CN117878931B - Emergency energy scheduling system and method for new energy power station - Google Patents
Emergency energy scheduling system and method for new energy power station Download PDFInfo
- Publication number
- CN117878931B CN117878931B CN202410277557.3A CN202410277557A CN117878931B CN 117878931 B CN117878931 B CN 117878931B CN 202410277557 A CN202410277557 A CN 202410277557A CN 117878931 B CN117878931 B CN 117878931B
- Authority
- CN
- China
- Prior art keywords
- power supply
- power
- information
- subsystem
- new energy
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012544 monitoring process Methods 0.000 claims abstract description 83
- 230000003993 interaction Effects 0.000 claims abstract description 29
- 238000006243 chemical reaction Methods 0.000 claims abstract description 28
- 238000007726 management method Methods 0.000 claims description 31
- 230000002159 abnormal effect Effects 0.000 claims description 30
- 238000003066 decision tree Methods 0.000 claims description 27
- 238000007637 random forest analysis Methods 0.000 claims description 25
- 230000004044 response Effects 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000003745 diagnosis Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 8
- 230000006978 adaptation Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000638 solvent extraction Methods 0.000 claims description 4
- 238000003776 cleavage reaction Methods 0.000 claims description 3
- 230000007017 scission Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 abstract description 7
- 230000008859 change Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000009472 formulation Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000002803 fossil fuel Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013496 data integrity verification Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- ZZUFCTLCJUWOSV-UHFFFAOYSA-N furosemide Chemical compound C1=C(Cl)C(S(=O)(=O)N)=CC(C(O)=O)=C1NCC1=CC=CO1 ZZUFCTLCJUWOSV-UHFFFAOYSA-N 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Abstract
The application provides an emergency energy scheduling system and method for a new energy power station, wherein the system comprises a power management subsystem, an electric energy distribution subsystem, an energy conversion subsystem, a data interaction and monitoring subsystem and a coordination control subsystem; the power management subsystem acquires the state information of the power supply and performs switching operation of the main power supply and the auxiliary power supply based on the state information; the electric energy distribution subsystem adjusts electric power output parameters of the power grid and the power supply based on the electric power supply information and the electric power demand information; the energy conversion subsystem converts the high-voltage direct current into low voltage electricity; the data interaction and monitoring subsystem monitors and acquires the operation information of the new energy power station; and the cooperative control subsystem generates a scheduling instruction based on the operation information and schedules all subsystems in the new energy power station. The application can timely respond and switch the main power supply and the auxiliary power supply of the new energy power station, ensure the stable operation of the new energy power station, and optimize the management and the dispatch of the new energy power station.
Description
Technical Field
The application relates to the technical field of energy scheduling, in particular to an emergency energy scheduling system and method for a new energy power station.
Background
New energy power stations generally refer to devices or systems that are powered using new energy sources (e.g., solar, wind, hydro, or electric) to replace traditional fossil fuel (e.g., coal, oil, and natural gas) energy sources. Among the full-swing drilling machine power stations, it is a new energy power station because it uses electricity rather than a conventional diesel engine, and the new energy power station is generally more efficient and has less impact on the environment than a conventional fossil fuel power station.
The new energy power station is generally designed with a flexible energy supply mode, can be adjusted according to requirements and conditions, and can be powered by a power grid or a power battery; new energy power stations are typically equipped with intelligent control systems, such as Vehicle Control Units (VCUs), to optimize energy consumption and improve efficiency, and are typically provided with remote control and monitoring capabilities, capable of data transmission and reception via wireless communication modules.
However, the conventional new energy power station does not have an effective management mechanism to monitor and manage the main power supply and the auxiliary power supply in real time, which may cause that the main power supply cannot be switched to the auxiliary power supply in time when a problem occurs in the main power supply, and the stable operation of the power station is affected. Meanwhile, the traditional new energy power station may not have an effective coordination control module to centrally manage and schedule the running states of all systems, which may lead to unreasonable resource allocation, influence the utilization efficiency of energy, and may not respond to the running state change of the power station in time to influence the stable running of the power station.
Disclosure of Invention
The application provides an emergency energy scheduling system and method for a new energy power station, and aims to solve the problems that in the prior art, the new energy power station cannot switch a main power supply and a secondary power supply in time, so that operation is unstable, and scheduling management efficiency of the new energy power station is low.
In order to achieve the above objective, an embodiment of a first aspect of the present application provides an emergency energy scheduling system for a new energy power station, including a power management subsystem, an electric energy distribution subsystem, an energy conversion subsystem, a data interaction and monitoring subsystem, and a coordination control subsystem;
the power management subsystem is used for acquiring state information of a power supply, the power supply comprises a main power supply and a secondary power supply, and switching operation of the main power supply and the secondary power supply is performed based on the state information so as to provide high-voltage direct current for the energy conversion subsystem;
The electric energy distribution subsystem is used for acquiring electric power supply information of a power grid and the power supply and electric power demand information of the new energy power station, and adjusting electric power output parameters of the power grid and the power supply based on the electric power supply information and the electric power demand information so as to control output of high-voltage direct current of the power grid and the power supply based on the electric power output parameters;
The energy conversion subsystem is used for converting high-voltage direct current into low-voltage electricity so as to respond to the electric power demand information of the new energy power station;
The data interaction and monitoring subsystem is used for monitoring and acquiring the operation information of the new energy power station;
The coordination control subsystem is used for generating a scheduling instruction based on the running information and scheduling the power management subsystem, the electric energy distribution subsystem, the energy conversion subsystem and the data interaction and monitoring subsystem based on the scheduling instruction.
