CN108429475B - Grid-connected inverter control method for wave power generation system - Google Patents
Grid-connected inverter control method for wave power generation system Download PDFInfo
- Publication number
- CN108429475B CN108429475B CN201810144406.5A CN201810144406A CN108429475B CN 108429475 B CN108429475 B CN 108429475B CN 201810144406 A CN201810144406 A CN 201810144406A CN 108429475 B CN108429475 B CN 108429475B
- Authority
- CN
- China
- Prior art keywords
- time
- inverter
- sliding mode
- grid
- moment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02M—APPARATUS FOR CONVERSION BETWEEN AC AND AC, BETWEEN AC AND DC, OR BETWEEN DC AND DC, AND FOR USE WITH MAINS OR SIMILAR POWER SUPPLY SYSTEMS; CONVERSION OF DC OR AC INPUT POWER INTO SURGE OUTPUT POWER; CONTROL OR REGULATION THEREOF
- H02M7/00—Conversion of ac power input into dc power output; Conversion of dc power input into ac power output
- H02M7/42—Conversion of dc power input into ac power output without possibility of reversal
- H02M7/44—Conversion of dc power input into ac power output without possibility of reversal by static converters
- H02M7/48—Conversion of dc power input into ac power output without possibility of reversal by static converters using discharge tubes with control electrode or semiconductor devices with control electrode
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02M—APPARATUS FOR CONVERSION BETWEEN AC AND AC, BETWEEN AC AND DC, OR BETWEEN DC AND DC, AND FOR USE WITH MAINS OR SIMILAR POWER SUPPLY SYSTEMS; CONVERSION OF DC OR AC INPUT POWER INTO SURGE OUTPUT POWER; CONTROL OR REGULATION THEREOF
- H02M1/00—Details of apparatus for conversion
- H02M1/0003—Details of control, feedback or regulation circuits
- H02M1/0025—Arrangements for modifying reference values, feedback values or error values in the control loop of a converter
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Inverter Devices (AREA)
Abstract
The invention discloses a grid-connected inverter control method for a wave power generation system. In order to realize rapid non-difference tracking, the invention adopts a global rapid terminal sliding mode control strategy based on a reinforcement learning algorithm, and compensates the rapid terminal sliding mode control strategy in real time through interaction of the reinforcement learning algorithm and the environment, so that the inverter has self-learning capability to external interference, and the robustness and the stability of the system are enhanced.
Description
Technical Field
The invention relates to the technical field of inverter control of a wave power generation system, in particular to a reinforcement learning algorithm and a terminal sliding mode control algorithm.
Background
Wave energy is an important component of ocean energy, and the reserve of the wave energy is very large, so that the wave energy has a wide development and utilization prospect. China is a big ocean country, available wave energy resources are extremely rich, and the development and utilization of the wave energy resources are one of the important contents for the development and utilization of ocean renewable energy resources in China. The wave energy development mainly adopts wave power generation, the wave power generation device is built on the sea, and electric energy is transmitted to the shore through a seabed composite cable. Because the wavelength, the wave height and the wave period are all changed, the wave energy is unstable and discontinuous, and the synchronization of the output voltage of the inverter, the amplitude of the voltage of the power grid and the phase is especially important by controlling. Most of traditional wave power generation grid-connected inverters adopt PI control algorithms, the PI control algorithms are simple to implement, but PI parameters need to be adjusted off line, the PI control algorithms are poor in robustness, and the application effect in small-scale wave power generation single-phase grid-connected inverters is poor.
The sliding mode variable structure control method is a nonlinear control method, the sliding mode of the sliding mode variable structure control method can be designed and is irrelevant to object parameters and disturbance, and therefore the sliding mode variable structure control method has the advantages of being fast in response, insensitive to corresponding parameter change and disturbance, free of system online identification, simple in physical implementation and the like. The conventional sliding mode surface is a linear function, and after the conventional sliding mode surface is reached, the system error cannot be converged in a limited time. According to the terminal sliding mode control strategy, a nonlinear function is introduced into a sliding mode surface, so that the sliding mode controller has overall rapidity. However, after the sliding mode surface is reached, the magnitude of the switch gain epsilon is fixed and unchanged, and the phenomenon of 'buffeting' cannot be avoided.
Disclosure of Invention
The technical problem is as follows: the invention provides a grid-connected inverter control method for a wave power generation system, wherein a global terminal sliding mode controller is used for controlling the duty ratio of a switching tube of an inverter, and a reinforcement learning algorithm is adopted to dynamically adjust the switching gain epsilon of the sliding mode controller on line, so that the phenomenon of buffeting is greatly weakened, and the robustness and the stability of the system are enhanced.
The technical scheme is as follows: the invention discloses a grid-connected inverter control method for a wave power generation system, which comprises the following steps:
step 1: initializing an evaluation network learning rate and a discount factor of a reinforcement learning algorithm, and designing a reinforcement learning signal according to a system error;
step 2: calculating an evaluation network error, and carrying out online adjustment on the weight of the evaluation network through the calculated evaluation network error;
and step 3: solving an optimal performance index function to obtain a global fast terminal sliding mode self-adaptive control rate based on a reinforcement learning principle;
and 4, step 4: and generating a global fast terminal sliding mode control algorithm control signal based on a reinforcement learning principle according to the self-adaptive control rate, and controlling the conduction time of the inverter switching tube.
Further, in the method of the present invention, in the step 1, the reinforcement learning signal r (t) is designed according to the following formula:
wherein, Uac(t) inverter AC output voltage at time t;is the grid voltage at time t; u (t) is the duty ratio of the switching tube at the time t, and is the system control quantity; r (t) is a reinforcement learning signal at time t.
Further, in the method of the present invention, in the step 2, the network error is calculated and evaluated according to the following formula:
ec(t)=γJ(t)-[J(t-1)-r(t)]
wherein e isc(t) the evaluation network error at time t; j (t) evaluating the network output at time t; j (t-1) is the evaluation network output at the time of t-1; gamma is a discount factor; r (t) is a reinforcement learning signal.
Further, in the method of the present invention, in the step 2, the weight of the evaluation network is adjusted online according to the following rules:
wherein, Wc(t) evaluating a network weight matrix at the moment t; wc(t +1) evaluating a network weight matrix at the moment of t + 1; Δ Wc(t) evaluating the variable quantity of the network weight matrix at the moment t; lcTo evaluate the network learning rate; ecAnd (t) is the square of the evaluation network error.
Further, in the method of the present invention, in the step 3, a global fast terminal sliding mode adaptive control rate based on a reinforcement learning principle is obtained according to the following formula:
wherein laIs an adaptive learning rate; u shapeac(t) inverter AC output voltage at time t; e.g. of the typec(t) evaluating network errors; ec(t) is the square of an evaluation network error, and delta epsilon (t) is the global fast terminal sliding mode self-adaptive control rate at the moment t; epsilon (t) is the sliding mode switch gain at time t.
Further, in the method of the present invention, in the step 4, the control signal is generated according to the following formula:
wherein, UdcIs the DC side voltage of the inverter; l is an inverter alternating current inductor; c is an inverter alternating current capacitor; r is an inverter alternating current resistor; u (t +1) is the duty ratio of the switching tube at the moment of t + 1;the difference value between the output voltage of the inverter at the moment t and the actual power grid voltage is obtained; e (t +1) is the difference value between the inverter output voltage at the moment of t +1 and the actual power grid voltage;is the grid voltage at time t;the grid voltage is at the moment t + 1;the grid voltage is the t-1 moment; u shapeac(t) inverter AC output voltage at time t; u shapeac(t-1) the inverter alternating current output voltage at the time of t-1; u shapeac(t +1) is the inverter alternating current output voltage at the moment of t + 1; s is a terminal sliding mode surface; t issThe method comprises the steps of sampling time, α, β, q, p and k are sliding mode adjusting parameters, α, β and k are positive numbers, q and p are positive integers, epsilon (t) is sliding mode switch gain at the moment t, and delta epsilon (t) is global fast terminal sliding mode self-adaptive control rate at the moment t.
Has the advantages that: compared with the prior art, the invention has the following advantages:
most of traditional wave power generation grid-connected inverters adopt PI control algorithms, the PI control algorithms are simple to implement and wide in application, but PI control algorithm parameters need to be adjusted offline, inherent defects of a classical control theory exist, system parameter changes and external disturbance are too sensitive, robustness is poor, and the application effect in small-scale wave power generation single-phase grid-connected inverters is poor.
The sliding mode variable structure control method is a nonlinear control method, the sliding mode of the sliding mode variable structure control method can be designed and is irrelevant to object parameters and disturbance, and therefore the sliding mode variable structure control method has the advantages of being fast in response, insensitive to corresponding parameter change and disturbance, free of system online identification, simple in physical implementation and the like. The conventional sliding mode surface is a linear function, and after the conventional sliding mode surface is reached, the system error cannot be converged in a limited time. According to the terminal sliding mode control strategy, a nonlinear function is introduced into a sliding mode surface, so that the sliding mode controller has overall rapidity. However, after the sliding mode surface is reached, the magnitude of the switch gain epsilon is fixed and unchanged, and the phenomenon of 'buffeting' cannot be avoided.
The invention takes the global terminal sliding mode control strategy as a main controller, and adopts the reinforcement learning algorithm to dynamically adjust the switching gain epsilon of the sliding mode controller on line, so that the control strategy of the inverter can be continuously self-adjusted according to the environmental characteristics, the phenomenon of buffeting is greatly weakened, and the robustness and the stability of the system are enhanced.
Drawings
Fig. 1 is a schematic structural diagram of a global fast terminal sliding mode control algorithm based on a reinforcement learning principle.
Fig. 2 is a schematic diagram of a hardware implementation main circuit structure.
Detailed Description
For a more detailed understanding of the present invention, reference is now made to the detailed description of the specific embodiments of the present invention, taken in conjunction with the accompanying drawings.
A control method of a grid-connected inverter for a wave power generation system is shown in figure 1, and the specific implementation comprises the following steps:
step 1: initializing an evaluation network learning rate and a discount factor of a reinforcement learning algorithm, and designing a reinforcement learning signal according to a system error;
the reinforcement learning signal r (t) is designed according to the following formula:
wherein, Uac(t) inverter AC output voltage at time t;is the grid voltage at time t; u (t) is the duty ratio of the switching tube at the moment f, and is the system control quantity; r (t) is a reinforcement learning signal at time t; the evaluation web learning rate is set to 0.3 and the discount factor is set to 0.95.
Step 2: calculating an evaluation network error, and carrying out online adjustment on the weight of the evaluation network through the calculated evaluation network error;
the evaluation network error is: e.g. of the typec(t)=γJ(t)-[J(t-1)-r(t)]
Wherein e isc(t) the evaluation network error at time t; j (t) evaluating the network output at time t; j (t-1) is the evaluation network output at the time of t-1; gamma is a discount factor; r (t) is a reinforcement learning signal.
And (3) carrying out online adjustment on the weight of the evaluation network according to the following rules: wc(t+1)=Wc(t)+ΔWc(t),
Wherein, Wc(t) evaluating a network weight matrix at the moment t; wc(t +1) evaluating a network weight matrix at the moment of t + 1; Δ Wc(t) evaluating the variable quantity of the network weight matrix at the moment t; lcTo evaluate the network learning rate; ecAnd (t) is the square of the evaluation network error.
And step 3: solving an optimal performance index function to obtain a global fast terminal sliding mode self-adaptive control rate based on a reinforcement learning principle;
wherein laIs an adaptive learning rate; u shapeac(t) inverter AC output voltage at time t; e.g. of the typec(t) evaluating network errors; ec(t) is the square of an evaluation network error, and delta epsilon (t) is the global fast terminal sliding mode self-adaptive control rate at the moment t; epsilon (t) is the sliding mode switch gain at time t.
And 4, step 4: and generating a global fast terminal sliding mode control algorithm control signal based on a reinforcement learning principle according to the self-adaptive control rate, and controlling the conduction time of the inverter switching tube.
The mathematical model of the grid-connected inverter of the wave power generation system is as follows:
wherein, UdcIs the DC side voltage of the inverter; l is an inverter alternating current inductor; c is an inverter alternating current capacitor; r is an inverter alternating current resistor; u (t) is the duty ratio of the switching tube at the time t, and is the system control quantity; u shapeac(t) inverter AC output voltage at time t; u shapeac(t-1) the inverter alternating current output voltage at the time of t-1; t issIs the sampling time; u shapeacAnd (t-2) is the alternating current output voltage of the inverter at the time t-2.
The terminal sliding mode control surface is as follows:
wherein the content of the first and second substances,the difference value between the output voltage of the inverter at the moment t and the actual power grid voltage is obtained; u shapeac(t) inverter AC output voltage at time t;is the grid voltage at time t; e (t-1) is the difference value between the output voltage of the inverter at the moment t-1 and the actual power grid voltage; t issThe sampling time is s is a terminal sliding mode surface, α, β, q and p are sliding mode adjusting parameters, α and β are positive numbers, and q and p are positive integers.
The Lyapunov function is:
obtaining a derivative of the Lyapunov function
Wherein the content of the first and second substances,is the derivative of the terminal sliding mode surface;is the derivative of the lyapunov function;
in order to make the Lyapunov function satisfy the stability conditionAnd obtaining the inverter control rate at the t +1 moment as follows:
wherein, UdcIs the DC side voltage of the inverter; l is an inverter alternating current inductor; c is an inverter alternating current capacitor; r is an inverter alternating current resistor; u (t +1) is the duty ratio of the switching tube at the moment of t + 1;the difference value between the output voltage of the inverter at the moment t and the actual power grid voltage is obtained; e (t +1) is the difference value between the inverter output voltage at the moment of t +1 and the actual power grid voltage;is the grid voltage at time t;the grid voltage is at the moment t + 1;the grid voltage is the t-1 moment; u shapeac(t) inverter AC output voltage at time t; u shapeac(t-1) the inverter alternating current output voltage at the time of t-1; u shapeac(t +1) is the inverter alternating current output voltage at the moment of t + 1; s is a terminal sliding mode surface; t issThe sampling time is α, β, q, p and k are sliding mode adjusting parameters, α, β and k are positive numbers, q and p are positive integers, and at the moment, the adjustment k is large, so that the moving point can quickly approach to the sampling timeAnd after the sliding mode switching surface is reached, the convergence rate is determined by α, β, q and p parameters, the convergence rate is adjusted according to multiple experiments, and delta epsilon (t) is the global fast terminal sliding mode self-adaptive control rate at the time t.
The algorithm is implemented by hardware, as shown in figure 2, the alternating current generated by the wave-activated generator is converted into direct current voltage U by the rectifying circuitdcThe global fast terminal sliding mode control algorithm based on the reinforcement learning principle is realized by programming on the DSP28335, and the voltage of the power grid is collected through an AD sampling circuitAnd a DC voltage UdcAnd the control quantity is PWM output duty ratio, and four switching tubes of the inverter are controlled, so that the output voltage of the inverter is synchronous with the amplitude and the phase of the grid voltage.
The above examples are only preferred embodiments of the present invention, it should be noted that: it will be apparent to those skilled in the art that various modifications and equivalents can be made without departing from the spirit of the invention, and it is intended that all such modifications and equivalents fall within the scope of the invention as defined in the claims.
Claims (5)
1. A grid-connected inverter control method for a wave power system is characterized by comprising the following steps:
step 1: initializing an evaluation network learning rate and a discount factor of a reinforcement learning algorithm, and designing a reinforcement learning signal r (t) according to the following formula according to a system error:
wherein, Uac(t) inverter AC output voltage at time t;is the grid voltage at time t; u (t) is the duty ratio of the switching tube at the time t, and is the system control quantity;r (t) is a reinforcement learning signal at time t;
step 2: calculating an evaluation network error, and carrying out online adjustment on the weight of the evaluation network through the calculated evaluation network error;
and step 3: solving an optimal performance index function to obtain a global fast terminal sliding mode self-adaptive control rate based on a reinforcement learning principle;
and 4, step 4: and generating a global fast terminal sliding mode control algorithm control signal based on a reinforcement learning principle according to the self-adaptive control rate, and controlling the conduction time of the inverter switching tube.
2. The grid-connected inverter control method for a wave power system according to claim 1, wherein the step 2 is to calculate and evaluate the network error according to the following formula:
ec(t)=γJ(t)-[J(t-1)-r(t)]
wherein e isc(t) the evaluation network error at time t; j (t) evaluating the network output at time t; j (t-1) is the evaluation network output at the time of t-1; gamma is a discount factor; r (t) is a reinforcement learning signal.
3. The grid-connected inverter control method for the wave power generation system according to claim 1 or 2, characterized in that in step 2, the weight of the evaluation network is adjusted on line according to the following rules:
wherein, Wc(t) evaluating a network weight matrix at the moment t; wc(t +1) is the evaluation network weight matrix at the moment of t +1, △ Wc(t) evaluating the variable quantity of the network weight matrix at the moment t; lcTo evaluate the network learning rate; ecAnd (t) is the square of the evaluation network error.
4. The grid-connected inverter control method for the wave power generation system according to claim 1 or 2, characterized in that, in the step 3, the global fast terminal sliding mode adaptive control rate based on the reinforcement learning principle is obtained according to the following formula:
wherein laIs an adaptive learning rate; u shapeac(t) inverter AC output voltage at time t; e.g. of the typec(t) evaluating network errors; ecAnd (t) is the square of an evaluation network error, △ epsilon (t) is the global fast terminal sliding mode adaptive control rate at the time t, and epsilon (t) is the sliding mode switch gain at the time t.
5. The grid-connected inverter control method for a wave power system according to claim 4, characterized in that in step 4, the control signal is generated according to the following formula:
wherein, UdcIs the DC side voltage of the inverter; l is an inverter alternating current inductor; c is an inverter alternating current capacitor; r is an inverter alternating current resistor; u (t +1) is the duty ratio of the switching tube at the moment of t + 1;the difference value between the output voltage of the inverter at the moment t and the actual power grid voltage is obtained; e (t +1) is the difference value between the inverter output voltage at the moment of t +1 and the actual power grid voltage;is the grid voltage at time t;the grid voltage is at the moment t + 1;for the grid voltage at time t-1;Uac(t) inverter AC output voltage at time t; u shapeac(t-1) the inverter alternating current output voltage at the time of t-1; u shapeac(t +1) is the inverter alternating current output voltage at the moment of t + 1; s is a terminal sliding mode surface; t issThe adaptive control method comprises the steps of sampling time, α, β, q, p and k are sliding mode adjustment parameters, α, β and k are positive numbers, q and p are positive integers, epsilon (t) is sliding mode switch gain at the time t, and △ epsilon (t) is global fast terminal sliding mode adaptive control rate at the time t.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810144406.5A CN108429475B (en) | 2018-02-11 | 2018-02-11 | Grid-connected inverter control method for wave power generation system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810144406.5A CN108429475B (en) | 2018-02-11 | 2018-02-11 | Grid-connected inverter control method for wave power generation system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108429475A CN108429475A (en) | 2018-08-21 |
CN108429475B true CN108429475B (en) | 2020-02-18 |
Family
ID=63156974
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810144406.5A Active CN108429475B (en) | 2018-02-11 | 2018-02-11 | Grid-connected inverter control method for wave power generation system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108429475B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111416384A (en) * | 2020-03-18 | 2020-07-14 | 天津大学 | Inverter control method for direct drive type wave power generation system |
CN113113928B (en) * | 2021-04-12 | 2022-09-09 | 国网江苏省电力有限公司电力科学研究院 | Flexible-direct system direct-current bus voltage control method and device based on deep reinforcement learning |
CN117767778B (en) * | 2024-02-22 | 2024-05-28 | 中国人民解放军空军预警学院 | Self-adaptive intelligent control method and system for inverter |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104595106A (en) * | 2014-05-19 | 2015-05-06 | 湖南工业大学 | Wind power generation variable pitch control method based on reinforcement learning compensation |
CN105141164A (en) * | 2015-08-11 | 2015-12-09 | 河海大学常州校区 | Sliding-mode control method for inverse global rapid terminal of single-phase photovoltaic grid-connected inverter |
CN106712552A (en) * | 2017-02-10 | 2017-05-24 | 南京航空航天大学 | Control method for VIENNA rectifier of aviation multi-electric engine |
CN106707763A (en) * | 2017-02-23 | 2017-05-24 | 河海大学常州校区 | Fuzzy-neural global rapid terminal sliding-mode control method of photovoltaic grid-connected inverter |
CN106877766A (en) * | 2017-02-10 | 2017-06-20 | 华南理工大学 | Double-fed induction wind driven generator automatic correction controling method based on nitrification enhancement |
CN107104616A (en) * | 2017-07-10 | 2017-08-29 | 广东工业大学 | A kind of direct-drive wave power generation system is layered Lu Bang Control Sampled-Data method and device |
-
2018
- 2018-02-11 CN CN201810144406.5A patent/CN108429475B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104595106A (en) * | 2014-05-19 | 2015-05-06 | 湖南工业大学 | Wind power generation variable pitch control method based on reinforcement learning compensation |
CN105141164A (en) * | 2015-08-11 | 2015-12-09 | 河海大学常州校区 | Sliding-mode control method for inverse global rapid terminal of single-phase photovoltaic grid-connected inverter |
CN106712552A (en) * | 2017-02-10 | 2017-05-24 | 南京航空航天大学 | Control method for VIENNA rectifier of aviation multi-electric engine |
CN106877766A (en) * | 2017-02-10 | 2017-06-20 | 华南理工大学 | Double-fed induction wind driven generator automatic correction controling method based on nitrification enhancement |
CN106707763A (en) * | 2017-02-23 | 2017-05-24 | 河海大学常州校区 | Fuzzy-neural global rapid terminal sliding-mode control method of photovoltaic grid-connected inverter |
CN107104616A (en) * | 2017-07-10 | 2017-08-29 | 广东工业大学 | A kind of direct-drive wave power generation system is layered Lu Bang Control Sampled-Data method and device |
Also Published As
Publication number | Publication date |
---|---|
CN108429475A (en) | 2018-08-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101572417B (en) | Maximum power tracking control method for monopole three-phase photovoltaic grid-connected system | |
CN101604848B (en) | Modified fuzzy sliding mode controlling method of monopole three-phase photovoltaic grid-connected system | |
CN108429475B (en) | Grid-connected inverter control method for wave power generation system | |
Barra et al. | Predictive direct power control for photovoltaic grid connected system: An approach based on multilevel converters | |
CN108512452B (en) | Control system and control method for current of direct-current micro-grid-connected converter | |
CN104037800B (en) | A kind of photovoltaic combining inverter current control method | |
Gu et al. | Fuzzy terminal sliding mode control for extracting maximum marine current energy | |
CN109638863B (en) | Multifunctional energy storage converter design method based on double deviation compensation control algorithm | |
CN103280842B (en) | Synchronization control method and synchronization control system for generating converter internal frequency by direct current (DC) voltage | |
Meddour et al. | A novel approach for PV system based on metaheuristic algorithm connected to the grid using FS-MPC controller | |
Barambones | Robust wind speed estimation and control of variable speed wind turbines | |
CN103929054A (en) | Soft starting method for photovoltaic grid-connected inverter | |
CN112688307A (en) | Alternating current-direct current hybrid microgrid controller and control method | |
CN107123991B (en) | Dynamic voltage restorer control method and device based on fuzzy particle swarm algorithm | |
CN113991715A (en) | Control method of medium-voltage direct-hanging asymmetric hybrid energy storage system under non-ideal power grid | |
CN110518625B (en) | Grid-connected inverter direct-current component suppression method with variable learning rate BP-PID control | |
Balakishan et al. | An ANN Based MPPT for Power Monitoring in Smart Grid using Interleaved Boost Converter | |
Heshmatian et al. | A control scheme for maximizing the delivered power to the load in a standalonewind energy conversion system | |
CN104167939B (en) | Method and device for modulating current transformer | |
CN114024340B (en) | Offshore wind power plant control system and model predictive control method | |
CN115864493A (en) | Photovoltaic inverter system and photovoltaic inverter control method | |
CN110048466B (en) | Prediction control method for grid-side converter model of double-fed wind power generation system | |
Agarwal et al. | Power quality improvement of photovoltaic distributed generation system using artificial neural network for environmental preservation | |
Li et al. | An adaptive single neural control for variable step-size P&O MPPT of marine current turbine system | |
Shukl et al. | Neural network based control algorithm for solar PV interfaced system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |