CN110912188A - Novel micro-grid energy management system based on AI - Google Patents
Novel micro-grid energy management system based on AI Download PDFInfo
- Publication number
- CN110912188A CN110912188A CN201911184721.1A CN201911184721A CN110912188A CN 110912188 A CN110912188 A CN 110912188A CN 201911184721 A CN201911184721 A CN 201911184721A CN 110912188 A CN110912188 A CN 110912188A
- Authority
- CN
- China
- Prior art keywords
- module
- algorithm
- data
- equipment
- time
- 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.)
- Pending
Links
- 230000006978 adaptation Effects 0.000 claims abstract description 11
- 238000007405 data analysis Methods 0.000 claims abstract description 10
- 230000004044 response Effects 0.000 claims abstract description 4
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims description 3
- 238000004146 energy storage Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012917 library technology Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 238000007726 management method Methods 0.000 claims 6
- 238000010248 power generation Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
- H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
Abstract
The invention discloses a novel micro-grid energy management system based on AI, which comprises an AI data prediction module, a data analysis module, an equipment adaptation module and an algorithm dynamic mounting module. The AI data prediction module is divided into a real-time data prediction part and a behavior prediction part, and the real-time data prediction part is used for adjusting parameters of a microgrid scheduling algorithm in time to realize advanced control; the behavior prediction is used for realizing the dynamic response of the micro-grid; the data analysis module is used for analyzing the running state of the equipment; the device adaptation module is used for rapidly adapting to different devices; and the algorithm dynamic mounting module is used for dynamic assembly and disassembly. The invention has the functions of optimized power generation dispatching, load management, real-time monitoring, automatic synchronization of the micro-grid and the like, can adapt to the multi-deformation form of the micro-grid, and has the characteristics of switching and changing of a dispatching algorithm, remote control, self-adaptation of equipment and the like.
Description
Technical Field
The invention relates to the field of micro-grids, in particular to a novel micro-grid energy management system based on AI.
Background
With social development and policy changes, traditional fossil energy is being used less and less in productive life, and governments are encouraging the development of new energy due to its high pollution. An important way for new energy to enter the application of urban load areas and the like is to adopt the utilization form of a micro-grid.
The micro-grid is a new energy utilization mode, and comprises a plurality of small wind driven generators, distributed photovoltaic power generation, user loads, a ground heat pump and other equipment, and the micro-grid manages the equipment, so that the economic benefit is maximized, and scientific and effective management is provided for the power utilization of users.
The micro-grid energy management system is a core part of micro-grid control. The traditional micro-grid energy management system adopts a common embedded control scheme, the control mode is simple and extensive, and accurate management, energy prediction and flexible and variable control strategies and schemes for users cannot be realized. The micro-grid has variability, and the traditional micro-grid energy management system is usually only suitable for one system, and when the micro-grid form changes, the energy management system needs to be developed again. Therefore, a new type of microgrid energy management system is needed.
Disclosure of Invention
The invention aims to solve the technical problems and provides a novel AI-based microgrid energy management system with data analysis, user management and energy algorithms.
In order to solve the technical problems, the invention adopts the following technical scheme:
a novel micro-grid energy management system based on AI comprises
The AI data prediction module is divided into a real-time data prediction part and a behavior prediction part, the real-time data prediction is directly carried out in the microgrid controller by adopting an artificial intelligence time sequence algorithm, and the operation condition of the equipment at the next moment is predicted in real time according to the data information of each equipment in the microgrid, so that the parameters of the microgrid scheduling algorithm are adjusted in time, and advanced control is realized; the behavior prediction means that historical data in the server is used for carrying out LSTM algorithm analysis to predict when a user adopts what kind of operation, so that charging and discharging of an energy storage system in the microgrid and energy output of other equipment are controlled in time, and dynamic response of the microgrid is realized;
the data analysis module analyzes data by adopting a multilayer perception network algorithm, marks illegal data, thereby distinguishing the running state of the equipment, filtering abnormal data and maintaining the equipment in advance;
the device adaptation module adopts the combination of Lua and C languages and uses a self-defined data format to meet the requirements of quick control and dynamic analysis; dynamically increasing, decreasing or modifying the model data of the micro-grid energy scheduling system by modifying the parameters of the equipment adaptation module; and
the algorithm dynamic mounting module adopts a dynamic library technology, namely, the dynamic mounting module is not linked to any algorithm library during compiling, but declares a control interface of each algorithm, and the specific implementation is in a specific scheduling algorithm.
Further, the AI data prediction module is specifically divided into large-scale long-time data prediction and short-time real-time data prediction in a layering manner.
Furthermore, the novel AI-based microgrid energy management system also comprises an authority management module which allocates different authorities to common users, maintainers and developers and stores the authorities in an embedded database, and adopts different management modes and dynamically limits operable modules for different login users so as to ensure the safe operation of the system.
Further, the novel AI-based microgrid energy management system also includes a user interface module, which is a display portion presented to a user.
The invention has the beneficial effects that: the invention has the functions of optimized power generation dispatching, load management, real-time monitoring, automatic synchronization of the micro-grid and the like, can adapt to the multi-deformation form of the micro-grid, and has the characteristics of switching and changing of a dispatching algorithm, remote control, self-adaptation of equipment and the like.
Detailed Description
The present invention will be described in further detail with reference to specific embodiments below:
the invention provides a complete solution for the problems of start-stop control, power distribution, use analysis of loads, hierarchical management of the loads and the like of each device in the field of micro-grids, and realizes a novel AI-based micro-grid energy management system with data analysis, user management and energy algorithms.
The novel AI-based microgrid energy management system comprises an AI data prediction module, a data analysis module, an equipment adaptation module, an algorithm dynamic mounting module, an authority management module, a user interface module and the like.
An AI data prediction module:
the AI data prediction module of the invention is divided into two parts of real-time data prediction and behavior prediction, and the specific layering is divided into large-scale long-time data prediction and short-time real-time data prediction. And the real-time data prediction is directly carried out in the microgrid controller by adopting an artificial intelligence time sequence algorithm. And according to the data information of each device in the microgrid, predicting the running condition of the device at the next moment in real time, and further adjusting the parameters of the microgrid scheduling algorithm in time to realize advanced control.
And the behavior prediction means that historical data in the server is used for carrying out LSTM algorithm analysis to predict when the user adopts what kind of operation, so that the charging and discharging of an energy storage system in the microgrid and the energy output of other equipment are controlled in time, and the dynamic response of the microgrid is realized.
A data analysis module:
the data analysis module is an important component of the invention. The data analysis can be used for analyzing the quality degree of the data in time, and further analyzing the running state of the equipment. And analyzing the data by adopting a multilayer perception network algorithm, and marking illegal data, thereby distinguishing the running state of the equipment, filtering abnormal data and maintaining the equipment in advance.
A device adaptation module:
the device adaptation module makes the invention quickly adaptable to different devices. When the number of the devices of the microgrid is increased or decreased, parameters of the device adaptation module are modified, and model data of the microgrid energy scheduling system can be increased, decreased or modified dynamically. The equipment adaptation module adopts the combination of Lua and C languages, uses a self-defined data format, and meets the requirements of quick control and dynamic analysis.
An algorithm dynamic mounting module:
in the present invention, the energy scheduling algorithm can be dynamically assembled and disassembled. Therefore, the problem that the micro-grid needs to be stopped when the algorithm is replaced is avoided, and the stable operation of the micro-grid can be maintained. The algorithm dynamic mounting module adopts a dynamic library technology, namely, the algorithm dynamic mounting module is not linked to any algorithm library during compiling, but declares a control interface of each algorithm, and the specific implementation is in a specific scheduling algorithm. Thus, the algorithm only needs to be mounted into the memory and initialized when the algorithm is assembled, and only needs to be destroyed and redirected when the algorithm is unloaded. It is only instantiated at runtime.
The authority management module:
the rights management of the present invention refers to rights management for a user. The authority management module allocates different authorities to common users, maintainers, developers and the like and stores the authorities in the embedded database, adopts different management modes to different login users and dynamically limits the modules which can be operated, thereby ensuring the safe operation of the system.
A user interface module:
the user interface module is the portion of the display presented to the user by the present invention. The user interface module adopts a WEB form, a GoAhead server is embedded in the system, and a front-end and back-end separation mode is adopted. The user can log in the system by using the browser, and different control interfaces can be displayed according to different user permissions.
In summary, the present invention is not limited to the above-mentioned embodiments, and those skilled in the art can propose other embodiments within the technical teaching of the present invention, but these embodiments are included in the scope of the present invention.
Claims (4)
1. A novel micro-grid energy management system based on AI, which is characterized by comprising
The AI data prediction module is divided into a real-time data prediction part and a behavior prediction part, the real-time data prediction is directly carried out in the microgrid controller by adopting an artificial intelligence time sequence algorithm, and the operation condition of the equipment at the next moment is predicted in real time according to the data information of each equipment in the microgrid, so that the parameters of the microgrid scheduling algorithm are adjusted in time, and advanced control is realized; the behavior prediction means that historical data in the server is used for carrying out LSTM algorithm analysis to predict when a user adopts what kind of operation, so that charging and discharging of an energy storage system in the microgrid and energy output of other equipment are controlled in time, and dynamic response of the microgrid is realized;
the data analysis module analyzes data by adopting a multilayer perception network algorithm, marks illegal data, thereby distinguishing the running state of the equipment, filtering abnormal data and maintaining the equipment in advance;
the device adaptation module adopts the combination of Lua and C languages and uses a self-defined data format to meet the requirements of quick control and dynamic analysis; dynamically increasing, decreasing or modifying the model data of the micro-grid energy scheduling system by modifying the parameters of the equipment adaptation module; and
the algorithm dynamic mounting module adopts a dynamic library technology, namely, the dynamic mounting module is not linked to any algorithm library during compiling, but declares a control interface of each algorithm, and the specific implementation is in a specific scheduling algorithm.
2. The AI-based novel microgrid energy management system of claim 1, wherein the AI data prediction module is further subdivided into large-scale long-time data prediction and short-time real-time data prediction in a specific hierarchy.
3. The AI-based novel microgrid energy management system of claim 1, further comprising an authority management module, which assigns different authorities to common users, maintainers and developers and stores them in the embedded database, and employs different management methods and dynamically limits the modules that can be operated for different login users to ensure the safe operation of the system.
4. The AI-based novel microgrid energy management system of claim 1, further comprising a user interface module which is a display portion presented to a user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911184721.1A CN110912188A (en) | 2019-11-27 | 2019-11-27 | Novel micro-grid energy management system based on AI |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911184721.1A CN110912188A (en) | 2019-11-27 | 2019-11-27 | Novel micro-grid energy management system based on AI |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110912188A true CN110912188A (en) | 2020-03-24 |
Family
ID=69818675
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911184721.1A Pending CN110912188A (en) | 2019-11-27 | 2019-11-27 | Novel micro-grid energy management system based on AI |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110912188A (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101119029A (en) * | 2007-09-28 | 2008-02-06 | 清华大学 | Automatic power generation controlled advance control method for power system |
CN103812112A (en) * | 2014-02-20 | 2014-05-21 | 国家电网公司 | Regional power grid automatic voltage control (AVC) method |
CN104967149A (en) * | 2015-06-29 | 2015-10-07 | 山东电力研究院 | Micro power grid wind and solar energy storage model prediction control method |
CN105490267A (en) * | 2015-12-28 | 2016-04-13 | 易事特集团股份有限公司 | Micro grid energy management system and energy management method |
CN106647712A (en) * | 2016-12-30 | 2017-05-10 | 上海科梁信息工程股份有限公司 | DC micrgrid control strategy testing system and method |
CN107423839A (en) * | 2017-04-17 | 2017-12-01 | 湘潭大学 | A kind of method of the intelligent building microgrid load prediction based on deep learning |
CN108539792A (en) * | 2018-05-15 | 2018-09-14 | 山东大学 | Micro-capacitance sensor internal unit fast evaluation method based on look-up table |
CN109088406A (en) * | 2018-06-26 | 2018-12-25 | 河海大学常州校区 | A kind of micro-capacitance sensor equivalent modeling method based on LSTM neural network |
CN110212585A (en) * | 2019-07-02 | 2019-09-06 | 国电联合动力技术有限公司 | Running of wind generating set Reliability Prediction Method, device and Wind turbines based on statistical analysis |
CN110222953A (en) * | 2018-12-29 | 2019-09-10 | 北京理工大学 | A kind of power quality hybrid perturbation analysis method based on deep learning |
CN110417015A (en) * | 2019-06-18 | 2019-11-05 | 湖北追日电气股份有限公司 | Micro-capacitance sensor Multiobjective Optimal Operation method and system based on Model Predictive Control |
-
2019
- 2019-11-27 CN CN201911184721.1A patent/CN110912188A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101119029A (en) * | 2007-09-28 | 2008-02-06 | 清华大学 | Automatic power generation controlled advance control method for power system |
CN103812112A (en) * | 2014-02-20 | 2014-05-21 | 国家电网公司 | Regional power grid automatic voltage control (AVC) method |
CN104967149A (en) * | 2015-06-29 | 2015-10-07 | 山东电力研究院 | Micro power grid wind and solar energy storage model prediction control method |
CN105490267A (en) * | 2015-12-28 | 2016-04-13 | 易事特集团股份有限公司 | Micro grid energy management system and energy management method |
CN106647712A (en) * | 2016-12-30 | 2017-05-10 | 上海科梁信息工程股份有限公司 | DC micrgrid control strategy testing system and method |
CN107423839A (en) * | 2017-04-17 | 2017-12-01 | 湘潭大学 | A kind of method of the intelligent building microgrid load prediction based on deep learning |
CN108539792A (en) * | 2018-05-15 | 2018-09-14 | 山东大学 | Micro-capacitance sensor internal unit fast evaluation method based on look-up table |
CN109088406A (en) * | 2018-06-26 | 2018-12-25 | 河海大学常州校区 | A kind of micro-capacitance sensor equivalent modeling method based on LSTM neural network |
CN110222953A (en) * | 2018-12-29 | 2019-09-10 | 北京理工大学 | A kind of power quality hybrid perturbation analysis method based on deep learning |
CN110417015A (en) * | 2019-06-18 | 2019-11-05 | 湖北追日电气股份有限公司 | Micro-capacitance sensor Multiobjective Optimal Operation method and system based on Model Predictive Control |
CN110212585A (en) * | 2019-07-02 | 2019-09-06 | 国电联合动力技术有限公司 | Running of wind generating set Reliability Prediction Method, device and Wind turbines based on statistical analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112332444A (en) | Microgrid energy management system based on digital twins | |
CN106485352A (en) | A kind of multiclass power supply generation schedule combination decision-making method | |
KR101298500B1 (en) | Micro-Grid Simulation Apparatus and Power Management System | |
CN104182902A (en) | Monitoring method based on centralized operation and maintenance system of dispatching data network | |
CN108039734B (en) | Renewable energy power generation power cluster control system and method | |
CN103559656A (en) | Demand response control system and method | |
CN112260322A (en) | Source network load storage simulation platform, method and system | |
CN114861539A (en) | Modeling and implementation method for 5G urban comprehensive energy Internet digital twin system | |
CN104463465A (en) | Real-time monitoring cluster processing method based on distributed models | |
Liu et al. | Proactive resilient day-ahead unit commitment with cloud computing data centers | |
CN102724100B (en) | A kind of board resource allocation system for composite services and method | |
CN112950001B (en) | Intelligent energy management and control system and method based on cloud edge closed-loop architecture | |
Zhao et al. | Workload and energy management of geo-distributed datacenters considering demand response programs | |
Yang et al. | The short-term economical operation problem for hydropower station using chaotic normal cloud model based discrete shuffled frog leaping algorithm | |
CN110912188A (en) | Novel micro-grid energy management system based on AI | |
CN104463430A (en) | Load dispatch control system | |
CN113904378A (en) | Virtual power plant resource regulation and control method, system and resource regulation and control terminal | |
CN116050754A (en) | Digital twinning-based virtual power plant collaborative management and control method and system | |
CN109597380A (en) | A kind of wisdom energy management plateform system based on Internet of Things and cloud computing technology | |
CN113872183A (en) | Comprehensive energy optimization and coordination system | |
Wiesner et al. | Software‐in‐the‐loop simulation for developing and testing carbon‐aware applications | |
CN107086587B (en) | A kind of data center's dominant eigenvalues control method based on Demand Side Response | |
CN205194065U (en) | Intelligent residential district electric quantity collection device based on thing networking | |
CN109961376A (en) | A kind of distributed energy storage apparatus management/control system and method | |
CN104932304A (en) | Micro-grid multi-agent control system and method |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210929 Address after: 300308 100 Hangtian Road, Airport Economic Zone, Binhai New Area, Tianjin Applicant after: TIANJIN RUIYUAN ELECTRICAL Co.,Ltd. Address before: No.1 Xinghua No.7 Branch Road, economic development zone, Xiqing District, Tianjin Applicant before: Tianjin Ruineng electric Co.,LTD. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200324 |