Further, the power management subsystem comprises a power supply monitoring module, a power supply switching control module and a fault diagnosis and protection module;
The power supply monitoring module is used for monitoring first state information of the main power supply and second state information of the auxiliary power supply;
the fault diagnosis and protection module is used for analyzing the first state information, generating a switching instruction when the main power supply is determined to be faulty based on the first state information, and sending the switching instruction to the power supply switching control module;
the power supply switching control module is used for realizing switching between the main power supply and the auxiliary power supply based on the switching instruction.
Further, the power supply monitoring module comprises a power supply adaptation selection sub-module, a dynamic threshold monitoring sub-module and an emergency fault response sub-module;
The power supply adaptation selection submodule is used for selecting a power supply adapter which is the same as the main power supply for the auxiliary power supply;
the dynamic threshold monitoring sub-module is used for monitoring and predicting the state information of the power supply in real time;
The emergency fault response sub-module is used for starting the auxiliary power supply to supply power when the main power supply fails.
Further, the dynamic threshold monitoring submodule comprises a parameter monitoring unit, a threshold setting unit, a real-time state analysis unit and a fault response unit;
The parameter monitoring unit is used for acquiring state information of the power supply, wherein the state information at least comprises current, voltage and temperature data characteristics;
The threshold setting unit is used for dynamically adjusting the parameter threshold of the power supply based on a preset dynamic threshold judging model by combining historical state data, the current running environment and the state information;
The real-time state analysis unit is used for visually displaying the state information, analyzing the state information based on a random forest algorithm by combining the parameter threshold value, and obtaining a prediction result of whether the state information is abnormal or not;
And the fault response unit is used for starting a fault diagnosis program and adjusting the operation parameters of the power supply when the prediction result is abnormal.
Further, the analyzing the state information based on the random forest algorithm to obtain a prediction result of whether the state information is abnormal, including:
acquiring characteristic variation of each data characteristic in the state information;
Based on the state information and the characteristic variation, acquiring a preprocessing data set of a random forest algorithm;
Acquiring a plurality of sub-data sets from the preprocessing data set based on a Bootstrap method;
Selecting a data feature with the minimum radix information gain from a group of randomly selected data features based on a binary recursive segmentation technology for each sub data set to segment, and constructing a decision tree;
constructing a random forest model by adopting all constructed decision trees, wherein each decision tree makes independent decisions on the state information;
Predicting the state information acquired in real time by using a random forest model, and obtaining a decision result by each tree;
if more than half of the decision trees predict that one of the data features belongs to the abnormal category, marking the data features as abnormal states, and determining that the state information is abnormal.
Further, the constructing a decision tree for each sub-data set by adopting a binary recursive partitioning technique, selecting, on each decision tree node, a data feature with the smallest radix information gain from a group of randomly selected data features for partitioning, including:
Randomly selecting data characteristics for each sub-data set, and calculating the base information gain of the data characteristics in the sub-data set;
Selecting a data feature with minimum base information gain, determining a division point of the sub-data set, and taking the data feature and the corresponding division point as an optimal feature and an optimal division point;
and dividing the sub-data set according to the optimal characteristics and the optimal dividing points.
Further, the calculation formula of the kene information gain is as follows:
In the method, in the process of the invention, And (3) withRepresenting two child nodes respectivelyAndThe number of samples in the sample set,Representing child nodesIs not pure in terms of the radical of (c) and (d),Representing child nodesIs not pure in terms of the radical of (c) and (d),Indicating total genii purity after cleavage.
Further, the obtaining the power supply information of the power grid and the power source and the power demand information of the new energy power station, and adjusting the power output parameters of the power grid and the power source based on the power supply information and the power demand information includes:
Acquiring power supply information of a power grid and the power supply;
Based on the historical power demand information and the state information of the power supply, predicting and obtaining the power demand information of the new energy power station;
formulating an electrical energy allocation strategy based on the electrical power supply information and the electrical power demand information;
a power output parameter of the power grid and the power source is determined based on the power distribution strategy.
Further, the generating a scheduling instruction based on the running information, and scheduling the power management subsystem, the electric energy distribution subsystem, the energy conversion subsystem, and the data interaction and monitoring subsystem based on the scheduling instruction includes:
evaluating the current running state of the new energy power station based on the running information;
based on the evaluation result, formulating a scheduling strategy, and generating a scheduling instruction according to the formulated scheduling strategy;
Scheduling the power management subsystem, the electric energy distribution subsystem, the energy conversion subsystem and the data interaction and monitoring subsystem based on the scheduling instruction;
acquiring feedback information, and verifying whether a scheduling result accords with expectations based on the feedback information;
and if the result does not accord with the expected or the current running state changes, re-evaluating the current running state and formulating a scheduling strategy.
To achieve the above object, a second aspect of the present application provides an emergency energy scheduling method for a new energy power station, which is applied to an emergency energy scheduling system for a new energy power station, including:
Acquiring state information of a power supply, wherein the power supply comprises a main power supply and a secondary power supply, and switching operation of the main power supply and the secondary power supply is performed based on the state information so as to provide high-voltage direct current;
Acquiring power supply information of a power grid and the power supply and power demand information of the new energy power station, and adjusting power output parameters of the power grid and the power supply based on the power supply information and the power demand information so as to control output of high-voltage direct current of the power grid and the power supply based on the power output parameters;
converting the high-voltage direct current into low voltage power to respond to the power demand information of the new energy power station;
monitoring and acquiring the operation information of the new energy power station;
And generating a scheduling instruction based on the running information, and scheduling the power management subsystem, the electric energy distribution subsystem, the energy conversion subsystem and the data interaction and monitoring subsystem based on the scheduling instruction.
The emergency energy scheduling system and the emergency energy scheduling method for the new energy power station have the beneficial effects that: when the main power supply fails, the power management subsystem is switched to the auxiliary power supply to supply power, so that the power station can quickly respond, the running stability of the power station is improved, and the loss caused by untimely switching is reduced; the electric energy distribution subsystem adjusts the electric power output parameters of the power supply in real time according to the electric power supply information and the electric power demand information, can adapt to different conditions, provides high-voltage direct current according with the demand, and has high energy utilization efficiency; meanwhile, the operation information of the new energy power station is monitored through the data interaction and monitoring subsystem, so that the cooperation control subsystem can reasonably and scientifically schedule all subsystems in the whole new energy power station, and management and scheduling of the new energy power station are optimized.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a schematic block diagram of an emergency energy scheduling system for a new energy power station according to an embodiment of the present application.
Fig. 2 is a schematic block diagram of a power management subsystem in an emergency energy dispatching system for a new energy power station according to an embodiment of the present application.
Fig. 3 is a schematic block diagram of a power monitoring module in an emergency energy dispatching system for a new energy power station according to an embodiment of the present application.
Fig. 4 is a schematic block diagram of a dynamic threshold detection sub-module in an emergency energy scheduling system for a new energy power station according to an embodiment of the present application.
Fig. 5 is a schematic flow chart of an emergency energy scheduling method for a new energy power station according to an embodiment of the application.
Reference numerals illustrate:
1. A power management subsystem; 11. a power supply monitoring module; 111. a power supply adaptation selection sub-module; 112. a dynamic threshold monitoring sub-module; 1121. a parameter monitoring unit; 1122. a threshold setting unit; 1123. a real-time state analysis unit; 1124. a fault response unit; 113. an intelligent prediction adjustment sub-module; 114. an emergency fault response sub-module; 12. a power supply switching control module; 13. a fault diagnosis and protection module; 2. a power distribution subsystem; 3. an energy conversion subsystem; 4. a data interaction and monitoring subsystem; 5. and a coordinated control subsystem.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
An emergency energy scheduling system and method for a new energy power station according to an embodiment of the present application are described below with reference to the accompanying drawings.
As shown in fig. 1, the system comprises a power management subsystem 1, an electric energy distribution subsystem 2, an energy conversion subsystem 3, a data interaction and monitoring subsystem 4 and a coordination control subsystem 5, wherein the power management subsystem 1 is used for acquiring state information of a power supply, the power supply comprises a main power supply and a secondary power supply, and switching operation of the main power supply and the secondary power supply is performed based on the state information so as to provide high-voltage direct current for the energy conversion subsystem 3; the electric energy distribution subsystem 2 is used for acquiring electric power supply information of the power grid and the power supply and electric power demand information of the new energy power station, and adjusting electric power output parameters of the power grid and the power supply based on the electric power supply information and the electric power demand information so as to control output of high-voltage direct current of the power grid and the power supply based on the electric power output parameters; the energy conversion subsystem 3 is used for converting high-voltage direct current into low voltage power to respond to the power demand information of the new energy power station; the data interaction and monitoring subsystem 4 is used for monitoring and acquiring the operation information of the new energy power station; the cooperative control subsystem 5 is configured to generate a scheduling instruction based on the operation information, and schedule the power management subsystem 1, the electric energy distribution subsystem 2, the energy conversion subsystem 3, and the data interaction and monitoring subsystem 4 based on the scheduling instruction.
Referring to fig. 2, in one embodiment, the power management subsystem 1 includes a power monitoring module 11, a fault diagnosis and protection module 13, and a power switching control module 12; the power supply monitoring module 11 is used for monitoring the first state information of the main power supply and the second state information of the auxiliary power supply; the fault diagnosis and protection module 13 is configured to analyze the first state information, generate a switching instruction when determining that the main power source has failed based on the first state information, and send the switching instruction to the power source monitoring module 11; the power supply switching control module 12 is configured to implement switching between the main power supply and the auxiliary power supply based on the switching instruction.
Specifically, the main task of the power management subsystem 1 is to ensure stable operation of the new energy power station, in which the power monitoring module 11 monitors state information of the power supply in real time, including working state and performance parameters, through real-time monitoring and flexible switching of the main power supply and the auxiliary power supply. The working state refers to the current state of the power supply, such as working, standby, shutdown, maintenance and the like, and the performance parameters refer to various parameters of each battery in the power supply, such as charge and discharge states, voltage, current, temperature and the like.
The fault diagnosis and protection module 13 is configured to diagnose a fault of the main power supply in real time and take protection measures, and if the fault of the main power supply is detected through the first status information, generate a switching instruction, send the switching instruction to the power supply switching control module 12, and notify the auxiliary power supply to rapidly take over the power supply. If the main power supply fails, the auxiliary power supply can rapidly take over the power supply, so that seamless switching between the main power supply and the auxiliary power supply is realized, and continuous power supply of the new energy power station is ensured.
Referring to FIG. 3, in one embodiment, the power monitoring module 11 includes a power adaptation selection sub-module 111, a dynamic threshold monitoring sub-module 112, an intelligent predictive conditioning sub-module 113, an emergency fault response sub-module 114; a power adapter selection sub-module 111 for selecting the same power adapter as the main power supply; the dynamic threshold monitoring sub-module 112 is configured to monitor and predict state information of the power supply in real time based on a preset dynamic threshold judgment model; an emergency fault response sub-module 114, configured to start the secondary power supply to supply power through an emergency fault response mechanism when the primary power supply fails; the intelligent prediction adjustment sub-module 113 is configured to automatically adjust output information of the power supply based on a preset prediction control algorithm. The predictive control algorithm in this embodiment refers to an algorithm for adjusting the output parameters of the power supply according to the actual power demand in the normal operation of the system, and the algorithm may be obtained by the operation rule in the actual power plant, which is not limited in this embodiment.
