;

[0013] S3. Solve each sub-problem based on the particle swarm optimization algorithm. In the particle swarm optimization algorithm, the position of the particle is defined to represent the power output value of the new energy power generation equipment and the charging and discharging power value of the energy storage equipment. The quality of the particle is evaluated according to the fitness function. The fitness function aims to maximize the sum of the output power benefit and the energy storage capacity benefit.

[0014] S4. Each computing node updates the particles according to the speed update formula and position update formula of the particle swarm optimization algorithm. The speed update formula is:

[0015] v ij (t+1)=w×v ij (t)+c1×r1×(pbest ij -x ij (t))+c2×r2×(gbest j -x ij (t)) The position update formula is:

[0016] x ij (t+1)=x ij (t)+v ij (t+1)

[0017] Where i represents the particle number, j represents the dimension, w represents the inertia weight, c1 and c2 represent the learning factors, r1 and c2 represent random numbers, pbest represents the individual optimal position, and gbest represents the global optimal position;

[0018] S5. Each computing node summarizes the local optimization results and transmits them to the central node through the communication network for comprehensive evaluation to obtain the global optimal power output and energy storage capacity allocation plan;

[0019] S6. Based on the global optimal allocation plan, control instructions are generated for each power generation equipment and energy storage equipment of the new energy power plant to achieve intelligent allocation of output power and energy storage capacity to maximize variable benefits.

[0020] Preferably, when establishing the power model, the influence of the efficiency curve of the power generation equipment, environmental factors and equipment aging factors on the power output are fully considered.

[0021] Preferably, in the distributed computing technology, data is exchanged between computing nodes via a high-speed data bus to ensure the real-time and accuracy of the data.

[0022] Preferably, in the particle swarm optimization algorithm, the dimensions of the particles are dynamically adjusted according to the characteristics of different new energy power generation equipment and energy storage equipment.

[0023] Preferably, a system for intelligently adjusting output power of a new energy power plant comprises a distributed data acquisition unit for collecting operating data of each power generation equipment and energy storage equipment in the new energy power plant;

[0024] A distributed computing unit, including multiple computing nodes, is used to solve the power allocation sub-problem based on the particle swarm optimization algorithm;

[0025] The central control unit is used to summarize the optimization results of each computing node and conduct a comprehensive evaluation to obtain the global optimal deployment plan;

[0026] The control instruction generation and execution unit is used to generate control instructions according to the global optimal deployment plan and control each device.

[0027] Preferably, the sensors in the distributed data acquisition unit include but are not limited to solar radiation sensors, wind speed sensors, power sensors and energy storage capacity sensors.

[0028] Preferably, each computing node of the distributed computing unit adopts a high-performance processor to improve computing efficiency.

[0029] Preferably, an efficient communication protocol is adopted between the central control unit and the distributed computing units to ensure the stability and reliability of data transmission.

[0030] Preferably, the control instruction generation and execution unit is connected to the equipment of the new energy power plant via an industrial control network.

[0031] Preferably, the system also includes a data storage unit for storing collected data, intermediate results in the calculation process and global optimal deployment plan information.

[0032] The present invention provides a method and system for intelligently adjusting the output power of a new energy power plant. It has the following beneficial effects:

[0033] 1. The present invention can accurately adjust the power of solar energy, wind power generation equipment and energy storage equipment according to real-time environmental conditions and equipment status. Through the particle swarm optimization algorithm, the sum of output power benefit and energy storage capacity benefit is maximized, effectively improving the energy utilization efficiency of new energy power plants.

[0034] 2. The present invention adopts a distributed computing architecture to decompose the power allocation problem into multiple sub-problems and assign them to different computing nodes for processing. The distributed architecture not only improves the computing efficiency, but also enhances the stability and reliability of the system. Even if a computing node fails, other nodes can still continue to work, ensuring the normal operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a flow chart of the method of the present invention;

[0036] Figure 2 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] Example:

[0039] Please see attached Figure 1-2 The embodiment of the present invention provides a method and system for intelligently adjusting the output power of a new energy power plant. The test is carried out in a new energy power plant including solar power generation, wind power generation and energy storage equipment. In the solar power generation area, solar panels with an area of ​​A = 1000 m2 are installed. The efficiency of the solar cell is η s =0.2, in the wind power generation area, the wind rotor swept area A is set rotor =500㎡ wind turbine, air density ρ = 1.2kg / m 3 , power coefficient C p According to the standard characteristic curve of the wind turbine at different wind speeds, the initial energy storage capacity E of the lithium battery pack used in the energy storage device iss (0) = 1000 kWh. The following steps are included:

[0040] S1. Establish a power output and energy storage capacity model for a new energy power plant, which includes but is not limited to the power output function of solar power generation equipment:

[0041] P s =η s ×A×I, where η s is the solar cell efficiency, A is the panel area, and I is the light intensity. For solar power generation equipment, the light intensity I is collected in real time by a high-precision solar radiation sensor. At a certain moment, the collected light intensity I = 800W / m 2 , according to the power output function P s =η s ×A×I, the solar power generation power P is calculated s =0.2×1000×800=160000W;

[0042] Power output function of wind turbine:

[0043] P w =0.5×ρ×A rotor ×C p ×V 3 , where ρ is the air density, A rotor is the swept area of ​​the wind wheel, C p is the power coefficient, V is the wind speed. For wind power generation equipment, the wind speed V is monitored in real time by the wind speed sensor. At another moment, the wind speed V=10m / s. Assume that C p =0.4, according to the power output function P w =0.5×ρ×A rotor ×C p ×V 3 , calculate the wind power generation power P w =0.5×1.2×500×0.4×10 3 =120000W;

[0044] The charging and discharging power of the energy storage device is collected by the corresponding power sensor and the energy storage capacity function E s (t) = E s (0)+∫0 t (P charge -P discharge )dt calculate the change of energy storage capacity;

[0045] S2. The power allocation problem is decomposed into three sub-problems: the solar power generation power optimization sub-problem, the wind power generation power optimization sub-problem and the energy storage device charging and discharging power optimization sub-problem. The three computing nodes of the distributed computing unit collect data from the corresponding areas respectively. For example, the computing node for processing the solar power generation problem collects solar radiation sensor data, solar panel area and efficiency data;

[0046] S3. Solve each sub-problem based on the particle swarm optimization algorithm. In the particle swarm optimization algorithm, the position of the particle is defined to represent the power output value of the new energy power generation equipment and the charging and discharging power value of the energy storage equipment. The quality of the particle is evaluated according to the fitness function. The fitness function aims to maximize the sum of the output power benefit and the energy storage capacity benefit.

[0047] S4. Each computing node updates the particles according to the speed update formula and position update formula of the particle swarm optimization algorithm. The speed update formula is:

[0048] v ij (t+1)=w×v ij (t)+c1×r1×(pbest ij -x ij (t))+c2×r2×(gbest j -x ij (t)) The position update formula is:

[0049] x ij (t+1)=x ij (t)+v ij (t+1)

[0050] Where i is the particle number, j is the dimension, w is the inertia weight, c1 and c2 are learning factors, r1 and c2 are random numbers, pbest is the individual optimal position, gbest is the global optimal position; v ij (t) is the velocity of particle i in dimension j in the tth iteration, which represents the inertia of the particle. Inertia makes the particle maintain a certain "impulse" in the original direction of motion. If w is large, the particle will be more inclined to maintain the original speed direction and continue to explore. If w is small, the particle is more likely to be affected by other factors and change the speed direction; c1×r1×(pbest ij -x ij (t)) reflects the cognitive ability of the particle, c1 determines the degree to which the particle learns from its own experience, r1 is a random number between [0,1], which is used to increase the randomness of the algorithm, and pbest ij is the individual optimal position of particle i in dimension j, x ij(t) is the current position of the particle in dimension j in the i-th iteration. This part makes the particle tend to fly to the best position it has ever found, guiding the particle to search in the local range; c2×r2×(gbest j -x ij (t)) is the social information sharing ability of the particle, c2 determines the degree to which the particle learns the optimal experience of the group, gbest j is the global optimal position of the entire particle swarm in dimension j. This term makes the particles tend to fly to the optimal position found by the entire group, allowing the particles to explore better areas globally.

[0051] In the computing node that processes the solar power generation optimization subproblem, the position of the particle is defined to represent the power output value of the solar power generation equipment and the charging and discharging power of the energy storage equipment related to solar energy. The particle dimension j is set to 2, and the particle number i ranges from 1 to 50. The position and velocity of the particle are initialized, the inertia weight w = 0.7, and the learning factor c1 = c2 = 1.4. In each iteration, the particle is updated according to the velocity update formula and the position update formula.

[0052] For the sub-problems of wind power generation and energy storage equipment, the particle swarm algorithm is also applied according to the equipment characteristics, and the particle dimension is dynamically adjusted according to the equipment characteristics. For example, in the sub-problem of wind power generation, as the wind speed variation range increases, the particle dimension is appropriately increased to search for the optimal solution more accurately.

[0053] S5. Each computing node transmits the local optimization result to the central control unit through the optical fiber bus. The central control unit receives the optimization results of the solar power generation sub-problem, the wind power generation sub-problem and the energy storage equipment sub-problem. The central control unit comprehensively considers factors such as grid load demand and equipment stability, and evaluates and obtains the global optimal power output and energy storage capacity allocation plan.

[0054] S6. Based on the global optimal allocation plan, control instructions are generated for each power generation equipment and energy storage equipment of the new energy power plant to achieve intelligent allocation of output power and energy storage capacity to maximize variable benefits. After executing these control instructions, it is observed that the output power and energy storage capacity of the new energy power plant can be intelligently adjusted according to actual conditions to maximize variable benefits.

[0055] During the entire implementation process, the solar radiation sensors, wind speed sensors, power sensors and energy storage capacity sensors in the distributed data acquisition unit collect data in real time and accurately. The high-performance processor of the distributed computing unit uses the Intel Core i9 processor to perform calculations efficiently. The central control unit and the distributed computing unit carry out stable and reliable data transmission through an efficient communication protocol based on TCP / IP. The control instruction generation and execution unit is connected to the new energy power plant equipment through industrial Ethernet. The data storage unit completely stores all relevant data for subsequent analysis and system optimization.

[0056] The above embodiments verify that the method and system for intelligently adjusting the output power of a new energy power plant of the present invention can effectively achieve the optimal configuration of power output and energy storage capacity, and improve the operating efficiency and economic benefits of the new energy power plant.

[0057] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligently adjusting the output power of a new energy power plant, characterized in that: The following steps are involved: S1. Establish a power output and energy storage capacity model for a new energy power plant, which includes but is not limited to the power output function of solar power generation equipment: P s =η s ×A×I, where η s is the solar cell efficiency, A is the panel area, and I is the light intensity; Power output function of wind turbine: P w =0.5×ρ×A rotor ×C p ×V 3 , where ρ is the air density, A rotor is the swept area of ​​the wind wheel, C p is the power coefficient, V is the wind speed; Energy storage capacity function of energy storage equipment: E s (t) = E s (0)+∫0 t (P charge -P discharge )dt, represents the energy storage capacity E at any time t s (t) and initial energy storage capacity E s (0) and the charging power P from the initial time 0 to time t charge and discharge power P discharge the relationship between; S2. Use distributed computing technology to decompose the entire power allocation problem into multiple sub-problems, each of which is assigned to a different computing node for processing. Each computing node collects real-time data on new energy power generation equipment and energy storage equipment in the corresponding area; S3. Solve each sub-problem based on the particle swarm optimization algorithm. In the particle swarm optimization algorithm, the position of the particle is defined to represent the power output value of the new energy power generation equipment and the charging and discharging power value of the energy storage equipment. The quality of the particle is evaluated according to the fitness function. The fitness function aims to maximize the sum of the output power benefit and the energy storage capacity benefit. S4. Each computing node updates the particles according to the speed update formula and position update formula of the particle swarm optimization algorithm. The speed update formula is: v ij (t+1)=w×v ij (t)+c1×r1×(pbest ij -x ij (t))+c2×r2×(gbest j -x ij (t)) The position update formula is: x ij (t+1)=x ij (t)+v ij (t+1) Where i represents the particle number, j represents the dimension, w represents the inertia weight, c1 and c2 represent the learning factors, r1 and c2 represent random numbers, pbest represents the individual optimal position, and gbest represents the global optimal position; S5. Each computing node summarizes the local optimization results and transmits them to the central node through the communication network for comprehensive evaluation to obtain the global optimal power output and energy storage capacity allocation plan; S6. Based on the global optimal allocation plan, control instructions are generated for each power generation equipment and energy storage equipment of the new energy power plant to achieve intelligent allocation of output power and energy storage capacity to maximize variable benefits.

2. According to claim 1, a method for intelligently adjusting the output power of a new energy power plant is characterized in that: When establishing the power model, the efficiency curve of the power generation equipment, environmental factors and the impact of equipment aging factors on power output are fully considered.

3. The method for intelligently adjusting the output power of a new energy power plant according to claim 1 is characterized in that: In distributed computing technology, data is exchanged between computing nodes through a high-speed data bus to ensure the real-time and accuracy of the data.

4. The method for intelligently adjusting the output power of a new energy power plant according to claim 1 is characterized in that: In the particle swarm optimization algorithm, the dimensions of particles are dynamically adjusted according to the characteristics of different renewable energy power generation equipment and energy storage equipment.

5. A system for intelligently adjusting output power of a new energy power plant, using a method for intelligently adjusting output power of a new energy power plant as claimed in any one of claims 1 to 4, characterized in that: include Distributed data acquisition unit, used to collect operating data of various power generation equipment and energy storage equipment in the new energy power plant; A distributed computing unit, including multiple computing nodes, is used to solve the power allocation sub-problem based on the particle swarm optimization algorithm; The central control unit is used to summarize the optimization results of each computing node and conduct a comprehensive evaluation to obtain the global optimal deployment plan; The control instruction generation and execution unit is used to generate control instructions according to the global optimal deployment plan and control each device.

6. A method and system for intelligently adjusting output power of a new energy power plant according to claim 5, characterized in that: The sensors in the distributed data acquisition unit include but are not limited to solar radiation sensors, wind speed sensors, power sensors and energy storage capacity sensors.

7. The intelligent power output allocation system of a new energy power plant according to claim 5 is characterized in that: Each computing node of the distributed computing unit adopts a high-performance processor to improve computing efficiency.

8. The intelligent power output allocation system of a new energy power plant according to claim 5 is characterized in that: An efficient communication protocol is adopted between the central control unit and the distributed computing units to ensure the stability and reliability of data transmission.

9. The intelligent power output allocation system of a new energy power plant according to claim 5 is characterized in that: The control instruction generation and execution unit is connected to the equipment of the new energy power plant through an industrial control network.

10. The intelligent power output allocation system of a new energy power plant according to claim 5, characterized in that: The system also includes a data storage unit for storing collected data, intermediate results in the calculation process and global optimal allocation plan information.

Images