CN116436160B - AGC performance index on-line monitoring system and method - Google Patents
AGC performance index on-line monitoring system and method Download PDFInfo
- Publication number
- CN116436160B CN116436160B CN202310317311.XA CN202310317311A CN116436160B CN 116436160 B CN116436160 B CN 116436160B CN 202310317311 A CN202310317311 A CN 202310317311A CN 116436160 B CN116436160 B CN 116436160B
- Authority
- CN
- China
- Prior art keywords
- running
- agc
- unit
- historical
- revolution
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000010801 machine learning Methods 0.000 claims abstract description 23
- 238000012937 correction Methods 0.000 claims abstract description 14
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 238000011068 loading method Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 18
- 230000003827 upregulation Effects 0.000 claims description 16
- 230000003828 downregulation Effects 0.000 claims description 15
- 238000010248 power generation Methods 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 230000033228 biological regulation Effects 0.000 description 22
- 230000004044 response Effects 0.000 description 14
- 230000008569 process Effects 0.000 description 8
- 238000012797 qualification Methods 0.000 description 6
- 230000005526 G1 to G0 transition Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002222 downregulating effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012905 input function Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/24—Arrangements for preventing or reducing oscillations of power in networks
- H02J3/241—The oscillation concerning frequency
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/48—Controlling the sharing of the in-phase component
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides an AGC performance index online monitoring system and method, wherein the system comprises: monitoring the model; the monitoring model is provided with a machine learning system, a configuration module, a correction module and a neural network unit constructed by the machine learning system, wherein the configuration module is used for configuring a plurality of reference output thresholds of the generator set under different reference AGC instructions according to the historical actual power and the historical set revolution of an equalization section corresponding to the historical AGC instructions; the running actual power of the unit and the running unit revolution loading resource data are acquired in real time through the acquisition device according to the running AGC instruction and under the running AGC instruction to train so as to acquire a stable interval corresponding to the running actual power and the running unit revolution under the running AGC instruction; the correction module is used for correcting a plurality of reference output thresholds under different reference AGC commands according to a stable interval corresponding to the running actual power and the machine running group revolution under the running AGC commands.
Description
Technical Field
The application belongs to the technical field of power generation, and particularly relates to an AGC performance index online monitoring system.
Background
In recent years, with the rapid development of ultra-high voltage transmission and new energy power generation, the power system of China faces great changes. When the extra-high voltage direct current transmission is interrupted due to faults or when new energy power generation such as wind power and the like fluctuates greatly, the safe and stable operation of the power grid depends on the peak regulation and frequency modulation capability of the thermal power generating unit. The key research content of the subject is how to fully utilize the heat accumulation of the on-line unit to discover the frequency modulation potential of the unit and ensure the stable frequency of the power grid when the external electric quantity of the power grid is larger and larger. When the power grid falls off at a larger frequency, the primary frequency modulation potential of the unit is fully utilized to reduce the frequency falling space, but the primary frequency modulation belongs to differential adjustment, and frequency deviation cannot be completely eliminated, so that the combined adjustment is needed by combining with AGC.
The flexible transformation of the coal motor unit is implemented according to the capacity of 20% per year, wherein the minimum technical output under the condition of stable combustion of the stored pure condensing unit and the extraction condensing unit respectively reaches 30% and 40% of rated capacity, the new pure condensing unit and the extraction condensing unit respectively reach 20% and 30%, and the extraction condensing unit with the thermoelectric ratio lower than 50% is transformed by referring to the standard of the pure condensing unit. And giving the peak regulation and frequency modulation priority generating capacity plan rewards to the unit which is modified according to the requirements according to the peak regulation depth and the actual operation peak regulation contribution. Meanwhile, AGC performance of the unit in different load sections after the flexibility is improved meets technical specification requirements, the unit adjusting speed is not lower than 1.0% Pe/min above 40% Pe (Pe is rated load), and not lower than 0.5% Pe/min below 40% Pe.
The actual power of the thermal power unit is changed along with the change of the power grid load instruction, and the remarkable problem of performance degradation is caused by the AGC performance and the performance of a related control system due to the change of factors such as coal quality, an actuating mechanism and the like. The common phenomenon is mainly that the actual regulation rate of the unit is lower than the standard rate regulated by the power grid, the regulation precision of the unit is reduced, and the AGC performance does not meet the requirement of the power grid. Therefore, indexes such as AGC regulation rate, response time and regulation precision of the units are required to be combined, various unit combinations are reasonably allocated according to the power grid regulation rate requirement, AGC unit dynamic allocation based on active power gaps of the regional power grid is implemented, the power grid ACE is ensured to meet the requirements specified by A1 and A2, and the power grid frequency is promoted to quickly return to 50Hz.
The safe and stable operation of the power system plays an important role in the national industrial production and economic development, along with the expansion of the scale of the power system, the mutual connection interaction between a gradually formed unit of the intelligent power grid and the power grid is tighter and tighter, the power grid provides stricter requirements for auxiliary services provided by the grid-connected unit, the assessment and evaluation standard of primary frequency modulation automatic power generation control of the grid-connected unit is also more definite and stricter, the on-line monitoring system of frequency modulation and peak regulation parameters of the power plant side is developed, the problems existing in the frequency modulation and peak regulation process of the grid-connected unit can be found in time, and the method has great significance in improving the capacity of the power generator unit for supporting the safe and stable operation of the power grid.
Aiming at the auxiliary service compensation and grid-connected operation assessment standard of the power grid, the operation statistics personnel can inquire about each assessment index of the two rules on the production site at present on the next day of unit operation, after the corresponding scheme is formulated according to the result of the next day inquiry and analysis reasons, the maintenance personnel and the operation personnel carry out strategy optimization and operation parameter adjustment, the optimized effect can be verified after waiting for a day, and the maintenance personnel and the operation personnel have great hysteresis, and when each index of the unit is found to be lower, the unit assessment or the competitive price surfing initiative is caused, so that the real-time monitoring, assessment and analysis management of the coordination performance index of the power generation side machine network are well, the quality of the AGC input R mode can be greatly improved, more unit input function R modes are strived for, the input time is increased, and the rewarding and electricity increasing plan is realized through the input AGC function R mode; meanwhile, after the parameter index of the AGC function is improved, the number of units and the operation time of the AGC function R mode can be increased, and primary frequency modulation assessment is reduced, so that higher economic compensation is obtained, and the units can obtain larger comprehensive benefit.
Among the prior art disclosures, for example, publication No.: "CN111564869B" discloses a method for evaluating AGC performance of a generator set, wherein the method comprises: acquiring an AGC instruction issued by a power grid dispatching control center; according to the AGC command, determining a response process of the generator set to the AGC command, wherein the response process comprises the following steps: stationary phase, up-regulation phase and down-regulation phase; according to the output states of the generator set in different response processes, an AGC state of the generator set is defined, and the AGC state comprises: waiting for available, up-adjust response, down-adjust response, up-adjust unavailable, and down-adjust unavailable; determining the current AGC state of the generator set according to the response process change of the generator set; calculating the duty ratio of different AGC states in a statistical period; according to the duty cycle of different AGC states, the formula is used: AGC state availability = response state duty cycle + waiting state duty cycle, calculating to obtain AGC state availability of the generator set, and response state duty cycle = (time of up-regulation response state + time of down-regulation response state)/statistics period total time, waiting state duty cycle = time of waiting availability state/statistics period total time, calculating to obtain waiting state duty cycle; the method for defining the AGC state of the generator set according to the output states of the generator set in different response processes comprises the following steps: when the generator set is in a stationary phase and the output of the generator set is maintained in the regulation dead zone, the AGC state of the generator set is waiting for availability; when the generator set is in an up-regulation period and the increasing output of the generator set can reach the regulation dead zone of the target AGC command, the AGC state of the generator set is up-regulation response; when the generator set is in a down-regulation period and the reduced output of the generator set can reach the regulation dead zone of the target AGC command, the AGC state of the generator set is a down-regulation response; when the generator set is in a stationary phase and the generator set output remains lower than the regulation dead zone of the current AGC command, or when the generator set is in an up-regulation phase and the generator set increasing output cannot reach the regulation dead zone of the target AGC command, the AGC of the generator set
The state is that up-regulation is not available; when the generator set is in a stationary phase and the generator set output remains higher than the adjustment dead zone of the current AGC command, or when the generator set is in a down-regulation phase and the generator set reduced output cannot reach the adjustment dead zone of the target AGC command, the AGC state of the generator set is down-regulation unavailable.