Specifically, the power adapter selection submodule 111 may select a power adapter having the same function as the main power module for the auxiliary power to ensure that the auxiliary power can smoothly take over when the main power fails; the dynamic threshold monitoring sub-module 112 monitors the power status information in real time by using a dynamic threshold judgment model, and the intelligent prediction adjustment sub-module 113 can automatically adjust the output voltage and current of the power supply by using a prediction control algorithm so as to adapt to the power demand of the power station; the emergency fault response sub-module 114 rapidly activates the secondary power module to take over the power supply by an emergency fault response mechanism when the primary power fails.
Referring to fig. 4, in one embodiment, the dynamic threshold monitoring sub-module 112 includes a parameter monitoring unit 1121, a threshold setting unit 1122, a real-time status analysis unit 1123, and a fault response unit 1124; the parameter monitoring unit 1121 is configured to obtain status information of the power supply; the threshold setting unit 1122 is configured to dynamically adjust a parameter threshold of the power supply based on a preset dynamic threshold judgment model in combination with the historical state data, the current operating environment and the state information; the real-time state analysis unit 1123 is configured to visually display the state information, and analyze the state information based on a random forest algorithm in combination with a parameter threshold to obtain a prediction result of whether the state information is abnormal; and a fault response unit 1124 for starting a fault diagnosis program when the predicted result is abnormal.
Specifically, in the dynamic threshold monitoring module, the threshold setting unit 1122 combines the historical state data, the current running environment and the state information to realize automatic adjustment of the parameter threshold, the parameter threshold can be regarded as an important reference index in the random forest algorithm, and when one or more running parameters in the state information of the power supply exceed the parameter threshold, the current power supply can be regarded as an abnormal state. The threshold setting unit 1122 may set the parameter threshold of the power supply according to different situations of the new energy power station, for example, the parameter threshold of the output voltage and the output current under the peak of the power consumption needs to be properly increased, so as to reduce the occurrence of false alarm or even false switching of the power supply.
Further, a dynamic threshold judgment model can be constructed based on historical electricity consumption information, electricity consumption prediction conditions under external factors such as different time and different seasons are obtained, so that parameter thresholds are dynamically set according to the electricity consumption prediction conditions, and scientific basis is further provided for dynamic setting of the parameter thresholds. Meanwhile, the cloud computing technology is also utilized to optimize the big data processing and remote monitoring capability. In addition, the parameter threshold value also needs to be adjusted according to different working states of the power supply so as to dynamically adapt to the power supply under different working states.
The real-time state analysis unit 1123 can visually display state information, so that a manager can better understand the running state of the power supply; and analyzing the state information based on a random forest algorithm and combining a parameter threshold value to obtain a prediction result of whether the state information is abnormal. Finally, the fault response unit 1124 automatically initiates a fault diagnosis procedure when a fault or abnormal condition is detected, and automatically restores or adjusts the operating parameters of the power supply when some abnormal minor conditions occur. In this embodiment, the state information abnormality is often involved, for example, the temperature of the main power battery is too high, and short circuit is often caused, and prediction can be achieved by monitoring the state information.
In one embodiment, the state information is analyzed based on a random forest algorithm to obtain a prediction result of whether the state information is abnormal, and the method further includes the following steps:
S101, acquiring feature variation of each data feature in state information;
S102, acquiring a preprocessing data set of a random forest algorithm based on state information and characteristic variation;
s103, acquiring a plurality of sub-data sets from the preprocessed data set based on a Bootstrap method;
S104, constructing a decision tree for each sub-data set by adopting a binary recursive segmentation technology, and selecting a data feature with the minimum radix information gain from a group of randomly selected data features on each decision tree node for segmentation;
S105, constructing a random forest model by adopting all the generated decision trees, wherein each tree makes independent decisions on the state information;
s106, predicting state information acquired in real time by using a random forest model, and acquiring a decision result by each tree;
And S107, if most decision trees predict that one of the data features belongs to an abnormal category, marking the data feature as an abnormal state, and determining that the state information is abnormal.
The method comprises the steps of constructing a decision tree for each sub-data set by adopting a binary recursive segmentation technology, selecting a data feature with the smallest radix information gain from a group of randomly selected data features on each decision tree node for segmentation, and further comprising the following steps:
S201, randomly selecting data characteristics on each decision tree node, and calculating the base information gain of the data characteristics in the sub-data set;
S202, selecting the data characteristic with the minimum gain of the radix information, determining the dividing points of the sub-data set, and taking the data characteristic and the corresponding dividing point as the optimal characteristic and the optimal dividing point;
S203, dividing the sub-data set according to the optimal characteristics and the optimal dividing points.
Specifically, the calculation formula of the gain of the kene information in this embodiment is:
In the method, in the process of the invention, And (3) withRepresenting two child nodes respectivelyAndThe number of samples in the sample set,Representing child nodesIs not pure in terms of the radical of (c) and (d),Representing child nodesIs not pure in terms of the radical of (c) and (d),Indicating total genii purity after cleavage.
Where, the genii-purity is an index for measuring the degree of confusion of a data set in a decision tree algorithm, for a data set, if all samples belong to the same class, the data set can be said to be completely pure, and the genii-purity is 0, whereas if the samples of a data set are uniformly distributed in a plurality of classes, the degree of confusion of the data set is the highest, and the genii-purity is close to 1.
Wherein,The calculation formula of the index is:
；
In the method, in the process of the invention, Representing categoriesIn the sampleIs used to determine the frequency of occurrence of the signal,Representation ofAn index.
Specifically, for steps S101-S107 and steps S201-S204, the embodiment first collects state information of the main power source or the auxiliary power source, mainly referring to performance parameters including various parameters such as current, voltage and temperature, and then calculates feature variation of data features to capture variation of current power source running state, and understand behavior and mode of the power source system in time sequence; the collected state information and feature variation of the power supply are then consolidated into a time series format, ensuring that the data features correspond correctly to the time nodes, thus forming the key step of preprocessing the data set that will be used to train the random forest model.
The training process of the random forest model begins with the generation of multiple sub-data sets from a pre-processed data set using a Bootstrap method. The Bootstrap method is a statistical resampling technique that generates new sub-data sets by randomly extracting samples (which may be repeated) from the original data set; and then, constructing a decision tree for each sub-data set by using a binary recursive segmentation technology, and selecting a feature with the smallest information gain from a group of randomly selected features on each node for segmentation, wherein the process is the key of the decision tree, and the information gain can help to select the feature with the most distinguishing capability so as to ensure that the purity of the sub-nodes is highest.
After all decision trees are built, they are combined to form a random forest model. Each tree can independently make a decision on the state information, so that the robustness and the accuracy of the random forest model are improved; finally, analyzing and predicting the new state information by using a random forest model; each decision tree generates a decision result, if most decision trees predict that a certain data point belongs to an abnormal category, the data point is marked as an abnormal state, and a majority voting decision mechanism of a random forest can effectively process noise and abnormal values.
In one embodiment, referring to fig. 4, obtaining power supply information of a power grid and a power source and power demand information of a new energy power station, and adjusting power output parameters of the power grid and the power source based on the power supply information and the power demand information, includes the steps of:
S301, acquiring power supply information of a power grid and a power supply;
S302, predicting and obtaining the power demand information of the new energy power station based on the historical power demand information and the state information of the power supply;
s303, formulating an electric energy distribution strategy based on the electric power supply information and the electric power demand information;
s304, determining power output parameters of the power grid and the power supply based on the power distribution strategy.
Specifically, the electric energy distribution subsystem 2 acquires the electric power supply information of the power source and the power grid in real time, and detects and records various parameters such as voltage, current, frequency and the like so as to know the real-time state of the power source; the power distribution module predicts the power demand information in the future week based on the historical power demand information and the state information of the power source, and predicts the future power demand information using time series analysis, machine learning or other prediction techniques; the power distribution subsystem 2 then formulates a power distribution strategy, such as when to draw power from the grid, when to draw power from the battery, and how to balance power demand between the battery and the grid, based on the power supply information of the power source and the predicted power demand information; the electric energy distribution subsystem 2 adjusts the electric power output parameters of the power supply and the power grid by controlling the electric power dispatching equipment according to an electric energy distribution strategy, and uses various switches, relays or other control equipment to control the electric power output; finally, the power distribution subsystem 2 continuously monitors the real-time power supply and demand conditions; if a discrepancy between the actual situation and the expected situation is found, or if there is a new operation state change, the power distribution subsystem 2 will go back to steps S301 to S304 to adjust the power distribution strategy.
In one embodiment, the energy conversion subsystem 3 converts high voltage DC to low voltage DC, and this process involves a device called a direct current-to-direct current (DC-DC) converter, which operates by switching the open and closed states of the circuit to change the flow path of the current, thereby achieving a rise or fall in voltage. In practice, the energy conversion subsystem 3 first receives high voltage direct current from a power source or grid. This high voltage direct current is then fed into a DC-DC converter; in the converter, the control circuit adjusts the switching frequency of the circuit according to the required output voltage, thereby changing the energy storage and release speed.
When the circuit is turned on, current passes through the inductor, storing energy; when the circuit is closed, current continues to pass through the inductor, releasing energy, but at this point the voltage drops. In this way, the DC-DC converter can convert high-voltage direct current into low-voltage direct current; finally, the converted low voltage direct current is sent out to be used by equipment or a system needing low voltage electricity. The energy conversion subsystem 3 also needs to monitor and adjust the output voltage throughout the process to ensure its stability and safety. If any abnormal change in voltage is found, the energy conversion subsystem 3 immediately adjusts the circuit parameters to ensure the output voltage is stable.
In one embodiment, the data interaction and monitoring subsystem 4 monitors the status of the new energy power station in real time and communicates with a remote monitoring center. The following is an extension and explanation of the functionality of the data interaction and monitoring subsystem 4: in actual operation, the data interaction and monitoring subsystem 4 first needs to collect operation information of the new energy power station through various sensors and devices, the operation information of the new energy power station may include power output, device status, environmental parameters, etc., and the data interaction and monitoring subsystem 4 has the capability of processing and analyzing these complex data so as to identify any abnormal situation or trend of change.
The data interaction and monitoring subsystem 4 needs to communicate with a remote monitoring center to report the collected operation information to an operator or a management system, and can also receive instructions from the remote monitoring center, which is implemented through various communication technologies, such as a wireless network, the internet, a dedicated communication line, and the like. To ensure the security and integrity of data, encryption techniques and data integrity verification techniques may need to be used.
In addition, the data interaction and monitoring subsystem 4 also has a certain decision-making capability, so that when an abnormal situation is detected, preset emergency measures such as power supply cut-off, standby equipment start-up, operation parameter adjustment and the like can be immediately executed; in this way, the data interaction and monitoring subsystem 4 can realize real-time monitoring of the new energy power station, ensure the safe operation of the equipment, and simultaneously provide real-time information about the system state for operators to assist in making better decisions.
In one embodiment, referring to fig. 5, when the coordination control module generates a scheduling instruction based on the operation information and schedules the power management subsystem 1, the electric energy distribution subsystem 2, the energy conversion subsystem 3, and the data interaction and monitoring subsystem 4 based on the scheduling instruction, the coordination control module further performs the following steps:
S401, evaluating the current running state of the new energy power station based on the running information;
S402, formulating a scheduling strategy based on the evaluation result, and generating a scheduling instruction according to the formulated scheduling strategy;
S403, scheduling the power management subsystem 1, the electric energy distribution subsystem 2, the energy conversion subsystem 3 and the data interaction and monitoring subsystem 4 based on the scheduling instruction to acquire feedback information;
S404, verifying whether a scheduling result meets expectations or not based on feedback information;
and S405, if the result does not accord with the expected or the current running state is changed, the current running state is estimated again and a scheduling strategy is formulated.
Specifically, the coordination control subsystem 5 needs to collect operation information of each subsystem in the new energy power station, and acquire real-time data from various sensors and devices, such as power output, device state, environmental parameters, etc., where the real-time data is key information for evaluating the operation state of the power station; based on the collected operation information, the coordination control subsystem 5 will evaluate the current operation state of the new energy power station, and perform data analysis and model calculation to learn information such as energy output, equipment performance, and possible faults of the new energy power station. Based on the state evaluation result, the coordination control subsystem 5 will make an appropriate scheduling policy to determine the operation mode of each system, for example, when the equipment needs maintenance, it needs to switch to the standby equipment; when the power demand increases, an increase in energy output and the like are required.
The coordination control subsystem 5 sends scheduling instructions to each subsystem in the new energy power station according to the formulated scheduling strategy so as to execute the formulated scheduling strategy, and controls the running states of a plurality of devices in each subsystem through a communication network, such as starting or closing the devices, adjusting the device parameters and the like.
After each subsystem executes the scheduling instruction, the coordination control subsystem 5 collects feedback information, verifies whether the scheduling result accords with the expectation, analyzes the actual operation information, and compares the actual operation information with the expectation result to determine whether the scheduling strategy is executed correctly; if the result does not meet the expectation or the running state of the power station changes, the coordination control subsystem 5 will re-perform state evaluation and scheduling policy formulation of each subsystem in the new energy power station, and the coordination control module needs to continuously perform data collection, state evaluation, policy formulation and instruction execution to ensure efficient running of the new energy power station.
In conclusion, the application can ensure the stable operation of the new energy power station through the real-time monitoring and flexible switching of the main power supply and the auxiliary power supply; the battery performance monitoring module can ensure that the battery runs in an optimal state, so that the stability and the service life of the main power supply and the auxiliary power supply are improved; when the fault diagnosis and protection module 13 finds out the fault of the main power supply, the fault diagnosis and protection module can rapidly inform the auxiliary power supply monitoring module 11 to take over the power supply, so as to ensure the continuous power supply of the power station; through the intelligent predictive regulation sub-module 113, the output voltage and current can be automatically regulated using a predictive control algorithm to accommodate the power demand of the power station; the dynamic threshold setting module can realize automatic adjustment of the dynamic threshold by combining the historical power demand information, the current running environment and the real-time state information, so that the flexibility and the response speed of the system are improved; the cloud computing technology is utilized to optimize the big data processing and remote monitoring capability, so that the running efficiency and the management effect of the system can be improved; the real-time state analysis unit 1123 can visually display and analyze the operation monitoring data, so that a manager can better understand the operation state of the power supply, and timely decision making and management are facilitated.
According to the application, by calculating the gain of the base information, the characteristic with the most segmentation value can be effectively selected on each node, which is beneficial to improving the prediction precision and efficiency of the model; bootstrap sampling is adopted to generate a plurality of sub-data sets and a random forest model is constructed, and decision is carried out by a plurality of decision trees, so that the risk of overfitting can be remarkably reduced, and the generalization capability of the model is improved; by collecting and processing the state information of the power supply in real time, the potential abnormal state can be timely identified, the problems can be timely found and solved, and the loss possibly caused by abnormal running state is reduced; the result of the decision tree is easy to understand, so that the decision process and the result of the random forest model can be conveniently explained, and the internal rule and the relation of the data can be understood.
The coordination control module can intensively manage the operation information of each subsystem in the new energy power station, thereby being beneficial to improving the operation efficiency of the new energy power station; by collecting real-time operation information and evaluating the current operation state of the new energy power station based on the operation information, the resource allocation can be effectively optimized, and the energy utilization efficiency can be improved; the cooperative control subsystem 5 can formulate a proper scheduling strategy according to different evaluation results, and has high flexibility of the scheduling strategy; after executing the scheduling instruction, the coordination control module collects feedback information to verify whether the scheduling result accords with the expectation, if the result does not accord with the expectation or the running state of the power station changes, the coordination control subsystem 5 can automatically carry out state evaluation and scheduling policy formulation again, and the automatic verification and feedback mechanism can effectively ensure the execution effect of the scheduling policy; through the real-time monitoring and scheduling of each subsystem in the new energy power station, the coordination control subsystem 5 can effectively prevent and solve various possible problems, and improve the operation safety of the new energy power station.
In order to achieve the above embodiment, the application further provides an emergency energy scheduling method for the new energy power station.
Fig. 5 is a schematic flow chart of an emergency energy scheduling method for a new energy power station according to an embodiment of the present application.
As shown in fig. 5, the method includes:
S1, acquiring state information of a power supply, wherein the power supply comprises a main power supply and an auxiliary power supply, and switching operation of the main power supply and the auxiliary power supply is performed based on the state information so as to provide high-voltage direct current;
S2, acquiring power supply information of a power grid and a power supply and power demand information of a new energy power station, and adjusting power output parameters of the power grid and the power supply based on the power supply information and the power demand information so as to control output of high-voltage direct current of the power grid and the power supply based on the power output parameters;
S3, converting the high-voltage direct current into low-voltage power to respond to the power demand information of the new energy power station;
S4, monitoring and acquiring operation information of the new energy power station;
And S5, generating a scheduling instruction based on the operation information, and scheduling the power management subsystem, the electric energy distribution subsystem, the energy conversion subsystem and the data interaction and monitoring subsystem based on the scheduling instruction.
It should be noted that the foregoing explanation of an embodiment of an emergency energy scheduling system for a new energy power station is also applicable to an emergency energy scheduling method for a new energy power station in this embodiment, and will not be repeated here.
While embodiments of the present application have been shown and described above, it should be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations of the above embodiments may be made by those skilled in the art without departing from the scope of the application.
Claims (6)
1. The emergency energy scheduling system for the new energy power station is characterized by comprising a power management subsystem (1), an electric energy distribution subsystem (2), an energy conversion subsystem (3), a data interaction and monitoring subsystem (4) and a coordination control subsystem (5);
the power management subsystem (1) is used for acquiring state information of a power supply, the power supply comprises a main power supply and a secondary power supply, and switching operation of the main power supply and the secondary power supply is performed based on the state information so as to provide high-voltage direct current to the energy conversion subsystem (3);
The electric energy distribution subsystem (2) is used for acquiring electric power supply information of an electric network and the power supply and electric power demand information of the new energy power station, and adjusting electric power output parameters of the electric network and the power supply based on the electric power supply information and the electric power demand information so as to control output of high-voltage direct current of the electric network and the power supply based on the electric power output parameters;
The energy conversion subsystem (3) is used for converting high-voltage direct current into low voltage power to respond to the power demand information of the new energy power station;
the data interaction and monitoring subsystem (4) is used for monitoring and acquiring the operation information of the new energy power station;
The coordination control subsystem (5) is used for generating a scheduling instruction based on the running information and scheduling the power management subsystem (1), the electric energy distribution subsystem (2), the energy conversion subsystem (3) and the data interaction and monitoring subsystem (4) based on the scheduling instruction;
The power management subsystem (1) comprises a power supply monitoring module (11), a power supply switching control module (12) and a fault diagnosis and protection module (13);
The power supply monitoring module (11) is used for monitoring first state information of the main power supply and second state information of the auxiliary power supply;
The fault diagnosis and protection module (13) is used for analyzing the first state information, generating a switching instruction when the main power supply is determined to be faulty based on the first state information, and sending the switching instruction to the power supply switching control module (12);
the power supply switching control module (12) is used for realizing switching between the main power supply and the auxiliary power supply based on the switching instruction;
the power supply monitoring module (11) comprises a power supply adaptation selection sub-module (111), a dynamic threshold monitoring sub-module (112) and an emergency fault response sub-module (114);
-said power adaptation selection sub-module (111) for selecting for said secondary power supply the same power adapter as said primary power supply;
the dynamic threshold monitoring sub-module (112) is used for monitoring and predicting state information of the power supply in real time;
The emergency fault response sub-module (114) is used for starting the auxiliary power supply to supply power when the main power supply fails;
The dynamic threshold monitoring sub-module (112) comprises a parameter monitoring unit (1121), a threshold setting unit (1122), a real-time state analysis unit (1123) and a fault response unit (1124);
-the parameter monitoring unit (1121) for obtaining status information of the power supply, the status information comprising at least current, voltage and temperature data characteristics;
the threshold setting unit (1122) is configured to dynamically adjust a parameter threshold of the power supply based on a preset dynamic threshold judgment model in combination with historical state data, a current operating environment and the state information;
The real-time state analysis unit (1123) is used for visually displaying the state information, analyzing the state information based on a random forest algorithm by combining the parameter threshold value, and obtaining a prediction result of whether the state information is abnormal or not;
The fault response unit (1124) is configured to start a fault diagnosis program when the prediction result is abnormal, and adjust an operation parameter of the power supply;
The random forest algorithm-based analysis is performed on the state information to obtain a prediction result of whether the state information is abnormal, and the method comprises the following steps:
acquiring characteristic variation of each data characteristic in the state information;
Based on the state information and the characteristic variation, acquiring a preprocessing data set of a random forest algorithm;
Acquiring a plurality of sub-data sets from the preprocessing data set based on a Bootstrap method;
Selecting a data feature with the minimum radix information gain from a group of randomly selected data features based on a binary recursive segmentation technology for each sub data set to segment, and constructing a decision tree;
constructing a random forest model by adopting all constructed decision trees, wherein each decision tree makes independent decisions on the state information;
Predicting the state information acquired in real time by using a random forest model, and obtaining a decision result by each tree;
if more than half of the decision trees predict that one of the data features belongs to the abnormal category, marking the data features as abnormal states, and determining that the state information is abnormal.
2. The emergency energy scheduling system for a new energy power station of claim 1, wherein said constructing a decision tree for each sub-data set using a binary recursive partitioning technique, at each decision tree node, selecting a data feature with a minimum kene information gain from a set of randomly selected data features for partitioning, comprises:
Randomly selecting data characteristics for each sub-data set, and calculating the base information gain of the data characteristics in the sub-data set;
Selecting a data feature with minimum base information gain, determining a division point of the sub-data set, and taking the data feature and the corresponding division point as an optimal feature and an optimal division point;
and dividing the sub-data set according to the optimal characteristics and the optimal dividing points.
3. The emergency energy scheduling system for a new energy power station according to claim 2, wherein the calculation formula of the base information gain is:
In the method, in the process of the invention, And (3) withRepresenting two child nodes respectivelyAndThe number of samples in the sample set,Representing child nodesIs not pure in terms of the radical of (c) and (d),Representing child nodesIs not pure in terms of the radical of (c) and (d),Indicating total genii purity after cleavage.
4. The emergency energy scheduling system for a new energy power station of claim 1, wherein the acquiring power supply information of the power grid and the power source and power demand information of the new energy power station, and adjusting power output parameters of the power grid and the power source based on the power supply information and the power demand information, comprises:
Acquiring power supply information of a power grid and the power supply;
Based on the historical power demand information and the state information of the power supply, predicting and obtaining the power demand information of the new energy power station;
formulating an electrical energy allocation strategy based on the electrical power supply information and the electrical power demand information;
a power output parameter of the power grid and the power source is determined based on the power distribution strategy.
5. The emergency energy scheduling system for a new energy power station of claim 1, wherein the generating scheduling instructions based on the operational information and scheduling the power management subsystem, the power distribution subsystem, the energy conversion subsystem, and the data interaction and monitoring subsystem based on the scheduling instructions comprises:
evaluating the current running state of the new energy power station based on the running information;
based on the evaluation result, formulating a scheduling strategy, and generating a scheduling instruction according to the formulated scheduling strategy;
Scheduling the power management subsystem, the electric energy distribution subsystem, the energy conversion subsystem and the data interaction and monitoring subsystem based on the scheduling instruction;
acquiring feedback information, and verifying whether a scheduling result accords with expectations based on the feedback information;
and if the result does not accord with the expected or the current running state changes, re-evaluating the current running state and formulating a scheduling strategy.
6. An emergency energy scheduling method for a new energy power station, applied to the emergency energy scheduling system for a new energy power station according to any one of claims 1 to 5, characterized by comprising:
Acquiring state information of a power supply, wherein the power supply comprises a main power supply and a secondary power supply, and switching operation of the main power supply and the secondary power supply is performed based on the state information so as to provide high-voltage direct current;
Acquiring power supply information of a power grid and the power supply and power demand information of the new energy power station, and adjusting power output parameters of the power grid and the power supply based on the power supply information and the power demand information so as to control output of high-voltage direct current of the power grid and the power supply based on the power output parameters;
converting the high-voltage direct current into low voltage power to respond to the power demand information of the new energy power station;
monitoring and acquiring the operation information of the new energy power station;
And generating a scheduling instruction based on the running information, and scheduling the power management subsystem, the electric energy distribution subsystem, the energy conversion subsystem and the data interaction and monitoring subsystem based on the scheduling instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410277557.3A CN117878931B (en) | 2024-03-12 | Emergency energy scheduling system and method for new energy power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410277557.3A CN117878931B (en) | 2024-03-12 | Emergency energy scheduling system and method for new energy power station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117878931A CN117878931A (en) | 2024-04-12 |
| CN117878931B true CN117878931B (en) | 2024-07-05 |
Family
ID=
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533089A (en) * | 2019-08-19 | 2019-12-03 | 三峡大学 | Adaptive non-intrusion type load recognition methods based on random forest |
| CN117474250A (en) * | 2023-10-31 | 2024-01-30 | 华能浙江能源销售有限责任公司 | New energy multifunctional integrated intelligent application system |
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533089A (en) * | 2019-08-19 | 2019-12-03 | 三峡大学 | Adaptive non-intrusion type load recognition methods based on random forest |
| CN117474250A (en) * | 2023-10-31 | 2024-01-30 | 华能浙江能源销售有限责任公司 | New energy multifunctional integrated intelligent application system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110429714B (en) | Cloud platform intelligent power distribution system based on big data | |
| CN102510125A (en) | Method and device for monitoring operation conditions of power primary equipment | |
| CN101833324B (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
| CN112327098A (en) | Power distribution network fault section positioning method based on low-voltage distribution network comprehensive monitoring unit | |
| CN117477794B (en) | Power distribution station power consumption management optimization system and method based on gateway machine data exchange | |
| CN117175655A (en) | Energy storage control method and system for distributed new energy power system | |
| CN117878931B (en) | Emergency energy scheduling system and method for new energy power station | |
| CN113258677A (en) | Intelligent power distribution cabinet (box) device and system with low-carbon regulation and control and early warning emergency repair functions | |
| CN117614140A (en) | Power distribution equipment operation monitoring system and method thereof | |
| CN112731827A (en) | Monitoring system for intelligent sensor for power equipment | |
| CN117878931A (en) | Emergency energy scheduling system and method for new energy power station | |
| CN116739550A (en) | Intelligent auxiliary decision-making method and system for rush repair | |
| CN115392640A (en) | Maintenance-oriented motor generator full life cycle cost efficiency evaluation system | |
| CN104979903A (en) | Patrol analysis method and device for centralized control center | |
| CN114825625A (en) | Operation and maintenance system and method for battery energy storage power station | |
| CN110909945B (en) | Power grid scheduling exception handling aid decision-making method | |
| CN115566738B (en) | Self-optimized wind turbine generator group control method and device | |
| CN118199254A (en) | Highway power supply control method and system | |
| CN113572159B (en) | Line tripping accident handling system based on knowledge reasoning of power grid regulation and control system | |
| CN117335578B (en) | Detection and regulation system for loop closing power conversion of low-voltage power distribution | |
| CN117495186A (en) | Stable operation assessment method for virtual smart grid | |
| CN117081093A (en) | Direct-hanging SVG integrated control device and control method thereof | |
| CN117993597A (en) | Automatic operation and maintenance deployment method for power grid | |
| CN117118020A (en) | Ship power station fault reconstruction system | |
| CN117544872A (en) | Efficient electric power data acquisition and transmission system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |