CN116565966B - Intelligent hydraulic power generation double microcomputer automatic synchronous control system - Google Patents
Intelligent hydraulic power generation double microcomputer automatic synchronous control system Download PDFInfo
- Publication number
- CN116565966B CN116565966B CN202310780307.7A CN202310780307A CN116565966B CN 116565966 B CN116565966 B CN 116565966B CN 202310780307 A CN202310780307 A CN 202310780307A CN 116565966 B CN116565966 B CN 116565966B
- Authority
- CN
- China
- Prior art keywords
- curve
- power
- time
- neural network
- network model
- 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
- 238000010248 power generation Methods 0.000 title claims abstract description 25
- 230000001360 synchronised effect Effects 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 102
- 238000003062 neural network model Methods 0.000 claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000011217 control strategy Methods 0.000 claims abstract description 24
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 89
- 238000013480 data collection Methods 0.000 claims description 16
- 238000004146 energy storage Methods 0.000 claims description 9
- 230000001105 regulatory effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 2
- 238000004891 communication Methods 0.000 abstract description 4
- 230000001276 controlling effect Effects 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/40—Synchronising a generator for connection to a network or to another generator
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03B—MACHINES OR ENGINES FOR LIQUIDS
- F03B15/00—Controlling
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- 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
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- 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
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- 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
-
- 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]
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Control Of Eletrric Generators (AREA)
Abstract
The invention discloses an intelligent hydroelectric generation double microcomputer automatic synchronous control system, which relates to the technical field of hydroelectric generation automatic synchronous control, and is characterized in that a first neural network model for predicting an output power curve and a second neural network model for predicting a power grid load curve are trained by collecting output power training data and load power training data, a historical hydraulic characteristic curve set and a historical output power curve of a hydroelectric generation set to be controlled are collected, a predicted output power curve and a predicted power grid load curve are obtained, and a microcomputer control strategy is generated based on the predicted output power curve and the predicted power grid load curve; the method and the device avoid the problem that real-time synchronous control cannot be realized due to communication delay of the generator set or monitoring equipment of the power grid in the actual power generation process, and improve the stability of the power grid of hydroelectric power generation.
Description
Technical Field
The invention relates to the technical field of automatic synchronous control of hydroelectric generation, in particular to an intelligent double microcomputer automatic synchronous control system for hydroelectric generation.
Background
In hydroelectric generation, a microcomputer is required to be configured at the generator set end and the power grid end; the microcomputer of the generator set is mainly responsible for monitoring and controlling the output power of the generator so as to ensure that the output power of the generator set is synchronous with the load power of the power grid and meet the requirements of the power grid; the power grid microcomputer is responsible for monitoring parameters such as frequency, phase and voltage of the power grid, and knowing the running state and load demand of the power grid in real time so as to regulate and control and synchronously control the power grid;
the output power of the hydroelectric generating set is dynamically changed, and the load power of the power grid is also dynamically changed, so that the real-time communication between the microcomputer of the hydroelectric generating set and the microcomputer of the power grid is required to ensure that the real-time control output power of the microcomputer of the hydroelectric generating set is consistent with the load power preservation of the power grid, but the method has extremely high real-time requirements, and the adjustment of the output power by the hydroelectric generating set can be caused to generate errors when the real-time performance is insufficient, such as network delay, so that the stability of the power grid is damaged; therefore, a method for generating an output power control strategy for a generator set microcomputer based on the load power of the power grid in advance is needed, and the stability of the power grid is ensured;
the application publication number CN107134809A discloses an automatic synchronization grid-connected system and a grid-connected method of a power plant, and provides a grid-connected system which comprises a power supply loop, wherein the power supply loop is led out from a control power supply busbar to provide power for a synchronization direct current input relay DTK11, a synchronization alternating current input relay DTK12, an automatic grid-connected relay K1 and an input loop, the power supply loop is connected to a synchronization device, the input loop is also connected to the synchronization device, and the synchronization device outputs signals to a DCS. The problem of one-key grid connection of the power plant is solved, the human intervention link is reduced, the non-synchronous grid connection is prevented, and the APS function of the modern power plant is adapted; the system and method fail to address the problem of generating a synchronization strategy for controlling output power for a microcomputer;
therefore, the invention provides an intelligent hydraulic power generation double microcomputer automatic synchronous control system.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the intelligent hydraulic power generation double microcomputer automatic synchronous control system provided by the invention avoids the problem that real-time synchronous control cannot be realized due to communication delay of a generator set or monitoring equipment of a power grid in the actual power generation process, and improves the stability of the power grid of the hydraulic power generation.
To achieve the above object, an embodiment according to a first aspect of the present invention provides an intelligent hydraulic power generation double microcomputer automatic synchronization control system, including a training data collection module, a model training module, a historical data collection module, and a microcomputer control strategy generation module; wherein, each module is connected by a wired and/or wireless network mode;
the training data collection module is mainly used for collecting output power training data and load power training data in advance;
the output power training data comprises a plurality of sets of hydraulic characteristic curve sets and output power curves corresponding to each set of hydraulic characteristic curve sets;
the hydraulic characteristic curves are collected into a water flow time curve, a water head time curve and a water level height time curve which are acquired in each hydraulic power generation period in the historical power generation process of each hydraulic power generation unit; the hydroelectric generation period is determined according to the actual withering period of the water source position of the hydroelectric generating set;
the water flow time curve is a curve of the water flow flowing through the hydroelectric generating set along with the time change in the hydroelectric generating period, and the water flow is obtained by measuring in real time by using a flow sensor;
the water head is the height difference of water flow, the water head time curve is the curve of the change of the height difference of the water flow flowing through the hydroelectric generating set along with time in the hydroelectric generating period, and the water head is obtained by measuring in real time by using a distance sensor;
the water level height time curve is a curve of the water level height of water flowing through each hydroelectric generating set along with time in a hydroelectric generating period, and the water level height is obtained by using a water level meter to measure in real time;
the output power curve is a curve of the power value output by the hydroelectric generating set in real time along with the time change in the hydroelectric generating period, and the output power value can be obtained through real-time monitoring of a microcomputer at the generator end;
the load power training data comprises a plurality of groups of power grid load curves;
each group of power grid load curves is a curve of the change of the power load power of a power grid connected with the hydroelectric generating set along with time in a hydroelectric generating period, and the power load can be obtained through real-time monitoring of a microcomputer at the power grid end;
the training data collection module sends the collected output power training data and the load power training data to the model training module;
the model training module is mainly used for training a first neural network model for predicting an output power curve based on output power training data and training a second neural network model for predicting a power grid load curve based on load power training data;
the first neural network model for predicting the output power curve is trained in the following manner:
according to a preset prediction time step T, a preset first sliding step length and a preset first sliding window length, converting a water flow time curve, a water head time curve, a water level height time curve and an output power curve in each group of hydraulic characteristic curve sets into a plurality of groups of first training samples by using a sliding window method, taking the first training samples as input of a first neural network model, taking a predicted output power curve of a future prediction time step T as output of the first neural network model, taking an output power curve corresponding to the group of hydraulic characteristic curve sets in output power training data as a prediction target in a subsequent prediction time step T of each first training sample, taking a prediction accuracy as a training target, taking a mean square error or an average absolute error as a loss function to measure the accuracy of the prediction result, updating the weight and bias of the model by a reverse propagation algorithm, and generating a first neural network model of the predicted output power curve; the first neural network model is an LSTM neural network model;
the second neural network model for predicting the power grid load curve is trained in the following manner:
presetting a predicted time step T, a second sliding step and a second sliding window length according to practical experience, converting a power grid load curve into a plurality of second training samples by using a sliding window method, taking each group of second training samples as input of a second neural network model, taking a predicted power grid load curve of a future predicted time step T as output of the second neural network model, taking the power grid load curve in the subsequent predicted time step T of load power training data as a prediction target in the subsequent predicted time step T of each second training sample, and training the second neural network model; generating a second neural network model for predicting a power grid load curve; the second neural network model is an RNN neural network model;
the model training module sends the trained first neural network model and second neural network model to the microcomputer control strategy generation module;
the historical data collection module is mainly used for collecting a historical hydraulic characteristic curve set and a historical output power curve of the hydroelectric generating set to be controlled;
the method for collecting the historical hydraulic characteristic curve set and the historical power grid load curve of the hydraulic generator set to be controlled is as follows:
the set of historical hydraulic signature curves includes: acquiring a water flow time curve, a water head time curve, a water level height time curve and an output power curve of the hydroelectric generating set to be controlled in real time from the water source position of the hydroelectric generating set to be controlled in the length of a first sliding window before the current time;
the historical grid load profile includes: acquiring a power grid load curve of a second sliding window length from the current time in real time of a power grid connected with a hydroelectric generating set to be controlled;
the historical data collection module sends the collected historical hydraulic characteristic curve set and the historical output power curve to the microcomputer control strategy generation module;
the microcomputer control strategy generation module is mainly used for obtaining an output power curve in a predicted future prediction time step and a power grid load curve in the predicted future prediction time step by using a first neural network model and a second neural network model respectively based on a historical hydraulic characteristic curve set and a historical output power curve, and generating a microcomputer control strategy based on the output power curve in the predicted future prediction time step and the power grid load curve in the predicted future prediction time step;
the way to obtain the output power curve in the predicted future predicted time step and the grid load curve in the predicted future predicted time step is:
taking a water flow time curve, a water head time curve, a water level height time curve and an output power curve in the historical hydraulic characteristic curve set as a first training sample, inputting the first training sample into a first neural network model, and obtaining an output power curve in a predicted future predicted time step length T output by the first neural network model;
taking the power grid load curve in the historical power grid load curve as a second training sample, inputting the second training sample into a second neural network model, and obtaining the power grid load curve in a predicted future prediction time step length T output by the second neural network model;
the mode of generating microcomputer control strategy is as follows:
the number of each unit time in the output power curve in the future prediction time step is marked as s, and the corresponding output power at the moment s is marked as Gs;
marking the electric load power corresponding to the moment s in the power grid load curve in the future prediction time step as Fs;
calculating a power adjustment value Rs at a moment s, wherein a calculation formula of the power adjustment value Rs is Rs=Gs-Fs;
the microcomputer control strategy is as follows: at the s-th moment after the current moment, the output power of the generator set is adjusted to be the power adjustment value Rs through the microcomputer of the generator set;
when the power regulating value Rs is smaller than 0, judging whether the electric quantity stored in the energy storage system corresponding to the hydroelectric generating set is larger than the power regulating value Rs, and if so, supplementing the maximum electric power provided in the energy storage system into the power grid to ensure the stable operation of the power grid; if the power regulation value Rs is smaller than the power regulation value Rs, the power shortage early warning is initiated;
it will be appreciated that the amount of power stored in the energy storage system in real time may be obtained by accumulating the power adjustment values Rs in time sequence.
Compared with the prior art, the invention has the beneficial effects that:
the invention trains a multi-characteristic time sequence prediction neural network model (LSTM neural network model) for predicting a future output power curve by collecting output power training data and load power training data in advance, trains a cyclic neural network model (RNN neural network model) for predicting a future power grid load curve by using the load power training data, collects a historical hydraulic characteristic curve set and a historical output power curve in the length of a past sliding window in real time for a hydroelectric generating set to be controlled, respectively predicts the output power curve and the power grid load curve in a future prediction time step length T through the historical hydraulic characteristic curve set and the historical output power curve, calculates the output power to be regulated for the hydroelectric generating set at each moment based on the output power curve and the power grid load curve, and further generates a microcomputer control strategy; by generating the generation strategy of the output power for the generator set in advance, the problem that real-time synchronous control cannot be realized due to communication delay of monitoring equipment of the generator set or the power grid in the actual power generation process is avoided, and the stability of the power grid of hydroelectric power generation is improved.
Drawings
FIG. 1 is a block diagram of an intelligent hydraulic power generation double microcomputer automatic synchronous control system according to the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the intelligent hydroelectric power generation double microcomputer automatic synchronous control system comprises a training data collection module, a model training module, a historical data collection module and a microcomputer control strategy generation module; wherein, each module is connected by a wired and/or wireless network mode;
the training data collection module is mainly used for collecting output power training data and load power training data in advance;
in a preferred embodiment, the output power training data includes a plurality of sets of hydraulic characteristic curves, and each set of hydraulic characteristic curves corresponds to an output power curve;
it can be understood that, with the popularization of hydroelectric power generation, different hydroelectric power plants can store historical power generation data, and the hydraulic data of each hydroelectric power generating set in each hydroelectric power generation period can correspond to a group of hydraulic characteristic curve sets;
the hydraulic characteristic curves are collected into a water flow time curve, a water head time curve and a water level height time curve which are acquired in each hydraulic power generation period in the historical power generation process of each hydraulic power generation unit; the hydroelectric generation period is determined according to the actual withering period of the water source position of the hydroelectric generating set;
the flow rate of water is an important factor for determining the output power of the generator set. The water flow directly influences the rotating speed and the rotating force of the turbine, and further influences the output power of the generator; the rotating force of the turbine is influenced by the water head, so that the output power of the generator is influenced; the water level can directly influence the flow speed and flow of water flow, thereby influencing the rotation speed and torque of the water turbine and further influencing the output power of the generator;
the water flow time curve is a curve of the water flow flowing through the hydroelectric generating set along with the time change in the hydroelectric generating period, and the water flow can be obtained by using a flow sensor to measure in real time;
the water head is the height difference of water flow, the water head time curve is the curve of the change of the height difference of the water flow flowing through the hydroelectric generating set along with time in the hydroelectric generating period, and the water head can be obtained by using a distance sensor for real-time measurement;
the water level height time curve is a curve of the water level height of water flowing through each hydroelectric generating set along with time in a hydroelectric generating period, and the water level height can be obtained by real-time measurement by using a water level meter;
the output power curve is a curve of the power value output by the hydroelectric generating set in real time along with the time change in the hydroelectric generating period, and the output power value can be obtained through real-time monitoring of a microcomputer at the generator end;
the load power training data comprises a plurality of groups of power grid load curves;
each group of power grid load curves is a curve of the change of the power load power of a power grid connected with the hydroelectric generating set along with time in a hydroelectric generating period, and the power load can be obtained through real-time monitoring of a microcomputer at the power grid end;
it will be appreciated that the withering period of the water source is generally related to the season, and the load power of the grid is also generally related to the season, so that the output power training data and the load power training data may use the same hydroelectric generation period as the training data acquisition period, and the training data includes the output power training data and the load power training data;
the training data collection module sends the collected output power training data and the load power training data to the model training module;
the model training module trains a first neural network model for predicting an output power curve based on the output power training data, and trains a second neural network model for predicting a power grid load curve based on the load power training data;
in a preferred embodiment, the first neural network model of the predicted output power curve is trained in the following manner:
according to a preset prediction time step T, a preset first sliding step length and a preset first sliding window length, converting a water flow time curve, a water head time curve, a water level height time curve and an output power curve in each group of hydraulic characteristic curve sets into a plurality of groups of first training samples by using a sliding window method, taking the first training samples as input of a first neural network model, taking a predicted output power curve of a future prediction time step T as output of the first neural network model, taking an output power curve corresponding to the group of hydraulic characteristic curve sets in output power training data as a prediction target in a subsequent prediction time step T of each first training sample, taking a prediction accuracy as a training target, taking a mean square error or an average absolute error as a loss function to measure the accuracy of the prediction result, updating the weight and bias of the model by a reverse propagation algorithm, and generating a first neural network model of the predicted output power curve; preferably, the first neural network model is an LSTM neural network model;
the second neural network model for predicting the power grid load curve is trained in the following manner:
presetting a predicted time step T, a second sliding step and a second sliding window length according to practical experience, converting a power grid load curve into a plurality of second training samples by using a sliding window method, taking each group of second training samples as input of a second neural network model, taking a predicted power grid load curve of a future predicted time step T as output of the second neural network model, taking the power grid load curve in the subsequent predicted time step T of load power training data as a prediction target in the subsequent predicted time step T of each second training sample, and training the second neural network model; generating a second neural network model for predicting a power grid load curve; preferably, the second neural network model is an RNN neural network model;
it should be noted that, the sliding window method is used as a conventional technical means of a cyclic neural network model or a time sequence prediction model, and the invention is not described in principle here; but for the purpose of facilitating the implementation of the invention, the invention provides the following examples regarding sliding window methods:
assuming that a time prediction model is to be trained with history data 1,2,3,4,5,6, set the prediction time step to 1, the sliding step to 1 and the sliding window length to 3; then 3 sets of training data and corresponding predicted target data are generated: [1,2,3], [2,3,4] and [3,4,5] are used as training data, and [4], [5] and [6] are respectively used as prediction targets;
the model training module sends the trained first neural network model and second neural network model to the microcomputer control strategy generation module;
the historical data collection module is mainly used for collecting a historical hydraulic characteristic curve set and a historical output power curve of the hydroelectric generating set to be controlled;
in a preferred embodiment, the collection of the historical hydraulic characteristic curve set and the historical grid load curve of the hydraulic generator set to be controlled is as follows:
the set of historical hydraulic signature curves includes: acquiring a water flow time curve, a water head time curve, a water level height time curve and an output power curve of the hydroelectric generating set to be controlled in real time from the water source position of the hydroelectric generating set to be controlled in the length of a first sliding window before the current time;
the historical grid load profile includes: acquiring a power grid load curve of a second sliding window length from the current time in real time of a power grid connected with a hydroelectric generating set to be controlled;
the historical data collection module sends the collected historical hydraulic characteristic curve set and the historical output power curve to the microcomputer control strategy generation module;
the microcomputer control strategy generation module obtains an output power curve in a predicted future prediction time step and a power grid load curve in the predicted future prediction time step by using a first neural network model and a second neural network model based on a historical hydraulic characteristic curve set and a historical output power curve, and generates a microcomputer control strategy based on the output power curve in the predicted future prediction time step and the power grid load curve in the predicted future prediction time step;
in a preferred embodiment, the output power curve in the predicted future prediction time step and the grid load curve in the predicted future prediction time step are obtained in the following manner:
taking a water flow time curve, a water head time curve, a water level height time curve and an output power curve in the historical hydraulic characteristic curve set as a first training sample, inputting the first training sample into a first neural network model, and obtaining an output power curve in a predicted future predicted time step length T output by the first neural network model;
taking the power grid load curve in the historical power grid load curve as a second training sample, inputting the second training sample into a second neural network model, and obtaining the power grid load curve in a predicted future prediction time step length T output by the second neural network model;
further, the mode of generating the microcomputer control strategy is as follows:
the number of each unit time in the output power curve in the future prediction time step is marked as s, and the corresponding output power at the moment s is marked as Gs;
marking the electric load power corresponding to the moment s in the power grid load curve in the future prediction time step as Fs;
calculating a power regulating value Rs of a moment s, wherein the calculation formula of the power regulating value Rs is Rs=Gs-Fs, and the power regulating value Rs represents the s-th moment after the current moment and needs to control the adjustment degree of the hydroelectric generating set on the output power;
the microcomputer control strategy is as follows: at the s-th moment after the current moment, the output power of the generator set is adjusted to be the power adjustment value Rs through the microcomputer of the generator set; it should be noted that, the microcomputer of the generator set may adjust the output power by adjusting the rotation speed of the water turbine or storing the redundant output power, and the adjusting method belongs to a conventional technical means in the field, and is not described herein;
in a further embodiment of the present invention, when the power adjustment value Rs is smaller than 0, it is determined whether the maximum electric power provided by the energy storage system corresponding to the hydro-electric generating set at this time is greater than the power adjustment value Rs, and if the maximum electric power is greater than or equal to the power adjustment value Rs, the electric quantity stored in the energy storage system is supplemented to the power grid, so as to ensure the smooth operation of the power grid; if the power regulation value Rs is smaller than the power regulation value Rs, the power shortage early warning is initiated;
it will be appreciated that the amount of power stored in the energy storage system in real time may be obtained by accumulating the power adjustment values Rs in time sequence.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (1)
1. The intelligent hydroelectric power generation double microcomputer automatic synchronous control system is characterized by comprising a training data collection module, a model training module, a historical data collection module and a microcomputer control strategy generation module; wherein, each module is connected by a wired and/or wireless network mode;
the training data collection module is used for collecting output power training data and load power training data in advance and sending the collected output power training data and load power training data to the model training module;
the model training module is used for training a first neural network model for predicting an output power curve based on the output power training data, training a second neural network model for predicting a power grid load curve based on the load power training data, and sending the trained first neural network model and second neural network model to the microcomputer control strategy generation module;
the historical data collection module is used for collecting a historical hydraulic characteristic curve set and a historical output power curve of the hydroelectric generating set to be controlled and sending the collected historical hydraulic characteristic curve set and the collected historical output power curve to the microcomputer control strategy generation module;
the microcomputer control strategy generation module is used for respectively obtaining an output power curve in a predicted future prediction time step and a power grid load curve in the predicted future prediction time step by using the first neural network model and the second neural network model based on the historical hydraulic characteristic curve set and the historical output power curve, and generating a microcomputer control strategy based on the output power curve in the predicted future prediction time step and the power grid load curve in the predicted future prediction time step;
the output power training data comprises a plurality of sets of hydraulic characteristic curve sets and output power curves corresponding to each set of hydraulic characteristic curve sets;
each group of hydraulic characteristic curves is a water flow time curve, a water head time curve and a water level height time curve which are acquired in each group of hydraulic power generation period in the historical power generation process of each hydraulic power generator set; the hydroelectric generation period is determined according to the withering period corresponding to the water source position of the hydroelectric generating set;
the water flow time curve is a curve of the water flow flowing through the hydroelectric generating set along with the time change in the hydroelectric generating period, and the water flow is obtained by measuring in real time by using a flow sensor;
the water head is the height difference of water flow, the water head time curve is the curve of the change of the height difference of the water flow flowing through the hydroelectric generating set along with time in the hydroelectric generating period, and the water head is obtained by measuring in real time by using a distance sensor;
the water level height time curve is a curve of the water level height of water flowing through each hydroelectric generating set along with time in a hydroelectric generating period, and the water level height is obtained by measuring in real time by using a water level gauge;
the output power curve is a curve of the power value output by the hydroelectric generating set in real time along with the time change in the hydroelectric generating period, and the output power value is obtained by monitoring the power value in real time through a microcomputer at the generator end;
the load power training data comprises a plurality of groups of power grid load curves;
each group of power grid load curves is a curve of the change of the power load power of a power grid connected with the hydroelectric generating set along with time in a hydroelectric generating period, and the power load is obtained through real-time monitoring of a microcomputer at a power grid end;
the first neural network model for predicting the output power curve is trained in the following manner:
according to a preset prediction time step T, a preset first sliding step length and a preset first sliding window length, converting a water flow time curve, a water head time curve, a water level height time curve and an output power curve in each group of hydraulic characteristic curve sets into a plurality of groups of first training samples by using a sliding window method, taking the first training samples as the input of a first neural network model, taking a predicted output power curve of a future prediction time step T as output by the first neural network model, taking an output power curve corresponding to the group of hydraulic characteristic curve sets in the output power training data as a prediction target in a subsequent prediction time step T of each first training sample, taking a preset prediction accuracy as a training target, taking a mean square error or an average absolute error as a loss function to measure the accuracy of a prediction result, updating the weight and bias of the model by a back propagation algorithm, and generating a first neural network model of a predicted output power curve; the first neural network model is an LSTM neural network model;
the second neural network model for predicting the power grid load curve is trained in the following manner:
presetting a predicted time step T, a second sliding step and a second sliding window length, converting a power grid load curve into a plurality of second training samples by using a sliding window method, taking each group of second training samples as input of a second neural network model, taking a predicted power grid load curve of a future predicted time step T as output of the second neural network model, taking a power grid load curve in a subsequent predicted time step T of load power training data as a prediction target in each subsequent predicted time step T of the second training samples, and training the second neural network model; generating a second neural network model for predicting a power grid load curve; the second neural network model is an RNN neural network model;
the method for collecting the historical hydraulic characteristic curve set and the historical power grid load curve of the hydraulic generator set to be controlled is as follows:
the set of historical hydraulic signature curves includes: acquiring a water flow time curve, a water head time curve, a water level height time curve and an output power curve of the hydroelectric generating set to be controlled in real time from the water source position of the hydroelectric generating set to be controlled in the length of a first sliding window before the current time;
the historical grid load profile includes: acquiring a power grid load curve of a second sliding window length from the current time in real time of a power grid connected with a hydroelectric generating set to be controlled;
the way to obtain the output power curve in the predicted future predicted time step and the grid load curve in the predicted future predicted time step is:
taking a water flow time curve, a water head time curve, a water level height time curve and an output power curve in the historical hydraulic characteristic curve set as a first training sample, inputting the first training sample into a first neural network model, and obtaining an output power curve in a predicted future predicted time step length T output by the first neural network model;
taking the power grid load curve in the historical power grid load curve as a second training sample, inputting the second training sample into a second neural network model, and obtaining the power grid load curve in a predicted future prediction time step length T output by the second neural network model;
the mode of generating microcomputer control strategy is as follows:
the number of each unit time in the output power curve in the future prediction time step is marked as s, and the corresponding output power at the moment s is marked as Gs;
marking the electric load power corresponding to the moment s in the power grid load curve in the future prediction time step as Fs;
calculating a power adjustment value Rs at a moment s, wherein a calculation formula of the power adjustment value Rs is Rs=Gs-Fs;
the microcomputer control strategy is as follows: at the s-th moment after the current moment, the output power of the generator set is adjusted to be the power adjustment value Rs through the microcomputer of the generator set;
when the power regulating value Rs is smaller than 0, judging whether the maximum electric power which can be provided in the energy storage system corresponding to the hydroelectric generating set at the moment is larger than the power regulating value Rs, and if so, supplementing the electric quantity stored in the energy storage system into a power grid; if the power regulation value Rs is smaller than the power regulation value Rs, the power shortage early warning is initiated;
the amount of power stored in real time in the energy storage system is obtained by accumulating the power adjustment values Rs in time sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310780307.7A CN116565966B (en) | 2023-06-29 | 2023-06-29 | Intelligent hydraulic power generation double microcomputer automatic synchronous control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310780307.7A CN116565966B (en) | 2023-06-29 | 2023-06-29 | Intelligent hydraulic power generation double microcomputer automatic synchronous control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116565966A CN116565966A (en) | 2023-08-08 |
| CN116565966B true CN116565966B (en) | 2023-10-24 |
Family
ID=87486455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310780307.7A Active CN116565966B (en) | 2023-06-29 | 2023-06-29 | Intelligent hydraulic power generation double microcomputer automatic synchronous control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116565966B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117729221B (en) * | 2024-02-18 | 2024-04-19 | 成都秦川物联网科技股份有限公司 | Ultrasonic water meter data synchronization method, internet of things system and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1131521A (en) * | 1997-05-12 | 1999-02-02 | Matsushita Electric Ind Co Ltd | Fuel cell system and power load prediction device |
| CN104600756A (en) * | 2015-01-29 | 2015-05-06 | 华中科技大学 | Cluster equivalent modeling method for small and medium size hydroelectric generating sets |
| CN109462231A (en) * | 2018-11-15 | 2019-03-12 | 合肥工业大学 | Optimization of Load Dispatching method, system and the storage medium of resident's micro-capacitance sensor |
| CN113919232A (en) * | 2021-10-25 | 2022-01-11 | 北京航天创智科技有限公司 | Photovoltaic power station power prediction method and system based on recurrent neural network |
| EP3968247A1 (en) * | 2019-06-21 | 2022-03-16 | Siemens Aktiengesellschaft | Power load data prediction method and device, and storage medium |
| CN114707767A (en) * | 2022-05-18 | 2022-07-05 | 长沙学院 | Method for predicting peak-adjustable power of new energy power system in off-peak period |
| CN115169723A (en) * | 2022-07-26 | 2022-10-11 | 华为数字能源技术有限公司 | Power generation power prediction method, load prediction method and model training method |
| CN115471362A (en) * | 2022-09-26 | 2022-12-13 | 东南大学 | Comprehensive energy source-load prediction method for depth feature-guided two-stage transfer learning |
| CN116316654A (en) * | 2023-02-27 | 2023-06-23 | 国网山东省电力公司济宁供电公司 | Intelligent household electrical appliance power consumption flexible load optimal scheduling method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020107851A1 (en) * | 2018-11-29 | 2020-06-04 | 天津大学 | Low-cost commissioning method and system for air conditioning system based on existing large-scale public building |
-
2023
- 2023-06-29 CN CN202310780307.7A patent/CN116565966B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1131521A (en) * | 1997-05-12 | 1999-02-02 | Matsushita Electric Ind Co Ltd | Fuel cell system and power load prediction device |
| CN104600756A (en) * | 2015-01-29 | 2015-05-06 | 华中科技大学 | Cluster equivalent modeling method for small and medium size hydroelectric generating sets |
| CN109462231A (en) * | 2018-11-15 | 2019-03-12 | 合肥工业大学 | Optimization of Load Dispatching method, system and the storage medium of resident's micro-capacitance sensor |
| EP3968247A1 (en) * | 2019-06-21 | 2022-03-16 | Siemens Aktiengesellschaft | Power load data prediction method and device, and storage medium |
| CN113919232A (en) * | 2021-10-25 | 2022-01-11 | 北京航天创智科技有限公司 | Photovoltaic power station power prediction method and system based on recurrent neural network |
| CN114707767A (en) * | 2022-05-18 | 2022-07-05 | 长沙学院 | Method for predicting peak-adjustable power of new energy power system in off-peak period |
| CN115169723A (en) * | 2022-07-26 | 2022-10-11 | 华为数字能源技术有限公司 | Power generation power prediction method, load prediction method and model training method |
| CN115471362A (en) * | 2022-09-26 | 2022-12-13 | 东南大学 | Comprehensive energy source-load prediction method for depth feature-guided two-stage transfer learning |
| CN116316654A (en) * | 2023-02-27 | 2023-06-23 | 国网山东省电力公司济宁供电公司 | Intelligent household electrical appliance power consumption flexible load optimal scheduling method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116565966A (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112219028B (en) | Wind turbine control method | |
| CN102725520B (en) | A wind turbine having a control method and controller for performing predictive control of a wind turbine generator | |
| KR101176394B1 (en) | Wind power generation system and its operation control method | |
| CN116565966B (en) | Intelligent hydraulic power generation double microcomputer automatic synchronous control system | |
| CN101931241B (en) | Wind farm grid-connected coordination control method | |
| EP2313652B1 (en) | A method of controlling a wind power plant | |
| CN112868157A (en) | Method for feeding electric power into an electric supply network and wind park | |
| CN102075014A (en) | Large grid real-time scheduling method for accepting access of wind power | |
| AU2007362449A1 (en) | Wind turbine generator system and operation control method therefor | |
| CN109038613A (en) | A kind of adaptive low frequency deloading method counted and wind-powered electricity generation virtual inertia/primary frequency modulation responds | |
| CN107869420B (en) | Method and system for controlling yaw of wind turbine farm | |
| CN110021942A (en) | A kind of frequency modulation control method based on DCS | |
| CN111244968A (en) | Wind power plant voltage control method and system considering influence of power grid voltage supporting capacity | |
| CN117905638B (en) | Wind driven generator optimal control method and system based on reinforcement learning | |
| JP2021114856A (en) | Wind power output prediction method and prediction device | |
| CN103557117A (en) | Power curve acquisition device for wind turbine generator system | |
| CN111130122B (en) | Online monitoring method for reactive power control capability of wind power plant | |
| CN115793558B (en) | Intelligent control system for secondary pipe network of heating power station | |
| CN108631368A (en) | The energy storage configuration method of meter and storage energy operation loss leeward storage system combined dispatching | |
| CN112943557B (en) | Wind power plant, wind generating set and method and equipment for predicting operation state of wind generating set | |
| CN212454682U (en) | Wind power plant wake flow control system based on externally-hung controller | |
| CN108431405B (en) | Method and system for controlling wind turbines in a wind turbine park | |
| CN117411081B (en) | Green energy consumption control method, device, equipment and storage medium | |
| EP4148938A1 (en) | System and method for controlling a power generating system | |
| CN107171366B (en) | Combustion turbine power control system and its control method for general mood complementary system |
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 |