However, the dead zone, the up-regulation period, the down-regulation period and the steady-state period are all set according to the parameters of the unit, and the set values can change differently according to the operation of the unit and the load of the unit, so that the set values cannot reflect the actual state of the unit.
Disclosure of Invention
Accordingly, the present invention is directed to an AGC performance index online monitoring system and method.
The technical scheme adopted by the invention is as follows:
an AGC performance index online monitoring system comprising:
monitoring the model;
the monitoring model is provided with a machine learning system, a configuration module, a correction module and a neural network unit constructed by the machine learning system,
the machine learning system is used for performing iterative training based on the historical data to obtain the historical actual power and the historical unit revolution of the equalizing interval corresponding to different historical AGC instructions in the historical data; forming resource data for iterative training of the neural network unit by using the historical actual transmission power of the equalizing interval corresponding to the historical AGC instruction and the revolution of the historical unit;
the configuration module is used for configuring a plurality of reference output thresholds of the generator set under different reference AGC instructions according to the historical actual power and the historical set revolution of the equalization section corresponding to the historical AGC instructions;
the neural network unit is used for connecting the machine learning system, and acquiring the running real power of the unit and the running unit revolution loading resource data through the acquisition device in real time according to the running AGC instruction and the running AGC instruction for training so as to acquire a stable interval corresponding to the running real power and the machine running unit revolution under the running AGC instruction;
the correction module is used for correcting a plurality of reference output thresholds under different reference AGC instructions according to a stable interval corresponding to the running actual power and the machine running group revolution under the running AGC instructions, so that the running performance of the unit is optimized.
Further, the machine learning system is configured to establish a unit power generation model with the historical AGC command and the historical unit rotational speed as inputs and with the generator historic power as output.
Further, the correction module includes:
the correction unit is used for correcting the reference output threshold value under the corresponding reference AGC command according to the stable interval corresponding to the running actual power and the machine running group revolution under each running AGC command;
a dynamic configuration unit that sets an adjustment dead zone based on a corrected reference output threshold under a reference AGC instruction;
and the disturbance monitoring unit is used for drawing an operation curve according to the real-time collected operation power, revising and adjusting the dead zone according to the operation curve and monitoring the operation condition of the unit according to the real-time collected operation power.
Further, the dynamic configuration unit configures a plurality of adjustment dead zones according to the corrected reference AGC instruction and the corrected reference output threshold corresponding to the reference AGC instruction in different setting sections.
Further, the disturbance monitoring unit draws an operation curve according to the operation real-time power collected in real time, and sets critical values of the up-regulation period and the stationary period according to the operation curve.
Further, the machine learning system also comprises a storage module and a task management module;
the task management module is used for collecting the running actual power and the machine running group revolution under different running AGC instructions in real time according to a set period, and storing the running actual power and the machine running group revolution under different running AGC instructions into the storage module;
based on the learning task, the machine learning system loads the running actual transmitting power and the machine running group transfer in the memory module under different running AGC instructions to carry out iterative training so as to optimize the resource data.
Further, the disturbance monitoring unit is further provided with a scanning unit, which is used for scanning the end point value of the operation curve based on the time sequence, and taking the first end point value at the time of T0 as a reference to determine whether the second end point value at the time of T1 has a positive difference value of a set interval, and if the difference is stable in the set interval in a plurality of continuous moments, the up-regulation period is set;
if the difference value tends to 0 in a plurality of continuous moments, setting to be a stable period;
if the negative difference value of the set section is present in a plurality of consecutive time points, the set section is set as the down-regulation period.
Further, the operation curves are arranged and output according to a set period.
The invention also provides an AGC performance index online monitoring method, which comprises the following steps:
step 1), a unit power generation model is built by taking a historical AGC instruction and a historical unit rotating speed as inputs and taking the historic power of a generator as output; forming resource data for iterative training of the neural network unit by using the historical actual transmission power of the equalizing interval corresponding to the historical AGC instruction and the revolution of the historical unit;
step 2) configuring a plurality of reference output thresholds of the generator set under different reference AGC instructions according to the historical actual power and the historical set revolution of the equalization section corresponding to the historical AGC instructions;
step 3) real-time acquisition of the running real-time power of the unit and the running unit revolution loading resource data by the acquisition device according to the running AGC instruction and the running AGC instruction for training so as to acquire a stable interval corresponding to the running real-time power and the running unit revolution under the running AGC instruction;
and 4) correcting a plurality of reference output thresholds under different reference AGC instructions according to a stable interval corresponding to the running actual power and the number of revolutions of the machine running set under the running AGC instructions, so as to optimize the running performance of the machine set.
Further, in step 4):
the method comprises the steps of A, correcting a reference output threshold under a corresponding reference AGC command according to a stable interval corresponding to running actual power and machine running group revolution under each running AGC command;
setting an adjustment dead zone based on a reference output threshold value under a corrected reference AGC command;
and C, drawing an operation curve according to the operation actual power acquired in real time, revising and adjusting the dead zone according to the operation curve, and monitoring the operation condition of the unit according to the operation actual power acquired in real time.
Further, in step C): the method comprises the steps of determining whether a second endpoint value at a time T1 has a difference value of a set interval or not based on an endpoint value of a time sequence scanning operation curve and taking a first endpoint value at the time T0 as a reference, and setting the difference value as an up-regulation period if the difference value is stabilized in the set interval in a plurality of continuous moments;
if the difference value tends to 0 in a plurality of continuous moments, setting to be a stable period;
if the negative difference value of the set section is present in a plurality of consecutive time points, the set section is set as the down-regulation period.
According to the method, the dead zone, the up-regulation period, the down-regulation period and the stabilization period are set and regulated based on historical operation data of the unit, unit parameters are not used as standards, meanwhile, the set values are dynamically modulated according to actual operation of the unit, so that quantitative research on primary frequency modulation contribution rate, small disturbance qualification rate and AGC performance indexes of the operation unit is achieved, various indexes are monitored in real time, two-stage control intelligent analysis can be achieved, main factors affecting AGC assessment indexes and corresponding countermeasures are achieved, and AGC service compensation is improved, and primary frequency modulation electric quantity assessment is reduced.
Combining the 'two rules' AGC regulation performance index calculation method, establishing a dynamic mathematical model, and developing an on-line monitoring system for the primary frequency modulation contribution rate, the small disturbance qualification rate and the AGC performance index; the primary frequency modulation contribution rate, the small disturbance qualification rate and the AGC performance index are quantized, and the historical data are analyzed to dynamically correct the AGC regulation performance index in real time when the AGC regulation performance index has problems.
Drawings
The following drawings are illustrative of the invention and are not intended to limit the scope of the invention, in which:
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of the frame principle of the system of the present invention;
FIG. 3 is an operational curve of an operational section of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions, design methods and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Examples
The invention provides an AGC performance index online monitoring system, comprising:
monitoring the model;
the monitoring model is provided with a machine learning system, a configuration module, a correction module and a neural network unit constructed by the machine learning system,
the machine learning system is used for performing iterative training based on the historical data to obtain the historical actual power and the historical unit revolution of the equalizing interval corresponding to different historical AGC instructions in the historical data; forming resource data for iterative training of the neural network unit by using the historical actual transmission power of the equalizing interval corresponding to the historical AGC instruction and the revolution of the historical unit;
the configuration module is used for configuring a plurality of reference output thresholds of the generator set under different reference AGC instructions according to the historical actual power and the historical set revolution of the equalization section corresponding to the historical AGC instructions;
the neural network unit is used for connecting the machine learning system, and acquiring the running real power of the unit and the running unit revolution loading resource data through the acquisition device in real time according to the running AGC instruction and the running AGC instruction for training so as to acquire a stable interval corresponding to the running real power and the machine running unit revolution under the running AGC instruction;
the correction module is used for correcting a plurality of reference output thresholds under different reference AGC instructions according to a stable interval corresponding to the running actual power and the machine running group revolution under the running AGC instructions, so that the running performance of the unit is optimized.
Further, the machine learning system is configured to establish a unit power generation model with the historical AGC command and the historical unit rotational speed as inputs and with the generator historic power as output.
Further, the correction module includes:
the correction unit is used for correcting the reference output threshold value under the corresponding reference AGC command according to the stable interval corresponding to the running actual power and the machine running group revolution under each running AGC command;
a dynamic configuration unit that sets an adjustment dead zone based on a corrected reference output threshold under a reference AGC instruction;
and the disturbance monitoring unit is used for drawing an operation curve according to the real-time collected operation power, revising and adjusting the dead zone according to the operation curve and monitoring the operation condition of the unit according to the real-time collected operation power.
Further, the dynamic configuration unit configures a plurality of adjustment dead zones according to the corrected reference AGC instruction and the corrected reference output threshold corresponding to the reference AGC instruction in different setting sections.
Further, the disturbance monitoring unit draws an operation curve according to the operation real-time power collected in real time, and sets critical values of the up-regulation period and the stationary period according to the operation curve.
Further, the machine learning system also comprises a storage module and a task management module;
the task management module is used for collecting the running actual power and the machine running group revolution under different running AGC instructions in real time according to a set period, and storing the running actual power and the machine running group revolution under different running AGC instructions into the storage module;
based on the learning task, the machine learning system loads the running actual transmitting power and the machine running group transfer in the memory module under different running AGC instructions to carry out iterative training so as to optimize the resource data.
Further, the disturbance monitoring unit is further provided with a scanning unit, which is used for scanning the end point value of the operation curve based on the time sequence, and taking the first end point value at the time of T0 as a reference to determine whether the second end point value at the time of T1 has a positive difference value of a set interval, and if the difference is stable in the set interval in a plurality of continuous moments, the up-regulation period is set;
if the difference value tends to 0 in a plurality of continuous moments, setting to be a stable period;
if the negative difference value of the set section is present in a plurality of consecutive time points, the set section is set as the down-regulation period.
Further, the operation curves are arranged and output according to a set period.
Referring to FIG. 3, FIG. 3 is a graph of operating curves from real-time collected operating power during actual operation of the unit, where P min J is the adjustable lower limit output of the unit, P max J is its adjustable upper limit force, P ni Is the rated output, P di The whole process of starting and stopping the grinding critical point power can be described as follows, wherein before the moment T0 and before the moment T1, the machine set stably operates near an output value P1, at the moment TO, an AGC control program issues a set point command with the power of P2 TO the machine set, the machine set starts TO expand the output (an up-regulating period), the machine set reliably spans an adjusting dead zone of P1 until the moment T1, then enters a stable period until the moment T2, the stable period process is finished, the machine set continues TO expand the output, enters an adjusting dead zone range for the first time until the moment T4, then slightly oscillates near P2 and stably operates near P2 until the moment T5, the AGC control program issues a new set point command TO the machine set, the power value is P3, and the machine set starts TO be adjusted down TO a down-regulating period subsequently; the adjustment dead zone is reliably crossed out at the time T6, enters the adjustment dead zone of P3 at the time T7, and stably runs nearby.
Examples
The invention also provides an AGC performance index online monitoring method, which comprises the following steps:
step 1), a unit power generation model is built by taking a historical AGC instruction and a historical unit rotating speed as inputs and taking the historic power of a generator as output; forming resource data for iterative training of the neural network unit by using the historical actual transmission power of the equalizing interval corresponding to the historical AGC instruction and the revolution of the historical unit;
step 2) configuring a plurality of reference output thresholds of the generator set under different reference AGC instructions according to the historical actual power and the historical set revolution of the equalization section corresponding to the historical AGC instructions;
step 3) real-time acquisition of the running real-time power of the unit and the running unit revolution loading resource data by the acquisition device according to the running AGC instruction and the running AGC instruction for training so as to acquire a stable interval corresponding to the running real-time power and the running unit revolution under the running AGC instruction;
and 4) correcting a plurality of reference output thresholds under different reference AGC instructions according to a stable interval corresponding to the running actual power and the number of revolutions of the machine running set under the running AGC instructions, so as to optimize the running performance of the machine set.
Further, in step 4):
the method comprises the steps of A, correcting a reference output threshold under a corresponding reference AGC command according to a stable interval corresponding to running actual power and machine running group revolution under each running AGC command;
setting an adjustment dead zone based on a reference output threshold value under a corrected reference AGC command;
and C, drawing an operation curve according to the operation actual power acquired in real time, revising and adjusting the dead zone according to the operation curve, and monitoring the operation condition of the unit according to the operation actual power acquired in real time.
Further, in step C): the method comprises the steps of determining whether a second endpoint value at a time T1 has a difference value of a set interval or not based on an endpoint value of a time sequence scanning operation curve and taking a first endpoint value at the time T0 as a reference, and setting the difference value as an up-regulation period if the difference value is stabilized in the set interval in a plurality of continuous moments;
if the difference value tends to 0 in a plurality of continuous moments, setting to be a stable period;
if the negative difference value of the set section is present in a plurality of consecutive time points, the set section is set as the down-regulation period.
According to the method, the dead zone, the up-regulation period, the down-regulation period and the stabilization period are set and regulated based on historical operation data of the unit, unit parameters are not used as standards, meanwhile, the set values are dynamically modulated according to actual operation of the unit, so that quantitative research on primary frequency modulation contribution rate, small disturbance qualification rate and AGC performance indexes of the operation unit is achieved, various indexes are monitored in real time, two-stage control intelligent analysis can be achieved, main factors affecting AGC assessment indexes and corresponding countermeasures are achieved, and AGC service compensation is improved, and primary frequency modulation electric quantity assessment is reduced.
Combining the 'two rules' AGC regulation performance index calculation method, establishing a dynamic mathematical model, and developing an on-line monitoring system for the primary frequency modulation contribution rate, the small disturbance qualification rate and the AGC performance index; the primary frequency modulation contribution rate, the small disturbance qualification rate and the AGC performance index are quantized, and the historical data are analyzed to dynamically correct the AGC regulation performance index in real time when the AGC regulation performance index has problems.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
- An agc performance index online monitoring system, comprising:monitoring the model;the monitoring model is provided with a machine learning system, a configuration module, a correction module and a neural network unit constructed by the machine learning system,the machine learning system is used for performing iterative training based on the historical data to obtain the historical actual power and the historical unit revolution of the equalizing interval corresponding to different historical AGC instructions in the historical data; forming resource data for iterative training of the neural network unit by using the historical actual transmission power of the equalizing interval corresponding to the historical AGC instruction and the revolution of the historical unit;the configuration module is used for configuring a plurality of reference output thresholds of the generator set under different reference AGC instructions according to the historical actual power and the historical set revolution of the equalization section corresponding to the historical AGC instructions;the neural network unit is used for connecting the machine learning system, and acquiring the running real power of the unit and the running unit revolution loading resource data through the acquisition device in real time according to the running AGC instruction and the running AGC instruction for training so as to acquire a stable interval corresponding to the running real power and the running unit revolution under the running AGC instruction;the correction module is used for correcting a plurality of reference output thresholds under different reference AGC instructions according to a stable interval corresponding to the running actual power and the running unit revolution under the running AGC instructions, so that the running performance of the unit is optimized;the correction module includes:the correction unit is used for correcting the reference output threshold value under the corresponding reference AGC command according to the stable interval corresponding to the running actual power and the running unit revolution under each running AGC command;a dynamic configuration unit that sets an adjustment dead zone based on a corrected reference output threshold under a reference AGC instruction;the disturbance monitoring unit is used for drawing an operation curve according to the operation actual power acquired in real time, revising and adjusting the dead zone according to the operation curve and monitoring the running condition of the unit according to the operation actual power acquired in real time;the dynamic configuration unit configures a plurality of adjustment dead zones according to the corrected reference AGC command and the corrected reference output threshold corresponding to the reference AGC command in different setting intervals.
- 2. The AGC performance index online monitoring system of claim 1, wherein the machine learning system is configured to establish a unit power generation model with historical AGC instructions and historical unit rotational speed as inputs and with generator historic power generation as output.
- 3. The AGC performance index online monitoring system of claim 1, wherein the disturbance monitoring unit draws an operation curve according to the operation real power collected in real time, and sets critical values of an up period and a stationary period according to the operation curve.
- 4. The AGC performance index online monitoring system of claim 1, wherein the machine learning system further comprises a storage module and a task management module;the task management module is used for collecting the running actual power and the running unit revolution under different running AGC instructions in real time according to a set period, and storing the running actual power and the running unit revolution under different running AGC instructions into the storage module;based on the learning task, the machine learning system loads the running actual transmitting power and the running machine set revolution in the storage module under different running AGC instructions to carry out iterative training so as to optimize the resource data.
- 5. The AGC performance index online monitoring system of claim 3 wherein the disturbance monitoring unit further comprises a scanning unit configured to scan an end point value of the operation curve based on the time sequence, and determine whether a second end point value at time T1 has a positive difference value of a set interval with reference to a first end point value at time T0, and if the difference is stable within the set interval in a plurality of consecutive times, set as an up period;if the difference value tends to 0 in a plurality of continuous moments, setting to be a stable period;if the negative difference value of the set section is present in a plurality of consecutive time points, the set section is set as the down-regulation period.
- 6. The AGC performance index online monitoring system of claim 5, wherein the operating curves are arranged and output according to a set period.
- The AGC performance index online monitoring method is characterized by comprising the following steps:step 1), a unit power generation model is built by taking a historical AGC instruction and a historical unit rotating speed as inputs and taking the historic power of a generator as output; forming resource data for iterative training of the neural network unit by using the historical actual transmission power of the equalizing interval corresponding to the historical AGC instruction and the revolution of the historical unit;step 2) configuring a plurality of reference output thresholds of the generator set under different reference AGC instructions according to the historical actual power and the historical set revolution of the equalization section corresponding to the historical AGC instructions;step 3) real-time acquisition of the running real-time power of the unit and the running unit revolution loading resource data by the acquisition device according to the running AGC instruction and the running AGC instruction for training so as to acquire a stable interval corresponding to the running real-time power and the running unit revolution under the running AGC instruction;step 4) correcting a plurality of reference output thresholds under different reference AGC instructions according to a stable interval corresponding to the running actual power and the running unit revolution under the running AGC instructions, so as to optimize the running performance of the unit;in step 4):the method comprises the steps of A, correcting a reference output threshold under a corresponding reference AGC command according to a stable interval corresponding to running actual power and running unit revolution under each running AGC command;setting an adjustment dead zone based on a reference output threshold value under a corrected reference AGC command;and C, drawing an operation curve according to the operation actual power acquired in real time, revising and adjusting the dead zone according to the operation curve, and monitoring the operation condition of the unit according to the operation actual power acquired in real time.
- 8. The AGC performance index online monitoring method of claim 7, wherein in step C): the method comprises the steps of determining whether a second endpoint value at a time T1 has a difference value of a set interval or not based on an endpoint value of a time sequence scanning operation curve and taking a first endpoint value at the time T0 as a reference, and setting the difference value as an up-regulation period if the difference value is stabilized in the set interval in a plurality of continuous moments;if the difference value tends to 0 in a plurality of continuous moments, setting to be a stable period;if the negative difference value of the set section is present in a plurality of consecutive time points, the set section is set as the down-regulation period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310317311.XA CN116436160B (en) | 2023-03-29 | 2023-03-29 | AGC performance index on-line monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310317311.XA CN116436160B (en) | 2023-03-29 | 2023-03-29 | AGC performance index on-line monitoring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116436160A CN116436160A (en) | 2023-07-14 |
| CN116436160B true CN116436160B (en) | 2023-12-22 |
Family
ID=87082577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310317311.XA Active CN116436160B (en) | 2023-03-29 | 2023-03-29 | AGC performance index on-line monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116436160B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488631A (en) * | 2015-12-04 | 2016-04-13 | 国家电网公司 | WAMS dynamic data based network source coordination online monitoring and assessment system |
| CN108363295A (en) * | 2017-12-27 | 2018-08-03 | 国网山东省电力公司电力科学研究院 | Fired power generating unit AGC Performance Assessment indexs based on System Discrimination calculate and prediction technique |
| CN111564869A (en) * | 2020-06-11 | 2020-08-21 | 国网山东省电力公司电力科学研究院 | Method and system for evaluating AGC performance of generator set |
| CN112149903A (en) * | 2020-09-22 | 2020-12-29 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Primary frequency modulation analysis and optimization method of thermal power generating unit based on BP neural network algorithm |
| CN112186811A (en) * | 2020-09-16 | 2021-01-05 | 北京交通大学 | AGC unit dynamic optimization method based on deep reinforcement learning |
| CN112819224A (en) * | 2021-01-29 | 2021-05-18 | 南京工程学院 | Unit output prediction and confidence evaluation method based on deep learning fusion model |
| CN115102239A (en) * | 2022-05-31 | 2022-09-23 | 国网湖南综合能源服务有限公司 | Energy storage power station primary frequency modulation control method and system considering SOC balance |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7085660B2 (en) * | 2003-05-13 | 2006-08-01 | Siemens Power Transmission & Distribution, Inc. | Energy management system in a power and distribution system |
-
2023
- 2023-03-29 CN CN202310317311.XA patent/CN116436160B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488631A (en) * | 2015-12-04 | 2016-04-13 | 国家电网公司 | WAMS dynamic data based network source coordination online monitoring and assessment system |
| CN108363295A (en) * | 2017-12-27 | 2018-08-03 | 国网山东省电力公司电力科学研究院 | Fired power generating unit AGC Performance Assessment indexs based on System Discrimination calculate and prediction technique |
| CN111564869A (en) * | 2020-06-11 | 2020-08-21 | 国网山东省电力公司电力科学研究院 | Method and system for evaluating AGC performance of generator set |
| CN112186811A (en) * | 2020-09-16 | 2021-01-05 | 北京交通大学 | AGC unit dynamic optimization method based on deep reinforcement learning |
| CN112149903A (en) * | 2020-09-22 | 2020-12-29 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Primary frequency modulation analysis and optimization method of thermal power generating unit based on BP neural network algorithm |
| CN112819224A (en) * | 2021-01-29 | 2021-05-18 | 南京工程学院 | Unit output prediction and confidence evaluation method based on deep learning fusion model |
| CN115102239A (en) * | 2022-05-31 | 2022-09-23 | 国网湖南综合能源服务有限公司 | Energy storage power station primary frequency modulation control method and system considering SOC balance |
Non-Patent Citations (1)
| Title |
|---|
| 适应电网多复杂工况的AGC控制模式转换技术研究;徐瑞 等;《电网技术》(第06期);第1785-1791页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116436160A (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114336702B (en) | Wind-solar storage station group power distribution collaborative optimization method based on double-layer random programming | |
| CN108092324B (en) | AGC control system and control method for wind power participating in peak shaving frequency modulation | |
| CN110518643B (en) | Control method and device for energy storage combined thermal power generating unit to participate in AGC frequency modulation | |
| CN110148956B (en) | Battery energy storage system auxiliary AGC control method based on MPC | |
| CN110768273A (en) | Control method for energy storage combined thermal power participation power grid secondary frequency modulation | |
| US11133676B2 (en) | System and method for fluctuating renewable energy-battery optimization to improve battery life-time | |
| CN116191473B (en) | Primary frequency modulation standby optimization method considering random-extreme disturbance | |
| CN115842359A (en) | Primary frequency modulation standby setting method of wind and light storage station considering dynamic frequency modulation performance | |
| CN111697578A (en) | Multi-target energy-storage-containing regional power grid operation control method | |
| CN109376426B (en) | Wind power grid-connected power scheduling method and device | |
| US20220220938A1 (en) | Method for controlling a renewable energy farm in compliance with obligations towards a power grid | |
| CN115471031A (en) | Low-carbon economic dispatching strategy for power system based on joint operation of carbon capture power plant and pumped storage | |
| CN116436160B (en) | AGC performance index on-line monitoring system and method | |
| CN110854852B (en) | Configuration method of key parameters of AGC main station in high-proportion hydropower area | |
| CN109888841A (en) | A kind of generating set load optimal distribution method | |
| CN115879714A (en) | Power system optimization scheduling method for electrolytic aluminum load participating in demand response | |
| CN113078639B (en) | High-proportion wind power system optimal scheduling method considering air conditioner load and frequency response | |
| CN106887848B (en) | Voltage power-less real-time control method based on Fuzzy Pattern Recognition | |
| CN115207918A (en) | Real-time stable control device suitable for new forms of energy grid-connected system | |
| CN115085252A (en) | Photovoltaic optimization network construction method for distribution network system | |
| CN114865715A (en) | MPC-based source network load-storage flexible resource real-time optimization scheduling method | |
| CN111404195B (en) | Intelligent gateway-based scheduling method for microgrid with distributed power supply | |
| CN108155675B (en) | Wind power plant group power optimization scheduling method based on prediction information and operation state | |
| CN111900740A (en) | Power system frequency modulation method and system based on demand response equipment | |
| CN116599163B (en) | High-reliability wind farm power control system based on frequency modulation control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |