CN111401731A - Risk control aid decision-making method and system based on artificial intelligence learning - Google Patents
Risk control aid decision-making method and system based on artificial intelligence learning Download PDFInfo
- Publication number
- CN111401731A CN111401731A CN202010174624.0A CN202010174624A CN111401731A CN 111401731 A CN111401731 A CN 111401731A CN 202010174624 A CN202010174624 A CN 202010174624A CN 111401731 A CN111401731 A CN 111401731A
- Authority
- CN
- China
- Prior art keywords
- risk
- power
- control
- load
- power grid
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000012954 risk control Methods 0.000 title claims abstract description 75
- 238000013473 artificial intelligence Methods 0.000 title claims description 35
- 230000009467 reduction Effects 0.000 claims abstract description 38
- 238000012502 risk assessment Methods 0.000 claims abstract description 13
- 230000005540 biological transmission Effects 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 20
- 238000011084 recovery Methods 0.000 claims description 19
- 238000009826 distribution Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000011217 control strategy Methods 0.000 claims description 9
- 230000002265 prevention Effects 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 6
- 230000003449 preventive effect Effects 0.000 claims description 4
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims 2
- 239000002994 raw material Substances 0.000 claims 2
- 238000007726 management method Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Power Engineering (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a risk control aid decision method and a system based on artificial learning, comprising a master control module, a risk control module and a risk control module, wherein the master control module constructs an operation risk control model by using a risk control strategy; the server module utilizes a risk control model to construct a set of regional power grid risk assessment and decision-making-assisting framework based on SCADA real-time data to generate a power grid operation risk index; the framework utilizes the risk control model to calculate, evaluate and analyze the power grid operation risk indexes, construct a corresponding risk pre-control scheme and generate a risk pre-control auxiliary decision. According to the method, the occurrence probability and the influence range of the system risk are reduced by determining the regional power grid operation risk index system and adopting an optimal load reduction and network reconstruction operation risk method, a set of regional power grid risk assessment and assistant decision-making system based on SCADA real-time data is developed, the occurrence probability and the consequences of the fault are effectively assessed and researched, and effective decision support is provided for preventing operation accidents.
Description
Technical Field
The invention relates to the technical field of power grid risk control, in particular to a risk control aid decision-making method and system based on artificial intelligence learning.
Background
With the rapid development of social life and production, the operation and application of power systems are becoming more and more complex and unstable. In this case, the accident rate of the system is relatively increased, and the loss is difficult to measure. Especially in the application of regional power grids, due to the fact that some devices are updated slowly and protective measures are not in place, the phenomena of heavy load and overload are caused frequently, the safety and stability of power grid operation are reduced, and certain difficulty is brought to maintaining normal power supply of the power grid.
According to the invention, the application of a risk theory is introduced into the safe operation evaluation of the power grid, the risk control process under a normal state and an expected fault state is mainly researched, the system risk occurrence probability and the influence range are reduced by determining a regional power grid operation risk index system and adopting an optimal load reduction and network reconstruction operation risk control method, and a regional power grid risk evaluation and decision-making assisting system based on SCADA real-time data is developed to effectively evaluate the probability and the consequence of the fault occurrence for research and analysis.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides a risk control assistant decision-making method based on artificial intelligence learning, which can effectively evaluate and research the probability and the consequence of the occurrence of the fault and can provide effective decision support for preventing the operation accidents.
In order to solve the technical problems, the invention provides the following technical scheme: the master control module constructs an operation risk control model by using a risk control strategy; the server module utilizes the risk control model to construct a set of regional power grid risk assessment and decision-making-assisting framework based on SCADA real-time data to generate a power grid operation risk index; and the framework utilizes the risk control model to calculate, evaluate and analyze the power grid operation risk indexes, construct a corresponding risk pre-control scheme and generate a risk pre-control auxiliary decision.
As a preferred solution of the risk control assistant decision method based on artificial intelligence learning according to the present invention, wherein: constructing the risk control model comprises the steps of achieving optimal load reduction by utilizing a load loss strategy and calculating power failure power in a risk state; and analyzing the network reconstruction in the power supply recovery process, and optimizing a network reconstruction model to obtain the risk control model.
As a preferred solution of the risk control assistant decision method based on artificial intelligence learning according to the present invention, wherein: the optimal load reduction is to calculate the power failure power in the risk state by adopting load loss operation and taking optimal generator set output arrangement and power flow distribution of a power grid as a basis, and comprises the following steps of reducing the operation risk of the power grid by utilizing a load reduction strategy and with the minimum load cost, wherein the optimal load reduction model utilizes the minimum total power failure power of the power grid as a target function, and comprises the following steps:
wherein, Δ PLi: loaded active, Δ QLi: amount of idle reduction, Nb: the number of the load loss nodes; the optimal load reduction objective function utilizes an equipment overload risk index, a voltage out-of-limit index and a load loss index, takes an overall risk value as a weighted sum of the optimal load reduction objective function, an operator sets importance degrees of various risks by utilizing an adjustment weight to obtain different optimal control strategies, and selects a continuous consequence value function, wherein a primal-dual interior point method mathematical model is as follows:
minf(x)＝ω1RLOL+ω2ROL+ω3RVV
wherein R isOLAnd ω1: equipment overload risk indicator and its weight, RVVAnd ω2: voltage out-of-limit indicator and its weight, RLOLAnd ω3: loss of load indicator and its weight, PijAnd Qij: active and reactive power, P, flowing from node i to jGiAnd QGi: active and reactive output power of the generator, PLiAnd QLi: active and reactive power of the respective load, PGi maxAnd PGi min: upper and lower limits of the active output of the generator, QGi maxAnd QGi min: upper and lower limits of reactive output of the generator, Pij maxAnd Pij min: upper and lower limits of the active transmission capacity of the transmission line, Vi minAnd Vi min: upper limit of voltage amplitude of each nodeAnd lower limit, Vi: node voltage, Δ PLi maxAnd Δ QLi max: the upper limit of the reduction of active and reactive loads.
As a preferred solution of the risk control assistant decision method based on artificial intelligence learning according to the present invention, wherein: when the power grid fails to cause load loss, the network reconstruction realizes power supply recovery, and the network reconstruction in the power supply recovery process is analyzed, wherein on the premise of recovering the most power loss load and recovering important loads preferentially, the optimal power supply path is selected by taking the constraint of a power flow equation and the active and reactive output limits of a generator as constraint conditions, and the network reconstruction model is as follows:
wherein, Wi: weight coefficient of importance of load, NOP: number of switching operations, PijAnd Qij: active and reactive power, P, flowing from node i to jGiAnd QGi: active and reactive output power of the generator, PLiAnd QLi: active and reactive power of the respective load, PGi maxAnd PGi min: upper and lower limits of the active output of the generator, QGi maxAnd QGi min: upper and lower limits of reactive output of the generator, Pij maxAnd Pij min: upper and lower limits of the active transmission capacity of the transmission line, Vi minAnd Vi min: upper and lower limits of voltage amplitude, V, at each nodeiTable: the node voltage.
As a preferred solution of the risk control assistant decision method based on artificial intelligence learning according to the present invention, wherein: the network reconstruction specifically comprises the steps of positioning a fault state and calculating load reduction; reconstructing a transformer substation, changing the state of a switch in the transformer substation, and realizing fault recovery; acquiring the fault influence range; reconstructing the power distribution network, and searching an investable support feeder line in the power distribution network with the fault to recover power supply; carrying out integral reconstruction, and seeking a load transfer path for further consideration of other power distribution areas in the system; and remote recovery, wherein a load transfer path is searched for other power supply areas to form a remote recovery scheme.
As a preferred solution of the risk control assistant decision method based on artificial intelligence learning according to the present invention, wherein: implementing the risk prevention control process, including obtaining a current state of the power grid; if the state is a normal state, executing a risk pre-control scheme running in the normal state; and if the fault state is detected, executing the risk pre-control scheme operated in the fault state.
As a preferred solution of the risk control assistant decision method based on artificial intelligence learning according to the present invention, wherein: the risk pre-control scheme running in the normal state comprises that if the risk pre-control scheme is in an unsafe state, the preventive control process in the normal state is started; if the feasible path exists, outputting a power generation power control scheme and ending the whole control process; and if no feasible path exists, controlling, solving and outputting the optimal load reduction based on the risk and a load reduction and supply scheme.
As a preferred solution of the risk control assistant decision method based on artificial intelligence learning according to the present invention, wherein: the risk pre-control scheme operating in the fault state comprises generating a basic fault set U1 and calculating a risk value in the U1; sequencing the U1 and generating a risk control set U2, and starting the preventive control process in the fault state; if the network reconstruction needs to be operated, operating the generated power and then scheduling and controlling and outputting a scheme; and if the network reconstruction is not required to be operated, solving and outputting a load reduction and supply scheme.
As a preferred solution of the risk control assistant decision system based on artificial intelligence learning according to the present invention, wherein: the master control module is used for constructing the risk control model; the server module is used for establishing a frame for regional power grid risk assessment and auxiliary decision-making based on the SCADA real-time data; the input management module is used for managing and operating all parameters in the system and defining the fault set; the analysis module is used for calculating and processing the power grid parameters input into the management module, obtaining risk indexes and formulating risk control strategies corresponding to the risk indexes; and the output management module is used for graphically processing the input data, storing the processing result of the risk indicator and the control strategy data and displaying the processing result and the control strategy data to a user.
The invention has the beneficial effects that: according to the method, the occurrence probability and the influence range of the system risk are reduced by determining the regional power grid operation risk index system and adopting an optimal load reduction and network reconstruction operation risk method, a set of regional power grid risk assessment and assistant decision-making system based on SCADA real-time data is developed, the occurrence probability and the consequences of the fault are effectively assessed and researched, and effective decision support is provided for preventing operation accidents.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
FIG. 1 is a schematic flow chart of a risk control aid decision method based on artificial intelligence according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of network reconstruction of a risk control aid decision method based on artificial intelligence according to a first embodiment of the present invention;
FIG. 3 is a schematic view of a normal risk prevention control flow of the risk control aid decision method based on artificial intelligence according to the first embodiment of the present invention;
FIG. 4 is a schematic view illustrating a risk prevention control flow under a fault condition of a risk control aid decision method based on artificial intelligence according to a first embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a risk-based prevention control flow of an artificial intelligence-based risk control aid decision method according to a first embodiment of the present invention;
FIG. 6 is a schematic diagram of a system for assessing risk of operation of SCADA real-time data of a risk control aid decision system based on artificial intelligence according to a second embodiment of the present invention;
FIG. 7 is a data flow diagram illustrating the overall structure of an artificial intelligence-based risk control aid decision system according to a second embodiment of the present invention;
FIG. 8 is a schematic diagram of a 220kv network connection of a risk control aid decision method based on artificial intelligence according to a first embodiment of the present invention;
FIG. 9 is a diagram illustrating the QC area network structure of the risk control aid decision method based on artificial intelligence according to the first embodiment of the present invention;
fig. 10 is a schematic block diagram illustrating the distribution of the artificial intelligence-based risk control aid decision system according to the second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
The method has the advantages that higher requirements are provided for safe and reliable power supply while the power grid is rapidly developed, the new situation that power supply is seriously short, the cross-regional large power grid stability contradiction is outstanding, and regional power is frequently operated is faced, and in addition, a series of power grid large-area power failure accidents occurring at home and abroad in recent years promote the power grid safety to rise to the strategic height of national safety and social stability, so that high attention is paid to all aspects, therefore, in order to make power grid safety risk management work in a targeted manner, the characteristics and the development trend of the power grid operation risk accidents must be deeply known and mastered, so that the artificial intelligent learning strategy is combined, and the power grid operation risk pre-control.
Referring to fig. 1 to 5, 8 and 9, a risk control aid decision method based on artificial intelligence learning is provided as a first embodiment of the present invention, and includes:
s1: the master control module 100 utilizes a risk control strategy to construct an operation risk control model, so as to realize a risk prevention control process. It should be noted that constructing the risk control model includes:
the optimal load reduction is achieved by utilizing a load loss strategy, and the power failure power in a risk state is calculated;
and analyzing the network reconstruction in the power supply recovery process, and optimizing the network reconstruction model to obtain a risk control model.
Further, the optimal load reduction is to adopt load loss operation, and calculate the power failure power under the risk state based on the optimal output arrangement of the generator set and the power flow distribution of the power grid, and the method comprises the following steps:
and reducing the operation risk of the power grid at the minimum load cost by using a load reduction strategy, wherein the optimal load reduction model uses the minimum total power failure power of the power grid as a target function, and comprises the following steps:
wherein, is Δ QLi: loaded active MW, Δ QLi: reduction of reactive power Mvar, Nb: the number of the load loss nodes;
the optimal load reduction objective function utilizes an equipment overload risk index, a voltage out-of-limit index and a load loss index, an overall risk value is used as a weighted sum of the optimal load reduction objective function, operators set the importance degree of various risks by utilizing an adjustment weight to obtain different optimal control strategies, and a continuous consequence value function is selected, wherein a primary dual interior point method mathematical model is as follows:
minf(x)＝ω1RLOL+ω2ROL+ω3RVV
wherein R isOLAnd ω1: equipment overload risk indicator and its weight, RVVAnd ω2: voltage out-of-limit indicator and its weight, RLOLAnd ω3: loss of load indicator and its weight, PijAnd Qij: active and reactive power, P, flowing from node i to jGiAnd QGi: active and reactive output power of the generator, PLiAnd QLi: active and reactive power of the respective load, PGi maxAnd PGi min: upper and lower limits of the active output of the generator, QGi maxAnd QGi min: upper and lower limits of reactive output of the generator, Pij maxAnd Pij min: upper and lower limits of the active transmission capacity of the transmission line, Vi minAnd Vi min: upper and lower limits of voltage amplitude, V, at each nodei: node voltage, Δ PLi maxAnd Δ QLi max: the upper limit of the reduction of active and reactive loads.
Preferably, when the power grid fails to cause load loss, the network reconstruction realizes power supply recovery, and the analysis of the network reconstruction in the power supply recovery process includes:
on the premise of recovering the most power-loss load and preferentially recovering the important load, the optimal power supply path is selected by using the constraints of a power flow equation and the active and reactive power output limits of the generator as constraint conditions, and a network reconstruction model is as follows:
wherein, Wi: weight coefficient of importance of load, NOP: number of switching operations, PijAnd Qij: active and reactive power, P, flowing from node i to jGiAnd QGi: power generationActive and reactive output power of the machine, PLiAnd QLi: active and reactive power of the respective load, PGi maxAnd PGi min: upper and lower limits of the active output of the generator, QGi maxAnd QGi min: upper and lower limits of reactive output of the generator, Pij maxAnd Pij min: upper and lower limits of the active transmission capacity of the transmission line, Vi minAnd Vi min: upper and lower limits of voltage amplitude, V, at each nodeiTable: the node voltage.
Specifically, referring to fig. 2, the network reconfiguration includes:
positioning the fault state and calculating the load reduction amount;
reconstructing the transformer substation, changing the switch state in the transformer substation, and realizing fault recovery;
acquiring a fault influence range;
reconstructing the power distribution network, and searching an investable support feeder line in the power distribution network with a fault to recover power supply;
carrying out integral reconstruction, and seeking a load transfer path for further consideration of other power distribution areas in the system;
and remote recovery, wherein a load transfer path is searched for other power supply areas to form a remote recovery scheme.
S2: the server module 200 utilizes the risk control model to construct a set of regional power grid risk assessment and decision-making assisting framework based on SCADA real-time data, and power grid operation risk indexes are generated. It should be noted that, referring to fig. 3, the risk pre-control scheme operating in the normal state includes:
if the monitoring device is in the unsafe state, starting a prevention control process in a normal state;
if the feasible path exists, outputting a power generation power control scheme and ending the whole control process;
and if no feasible path exists, controlling, solving and outputting an optimal load reduction scheme based on the risk.
Further, referring to fig. 4, the risk pre-control scheme for operation in a fault condition includes:
generating a basic fault set U1, and calculating a risk value in U1;
sequencing the U1, generating a risk control set U2, and starting a prevention control process in a fault state;
if the network reconstruction needs to be operated, operating the generated power, then scheduling and controlling and outputting a scheme;
and if the network reconstruction is not needed to be operated, solving and outputting a load reduction and supply scheme.
S3: the framework utilizes the risk control model to calculate, evaluate and analyze the power grid operation risk indexes, construct a corresponding risk pre-control scheme and generate a risk pre-control auxiliary decision. It is also noted that forming risk pre-control aid decisions includes:
acquiring the current state of a power grid;
if the state is a normal state, executing a risk pre-control scheme running in the normal state;
and if the fault state is detected, executing a risk pre-control scheme running under the fault state.
Preferably, control auxiliary measures are implemented aiming at operation risks in regional power grid operation, identification analysis needs to be carried out aiming at operation hazard factors, and the identification analysis is mainly divided into external reasons and internal reasons, wherein the external reasons refer to a series of influences of natural environments encountered by a power grid in an operation process, such as severe weather, mountain fire and other conditions; the internal reasons refer to the influence of the power grid operation quality, such as the conditions of reasonable power grid structure and power distribution, equipment operation quality, personnel operation quality and the like; referring to fig. 5, in order to better explain risk identification and risk pre-control, the present embodiment explains by a main wiring method of a 220kv system, the most typical current operation method is that two bus-bar sections all adopt two bus-bar switches, the two section switches are in a closed position, but some section breakers only have one group of current transformers, and have a dead zone problem, if a fault occurs in the dead zone, it takes longer time to remove the fault, and the method of the present invention adopts an artificial intelligence deep learning strategy, reconstructs a risk operation pre-control method by using a risk control model, realizes risk-based pre-control, and when the fault is scanned in the system, only one switch in a ring needs to be disconnected, so that the grid operation risk can be reduced, and the fault can be eliminated.
Preferably, in the embodiment, risk assessment is performed by regional power grid operation, risk indexes of the regional power grid are calculated, a corresponding risk control strategy is formulated, the operation risk of the regional power grid is calculated and analyzed, and the potential fault risk of the power grid is controlled from a quantitative perspective; referring to fig. 8, a schematic diagram of network connection of a 220kV power transmission line of a power grid in the area is shown, the power transmission line is formed by interconnecting a 500kV substation, a 220kV power station and a 220kV power transmission line to operate in a closed loop, referring to fig. 9, a schematic diagram of a 110kV power supply area power grid structure of the power grid in the area is shown, the power transmission line is composed of a 110kV substation, a 220kV three-winding transformer, a 110kV double-winding transformer and a 110kV power transmission line, risk assessment parameters are output by using the 220kV power transmission line and the 110kV power supply structure, and all risk index calculation results of the power transmission line:
table 1: 220kV transmission line operation risk table in central station 2 power supply area.
Table 2: QC power supply district 110kV transmission line operation risk index table.
Table 3: and a QC area power supply area transformer operation risk table.
Table 4: and (5) a QC power supply area bus operation risk table.
Referring to tables 1 to 4, a corresponding risk control method is formulated according to the risk assessment results, as shown in the following tables:
table 5: and (5) a risk control method table of an evaluation result.
It can be seen from the example analysis of table 5 that the equipment overload risk can be solved by changing the operation of the series power supply and reducing the load of the power supply terminal area, the power supply recovery of other paths can be found in the face of the power transmission line fault, and when the bus N-1 fault occurs, the bus can be transferred through the reconstruction in the station, and the system state can be recovered.
Preferably, in order to verify and explain the technical effect adopted in the method of the present invention, the embodiment selects the traditional power grid operation safety management method to perform a comparison test with the method of the present invention, and compares the test results by means of scientific demonstration to verify the real effect of the method of the present invention; the traditional power grid operation safety management method lacks a power grid operation safety management system which can uniformly coordinate forces of all parties to carry out safe driving and protecting for the power grid, and lacks certain scheduling coordination force aiming at power grid network frame planning, equipment operation and maintenance, power grid operation safety and the like; in order to verify that the method of the present invention has the advantages of effectively evaluating and researching the occurrence probability and consequences of the power grid operation fault compared with the conventional method, and providing effective decision support for preventing operation accidents, in the present embodiment, 10 sets of tests and comparisons are respectively performed on IEEE9 nodes by using the conventional power grid operation safety management method (i.e., identifying and analyzing the potential risk existing in the power grid operation, and identifying the potential or inherent harmful factors affecting the power grid operation safety by using management and control measures) and the method of the present invention, and in order to make the branch overload condition in the simulation result obvious, the present embodiment adjusts the branch rated power capacity value to 0.5 times of the original value, and the specific test results are shown in the following table:
table 6: and controlling the power grid operation risk to test the pair data table in an auxiliary decision mode.
Referring to table 6, it can be seen that the conventional power grid operation safety management method can only find out a fault circuit, but lacks a certain ability to remove the fault circuit, but the method of the present invention can not only accurately determine the operation risk state of each circuit, but also can use an artificial intelligence deep learning strategy to adjust and read a risk pre-control method, find out a strategy method suitable for eliminating the fault circuit, and verify that the method of the present invention can provide effective auxiliary decision support for power grid operation risk fault pre-control.
Example 2
Referring to fig. 6, fig. 7 and fig. 10, a second embodiment of the present invention, which is different from the first embodiment, provides an artificial intelligence learning-based risk control aid decision system, including a master control module 100 for constructing a risk control model.
And the server module 200 is used for establishing a regional power grid risk assessment and decision-making assisting framework based on SCADA real-time data.
And the input management module 300 is used for managing and operating all parameters in the system and defining a fault set.
And the analysis module 400 is configured to calculate and process the power grid parameters input into the management module 300, obtain a risk indicator, and formulate a risk control policy corresponding to the risk indicator.
And the output management module 500 is used for graphically processing the input data, storing the processing result of the risk indicator and the control strategy data, and displaying the processing result and the control strategy data to the user.
Preferably, referring to fig. 6, the system of the invention constructs an overall software framework through a database server, a power grid model, an SCADA database and an ftp server, provides service support for the system on data storage, processing and graphical simulation, and each functional module forms a risk assessment system and provides an intelligent interface of human-computer interaction; referring to fig. 7, the data flow of the overall software structure is composed of an input management module 300, an analysis module 400, and an output management module 500, the system of the present invention uses the input management module 100 as an interface between a user and software, obtains a risk index in combination with the analysis module 400, makes a corresponding risk control policy for the index, stores the risk index processing result and the control policy data by using the output management module 500, and finally displays the risk index processing result and the control policy data to the user by using an intuitive interface such as a graph, a report, and data statistics.
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (9)
1. A risk control aid decision-making method based on artificial intelligence learning is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the master control module (100) constructs an operation risk control model by using a risk control strategy;
the server module (200) utilizes the risk control model to construct a set of regional power grid risk assessment and decision-making-assisting framework based on SCADA real-time data, and power grid operation risk indexes are generated;
and the framework utilizes the risk control model to calculate, evaluate and analyze the power grid operation risk indexes, construct a corresponding risk pre-control scheme and generate a risk pre-control auxiliary decision.
2. The artificial intelligence learning-based risk control aid decision method according to claim 1, characterized by: constructing the risk control model includes the steps of,
the optimal load reduction is achieved by utilizing a load loss strategy, and the power failure power in a risk state is calculated;
and analyzing the network reconstruction in the power supply recovery process, and optimizing a network reconstruction model to obtain the risk control model.
3. The artificial intelligence learning-based risk control aid decision method according to claim 1 or 2, characterized by: the optimal load reduction is to calculate the power failure power under the risk state by adopting load loss operation and based on optimal generator set output arrangement and power flow distribution of a power grid, and comprises the following steps of,
and reducing the operation risk of the power grid at the minimum load cost by using a load reduction strategy, wherein the optimal load reduction model uses the minimum total power failure power of the power grid as an objective function, and comprises the following steps:
wherein, Δ PLi: loaded active power (MW), Δ QLi: amount of reactive power reduction (Mvar), Nb: the number of the load loss nodes;
the optimal load reduction objective function utilizes an equipment overload risk index, a voltage out-of-limit index and a load loss index, takes an overall risk value as a weighted sum of the optimal load reduction objective function, an operator sets importance degrees of various risks by utilizing an adjustment weight to obtain different optimal control strategies, and selects a continuous consequence value function, wherein a primal-dual interior point method mathematical model is as follows:
min f(x)＝ω1RLOL+ω2ROL+ω3RVV
wherein R isOLAnd ω1: equipment overload risk indicator and its weight, RVVAnd ω2: voltage out-of-limit indicator and its weight, RLOLAnd ω3: loss of load indicator and its weight, PijAnd Qij: active and reactive power, P, flowing from node i to jGiAnd QGi: active and reactive output power of the generator, PLiAnd QLi: active and reactive power of the respective load, PGi maxAnd PGi min: upper and lower limits of the active output of the generator, QGi maxAnd QGi min: upper and lower limits of reactive output of the generator, Pij maxAnd Pij min: upper and lower limits of the active transmission capacity of the transmission line, Vi minAnd Vi min: upper and lower limits of voltage amplitude, V, at each nodei: node voltage, Δ PLi maxAnd Δ QLi max: the upper limit of the reduction of active and reactive loads.
4. The artificial intelligence learning-based risk control aid decision method according to claim 1 or 2, characterized by: when the power grid fails to cause load loss, the network reconstruction realizes power supply recovery, and the network reconstruction in the power supply recovery process is analyzed, including,
on the premise of recovering the most power-loss load and preferentially recovering the important load, and taking the current equation constraint and the active and reactive power output limits of the generator as constraint conditions, selecting the optimal power supply path, wherein the network reconstruction model comprises the following steps:
max f1(x)＝∑i∈LWiPLi，min f2(x)＝NOP
wherein, Wi: weight coefficient of importance of load, NOP: number of switching operations, PijAnd Qij: active and reactive power, P, flowing from node i to jGiAnd QGi: active and reactive output power of the generator, PLiAnd QLi: active and reactive power of the respective load, PGi maxAnd PGi min: upper and lower limits of the active output of the generator, QGi maxAnd QGi min: upper and lower limits of reactive output of the generator, Pij maxAnd Pij min: upper and lower limits of the active transmission capacity of the transmission line, Vi minAnd Vi min: upper and lower limits of voltage amplitude, V, at each nodeiTable: the node voltage.
5. The artificial intelligence learning-based risk control aid decision method according to claim 4, characterized by: the network reconfiguration may specifically include the steps of,
positioning the fault state and calculating the load reduction amount;
reconstructing a transformer substation, changing the state of a switch in the transformer substation, and realizing fault recovery;
acquiring the fault influence range;
reconstructing the power distribution network, and searching an investable support feeder line in the power distribution network with the fault to recover power supply;
carrying out integral reconstruction, and seeking a load transfer path for further consideration of other power distribution areas in the system;
and remote recovery, wherein a load transfer path is searched for other power supply areas to form a remote recovery scheme.
6. The artificial intelligence learning-based risk control aid decision method according to claim 1, characterized by: and realizing a risk prevention control process by using the risk pre-control assistant decision, comprising,
acquiring the current state of the power grid;
if the state is a normal state, executing a risk pre-control scheme running in the normal state;
and if the fault state is detected, executing the risk pre-control scheme operated in the fault state.
7. The artificial intelligence learning-based risk control aid decision method according to claim 1 or 6, characterized by: the risk pre-control scheme operating in the normal state includes,
if the monitoring device is in an unsafe state, starting the preventive control process in the normal state;
if the feasible path exists, outputting a power generation power control scheme and ending the whole control process;
and if no feasible path exists, controlling, solving and outputting the optimal load reduction based on the risk and a load reduction and supply scheme.
8. The artificial intelligence learning-based risk control aid decision method according to claim 1 or 6, characterized by: the risk precontrol scheme operating in the fault condition includes,
generating a basic fault set U1 and calculating a risk value in the U1;
sequencing the U1 and generating a risk control set U2, and starting the preventive control process in the fault state;
if the network reconstruction needs to be operated, operating the generated power and then scheduling and controlling and outputting a scheme;
and if the network reconstruction is not required to be operated, solving and outputting a load reduction and supply scheme.
9. A risk control aid decision-making system based on artificial intelligence learning is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
a master control module (100) for constructing the risk control model;
a server module (200) for establishing the framework of regional grid risk assessment and aid decision based on the SCADA real-time data;
the input management module (300) is used for managing and operating all parameters in the system and defining the fault set;
the analysis module (400) is used for calculating and processing the power grid parameters input into the management module (300), obtaining risk indexes and formulating risk control strategies corresponding to the risk indexes;
and the output management module (500) is used for graphically processing the input data, storing the processing result of the risk indicator and the control strategy data and displaying the processing result and the control strategy data to a user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010174624.0A CN111401731A (en) | 2020-03-13 | 2020-03-13 | Risk control aid decision-making method and system based on artificial intelligence learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010174624.0A CN111401731A (en) | 2020-03-13 | 2020-03-13 | Risk control aid decision-making method and system based on artificial intelligence learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111401731A true CN111401731A (en) | 2020-07-10 |
Family
ID=71430855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010174624.0A Withdrawn CN111401731A (en) | 2020-03-13 | 2020-03-13 | Risk control aid decision-making method and system based on artificial intelligence learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401731A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112187956A (en) * | 2020-10-26 | 2021-01-05 | 南京集新萃信息科技有限公司 | Open type Internet of things data management method and system |
| CN112398129A (en) * | 2020-12-04 | 2021-02-23 | 广东电网有限责任公司 | Power grid post-accident risk control aid decision-making method and device and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130232094A1 (en) * | 2010-07-16 | 2013-09-05 | Consolidated Edison Company Of New York | Machine learning for power grid |
| CN107194574A (en) * | 2017-05-16 | 2017-09-22 | 中国能源建设集团江苏省电力设计院有限公司 | A kind of grid security risk assessment method based on load loss |
| US20180059186A1 (en) * | 2015-07-10 | 2018-03-01 | Qibei YANG | High-voltage circuit breaker opening and closing time online monitoring apparatus, smart multi-dimensional big data analyzing expert system for high-voltage circuit breaker in power grid and method therefor |
| CN108090674A (en) * | 2017-12-18 | 2018-05-29 | 贵州电网有限责任公司 | The risk assessment of the area power grid method of operation and aid decision-making method and system |
| CN108537433A (en) * | 2018-04-04 | 2018-09-14 | 国电南瑞科技股份有限公司 | Area power grid method for prewarning risk based on multidimensional evaluation index |
| CN109816161A (en) * | 2019-01-14 | 2019-05-28 | 中国电力科学研究院有限公司 | A kind of power distribution network operation computer-aided decision support System and its application method |
| CN110311376A (en) * | 2019-07-31 | 2019-10-08 | 三峡大学 | A kind of Electrical Power System Dynamic security evaluation collective model and space-time method for visualizing |
| CN110717665A (en) * | 2019-09-30 | 2020-01-21 | 国家电网有限公司 | System and method for fault identification and trend analysis based on scheduling control system |
-
2020
- 2020-03-13 CN CN202010174624.0A patent/CN111401731A/en not_active Withdrawn
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130232094A1 (en) * | 2010-07-16 | 2013-09-05 | Consolidated Edison Company Of New York | Machine learning for power grid |
| US20180059186A1 (en) * | 2015-07-10 | 2018-03-01 | Qibei YANG | High-voltage circuit breaker opening and closing time online monitoring apparatus, smart multi-dimensional big data analyzing expert system for high-voltage circuit breaker in power grid and method therefor |
| CN107194574A (en) * | 2017-05-16 | 2017-09-22 | 中国能源建设集团江苏省电力设计院有限公司 | A kind of grid security risk assessment method based on load loss |
| CN108090674A (en) * | 2017-12-18 | 2018-05-29 | 贵州电网有限责任公司 | The risk assessment of the area power grid method of operation and aid decision-making method and system |
| CN108537433A (en) * | 2018-04-04 | 2018-09-14 | 国电南瑞科技股份有限公司 | Area power grid method for prewarning risk based on multidimensional evaluation index |
| CN109816161A (en) * | 2019-01-14 | 2019-05-28 | 中国电力科学研究院有限公司 | A kind of power distribution network operation computer-aided decision support System and its application method |
| CN110311376A (en) * | 2019-07-31 | 2019-10-08 | 三峡大学 | A kind of Electrical Power System Dynamic security evaluation collective model and space-time method for visualizing |
| CN110717665A (en) * | 2019-09-30 | 2020-01-21 | 国家电网有限公司 | System and method for fault identification and trend analysis based on scheduling control system |
Non-Patent Citations (2)
| Title |
|---|
| 丁施尹: "地区电网运行风险评估及控制", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 黄镇: "基于最优潮流的电网连锁故障路径仿真及风险优化控制", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112187956A (en) * | 2020-10-26 | 2021-01-05 | 南京集新萃信息科技有限公司 | Open type Internet of things data management method and system |
| CN112398129A (en) * | 2020-12-04 | 2021-02-23 | 广东电网有限责任公司 | Power grid post-accident risk control aid decision-making method and device and storage medium |
| CN112398129B (en) * | 2020-12-04 | 2023-09-05 | 广东电网有限责任公司 | Auxiliary decision-making method, device and storage medium for risk control after power grid accident |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020147349A1 (en) | Power distribution network operation aided decision-making analysis system and method | |
| Chuansheng et al. | Safety evaluation of smart grid based on AHP-entropy method | |
| CN107194574B (en) | Power grid security risk assessment method based on load loss | |
| CN104809665B (en) | A kind of power distribution network method for early warning based on improvement Apriori algorithm | |
| CN101246569A (en) | Electric network energy quality synthetic appraisement method based on analytic hierarchy process and fuzzy algorithm | |
| CN113191687B (en) | Elastic power distribution network panoramic information visualization method and system | |
| CN111680872A (en) | Power grid risk calculation method based on multi-source data fusion | |
| CN111401731A (en) | Risk control aid decision-making method and system based on artificial intelligence learning | |
| Guo et al. | Evidence-based approach to power transmission risk assessment with component failure risk analysis | |
| CN114744616A (en) | Power recovery auxiliary decision-making method for power distribution network | |
| CN115603459A (en) | Digital twin technology-based power distribution network key station monitoring method and system | |
| Liu et al. | Seismic resilience evaluation and retrofitting strategy for substation system | |
| CN114548800A (en) | Future-state power grid maintenance risk identification method and device based on power grid knowledge graph | |
| CN112200458A (en) | Power distribution network planning data application method and system | |
| CN115423387A (en) | Intelligent early warning method and system for field behaviors of live working personnel of extra-high voltage line | |
| CN113780777A (en) | Comparison analysis method for synchronous line loss and theoretical line loss | |
| Ahmad et al. | An expert system-based restoration method for energy services | |
| Han et al. | A deducing-based reliability optimization for electrical equipment with constant failure rate components duration their mission profile | |
| CN115952981A (en) | Transmission and distribution system planning auxiliary system | |
| CN114913032A (en) | Transformer substation operation energy consumption assessment method | |
| Melendez-Norona et al. | Design of a Massive Open Online Course on Electrical Microgrids Cybersecurity and Optimization | |
| Qin et al. | Transmission Line Fault Diagnosis and Location System in Distribution Network Based on PSO | |
| CN113158382A (en) | Computer-aided decision support system for power grid planning | |
| Chen et al. | An advanced decision-support tool for electricity infrastructure operations | |
| CN104268694A (en) | Evaluating method for control system of active power distribution network and planning method for active power distribution network |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200710 |