CN105024390B - Micro-grid battery energy storage system frequency modulation control method based on BP neural network - Google Patents
Micro-grid battery energy storage system frequency modulation control method based on BP neural network Download PDFInfo
- Publication number
- CN105024390B CN105024390B CN201510432371.1A CN201510432371A CN105024390B CN 105024390 B CN105024390 B CN 105024390B CN 201510432371 A CN201510432371 A CN 201510432371A CN 105024390 B CN105024390 B CN 105024390B
- Authority
- CN
- China
- Prior art keywords
- frequency
- neural network
- micro
- storage system
- energy storage
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/10—Flexible AC transmission systems [FACTS]
Abstract
The present invention provides a kind of micro-grid battery energy storage system frequency modulation control method based on BP neural network, including：Measure the real-time frequency value of micro-grid battery energy storage system；The frequency-splitting between real-time frequency value and the rated frequency value of micro-grid battery energy storage system is obtained, and frequency-splitting is inputted in BP neural network and carries out intelligent inference, to obtain the parameter of current optimal PI controllers；Parameter tuning carries out PI controllers according to the parameter of current optimal PI controllers, and the inverter control active power difference reference value of micro-grid battery energy storage system is obtained according to frequency-splitting using the PI controllers after parameter tuning；According to active power difference with reference to active power reference value is worth to, PQ inversion controls are taken so that micro-grid battery energy storage system carries out system frequency modulation.This method can effectively improve precision and microgrid frequency stability in micro-grid battery energy storage system active power controller.
Description
Technical field
The present invention relates to electric system microgrid field, more particularly to a kind of microgrid battery storage based on BP neural network
Can system frequency modulation control method.
Background technology
In recent years, micro-capacitance sensor because its distributed generation resource is accessed in perfect compatibility, become the important set of intelligent grid
It is one of direction of national grid future development into part.Micro-capacitance sensor is mainly by distributed generation resource, energy storage device, power electronics
Equipment, load etc. form, and are both a region controllable in bulk power grid and the miniature power train of an independent completion
System, therefore, micro-grid operation mode have grid-connected and two kinds of operational modes of isolated power grid, and in being incorporated into the power networks, microgrid passes through distribution
Net access bulk power grid, with bulk power grid cooperation, realizes two-way circulating for electric energy.When the grid collapses or power grid electric energy
When quality cannot meet that user requires, microgrid will be switched off PCC points, be transferred to isolated power grid pattern.
After micro-capacitance sensor is transferred to isolated power grid, as miniature electric system, its inertia very little, power supply is contributed or load
Fluctuation all by because of the oscillation on large scale of its system frequency, even results in micro-grid system collapse.And micro-capacitance sensor is as distributed power generation
Effective and web form, its output power supply, which is given, natively contains the renewable energy power generation devices such as a large amount of wind turbines, photovoltaic, small power station,
The intermittence and fluctuation that these distributed generation resources will inevitably trigger power supply to contribute with the change of external environment, this is right
The running power-balance of micro-grid system proposes serious threat, therefore, for a large amount of renewable energy power generation devices in microgrid
It is possible go out fluctuation, it is necessary to energy storage device carry out fast and accurately supplement balance.Therefore, it is necessary to micro-grid system is solved by storage
Can system progress frequency modulation control.
Micro-grid energy storage system is under the frequency modulation control device control of its own, quick tracing compensation system power deviation, when
The control algolithm that preceding controller uses substantially adjusts two kinds containing droop control and urgent Direct Power, but all types of controls
Nearly all contain PI controlling units in device processed, need to join by PI between the input of control frequency departure and control power adjustment output
Number is handled, and to realize, fast and accurately frequency modulation responds, and the PI parameter tunings of frequency modulation control device are particularly significant.At the same time,
Micro-capacitance sensor is as strongly non-linear system, in frequency-modulating process, systematic parameter have time variation with it is non-linear, increase parameter tuning hardly possible
Degree, and for the parameter that specific micro-grid system, specific operating mode are adjusted after significantly change occurs for system performance, will not have suitable
Ying Xing, can not carry out adaptation of overall importance.Therefore, how accurately to realize control parameter in system frequency modulation operating mode change procedure
Self-adaptive sites, are a problem to be solved.
The content of the invention
The purpose of the present invention is intended at least solve one of above-mentioned technological deficiency.
For this reason, it is an object of the invention to propose a kind of micro-grid battery energy storage system frequency modulation control based on BP neural network
Method.This method can effectively improve precision and microgrid frequency stabilization in micro-grid battery energy storage system active power controller
Property.
To achieve these goals, embodiment of the invention discloses that a kind of microgrid battery energy storage based on BP neural network
System frequency modulation control method, comprises the following steps：Measure the real-time frequency value of the micro-grid battery energy storage system；Obtain the reality
When frequency values and the micro-grid battery energy storage system rated frequency value between frequency-splitting, and the frequency-splitting is inputted
Intelligent inference is carried out in trained BP neural network, to obtain the parameter of current optimal PI controllers；According to described
The parameter of current optimal PI controllers carries out the PI controllers parameter tuning, and utilizes the PI controllers after parameter tuning
According to the frequency-splitting, the inverter control active power difference reference value of the micro-grid battery energy storage system is obtained；According to
The active power difference takes PQ inversion controls so that the microgrid battery energy storage system with reference to active power reference value is worth to
System carry out system frequency modulation.
In addition, the micro-grid battery energy storage system frequency modulation control side according to the above embodiment of the present invention based on BP neural network
Method can also have technical characteristic additional as follows：
In some instances, the parameter of the PI controllers includes Proportional coefficient K p and integral coefficient Ki.
In some instances, intelligent push away is carried out in described input frequency-splitting in trained BP neural network
Reason, before obtaining the parameter of current optimal PI controllers, to further include：The BP neural network is trained to obtain
State trained BP neural network.
In some instances, the BP neural network is trained, specifically included：The BP neural network is to predetermined letter
Breath carries out forward-propagating and the backpropagation of error, obtains the weights of each layer of optimal neuron in the BP neural network,
Wherein, the weights of each layer of optimal neuron are used for according to the microgrid battery energy storage system with biasing in the BP neural network
The consecutive variations of the frequency error of system, assess current working in real time, provide the parameter of current optimal PI controllers.
In some instances, the training sample of the BP neural network is configured according to following setting principle：(the frequency
The absolute value of rate difference | deltaf | the Proportional coefficient K p) used during more than the first preset difference value is more than (frequency-splitting
Absolute value | deltaf | the Proportional coefficient K p) used less than first preset difference value and when being more than the second preset difference value, wherein,
First preset difference value is more than second preset difference value；(absolute value of the frequency-splitting | deltaf | it is pre- more than first
If the integral coefficient Ki used during difference) be less than (absolute value of the frequency-splitting | deltaf | it is default less than described first poor
Value and be more than the integral coefficient Ki used during the second preset difference value)；(absolute value of the frequency-splitting | deltaf | less than described
The Proportional coefficient K p) that first preset difference value and being more than uses during the second preset difference value be more than (absolute value of the frequency-splitting |
Deltaf | the Proportional coefficient K p) used during less than second preset difference value；(absolute value of the frequency-splitting | deltaf |
The integral coefficient Ki used less than first preset difference value and when being more than the second preset difference value) it is more than (frequency-splitting
Absolute value | deltaf | the integral coefficient Ki used during less than second preset difference value).
Micro-grid battery energy storage system frequency modulation control method based on BP neural network according to embodiments of the present invention, Ke Yiyou
Effect adapts to the non-linear and time variation of the operating parameter under microgrid different frequency error operating mode, realizes the control under different frequency operating mode
Parameter self-tuning processed, obtains optimal system dynamic response, realizes that the preferable dynamic response of micro-grid battery energy storage system frequency modulation is special
Property and robustness, effectively improve the precision and microgrid frequency stability in micro-grid battery energy storage system active power controller.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein,
Fig. 1 is the micro-grid battery energy storage system frequency modulation control method based on BP neural network of one embodiment of the invention
Flow chart；
Fig. 2 is the schematic diagram of three layers of BP neural network of one embodiment of the invention；
Fig. 3 is control of the trained BP neural network of one embodiment of the invention for the absolute value of system frequency difference
The schematic diagram of parameter response output processed；
Fig. 4 is the trained BP neural network of another embodiment of the present invention for the absolute value of system frequency difference
The schematic diagram of control parameter response output；
Fig. 5 is the main electrical scheme signal of the micro-grid battery energy storage system based on BP neural network of one embodiment of the invention
Figure；
Fig. 6 is the control of the micro-grid battery energy storage system frequency modulation control based on BP neural network of one embodiment of the invention
Block diagram；
Fig. 7 is using the frequency modulation design sketch of fixed PI in correlation technique；And
Fig. 8 is the frequency modulation of the micro-grid battery energy storage system frequency modulation control based on BP neural network of one embodiment of the invention
Design sketch.
Embodiment
The embodiment of the present invention is described below in detail, the example of embodiment is shown in the drawings, wherein identical from beginning to end
Or similar label represents same or similar element or has the function of same or like element.Retouched below with reference to attached drawing
The embodiment stated is exemplary, and is only used for explaining the present invention, and is not considered as limiting the invention.
In the description of the present invention, it is to be understood that term " " center ", " longitudinal direction ", " transverse direction ", " on ", " under ",
The orientation or position relationship of the instruction such as "front", "rear", "left", "right", " vertical ", " level ", " top ", " bottom ", " interior ", " outer " are
Based on orientation shown in the drawings or position relationship, it is for only for ease of the description present invention and simplifies description, rather than instruction or dark
Show that the device of meaning or element there must be specific orientation, with specific azimuth configuration and operation, thus it is it is not intended that right
The limitation of the present invention.In addition, term " first ", " second " are only used for description purpose, and it is not intended that instruction or hint are opposite
Importance.
In the description of the present invention, it is necessary to illustrate, unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or be integrally connected；Can
To be mechanical connection or be electrically connected；It can be directly connected, can also be indirectly connected by intermediary, Ke Yishi
Connection inside two elements.For the ordinary skill in the art, with concrete condition above-mentioned term can be understood at this
Concrete meaning in invention.
The description micro-grid battery energy storage system tune based on BP neural network according to embodiments of the present invention below in conjunction with the accompanying drawings
Frequency control method.
Fig. 1 is the micro-grid battery energy storage system frequency modulation control side according to an embodiment of the invention based on BP neural network
The flow chart of method.As shown in Figure 1, the micro-grid battery energy storage system tune according to an embodiment of the invention based on BP neural network
Frequency control method, includes the following steps：
S101：Measure the real-time frequency value of micro-grid battery energy storage system.Measure micro-grid system (microgrid battery energy storage system
System) real-time frequency value f.
S102：The frequency-splitting between real-time frequency value and the rated frequency value of micro-grid battery energy storage system is obtained, and will
Frequency-splitting inputs in trained BP neural network and carries out intelligent inference, to obtain the ginseng of current optimal PI controllers
Number.That is, by the rated frequency of the frequency instantaneous value of measurement and micro-grid battery energy storage system (such as using standard frequency as
Exemplified by 50Hz) it is compared, input quantity of its frequency-splitting as BP neural network, BP neural network will be according to current system frequency
Rate difference (i.e. frequency departure) input quantity carries out intelligent inference, the parameter of the current optimal PI controllers of adaptive polo placement.Wherein,
The parameter of PI controllers includes Proportional coefficient K p and integral coefficient Ki.
S103：Parameter tuning carries out PI controllers according to the parameter of current optimal PI controllers, and it is whole using parameter
PI controllers after fixed obtain the inverter control active power difference reference of micro-grid battery energy storage system according to frequency-splitting
Value.In other words, real-time controller parameters setting, handles system frequency deviation, obtains battery energy storage system inverter control
It is formed with work(power difference reference value.
S104：According to active power difference with reference to active power reference value is worth to, PQ inversion controls are taken so that microgrid
Battery energy storage system carries out system frequency modulation.Taken according to active power difference with reference to active power reference value P_ref is worth to
PQ inversion controls, battery energy storage system quickly adjust active output, carry out system frequency modulation.
In one embodiment of the invention, intelligence will carried out in frequency-splitting input trained BP neural network
Energy reasoning, before obtaining the parameter of current optimal PI controllers, to further include：BP neural network is trained to obtain
Trained good BP neural network.
Specifically, the BP neural network is trained, including：BP neural network carries out predetermined information positive biography
The backpropagation with error is broadcast, obtains the weights of each layer of optimal neuron in the BP neural network, wherein, BP nerve nets
The weights of each layer of optimal neuron are used to be become according to the continuous of frequency error of micro-grid battery energy storage system with biasing in network
Change, assess current working in real time, provide the parameter of current optimal PI controllers.
More specifically, the training of BP neural network is as follows：
As a specific example, the structure of classical BP neural network as shown in Fig. 2, by input layer, output layer with
And one or more layers hidden layer composition, appropriate connection weight between layers will make BP neural network well with biasing
The deterministic process of biological nervous system is simulated, weights and the biasing of BP neural network need to be formed by training, in training process
In, the forward-propagating for carrying out given information and the backpropagation of error are finally obtained optimal each layer nerve by BP neural network
The weights of member, realize the optimal processing to complicated nonlinear system, and neutral net provides its desired output to specific input information.
The BP neural network taken in this method is trained neutral net, and weights and the biasing of the network will be according to micro-grid system frequencies
The consecutive variations of rate error, assess current working in real time, provide current optimal control parameter.In one embodiment of the present of invention
In, take the BP neuronal structures of 1-3-1-2, i.e. one input quantity of input layer, first layer hidden layer contains 3 nodes, and second
Layer hidden layer contains 1 node, and output quantity is Kp and Ki.
In one embodiment of the invention, the training sample of BP neural network is configured according to following setting principle：
1st, (absolute value of frequency-splitting | deltaf | the Proportional coefficient K p) used during more than the first preset difference value is more than (frequency
The absolute value of rate difference | deltaf | the proportionality coefficient used less than first preset difference value and when being more than the second preset difference value
Kp), wherein, the first preset difference value is more than the second preset difference value；
2nd, (absolute value of frequency-splitting | deltaf | the integral coefficient Ki used during more than the first preset difference value) it is less than (frequency
The absolute value of rate difference | deltaf | the integral coefficient Ki used less than the first preset difference value and when being more than the second preset difference value)；
3rd, (absolute value of frequency-splitting | deltaf | used less than the first preset difference value and when being more than the second preset difference value
Proportional coefficient K p) be more than (absolute value of frequency-splitting | deltaf | the Proportional coefficient K p) used during less than the second preset difference value；
4th, (absolute value of frequency-splitting | deltaf | used less than the first preset difference value and when being more than the second preset difference value
Integral coefficient Ki) be more than (absolute value of frequency-splitting | deltaf | the integral coefficient Ki used during less than the second preset difference value).
That is, the training sample setting principle of BP neural network is as follows, first, when frequency departure absolute value |
Deltaf | when larger, take larger Proportional coefficient K p to accelerate dynamic response, be aided with smaller Ki.Second, when frequency departure is absolute
Value | deltaf | when moderate, reduce control scale parameter Kp, Ki suitably increases at this time, accelerates system response time.3rd, when frequency
Rate absolute value of the bias | deltaf | when smaller, system convergence stable state, further reduces Proportional coefficient K p, while takes smaller
Integral coefficient Ki so that system has good dynamic property.As shown in Figure 3 and Figure 4, trained BP nerves are provided respectively
Network is for system frequency error absolute value | deltaf | control parameter response output.
Micro-grid battery energy storage system frequency modulation control method based on BP neural network according to embodiments of the present invention, Ke Yiyou
Effect adapts to the non-linear and time variation of the operating parameter under microgrid different frequency error operating mode, realizes the control under different frequency operating mode
Parameter self-tuning processed, obtains optimal system dynamic response, realizes that the preferable dynamic response of micro-grid battery energy storage system frequency modulation is special
Property and robustness, effectively improve the precision and microgrid frequency stability in micro-grid battery energy storage system active power controller.
In order to more profoundly understand the method for the embodiment of the present invention, the present invention is done below in conjunction with specific example and is further retouched
State.
Microgrid (micro-grid battery energy storage system) main wiring diagram is as shown in figure 5, be taken based on the microgrid battery of BP neural network
The control block diagram of energy-storage system frequency modulation control is as shown in Figure 6.Wherein, f0It is that micro-capacitance sensor frequency rated value 50Hz, f are mains frequency
Measured value, TfIt is low-pass filter time constant, Kp and KiIt is the ratio system of energy-storage system frequency-modulation control system PI controllers respectively
Number and integral constant.PrefIt is the reference value of battery system active power output.
Fig. 7 is the frequency modulation design sketch that fixed PI is taken in correlation technique.Fig. 8 is the embodiment of the present invention based on BP nerve nets
The micro-grid battery energy storage system frequency modulation design sketch of network.Isolated power grid is transferred in 0.05s in simulation example, in 0.1s, load
Increase by 20% suddenly., power shortage all provides by battery energy storage system.
The frequency modulation design sketch adjusted of PI under contrast different modes, it can be seen that the embodiment of the present invention based on BP neural network
Micro-grid battery energy storage system frequency modulation control can adapt to the time-varying of electrical network parameter with non-linear, when system frequency difference is larger
When, the response of Kp acceleration systems is improved, and when frequency is close to steady-state value, Kp proportionality coefficients are reduced, are reduced temporary in frequency-modulating process
State overshoot, while integral coefficient effectively shows good response characteristic with proportionality coefficient, effectively improves system frequency stabilization
Property.
Although the embodiment of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, those of ordinary skill in the art are not departing from the principle of the present invention and objective
In the case of above-described embodiment can be changed within the scope of the invention, change, replace and modification.
Claims (5)
- A kind of 1. micro-grid battery energy storage system frequency modulation control method based on BP neural network, it is characterised in that including following step Suddenly：Measure the real-time frequency value of the micro-grid battery energy storage system；Obtain the frequency-splitting between the real-time frequency value and the rated frequency value of the micro-grid battery energy storage system, and by institute State frequency-splitting input and carry out intelligent inference in trained BP neural network, to obtain current optimal PI controllers Parameter；Parameter tuning is carried out to the PI controllers according to the parameter of the current optimal PI controllers, and utilizes parameter tuning PI controllers afterwards obtain the inverter control active power difference of the micro-grid battery energy storage system according to the frequency-splitting Reference value；According to the active power difference with reference to active power reference value is worth to, PQ inversion controls are taken so that the microgrid is electric Pond energy-storage system carries out system frequency modulation.
- 2. the micro-grid battery energy storage system frequency modulation control method according to claim 1 based on BP neural network, its feature It is, the parameter of the PI controllers includes Proportional coefficient K p and integral coefficient Ki.
- 3. the micro-grid battery energy storage system frequency modulation control method according to claim 2 based on BP neural network, its feature It is, intelligent inference will be carried out in frequency-splitting input trained BP neural network described, it is current optimal to obtain PI controllers parameter before, further include：The BP neural network is trained to obtain the trained BP Neutral net.
- 4. the micro-grid battery energy storage system frequency modulation control method according to claim 3 based on BP neural network, its feature It is, the BP neural network is trained, is specifically included：The BP neural network carries out forward-propagating and the backpropagation of error to predetermined information, obtains in the BP neural network The weights of each layer of optimal neuron, wherein, the weights of each layer of optimal neuron and biasing in the BP neural network For the consecutive variations of the frequency error according to the micro-grid battery energy storage system, current working is assessed in real time, is provided currently most The parameter of excellent PI controllers.
- 5. according to micro-grid battery energy storage system frequency modulation control side of the claim 2-4 any one of them based on BP neural network Method, it is characterised in that the training sample of the BP neural network is configured according to following setting principle：The absolute value of the frequency-splitting | deltaf | the Proportional coefficient K p used during more than the first preset difference value is more than the frequency The absolute value of rate difference | deltaf | the proportionality coefficient used less than first preset difference value and when being more than the second preset difference value Kp, wherein, first preset difference value is more than second preset difference value；The absolute value of the frequency-splitting | deltaf | the integral coefficient Ki used during more than the first preset difference value is less than the frequency The absolute value of rate difference | deltaf | the integral coefficient used less than first preset difference value and when being more than the second preset difference value Ki；The absolute value of the frequency-splitting | deltaf | used less than first preset difference value and when being more than the second preset difference value Proportional coefficient K p be more than the frequency-splitting absolute value | deltaf | the ratio used during less than second preset difference value COEFFICIENT K p；The absolute value of the frequency-splitting | deltaf | used less than first preset difference value and when being more than the second preset difference value Integral coefficient Ki be more than the frequency-splitting absolute value | deltaf | the integration used during less than second preset difference value COEFFICIENT K i.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510432371.1A CN105024390B (en) | 2015-07-21 | 2015-07-21 | Micro-grid battery energy storage system frequency modulation control method based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510432371.1A CN105024390B (en) | 2015-07-21 | 2015-07-21 | Micro-grid battery energy storage system frequency modulation control method based on BP neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105024390A CN105024390A (en) | 2015-11-04 |
| CN105024390B true CN105024390B (en) | 2018-04-20 |
Family
ID=54414176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510432371.1A Active CN105024390B (en) | 2015-07-21 | 2015-07-21 | Micro-grid battery energy storage system frequency modulation control method based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105024390B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105633990B (en) * | 2016-02-04 | 2018-06-19 | 清华大学 | Micro-capacitance sensor flywheel energy storage system frequency modulation method and device based on BP neural network |
| CN105633944B (en) * | 2016-02-04 | 2018-04-10 | 清华大学 | Fast dynamic response control method based on the grid-connected flywheel energy storage system of direct current |
| CN111523654B (en) * | 2019-02-03 | 2024-03-29 | 上海寒武纪信息科技有限公司 | Processing device and method |
| CN110824920B (en) * | 2019-11-12 | 2023-06-02 | 深圳供电局有限公司 | Household energy storage power supply frequency modulation control method and system |
| US20210296902A1 (en) * | 2020-03-17 | 2021-09-23 | King Fahd University Of Petroleum And Minerals | Battery energy storage-based controller for improving microgrid power quality |
| CN111585292B (en) * | 2020-07-02 | 2022-05-17 | 合肥工业大学 | Island microgrid frequency modulation control method and service device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102761133B (en) * | 2012-07-26 | 2014-09-03 | 南方电网科学研究院有限责任公司 | Method for controlling frequency modulation of micro-grid battery energy storage system based on fuzzy control |
| CN103457297B (en) * | 2013-07-12 | 2015-11-18 | 武汉大学 | Pull-in frequency deviation feedback control voltage realizes the meritorious closed loop control method regulated |
| CN103647295B (en) * | 2013-12-12 | 2015-07-08 | 南京四方亿能电力自动化有限公司 | Micro electrical network energy storage sectional type emergency frequency modulation control method |
| CN104408562B (en) * | 2014-11-25 | 2018-01-16 | 许继集团有限公司 | A kind of photovoltaic system generating efficiency comprehensive estimation method based on BP neural network |
-
2015
- 2015-07-21 CN CN201510432371.1A patent/CN105024390B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105024390A (en) | 2015-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105024390B (en) | Micro-grid battery energy storage system frequency modulation control method based on BP neural network | |
| US10230239B2 (en) | Hierarchical robust model predictive voltage and VAR control with coordination and optimization of autonomous DER voltage control | |
| Panda | Multi-objective evolutionary algorithm for SSSC-based controller design | |
| Khodabakhshian et al. | Multi-machine power system stabilizer design by using cultural algorithms | |
| CN108539798B (en) | Secondary regulation strategy of energy storage system based on model predictive control | |
| CN102761133B (en) | Method for controlling frequency modulation of micro-grid battery energy storage system based on fuzzy control | |
| CN105226664B (en) | A kind of active distribution network reactive voltage layer distributed control method for coordinating | |
| CN105633990B (en) | Micro-capacitance sensor flywheel energy storage system frequency modulation method and device based on BP neural network | |
| CN110518575A (en) | Multiple Time Scales active distribution network voltage optimization control method based on region division | |
| Farahani | Intelligent control of SVC using wavelet neural network to enhance transient stability | |
| CN107579543A (en) | A kind of isolated island micro-capacitance sensor distributed and coordinated control method based on muti-layer control tactics | |
| Banerjee et al. | A novel explicit disturbance model-based robust damping of interarea oscillations through MTDC grids embedded in AC systems | |
| Liang et al. | An interconnected microgrids-based transactive energy system with multiple electric springs | |
| CN105226700B (en) | Primary frequency modulation control method and device based on valve flow characteristic dynamic adjustment | |
| CN105917544A (en) | Method and regulatory and/or control device for the operation of a wind energy installation and/or a wind farm, and wind energy installation and wind farm | |
| US20160141877A1 (en) | Method and device for controlling power generators of a subgrid within an interconnected grid | |
| CN111478344B (en) | Energy microgrid load frequency control method and system and related products | |
| Malla et al. | Supplementary control for virtual synchronous machine based on adaptive dynamic programming | |
| Zhang et al. | Enhancing optimal excitation control by adaptive fuzzy logic rules | |
| CN108110751A (en) | Emergency flight control electric system stabilizing method | |
| CN106301049B (en) | The optimal guaranteed cost control methods of current source inverter mixing H2/H ∞ | |
| Gheisarnejad et al. | Reducing impact of constant power loads on DC energy systems by artificial intelligence | |
| Jafari et al. | Adaptive intelligent secondary control of microgrids using a biologically-inspired reinforcement learning | |
| CN106950831A (en) | A kind of reactive-load compensation method for offline optimization/switch online | |
| CN109088418A (en) | A kind of electric distribution network reactive-voltage control method based on universal model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |