CN116317110B - Power grid dispatching operation previewing method and system considering source load bilateral fluctuation - Google Patents
Power grid dispatching operation previewing method and system considering source load bilateral fluctuation Download PDFInfo
- Publication number
- CN116317110B CN116317110B CN202310077873.1A CN202310077873A CN116317110B CN 116317110 B CN116317110 B CN 116317110B CN 202310077873 A CN202310077873 A CN 202310077873A CN 116317110 B CN116317110 B CN 116317110B
- Authority
- CN
- China
- Prior art keywords
- scheduling
- module
- power grid
- decision
- intelligent
- 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
Abstract
The invention belongs to the field of power grid operation analysis, and discloses a power grid dispatching operation previewing method and system considering source load bilateral fluctuation; the system comprises: the intelligent deduction module of the dispatching operation is used for generating a running section of the basic power grid and acquiring dispatching operation setting data, faults and fault occurrence conditions; performing time-period-by-time analog simulation on the running section of the basic power grid to obtain a tide result; the scheduling decision intelligent agent module is used for providing an online decision model for the simulation of the scheduling operation intelligent deduction module; and the knowledge model management module is used for providing scheduling knowledge for the scheduling operation intelligent deduction module and the scheduling decision agent module. The invention introduces reinforcement learning technology to realize intelligent deduction and deduction of the power grid operation trend in the whole scheduling operation process under the background of source load bilateral uncertainty, optimizes the scheduling operation scheme and operation flow, and realizes intelligent deduction and deduction of the power grid scheduling operation; the invention can assist the dispatch operator to better avoid the system risk.
Description
Technical Field
The invention belongs to the field of power grid operation analysis, and particularly relates to a power grid dispatching operation previewing method and system considering source load bilateral fluctuation.
Background
With the centralized grid connection of large-scale new energy and the distributed access of large-scale high-permeability new energy, uncertainty of prediction errors of a source side and a load side is caused, difficulty in analysis of power grid operation trend is remarkably increased, and power grid dispatching operation faces unprecedented challenges. In addition, as the power market reforms continuously deeply and perfectly, the power grid regulation and control operation enters a safe and economical and repeated mode, so that the power grid margin is reduced, the power outage window period is shortened, the operation boundary is complicated, and the requirements on compliance, transparency and lean of regulation operation are objectively improved.
Aiming at the complex situations of high-proportion access of new energy and distributed power sources, enhanced source load bilateral volatility and uncertainty, enhanced system operation trend variability and uncertainty and the like, the practical problem of potential safety hazard for regulating and controlling operation is solved. The traditional power grid scheduling operation previewing method mainly realizes power grid overhaul plan time period scheduling operation based on a deterministic system operation mode, tide calculation and other methods, meets the supply and demand balance of a system power supply and a load side, and is difficult to meet the huge influence and potential risk calculation requirements of uncertainty factors generated by source load bilateral fluctuation caused by increasingly-growing new energy grid connection and adjustable load on power grid scheduling.
Disclosure of Invention
The invention aims to provide a power grid dispatching operation previewing method and system considering source load bilateral fluctuation, so as to solve the technical problems.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, the present invention provides a power grid dispatching operation previewing system considering source load bilateral fluctuation, including:
the intelligent deduction module of the dispatching operation is used for generating a basic power grid operation section containing source load bilateral fluctuation information, and acquiring dispatching operation setting data, faults and fault occurrence conditions, an online decision model and dispatching knowledge; performing time-period-by-time analog simulation on the running section of the basic power grid to obtain a tide result;
the scheduling decision agent module is used for providing an online decision model for the simulation of the scheduling operation intelligent deduction module according to scheduling knowledge;
and the knowledge model management module is used for providing scheduling knowledge for the scheduling operation intelligent deduction module and the scheduling decision agent module.
The invention is further improved in that: the scheduling operation intelligent deduction module comprises a basic operation section generation module, a scheduling operation setting module, an expected fault setting module and a scheduling operation simulation deduction module;
The basic operation section generation module is used for acquiring power grid operation sections and scheduling plan data according to the scene and time set by a user to form corresponding basic power grid operation sections containing source load bilateral fluctuation information;
the dispatching operation setting module is used for acquiring power grid model data and providing a power grid equipment list for a user to set dispatching operation;
the expected fault setting module is used for acquiring power grid model data and providing the power grid model data for a user to set faults and fault occurrence conditions;
and the scheduling operation simulation deduction module is used for performing time-period simulation on the running section of the basic power grid according to the acquired scheduling operation setting data, the fault and fault occurrence conditions, the online decision model and the scheduling knowledge, and obtaining a tide result.
The invention is further improved in that: the scheduling decision-making agent module comprises a reinforcement learning training module and a scheduling decision-making agent module;
the reinforcement learning training module is used for acquiring historical operation, monitoring, planning and prediction data required by training, and constructing training samples for decision making under the conditions of medium-long maintenance, equipment operation and equipment failure through a simulator aiming at the set time dimension and the concerned problems; acquiring data of a security control model, a stability rule, an overhaul rule and an accident plan from scheduling knowledge of a knowledge model management module, and providing a calculation model for intelligent agent action simulation and intelligent agent rewarding function construction; based on a power grid operation data training sample, taking unit output adjustment and equipment start-stop as action spaces, taking unit constraint, network constraint and balance constraint as conditions, taking scheduling operation knowledge and an optimization algorithm as heuristic guidance, taking a power grid safety low-carbon quantification index of equipment load rate and new energy consumption as evaluation, constructing a corresponding sample, a decision model and a reward function according to a set scheduling operation scene, performing data interaction with a power grid operation simulation simulator, performing scheduling operation simulation agent training, and obtaining a scheduling decision agent module.
The invention is further improved in that: the scheduling decision-making agent module comprises a real-time operation scheduling decision-making agent, an ultra-short-term risk prevention scheduling operation agent and an overhaul period optimization agent;
the intelligent scheduling and decision-making agent, the intelligent scheduling and operation agent for ultra-short-term risk prevention or the maintenance period optimization agent are operated in real time and are used for receiving the decision instruction and the power grid operation section data sent by the intelligent scheduling and operation deduction module, generating a decision result on line and then feeding back to the intelligent scheduling and operation deduction module for performing the operation deduction after the decision.
The invention is further improved in that: the scheduling decision-making agent module also comprises a training and decision-making process monitoring module;
the training and decision process monitoring module is used for managing the training process of the intelligent body, starting or stopping training the intelligent body, and checking one or more of training time, duration, rotation, convergence curve, state space and strategy table of the intelligent body.
The invention is further improved in that: the knowledge model management module comprises a steady operation rule management module, a security policy management module, an accident electronic plan management module and a maintenance plan arrangement knowledge management module;
The stable operation rule management module, the security policy management module, the accident electronic plan management module and the maintenance plan arrangement knowledge management module are respectively used for managing the dispatching knowledge of the stable operation rule, the security policy, the accident electronic plan and the maintenance plan arrangement.
In a second aspect, the present invention provides a method for predicting grid dispatching operations in consideration of source load bilateral fluctuation, including:
generating a basic power grid operation section containing source load bilateral fluctuation information; generating an online decision model according to the scheduling knowledge;
acquiring scheduling operation setting data, faults and fault occurrence conditions, an online decision model and scheduling knowledge; and performing time-period-by-time analog simulation on the running section of the basic power grid to obtain a tide result.
The invention is further improved in that: the generating of the basic power grid operation section specifically comprises the following steps: acquiring power grid operation sections and scheduling plan data according to scenes and time set by a user to form corresponding basic power grid operation sections containing source load bilateral fluctuation information; the scheduling operation setting data are obtained by performing scheduling operation setting by a user according to a power grid equipment list in the power grid model data; the faults and the fault occurrence conditions are obtained by setting the faults and the fault occurrence conditions according to the power grid model data by a user.
The invention is further improved in that: the online decision model is generated by a scheduling decision agent module; the scheduling decision-making agent module comprises a reinforcement learning training module and a scheduling decision-making agent module;
the reinforcement learning training module is used for acquiring historical operation, monitoring, planning and prediction data required by training, and constructing training samples for decision making under the conditions of medium-long maintenance, equipment operation and equipment failure through a simulator aiming at the set time dimension and the concerned problems; acquiring data of a security control model, a stability rule, an overhaul rule and an accident plan from scheduling knowledge of a knowledge model management module, and providing a calculation model for intelligent agent action simulation and intelligent agent rewarding function construction; based on a power grid operation data training sample, taking unit output adjustment and equipment start-stop as action spaces, taking unit constraint, network constraint and balance constraint as conditions, taking scheduling operation knowledge and an optimization algorithm as heuristic guidance, taking a power grid safety low-carbon quantification index of equipment load rate and new energy consumption as evaluation, constructing a corresponding sample, a decision model and a reward function according to a set scheduling operation scene, performing data interaction with a power grid operation simulation simulator, performing scheduling operation simulation agent training, and obtaining a scheduling decision agent module.
The invention is further improved in that: the scheduling decision-making agent module comprises a real-time operation scheduling decision-making agent, an ultra-short-term risk prevention scheduling operation agent and an overhaul period optimization agent;
the intelligent scheduling and decision-making agent, the intelligent scheduling and operation agent for ultra-short-term risk prevention or the maintenance period optimization agent are operated in real time and are used for receiving the decision instruction and the power grid operation section data sent by the intelligent scheduling and operation deduction module, generating a decision result on line and then feeding back to the intelligent scheduling and operation deduction module for performing the operation deduction after the decision.
The invention is further improved in that: the scheduling decision-making agent module also comprises a training and decision-making process monitoring module;
the training and decision process monitoring module is used for managing the training process of the intelligent body, starting or stopping training the intelligent body, and checking one or more of training time, duration, rotation, convergence curve, state space and strategy table of the intelligent body.
The invention is further improved in that: the knowledge model management module comprises a steady operation rule management module, a security policy management module, an accident electronic plan management module and a maintenance plan arrangement knowledge management module;
The stable operation rule management module, the security policy management module, the accident electronic plan management module and the maintenance plan arrangement knowledge management module are respectively used for managing the dispatching knowledge of the stable operation rule, the security policy, the accident electronic plan and the maintenance plan arrangement.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a power grid dispatching operation deduction method and a power grid dispatching operation deduction system considering source load bilateral fluctuation, which are based on big data and artificial intelligence technology, realize the quantification of uncertainty factors, introduce reinforcement learning technology to realize the intelligent deduction and deduction of power grid operation trend in the whole dispatching operation process under the source load bilateral uncertainty background, optimize dispatching operation scheme and operation flow, and realize the intelligent deduction and deduction of power grid dispatching operation; the invention can assist the dispatch operator to better avoid the system risk.
The invention solves the problems that the running trend of the power grid is complex and changeable due to the high-permeability new energy with strong randomness and volatility, and the planned operation risk is increased, and can optimize the operation period and reduce the planned operation risk according to the fluctuation condition of the new energy. In order to cope with the fluctuation of new energy, the scheduling adjustment frequency and difficulty of the traditional power supply are increased, and the system can optimize the power generation plan, stabilize the fluctuation of the new energy, reduce the problems of wind abandoning, light abandoning and the like.
The randomness and fluctuation of the two sides of the source load increase the difficulty of prediction and the uncertainty of a prediction error, so that the variability and uncertainty of the running trend of the power grid are caused, and the regulating pressure of the traditional power supply of the power grid and the frequency of the dispatching operation of the power grid are increased. The invention is based on big data and artificial intelligence technology, and realizes intelligent deduction of scheduling operation under the influence of double-side uncertainty factors of a power supply side and a load side.
The existing dispatching operation depends on the traditional deterministic analysis method and dispatching experience, the influence of source load double-side uncertainty is not quantified, the operation scheme cannot be quantitatively analyzed and optimized, the problem of operation risks is avoided, and the problem of adjustment and dispatching operation of a tide overrun unit is solved by the traditional optimization algorithm. The system designed by the invention introduces reinforcement learning technology to realize intelligent deduction and deduction of the power grid operation trend in the whole scheduling operation process under the background of source load double-side uncertainty, and optimize the scheduling operation scheme and operation flow.
The invention considers that the power spot market reduces the operation margin of the power grid, improves the compliance, transparency and lean requirements of the dispatching operation, and accurately previews the power grid and the whole dispatching operation process of the power grid. And big data and artificial intelligence technology play a good role in processing uncertainty, have potential to deal with the influence of the uncertainty of the two sides of the power grid source load on the power grid, and particularly reinforcement learning has specific technical advantages in processing and environment interaction type problems. The system reduces the difficulty of power grid dispatching operation under the background of high-proportion new energy consumption and electric power spot market.
Based on large electric power data such as weather, disasters, real-time modes, massive historical operation information and the like, the large data analysis and artificial intelligence technology is applied to high-precision prediction of the double-side uncertainty operation trend of the source load, an accurate source load operation situation is provided for power grid dispatching operation prediction, and under the background of the double-side high uncertainty of the source load, the intelligent method is explored and introduced to realize intelligent prediction of the dispatching operation and intelligent deduction of the dispatching operation, so that the risk of power grid regulation and control operation is reduced. The upgrade construction of the large power grid regulation system integrates the large power data information including weather live, typhoon disasters, operation information and the like, and creates good data base conditions for further introducing large data and exploring and improving the analysis capability of the traditional power system by an artificial intelligence method.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
FIG. 1 is a block diagram of a power grid scheduling operation previewing system considering source load bilateral fluctuation;
fig. 2 is a general flow chart of a method for predicting grid dispatching operation in consideration of source load double-sided fluctuation.
Fig. 3 is a schematic structural diagram of an electronic device according to the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings in connection with embodiments. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
The following detailed description is exemplary and is intended to provide further details of the invention. Unless defined otherwise, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the invention.
Example 1
The invention provides a power grid dispatching operation previewing system considering source load bilateral fluctuation, which is used for acquiring source load fluctuation trend analysis results in the day-ahead and day-ahead stages, carrying out simulation deduction aiming at a day-ahead maintenance plan, day-ahead dispatching operation, various faults, day-ahead and day-ahead power grid operation conditions, intuitively displaying the state change of a continuous operation process of a power grid under different scenes, prompting possible operation risks, starting intelligent decision aiming at the operation risks, and giving risk prevention and control decision results comprehensively considering security control strategies, operation regulations and accident plan related rules. And acquiring medium-long term new energy and load prediction and medium-long term maintenance plan data, carrying out power grid operation condition simulation deduction day by day aiming at the medium-long term maintenance plan, prompting possible operation risks day by day, starting intelligent decision aiming at the operation risks, and giving out risk prevention and control decision results considering scheduling rules such as maintenance rules, operation regulations and the like. The source load fluctuation trend analysis result is provided by a data input module, and power grid operation prediction data or trend analysis data of a power source side and a load side are used as part of input data of the system.
Referring to fig. 1, the present invention provides a power grid dispatching operation previewing system considering source load bilateral fluctuation, comprising 3 sub-modules: scheduling operation intelligent deduction module, scheduling decision agent module, and knowledge model management module:
the intelligent deduction module of the dispatching operation is used for generating a basic power grid operation section containing source load bilateral fluctuation information, and acquiring dispatching operation setting data, faults and fault occurrence conditions, an online decision model and dispatching knowledge; and performing time-period-by-time analog simulation on the running section of the basic power grid to obtain a tide result. The scheduling operation intelligent deduction module comprises a basic operation section generation module, a scheduling operation setting module, an expected fault setting module and a scheduling operation simulation deduction module. The basic operation section generation module is used for acquiring the latest power grid operation section and scheduling plan data from the data extraction and processing module according to the scene and time set by the user to form a corresponding basic power grid operation section containing source load double-side fluctuation information; the dispatching operation setting module is used for acquiring power grid model data from the data extraction and processing module and providing a power grid equipment list for a user to set dispatching operation; the expected fault setting module is used for acquiring power grid model data from the data platform and setting faults and fault occurrence conditions by a user; the scheduling operation simulation deduction module is used for performing time-period simulation on the running section of the basic power grid according to the acquired scheduling operation setting data, fault and fault occurrence conditions, the online decision model and scheduling knowledge, and storing a trend result obtained by analysis into the data extraction and processing module. And the extraction and processing module stores the latest power grid operation section, scheduling plan data and model data.
And the scheduling decision agent module is used for providing an online decision model for the simulation of the scheduling operation intelligent deduction module according to scheduling knowledge. The scheduling decision-making agent module comprises a reinforcement learning training module, a scheduling decision-making agent module and a training and decision-making process monitoring module, and three agents of maintenance planning, power grid ultra-short-term running risk prevention and power grid real-time scheduling risk prevention are finally constructed.
The reinforcement learning training module is used for acquiring historical operation, monitoring, planning and prediction data (in a specific embodiment, the reinforcement learning training module comprises a basic power grid operation section, historical power grid historical operation data, a historical maintenance plan, a historical equipment fault and a historical power generation plan which are generated by the basic operation section generation module and comprise source load bilateral fluctuation information), and aiming at the problems focused on different time dimensions, training samples for decision making under various scenes such as medium and long time maintenance, equipment operation and equipment fault are constructed through a simulator; acquiring data of a security control model, a stability rule, an overhaul rule and an accident plan from a knowledge model management module, and providing a calculation model for intelligent agent action simulation and intelligent agent rewarding function construction; the scheduling decision agent trains samples based on power grid mass operation data, takes unit output adjustment and equipment start and stop as action spaces, takes unit constraint, network constraint and balance constraint as conditions, takes scheduling operation knowledge and an optimization algorithm as heuristic guidance, takes power grid safety low-carbon quantization indexes of equipment load rate and new energy consumption as evaluation, constructs corresponding samples, decision models and rewarding functions according to different scheduling operation scenes, performs data interaction with a power grid operation simulation simulator, and performs scheduling operation simulation agent training to obtain a scheduling decision agent module.
The power grid operation simulation simulator adopts a power flow calculation service to provide a power flow simulator for power grid model deduction and intelligent body training. The tide calculation function is used for providing three modes of using modes of a tide calculation API of a standard interface, a tide calculation executable command and a tide calculation service for a system developer and a dispatching user. The service developer or the function user should reasonably select the use mode of the tide computing function according to the own requirements. The power grid operation simulation simulator uses a basic power grid operation section containing source-load double-side fluctuation information, carries out load flow calculation simulation according to the designated time of an operator and the regulation and control operation instruction generated by the scheduling decision agent in different scenes, and judges whether the regulation and control requirement threshold value is met or not, so that a simulation result is obtained. The simulation result can be used for carrying out power grid risk evolution process and trend analysis, planning operation risk prevention and control, scheduling behavior simulation deduction, power grid risk point and decision-making auxiliary analysis and the like.
The scheduling decision agent module comprises a real-time operation scheduling decision agent, an ultra-short-term risk prevention scheduling operation agent and an overhaul period optimization agent, which are online decision models generated after offline training of the reinforcement learning training module, and interact with the scheduling operation intelligent deduction module. The method comprises the steps of receiving a decision instruction and power grid operation section data sent by a scheduling operation intelligent deduction module, generating a decision result on line, feeding back the decision result to the scheduling operation intelligent deduction module to conduct decision operation deduction, and intuitively displaying an improvement effect on power grid operation after a relevant strategy is adopted to a user.
The training and decision process monitoring module is used for managing the training process of the intelligent agents, starting and stopping training the intelligent agents, checking the latest training time, time length, rotation, convergence curve, state space and strategy table of the three intelligent agents, and facilitating the user to master the training condition and running performance of the intelligent agents.
The knowledge model management module comprises a steady operation rule management module, a security policy management module, an accident electronic plan management module and a maintenance plan scheduling knowledge management module, and is used for acquiring imported or entered scheduling knowledge and providing the imported or entered scheduling knowledge for the reinforcement learning training module, the scheduling decision agent module and the scheduling operation intelligent deduction module. The scheduling knowledge comprises stable operation rules, security control strategies, accident electronic plans and maintenance planning knowledge. The stable operation rule management module, the security policy management module, the accident electronic plan management module and the maintenance plan arrangement knowledge management module are respectively used for managing the stable operation rule, the security policy, the accident electronic plan and the maintenance plan arrangement knowledge.
The invention relates to input and output data of a power grid dispatching operation previewing system considering source load bilateral fluctuation, which comprises the following steps of:
1. Intelligent deduction module for scheduling operation
1) Basic operation section generating module
And obtaining corresponding power grid model, operation, prediction and planning data according to the simulation deduction scene set by the user, and generating a basic power grid operation section in the middle-long term, day-ahead, day-in and real-time multiple scenes.
Basic operation section generation module input:
a) Acquiring external environment information, including: external conventional weather and disaster information, grid source load uncertainty information and grid information. The above information may take into account multiple time scales such as historical data, live or real-time running information, and predicted or future state data information.
Among other things, conventional weather and disaster information includes: actual measurement data, forecast data and historical data of meteorological parameters; the meteorological parameters include: temperature, humidity, air pressure, wind, rain, thunder, forest fire, ice coating, typhoon.
b) Grid source load uncertainty information, including: grid power source side operation data and grid load side operation data; the power grid power supply side operation data comprises: one or more of distributed power supply and intermittent new energy sources; the power grid load side operation data includes: impact load, compliant load, and conventional load information.
c) Grid information, including: grid operation information, grid prediction information and grid historical operation section data. The power grid operation information includes: one or more of system model information, measurement information and real-time operation data of equipment fault information. The power grid prediction information includes: prediction data of short-term and ultra-short-term new energy prediction results, short-term and ultra-short-term system load prediction results, daily unit plans and maintenance plans. The historical operation section data of the power grid comprises: one or more of grid history model information, history measurement information, out-of-limit information, scheduling operation information, equipment fault data, and typical historical fault operation information.
And outputting by a basic operation section generating module: the medium-long term, day-ahead, day-in, real-time basic power grid operation section containing source load bilateral fluctuation information.
2) Scheduling operation setting module
The method is used for setting the line needing simulation deduction, the switching state of the unit and the power adjustment of the unit.
Scheduling operation setting module input: grid model, user set operational information (time, device name, device switching and power adjustment).
Scheduling operation setting module output: device operation information.
3) Expected failure setting module
For setting the expected faults that need to be deduced by simulation.
The expected fault setting module inputs: grid model, user defined fault information (device name, start-up conditions).
The expected fault setting module outputs: failure information is envisioned.
4) Simulation deduction module for scheduling operation
The method is used for acquiring scheduling operation information or intelligent decision information, and simulating the running condition of the power grid in a continuous period by adopting a stable and efficient tide algorithm.
Scheduling operation simulation deduction module input: medium-long term, day-ahead, day-in, real-time power grid basic operation section, short-term and ultra-short-term new energy probability prediction results, short-term and ultra-short-term system load probability prediction results, equipment operation information, expected fault information, security control strategies, stability rules, stability section definition and quota, and agent decision;
and (3) outputting by a scheduling operation simulation deduction module: the method comprises the steps of a unit, a line, a transformer, a stable section basic power flow result, a simulated operation power flow result considering source load fluctuation, simulated operation out-of-limit information considering source load fluctuation, simulated operation risk prevention and control decision considering source load fluctuation and medium-long-term maintenance planning result.
2. Scheduling decision agent
1) Reinforced learning training module
And the reinforcement learning training module performs offline training on the scheduling decision agents, and establishes three agents including maintenance planning, power grid ultra-short-term operation risk prevention and power grid real-time scheduling risk prevention.
Reinforcement learning training module input: grid operation section, historical grid historical operation data, historical overhaul plan, historical equipment faults, historical power generation plan, stability control strategy, stability operation rule, overhaul rule and accident plan.
Reinforcement learning training module output: and (3) scheduling maintenance, ultra-short-term running risk prevention of the power grid and real-time scheduling decision-making intelligent body of the power grid.
2) Scheduling decision agent
And carrying out online decision on the running risk found by the simulation deduction of the scheduling operation, and giving out a power grid scheduling strategy for preventing and eliminating the risk. Introducing an artificial intelligent analysis theory (reinforcement learning method), constructing a scheduling behavior intelligent agent according to input data, taking a series of power grid scheduling control decision steps of a power grid operation simulator considering source load bilateral uncertainty as actions, performing system state observation and monitoring through power grid measurement, performing power grid state quantitative evaluation as evaluation rewards of the power grid scheduling control decision steps or feeding the evaluation rewards back to the scheduling behavior intelligent agent, and circulating the data learning mechanism until a scheduling decision model meeting system operation conditions is generated.
The input of the module is external environment and disaster information, source-load double-side uncertainty data and power grid operation information.
The output of the module is a scheduling decision model based on artificial intelligence (reinforcement learning).
Input: deducing risk information, deducing an analysis operation section and deducing operation information;
and (3) outputting: and (3) a unit adjustment strategy and a maintenance plan adjustment strategy.
3) Monitoring module for training and decision process
For setting the expected faults that need to be deduced by simulation.
Input: agent training time, iteration turns, status, rewards value, status space, policy space.
3. Knowledge model management
The method is used for importing or inputting various scheduling knowledge by a user and is used for constructing rewarding functions and operation constraints by scheduling decision-making agents.
Knowledge model management input: stable operation rules, security control strategies, accident electronic plans, and scheduling control operation knowledge of maintenance planning.
Knowledge model management output: stable section limit, safety control model, adjustable unit and load and maintenance constraint criterion.
4. The data extraction and processing module is used for providing data support for data perception, data integration, data storage, data identification and data calculation, and is also used for supporting data application of the webpage terminal and the mobile terminal. The data extraction and processing module is used for carrying out format unification on the external environment information acquired by the data acquisition module, so that external environment and disaster information and source load uncertainty access power grid data and power grid operation information with the unified format can be provided.
According to the invention, new energy power generation and distributed power supply load power prediction are adopted, prediction error uncertainty is analyzed, the daily operation trend of the power grid is accurately predicted, and a data base is provided for power grid trend analysis.
The invention establishes a scheduling operation knowledge model, carries out simulation training by utilizing massive historical operation data of the power grid based on reinforcement learning and other technologies, constructs scheduling decision behavior intelligent agents and intelligently simulates scheduling operation behaviors.
The invention realizes the whole process preview of the dispatching operation and the power grid operation, simulates the power grid trend change in a designated time period in a sand table deduction mode, and perfects the simulation means for regulating and controlling the operation business scene.
The method can solve the problems of uncertain analysis results and high risk of the dispatching operation caused by the uncertainty of the two sides of the source load for the power grid with rich new energy resources, optimize the dispatching operation scheme, reduce the risk of the dispatching operation, improve the level of the regulation operation, and can be used for field deployment based on platforms such as intelligent dispatching control systems of different types of power grids. Meanwhile, uncertainty of two sides of a source load is changed into certainty, stable operation of the electric power spot market is supported, and applicability and popularization are strong.
The invention combines the actual dispatching operation engineering of the large power grid, prospectively introduces an artificial intelligence method, breaks the limitation of traditional system deterministic analysis and calculation, and has very wide application and popularization prospects.
The invention is based on the introduction of big data and artificial intelligence (reinforcement learning) technology, can improve the limitation of the traditional method through a data driving means, and the scheduling operation condition of the target period of the simulation deduction is fed back to the regulation personnel in advance for reference, thereby reducing the potential operation risk.
Example 2
The invention provides a power grid dispatching operation previewing method considering source load bilateral fluctuation, which comprises the following steps:
generating a basic power grid operation section, and acquiring scheduling operation setting data, faults and fault occurrence conditions, an online decision model and scheduling knowledge; and performing time-period-by-time analog simulation on the running section of the basic power grid to obtain a tide result.
In one embodiment: the generating of the basic power grid operation section specifically comprises the following steps: acquiring power grid operation sections and scheduling plan data according to scenes and time set by a user to form corresponding basic power grid operation sections containing source load bilateral fluctuation information; the scheduling operation setting data are obtained by performing scheduling operation setting by a user according to a power grid equipment list in the power grid model data; the faults and the fault occurrence conditions are obtained by setting the faults and the fault occurrence conditions according to the power grid model data by a user.
In one embodiment: the online decision model is generated by a scheduling decision agent module; the scheduling decision-making agent module comprises a reinforcement learning training module and a scheduling decision-making agent module;
the reinforcement learning training module is used for acquiring historical operation, monitoring, planning and prediction data required by training, and constructing training samples for decision making under the conditions of medium-long maintenance, equipment operation and equipment failure through a simulator aiming at the set time dimension and the concerned problems; acquiring data of a security control model, a stability rule, an overhaul rule and an accident plan from a knowledge model management module, and providing a calculation model for intelligent agent action simulation and intelligent agent rewarding function construction; based on a power grid operation data training sample, taking unit output adjustment and equipment start-stop as action spaces, taking unit constraint, network constraint and balance constraint as conditions, taking scheduling operation knowledge and an optimization algorithm as heuristic guidance, taking a power grid safety low-carbon quantification index of equipment load rate and new energy consumption as evaluation, constructing a corresponding sample, a decision model and a reward function according to a set scheduling operation scene, performing data interaction with a power grid operation simulation simulator, performing scheduling operation simulation agent training, and obtaining a scheduling decision agent module.
In one embodiment: the scheduling decision-making agent module comprises a real-time operation scheduling decision-making agent, an ultra-short-term risk prevention scheduling operation agent and an overhaul period optimization agent; the intelligent scheduling and decision-making agent, the intelligent scheduling and operation agent for ultra-short-term risk prevention or the maintenance period optimization agent are operated in real time and are used for receiving the decision instruction and the power grid operation section data sent by the intelligent scheduling and operation deduction module, generating a decision result on line and then feeding back to the intelligent scheduling and operation deduction module for performing the operation deduction after the decision.
In one embodiment: the scheduling decision-making agent module also comprises a training and decision-making process monitoring module; the training and decision process monitoring module is used for managing the training process of the intelligent body, starting or stopping training the intelligent body, and checking one or more of training time, duration, rotation, convergence curve, state space and strategy table of the intelligent body.
In one embodiment: the scheduling knowledge is stored in a knowledge model management module; the knowledge model management module comprises a steady operation rule management module, a security policy management module, an accident electronic plan management module and a maintenance plan arrangement knowledge management module; the stable operation rule management module, the security policy management module, the accident electronic plan management module and the maintenance plan arrangement knowledge management module are respectively used for managing the stable operation rule, the security policy, the accident electronic plan and the maintenance plan arrangement knowledge.
Example 3
Referring to fig. 2, the power grid dispatching operation previewing system considering source load bilateral fluctuation can be applied to scenes such as real-time dispatching, ultra-short term prevention control and maintenance planning in the daytime. The following is exemplified by an embodiment of the service planning.
Setting a scene of the selected target deduction as a maintenance planning scene, setting a maintenance time period of the target deduction, and acquiring basic section information related to calculation deduction. On the basis, the maintenance planning and arrangement agent is obtained through reinforcement learning training, and the data base of the agent training comprises the basic section information and the scene, namely, a knowledge model related to the maintenance planning and arrangement scene. And finally, calculating an optimal operation period through a power grid operation simulation simulator to obtain an optimized maintenance plan operation period. The following is a specific content example of each part, referring to fig. 2, the invention also provides a power grid dispatching operation previewing method considering source load bilateral fluctuation, comprising the following steps:
the scheduling operation setting module sets a target deduction period: the period selection may be selecting a mid-long term, day-ahead scenario; and selecting deduction time and setting a specific time period. Medium-long term maintenance schedule setting: the multi-day maintenance plan to be deduced can be set, and a plurality of devices for maintenance can be placed in the same maintenance group for naming and saving, and the deduction is carried out according to the maintenance group. Equipment such as lines, transformers, buses, units and the like can be added in the overhaul group, and overhaul start dates and overhaul stop dates of the equipment are respectively set. Setting a daily maintenance plan: the maintenance schedule within 1 day to be deduced can be set, equipment such as lines, transformers, buses, units and the like can be added, and the maintenance starting period and the maintenance stopping period of the equipment are respectively set.
The basic operation section generation module is used for preparing basic section data: and acquiring the latest power grid operation section and scheduling plan data from the data extraction and processing module according to the scene and time set by the user to form a corresponding basic power grid operation section. In a specific embodiment, a massive historical full-network section file can be obtained from the data extraction and processing module, and the massive historical full-network section file comprises a power grid model, parameters, remote signaling telemetry data and a ground state power flow calculation result. Intercepting a power grid model and data within a limited time of a certain province or region of a target, carrying out equivalence on a power grid boundary, extracting actual active power of a historical unit and a load, and taking the actual active power as sample data of power grid prediction and operation intelligent body training.
Reinforcement learning training module: (1) Constructing an overhaul plan, arranging an agent training sample, acquiring a historical multi-month continuous running section, calling a scheduling operation setting under a training sample construction function, changing a network topology structure by setting scheduling operation content and operation time period, calling a unit and load setting function, changing a unit and load power level, and calling a power grid operation simulation simulator to generate a tide section based on the changed network topology and power injection data. Meanwhile, historical maintenance plan, maintenance plan setting data deduced during medium-term maintenance and time setting are imported. And constructing a training sample library for arranging the intelligent agent in the medium-and-long-term maintenance plan, and enhancing the robustness of the intelligent agent in optimizing decisions.
(2) Importing an overhaul plan arranging agent training sample: and importing a training sample set constructed by a user, or directly importing a power grid operation section set generated by deduction of a historical overhaul plan and a medium-long-term overhaul plan and medium-long-term overhaul setting information.
(3) And (3) optimizing the training of the intelligent body in the overhaul period, based on the latest imported training sample, taking the unit output adjustment and equipment start-stop as an action space, taking unit constraint, network constraint and balance constraint as conditions, taking scheduling operation knowledge and an optimization algorithm as heuristic guidance, taking the low-carbon quantitative indexes of the power grid safety such as equipment load rate, new energy consumption and the like as evaluation, constructing a decision model and a reward function, performing data interaction with a power grid operation simulation module, and performing overhaul plan scheduling intelligent body training to obtain the trained overhaul plan scheduling intelligent body.
The maintenance schedule is arranged for monitoring the training process of the intelligent agent, and indexes such as the starting time, the ending time, the training progress, the average training time consumption of the training sample and the like of the training can be checked through the training and decision process monitoring module.
And the knowledge model management module acquires an electronic file of maintenance planning knowledge from the designated position, analyzes rules and stores the rules into the map database. And finishing overhaul plan programming knowledge input, manually inputting overhaul plan programming rules such as the same-stop equipment, the mutual exclusion equipment and the like by a user, and storing data input by the user into a graph database. The maintenance scheduling knowledge is checked, related maintenance scheduling knowledge information can be inquired, edited and deleted, and whether the maintenance scheduling knowledge is effective or not can be set.
And (3) deduction of maintenance plan: the scheduling operation simulation deduction module calculates to simulate deduction calculation on the current scheme, performs power flow analysis in time intervals, and gives power flow results of loads, units, lines, transformers and stable sections; if the power flow is out of limit in the deduction process, all the sections after deduction are sent to an agent scheduling decision module for decision making, and deduction is performed again after a unit adjustment strategy is obtained; and if the limit is still exceeded, sending the overhaul information and the basic tide section to a medium-long-term overhaul preparation intelligent agent for carrying out plan rearrangement, and carrying out result deduction after overhaul plan optimization after rearrangement. The result display can check the load, the unit, the line, the transformer and the tidal current results of the stable section after the base state, the original maintenance plan, the maintenance plan operation optimization and the maintenance plan time period optimization in the form of a table and a curve, and check the deduction result curve in a comparison way; the stable section and equipment out-of-limit information after the ground state, the original maintenance plan, the maintenance plan operation optimization and the maintenance plan time period optimization can be checked; the unit adjustment strategy corresponding to the maintenance schedule operation optimization and the maintenance schedule time period optimization can be checked through tables and curves, and the equipment maintenance starting time after the maintenance schedule time period optimization can be checked.
Example 4
Referring to fig. 3, the present invention further provides an electronic device 100 for implementing the power grid scheduling operation previewing method considering source load bilateral fluctuation; the electronic device 100 comprises a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.
The memory 101 may be used to store the computer program 103, and the processor 102 implements the method steps of the grid dispatching operation predicting method described in embodiment 1 or 2, which considers source load double-sided fluctuation, by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data) created according to the use of the electronic device 100, and the like. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), at least one disk storage device, a Flash memory device, or other non-volatile solid state storage device.
The at least one processor 102 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The processor 102 may be a microprocessor or the processor 102 may be any conventional processor or the like, the processor 102 being a control center of the electronic device 100, the various interfaces and lines being utilized to connect various portions of the overall electronic device 100.
The memory 101 in the electronic device 100 stores a plurality of instructions to implement a grid scheduling operation previewing method considering source load double-sided fluctuations, the processor 102 being executable to implement:
generating a basic power grid operation section containing source load bilateral fluctuation information; generating an online decision model according to the scheduling knowledge;
acquiring scheduling operation setting data, faults and fault occurrence conditions, an online decision model and scheduling knowledge; and performing time-period-by-time analog simulation on the running section of the basic power grid to obtain a tide result.
Example 5
The modules/units integrated in the electronic device 100 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, and a Read-Only Memory (ROM).
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (6)
1. The utility model provides a power grid scheduling operation previewing system considering source load bilateral fluctuation which is characterized by comprising:
the intelligent deduction module of the dispatching operation is used for generating a basic power grid operation section containing source load bilateral fluctuation information, and acquiring dispatching operation setting data, faults and fault occurrence conditions, an online decision model and dispatching knowledge; performing time-period-by-time analog simulation on the running section of the basic power grid to obtain a tide result;
The scheduling decision agent module is used for providing an online decision model for the simulation of the scheduling operation intelligent deduction module according to scheduling knowledge;
the knowledge model management module is used for providing scheduling knowledge for the scheduling operation intelligent deduction module and the scheduling decision agent module;
the scheduling operation intelligent deduction module comprises a basic operation section generation module, a scheduling operation setting module, an expected fault setting module and a scheduling operation simulation deduction module;
the basic operation section generation module is used for acquiring power grid operation sections and scheduling plan data according to the scene and time set by a user to form corresponding basic power grid operation sections containing source load bilateral fluctuation information;
the dispatching operation setting module is used for acquiring power grid model data and providing a power grid equipment list for a user to set dispatching operation;
the expected fault setting module is used for acquiring power grid model data and providing the power grid model data for a user to set faults and fault occurrence conditions;
the scheduling operation simulation deduction module is used for performing time-period simulation on the running section of the basic power grid according to the acquired scheduling operation setting data, faults and fault occurrence conditions, the online decision model and scheduling knowledge, and obtaining a tide result;
The scheduling decision-making agent module comprises a reinforcement learning training module and a scheduling decision-making agent module;
the reinforcement learning training module is used for acquiring historical operation, monitoring, planning and prediction data required by training, and constructing training samples for decision making under the conditions of medium-long maintenance, equipment operation and equipment failure through a simulator aiming at the set time dimension and the concerned problems; acquiring data of a security control model, a stability rule, an overhaul rule and an accident plan from scheduling knowledge of a knowledge model management module, and providing a calculation model for intelligent agent action simulation and intelligent agent rewarding function construction; based on a power grid operation data training sample, taking unit output adjustment and equipment start-stop as action spaces, taking unit constraint, network constraint and balance constraint as conditions, taking scheduling operation knowledge and an optimization algorithm as heuristic guidance, taking a power grid safety low-carbon quantization index as evaluation, constructing a corresponding sample, a decision model and a reward function according to a set scheduling operation scene, performing data interaction with a power grid operation simulation simulator, and performing scheduling operation simulation agent training to obtain a scheduling decision agent module;
the knowledge model management module comprises a steady operation rule management module, a security policy management module, an accident electronic plan management module and a maintenance plan arrangement knowledge management module;
The stable operation rule management module, the security policy management module, the accident electronic plan management module and the maintenance plan arrangement knowledge management module are respectively used for managing the dispatching knowledge of the stable operation rule, the security policy, the accident electronic plan and the maintenance plan arrangement.
2. The grid scheduling operation previewing system considering source-load double-sided fluctuation according to claim 1, wherein the scheduling decision agent module comprises a real-time operation scheduling decision agent, an ultra-short-term risk prevention scheduling operation agent and an overhaul period optimization agent;
the intelligent scheduling and decision-making agent, the intelligent scheduling and operation agent for ultra-short-term risk prevention or the maintenance period optimization agent are operated in real time and are used for receiving the decision instruction and the power grid operation section data sent by the intelligent scheduling and operation deduction module, generating a decision result on line and then feeding back to the intelligent scheduling and operation deduction module for performing the operation deduction after the decision.
3. The grid dispatching operation previewing system considering source load double-sided fluctuation according to claim 1, wherein the dispatching decision agent module further comprises a training and decision process monitoring module;
the training and decision process monitoring module is used for managing the training process of the intelligent body, starting or stopping training the intelligent body, and checking one or more of training time, duration, rotation, convergence curve, state space and strategy table of the intelligent body.
4. The power grid dispatching operation previewing method considering source load bilateral fluctuation is characterized by comprising the following steps of:
generating a basic power grid operation section, and acquiring scheduling operation setting data, faults and fault occurrence conditions, an online decision model and scheduling knowledge; performing time-period-by-time analog simulation on the running section of the basic power grid to obtain a tide result;
the generating of the basic power grid operation section specifically comprises the following steps: acquiring power grid operation sections and scheduling plan data according to scenes and time set by a user to form corresponding basic power grid operation sections containing source load bilateral fluctuation information; the scheduling operation setting data are obtained by performing scheduling operation setting by a user according to a power grid equipment list in the power grid model data; the faults and the fault occurrence conditions are obtained by setting the faults and the fault occurrence conditions according to the power grid model data by a user;
the online decision model is generated by a scheduling decision agent module; the scheduling decision-making agent module comprises a reinforcement learning training module and a scheduling decision-making agent module;
the reinforcement learning training module is used for acquiring historical operation, monitoring, planning and prediction data required by training, and constructing training samples for decision making under the conditions of medium-long maintenance, equipment operation and equipment failure through a simulator aiming at the set time dimension and the concerned problems; acquiring data of a security control model, a stability rule, an overhaul rule and an accident plan from a knowledge model management module, and providing a calculation model for intelligent agent action simulation and intelligent agent rewarding function construction; based on a power grid operation data training sample, taking unit output adjustment and equipment start-stop as action spaces, taking unit constraint, network constraint and balance constraint as conditions, taking scheduling operation knowledge and an optimization algorithm as heuristic guidance, taking a power grid safety low-carbon quantification index of equipment load rate and new energy consumption as evaluation, constructing a corresponding sample, a decision model and a reward function according to a set scheduling operation scene, performing data interaction with a power grid operation simulation simulator, performing scheduling operation simulation agent training, and obtaining a scheduling decision agent module;
The scheduling decision-making agent module comprises a real-time operation scheduling decision-making agent, an ultra-short-term risk prevention scheduling operation agent and an overhaul period optimization agent; the intelligent scheduling and judging module is used for receiving the decision instruction and the power grid operation section data sent by the intelligent scheduling and judging module, generating a decision result on line and feeding back the decision result to the intelligent scheduling and judging module for carrying out operation judgment after decision;
the scheduling decision-making agent module also comprises a training and decision-making process monitoring module; the training and decision process monitoring module is used for managing the training process of the intelligent body, starting or stopping training the intelligent body, and checking one or more of training time, duration, rotation, convergence curve, state space and strategy table of the intelligent body;
the scheduling knowledge is stored in a knowledge model management module; the knowledge model management module comprises a steady operation rule management module, a security policy management module, an accident electronic plan management module and a maintenance plan arrangement knowledge management module; the stable operation rule management module, the security policy management module, the accident electronic plan management module and the maintenance plan arrangement knowledge management module are respectively used for managing the stable operation rule, the security policy, the accident electronic plan and the maintenance plan arrangement knowledge.
5. An electronic device comprising a processor and a memory, the processor configured to execute a computer program stored in the memory to implement the grid scheduling operation previewing method considering source load double-sided fluctuations according to claim 4.
6. A computer readable storage medium storing at least one instruction which when executed by a processor implements a grid scheduling operation previewing method according to claim 4 taking into account source load double side fluctuations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310077873.1A CN116317110B (en) | 2023-01-17 | Power grid dispatching operation previewing method and system considering source load bilateral fluctuation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310077873.1A CN116317110B (en) | 2023-01-17 | Power grid dispatching operation previewing method and system considering source load bilateral fluctuation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116317110A CN116317110A (en) | 2023-06-23 |
| CN116317110B true CN116317110B (en) | 2023-11-14 |
Family
ID=
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018059096A1 (en) * | 2016-09-30 | 2018-04-05 | 国电南瑞科技股份有限公司 | Combined decision method for power generation plans of multiple power sources, and storage medium |
| CN110994790A (en) * | 2019-12-04 | 2020-04-10 | 南京南瑞继保电气有限公司 | Enterprise power grid dispatching knowledge decision analysis system |
| CN112560227A (en) * | 2020-11-25 | 2021-03-26 | 国网河北省电力有限公司 | Simulation rehearsal method for power grid dispatching day-ahead plan |
| CN114219216A (en) * | 2021-11-16 | 2022-03-22 | 华南理工大学 | Operation scheduling method, system, device and medium for power system |
| CN114386256A (en) * | 2021-12-28 | 2022-04-22 | 国网浙江省电力有限公司电力科学研究院 | Regional electric heating system optimal scheduling method considering flexibility constraint of electric heating equipment and heat supply network characteristics |
| CN114626670A (en) * | 2022-01-25 | 2022-06-14 | 合肥工业大学 | Power grid dispatching rapid optimization method based on knowledge matrix cross-dimension migration |
| CN114744764A (en) * | 2022-04-25 | 2022-07-12 | 南方电网科学研究院有限责任公司 | Digital twin terminal, system and terminal control method for power distribution network |
| WO2022160705A1 (en) * | 2021-01-26 | 2022-08-04 | 中国电力科学研究院有限公司 | Method and apparatus for constructing dispatching model of integrated energy system, medium, and electronic device |
| CN114997566A (en) * | 2022-04-18 | 2022-09-02 | 国网辽宁省电力有限公司电力科学研究院 | Power grid blocking risk assessment method and system considering node connectivity loss |
| CN115241885A (en) * | 2022-07-26 | 2022-10-25 | 中国电力科学研究院有限公司 | Power grid real-time scheduling optimization method and system, computer equipment and storage medium |
| CN115293052A (en) * | 2022-09-01 | 2022-11-04 | 国家电网有限公司华北分部 | Power system active power flow online optimization control method, storage medium and device |
| CN115358558A (en) * | 2022-08-15 | 2022-11-18 | 云南电网有限责任公司玉溪供电局 | Real-time power grid state safety checking method based on digital preplan model |
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018059096A1 (en) * | 2016-09-30 | 2018-04-05 | 国电南瑞科技股份有限公司 | Combined decision method for power generation plans of multiple power sources, and storage medium |
| CN110994790A (en) * | 2019-12-04 | 2020-04-10 | 南京南瑞继保电气有限公司 | Enterprise power grid dispatching knowledge decision analysis system |
| CN112560227A (en) * | 2020-11-25 | 2021-03-26 | 国网河北省电力有限公司 | Simulation rehearsal method for power grid dispatching day-ahead plan |
| WO2022160705A1 (en) * | 2021-01-26 | 2022-08-04 | 中国电力科学研究院有限公司 | Method and apparatus for constructing dispatching model of integrated energy system, medium, and electronic device |
| CN114219216A (en) * | 2021-11-16 | 2022-03-22 | 华南理工大学 | Operation scheduling method, system, device and medium for power system |
| CN114386256A (en) * | 2021-12-28 | 2022-04-22 | 国网浙江省电力有限公司电力科学研究院 | Regional electric heating system optimal scheduling method considering flexibility constraint of electric heating equipment and heat supply network characteristics |
| CN114626670A (en) * | 2022-01-25 | 2022-06-14 | 合肥工业大学 | Power grid dispatching rapid optimization method based on knowledge matrix cross-dimension migration |
| CN114997566A (en) * | 2022-04-18 | 2022-09-02 | 国网辽宁省电力有限公司电力科学研究院 | Power grid blocking risk assessment method and system considering node connectivity loss |
| CN114744764A (en) * | 2022-04-25 | 2022-07-12 | 南方电网科学研究院有限责任公司 | Digital twin terminal, system and terminal control method for power distribution network |
| CN115241885A (en) * | 2022-07-26 | 2022-10-25 | 中国电力科学研究院有限公司 | Power grid real-time scheduling optimization method and system, computer equipment and storage medium |
| CN115358558A (en) * | 2022-08-15 | 2022-11-18 | 云南电网有限责任公司玉溪供电局 | Real-time power grid state safety checking method based on digital preplan model |
| CN115293052A (en) * | 2022-09-01 | 2022-11-04 | 国家电网有限公司华北分部 | Power system active power flow online optimization control method, storage medium and device |
Non-Patent Citations (3)
| Title |
|---|
| 多级智能电网调控***集中运维模式的探讨;邢颖;郎燕生;***;张印;王炤光;李丹;杨宁;安天瑜;;电力***保护与控制(第15期);148-154 * |
| 支撑一体化大电网的调度控制***架构及关键技术;许洪强;姚建国;於益军;汤必强;;电力***自动化(第06期);7-14 * |
| 考虑荷源双侧不确定性的跨区域灵活性鲁棒优化运行策略;李笑竹;王维庆;王海云;武家辉;徐其丹;常鹏;;高电压技术(第05期);84-95 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108736465B (en) | Future-state power grid model construction method and device | |
| Kamalinia et al. | Security-constrained expansion planning of fast-response units for wind integration | |
| CN110543697B (en) | Electric power market simulation running system | |
| CN110222924B (en) | Multi-mode urban rail transit station passenger flow control system and control method | |
| CN109145362A (en) | A kind of power network modeling method and system | |
| CN104463465A (en) | Real-time monitoring cluster processing method based on distributed models | |
| CN112260322A (en) | Source network load storage simulation platform, method and system | |
| CN115528749A (en) | Real-time market and power grid dispatching joint deduction method, system, equipment and medium | |
| Shendryk et al. | Decision making for energy management in smart grid | |
| CN111798088A (en) | Power grid dispatching method and system | |
| CN109670863A (en) | A kind of power supply company's scale of investment optimization method and calculate equipment | |
| CN116599160B (en) | Active sensing method and system for new energy station cluster and new energy station | |
| CN116317110B (en) | Power grid dispatching operation previewing method and system considering source load bilateral fluctuation | |
| CN116317110A (en) | Power grid dispatching operation previewing method and system considering source load bilateral fluctuation | |
| CN116029412A (en) | Power distribution network plan power outage execution tracking and optimization decision method | |
| CN116011722A (en) | Large power grid-oriented man-machine cooperation regulation and control method, module and device | |
| CN111339664B (en) | Layer-by-layer load modeling method and system based on edge calculation | |
| CN107942721A (en) | A kind of emulation mode and system of supporting scheduling system to verify | |
| Gianluigi et al. | The innovative FlexPlan methodology to reap the benefits of including storage and load flexibility in grid planning: methodology and regional study cases | |
| Istanbullu et al. | BIM Digital twins environment to enhance construction process | |
| Kang et al. | Distributed plug-in electric vehicles charging strategy considering driver behaviours and load constraints | |
| Kalantayevskaya et al. | Design of decision-making support system in power grid dispatch control based on the forecasting of energy consumption | |
| CN110188898A (en) | A kind of power distribution network Dispatching intelligent tickets system and method based on line chart | |
| CN115983435B (en) | Cross-provincial electric energy market feasibility domain optimization method and system | |
| CN114330563B (en) | Power dispatching plan generation method, equipment and medium based on GAN model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |