CN110048420B - Method, device and medium for random optimal scheduling of power distribution network - Google Patents
Method, device and medium for random optimal scheduling of power distribution network Download PDFInfo
- Publication number
- CN110048420B CN110048420B CN201910402407.XA CN201910402407A CN110048420B CN 110048420 B CN110048420 B CN 110048420B CN 201910402407 A CN201910402407 A CN 201910402407A CN 110048420 B CN110048420 B CN 110048420B
- Authority
- CN
- China
- Prior art keywords
- load
- value
- distributed power
- power supply
- cluster
- 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
Images
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
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The embodiment of the invention discloses a method, a device and a medium for randomly optimizing and scheduling a power distribution network, which are used for acquiring a load historical value, a distributed power supply historical output value and a historical meteorological condition value of the power distribution network; respectively carrying out cluster division on the distributed power sources and the loads based on fuzzy clustering to obtain a plurality of distributed power source clusters and a plurality of load clusters; and processing each cluster by using the corresponding prediction model of each cluster to obtain an output predicted value and a load predicted value. By cluster division, the accuracy of the prediction result is improved. According to the output predicted value, the load predicted value and various power distribution network costs, establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition; and solving the objective function under the constraint condition by using a hybrid intelligent algorithm to obtain a power distribution network scheduling result. The constraint conditions fully consider the output of the distributed power supply and the randomness of the load, and can better meet the safe and stable operation of the power distribution network.
Description
Technical Field
The invention relates to the technical field of power distribution networks, in particular to a method and a device for randomly optimizing and scheduling a power distribution network and a computer readable storage medium.
Background
The load is the basis of the operation and planning of the power system, and the scheduling potential of the user side is greatly improved along with the improvement of the permeability of the distributed power supply. In the development process of the scheduling technology of the active power distribution network, two problems which need to be solved urgently mainly exist, namely how to accurately predict the output and the user load of the distributed power supply, and how to consider the output and the load randomness of the distributed power supply.
In a conventional power distribution network scheduling mode, load and distributed output values are often roughly predicted, prediction errors and real-time fluctuation are adjusted through energy storage and flexible loads, but the mode is not accurate enough in load and distributed output prediction, and even completely fails in an extreme scene. And the flexible load or the load shedding is used for balancing the load fluctuation of the power distribution network and the distributed output, and the randomness of the load fluctuation can cause great flexible load scheduling and standby cost, so that the safe and stable operation of the power distribution network is not facilitated.
Therefore, how to improve the accuracy of prediction while ensuring the safe and stable operation of the power distribution network is a problem to be solved urgently by technical personnel in the field.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a device for randomly and optimally scheduling a power distribution network and a computer readable storage medium, which can improve the accuracy of prediction while ensuring the safe and stable operation of the power distribution network.
In order to solve the above technical problem, an embodiment of the present invention provides a method for randomly optimizing and scheduling a power distribution network, including:
acquiring historical data of the power distribution network; the historical data comprises a load historical value, a distributed power supply historical output value and a historical meteorological condition value;
performing cluster division on the distributed power supplies based on fuzzy clustering to obtain a plurality of distributed power supply clusters;
performing cluster division on the load based on the fuzzy clustering to obtain a plurality of load clusters;
processing the output value of the target distributed power supply and the meteorological condition value corresponding to the corresponding distributed power supply cluster by using each prediction model, and determining the output prediction value of each distributed power supply cluster;
processing a target load value and a meteorological condition value corresponding to a corresponding load cluster by using each prediction model, and determining a load prediction value of each load cluster;
establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition according to the output predicted value, the load predicted value and various power distribution network costs;
and solving the objective function under each constraint condition by using a hybrid intelligent algorithm to obtain a power distribution network scheduling result.
Optionally, the performing cluster division on the distributed power sources based on the fuzzy clustering to obtain a plurality of distributed power source clusters includes:
establishing a distributed output observation data matrix corresponding to the historical output value of the distributed power supply;
and according to the preset initial membership degree matrixes and the corresponding initial clustering centers thereof, carrying out cluster division on the distributed output observation data matrix to obtain a plurality of distributed power supply clusters.
Optionally, the performing cluster division on the load based on the fuzzy clustering to obtain a plurality of load clusters includes:
establishing a load observation data matrix corresponding to the load historical value;
and according to the preset initial membership degree matrixes and the corresponding initial clustering centers thereof, carrying out cluster division on the load observation data matrix to obtain a plurality of load clusters.
Optionally, the processing, by using each prediction model, the target distributed power output value and the meteorological condition value corresponding to the corresponding distributed power cluster, and determining the output predicted value of each distributed power cluster includes:
extracting characteristic values of each distributed power supply cluster; the characteristic values comprise historical output values of the distributed power supplies corresponding to the current day, historical meteorological condition values corresponding to the current day and historical output values of the distributed power supplies corresponding to the previous day;
converting each characteristic value into standard data;
training a pre-established extreme learning machine by using the standard data;
and inputting the standard value of the output value of the target distributed power supply corresponding to each distributed power supply cluster and the standard value of the meteorological condition value into a trained extreme learning machine to obtain the output predicted value of each distributed power supply cluster.
Optionally, the processing the target load value and the meteorological condition value corresponding to the corresponding load cluster by using each prediction model, and determining the load prediction value of each load cluster includes:
extracting characteristic values of each load cluster; the characteristic values comprise a load historical value corresponding to the current day, a historical meteorological condition value corresponding to the current day and a load historical value corresponding to the previous day;
converting each characteristic value into standard data;
training a pre-established extreme learning machine by using the standard data;
and inputting the target load value and the meteorological condition value corresponding to each load cluster into a trained extreme learning machine to obtain a load predicted value of each load cluster.
Optionally, the establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition according to the output predicted value, the load predicted value and various power distribution network costs includes:
the objective function is established according to the following formula,
wherein F represents the scheduling total cost, T is the optimized scheduling period, Pgrid(t) represents the amount of power purchased from the grid company at time t, cgrid(t) represents the purchase price of electricity from the large power grid at time t, m represents the number of flexible loads, NS represents the number of energy storage devices, NG represents the number of distributed power sources, Cloadi(t) represents the scheduling cost of the flexible load, Cstorj(t) represents the scheduling cost of the energy storage device, CDGk(t) represents the scheduling cost of the distributed power supply,
each scheduling cost formula is as follows:
in the formula, alphai,βiRespectively scheduling cost coefficients for the flexible load; pload0An active initial value before flexible load scheduling is obtained; delta PloadiIs the flexible load power variation; lambda [ alpha ]essRepresenting the cost factor, P, of the storage batterystorj(t) represents the discharge capacity of the jth energy storage device at time t, ak,bk,ckRespectively, the cost factor, P, of the distributed power supplyDGk(t) represents a force output value of the kth distributed device at the time t;
the constraints include active power balance constraints and system standby constraints,
the active power balance constraint formula is as follows:
in the formula, Pd(t) load demand for a period t;
the system standby constraint equation is as follows:
in the formula (I), the compound is shown in the specification,flexibilityMaximum adjustment of load, PresFor system backup requirements, β is the confidence that the inequality holds.
The embodiment of the invention also provides a device for randomly optimizing and scheduling the power distribution network, which comprises an acquisition unit, a distributed power supply dividing unit, a load dividing unit, a distributed power supply prediction unit, a load prediction unit, an establishing unit and a solving unit;
the acquisition unit is used for acquiring historical data of the power distribution network; the historical data comprises a load historical value, a distributed power supply historical output value and a historical meteorological condition value;
the distributed power supply dividing unit is used for carrying out cluster division on the distributed power supplies based on fuzzy clustering to obtain a plurality of distributed power supply clusters;
the load dividing unit is used for carrying out cluster division on the load based on fuzzy clustering to obtain a plurality of load clusters;
the distributed power supply prediction unit is used for processing a target distributed power supply output value and a meteorological condition value corresponding to a corresponding distributed power supply cluster by using each prediction model to determine an output prediction value of each distributed power supply cluster;
the load prediction unit is used for processing a target load value and a meteorological condition value corresponding to the corresponding load cluster by using each prediction model to determine a load prediction value of each load cluster;
the establishing unit is used for establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition according to the output predicted value, the load predicted value and various power distribution network costs;
and the solving unit is used for solving the objective function under each constraint condition by using a hybrid intelligent algorithm to obtain a distribution network scheduling result.
Optionally, the distributed power supply partitioning unit includes a matrix establishing subunit and a cluster partitioning subunit;
the matrix establishing subunit is used for establishing a distributed output observation data matrix corresponding to the historical output value of the distributed power supply;
and the cluster dividing subunit is used for dividing the clusters of the distributed output observation data matrix according to each preset initial membership matrix and the corresponding initial clustering center thereof so as to obtain a plurality of distributed power supply clusters.
Optionally, the load dividing unit includes a matrix establishing subunit and a cluster dividing subunit;
the matrix establishing subunit is used for establishing a load observation data matrix corresponding to the load historical value;
and the cluster division subunit is used for dividing the clusters of the load observation data matrix according to each preset initial membership matrix and the corresponding initial clustering center thereof so as to obtain a plurality of load clusters.
Optionally, the distributed power supply prediction unit includes an extraction subunit, a transformation subunit, a training subunit, and an obtaining subunit;
the extraction subunit is configured to perform characteristic value extraction on each distributed power supply cluster; the characteristic values comprise historical output values of the distributed power supplies corresponding to the current day, historical meteorological condition values corresponding to the current day and historical output values of the distributed power supplies corresponding to the previous day;
the transformation unit is used for transforming each characteristic value into standard data;
the training subunit is used for training a pre-established extreme learning machine by using the standard data;
the obtaining subunit is configured to input the standard value of the output value of the target distributed power source corresponding to each distributed power source cluster and the standard value of the weather condition value into a trained extreme learning machine, so as to obtain the output predicted value of each distributed power source cluster.
Optionally, the load prediction unit comprises an extraction subunit, a transformation subunit, a training subunit and an obtaining subunit;
the extraction subunit is configured to perform feature value extraction on each load cluster; the characteristic values comprise a load historical value corresponding to the current day, a historical meteorological condition value corresponding to the current day and a load historical value corresponding to the previous day;
the transformation unit is used for transforming each characteristic value into standard data;
the training subunit is used for training a pre-established extreme learning machine by using the standard data;
and the obtaining subunit is used for inputting the target load value and the meteorological condition value corresponding to each load cluster into a trained extreme learning machine so as to obtain a load predicted value of each load cluster.
Optionally, the establishing unit is specifically configured to establish the objective function according to the following formula,
wherein F represents the scheduling total cost, T is the optimized scheduling period, Pgrid(t) represents the amount of power purchased from the grid company at time t, cgrid(t) represents the purchase price of electricity from the large power grid at time t, m represents the number of flexible loads, NS represents the number of energy storage devices, NG represents the number of distributed power sources, Cloadi(t) represents the scheduling cost of the flexible load, Cstorj(t) represents the scheduling cost of the energy storage device, CDGk(t) represents the scheduling cost of the distributed power supply,
each scheduling cost may be represented as:
in the formula, alphai,βiRespectively scheduling cost coefficients for the flexible load; pload0An active initial value before flexible load scheduling is obtained; delta PloadiIs the flexible load power variation; lambda [ alpha ]essRepresenting the cost factor, P, of the storage batterystorj(t) denotes the jth at time tDischarge capacity of the energy storage device, ak,bk,ckRespectively, the cost factor, P, of the distributed power supplyDGk(t) represents a force output value of the kth distributed device at the time t;
the constraints include active power balance constraints and system standby constraints,
the active power balance constraint formula is as follows:
in the formula, Pd(t) load demand for a period t;
the system standby constraint equation is as follows:
in the formula (I), the compound is shown in the specification,maximum adjustment of compliant load, PresFor system backup requirements, β is the confidence that the inequality holds.
The embodiment of the invention also provides a device for randomly and optimally scheduling the power distribution network, which comprises the following steps:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the method for stochastic optimal scheduling of a power distribution network as described above.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for randomly optimizing and scheduling a power distribution network as described above are implemented.
According to the technical scheme, historical data of the power distribution network are obtained; the historical data comprises a load historical value, a distributed power supply historical force output value and a historical meteorological condition value; performing cluster division on the distributed power supplies based on fuzzy clustering to obtain a plurality of distributed power supply clusters; performing cluster division on the load based on the fuzzy clustering to obtain a plurality of load clusters; processing the output value of the target distributed power supply and the meteorological condition value corresponding to the corresponding distributed power supply cluster by using each prediction model, and determining the output prediction value of each distributed power supply cluster; processing the target load value and the meteorological condition value corresponding to the corresponding load cluster by using each prediction model, and determining the load prediction value of each load cluster; after the cluster is divided, the sample characteristics are more obvious, and the obtained prediction result is more accurate. According to the output predicted value, the load predicted value and various power distribution network costs, establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition; and solving the objective function under the constraint condition by using a hybrid intelligent algorithm to obtain a distribution network scheduling result. The constraint conditions fully consider the output of the distributed power supply and the randomness of the load, and can better meet the safe and stable operation of the power distribution network.
Drawings
In order to illustrate the embodiments of the present invention more clearly, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained by those skilled in the art without inventive effort.
Fig. 1 is a flowchart of a method for randomly optimizing and scheduling a power distribution network according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a device for randomly optimizing and scheduling a power distribution network according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a hardware structure of a device for randomly optimizing and scheduling a power distribution network according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative work belong to the protection scope of the present invention.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Next, a method for randomly optimizing and scheduling a power distribution network according to an embodiment of the present invention is described in detail. Fig. 1 is a flowchart of a method for randomly optimizing and scheduling a power distribution network according to an embodiment of the present invention, where the method includes:
s101: and acquiring historical data of the power distribution network.
The historical data comprises a load historical value, a distributed power supply historical output value and a historical meteorological condition value.
In a specific implementation, historical values of loads and historical output values of distributed power supplies under a certain distribution network every day in the last three years can be collected, and simultaneously, weather condition values of the day matched with the historical values can be collected. The meteorological conditions may include temperature, humidity, air pressure, wind speed, solar radiation intensity, and other parameters.
S102: and carrying out cluster division on the distributed power supply based on fuzzy clustering to obtain a plurality of distributed power supply clusters.
After the cluster division is carried out on the distributed power supply, the sample characteristics are more obvious, the training iteration times are reduced, and the obtained prediction result is more accurate. And the prediction speed is greatly improved, and the real-time prediction of the distributed power supply output in a short time scale is facilitated.
In specific implementation, a distributed output observation data matrix corresponding to the historical output value of the distributed power supply can be established, and the corresponding matrix form is as follows:
X=[x1,x2,...,xs];
wherein x isi=[xi1,xi2,...,xin],xinIs the result of the nth observation of the ith variable, and s is the variableNumber of the obtained product.
In the embodiment of the invention, a plurality of initial membership degree matrixes and initial clustering centers corresponding to the initial membership degree matrixes can be established in advance. And according to each initial membership matrix and the corresponding initial clustering center thereof, carrying out cluster division on the distributed output observation data matrix to obtain a plurality of distributed power supply clusters.
When the distributed power source cluster is divided, a fuzzy clustering objective function shown in the following formula can be established:
wherein P is a cluster center matrix, and P ═ P1,p2,...,pc],pcClass c centers; u is a membership matrix, whereindjk=||xk-vj||A=(xk-vj)TA(xk-vj) Is sample xkTo the center of the cluster vjDistance norm of (d).
The clustering center and the membership degree are updated in an iterative mode, so that the distributed power supply clusters can be divided, and the iterative formula is as follows:
wherein, N represents the number of the divided clusters, and l is an iterative algebra.
S103: and carrying out cluster division on the load based on the fuzzy clustering to obtain a plurality of load clusters.
In the embodiment of the invention, a load observation data matrix corresponding to the load historical value can be established; and according to the preset initial membership degree matrixes and the corresponding initial clustering centers thereof, carrying out cluster division on the load observation data matrix to obtain a plurality of load clusters.
The load cluster division is similar to the distributed power supply cluster division, and for the load cluster division, the distributed power supply cluster division process may be specifically referred to, and details are not described herein.
S104: and processing the target distributed power output value and the meteorological condition value corresponding to the corresponding distributed power cluster by using each prediction model, and determining the output predicted value of each distributed power cluster.
When the output prediction value of each distributed power supply cluster is used, firstly, the characteristic value of each distributed power supply cluster needs to be extracted.
The characteristic values comprise historical output values of the distributed power supplies corresponding to the current day, historical meteorological condition values corresponding to the current day and historical output values of the distributed power supplies corresponding to the previous day.
The extracted eigenvalues can be represented in matrix form:
I=[i1,i2,...,is];
in the formula ij=[ij1,ij2,...,ijn],ijnIs the result of the nth observation of the jth variable, and s is the number of the variables.
In order to ensure the unification of various data forms, all characteristic values need to be converted into standard data. The normalization method is as follows:
wherein f isiRepresents the current input value of the ith data,normalized value, f, representing the ith dataimaxRepresents the maximum value of the ith data, fiminRepresents the minimum value of the ith data.
Training a pre-established extreme learning machine by using standard data; and inputting the standard value of the output value of the target distributed power supply corresponding to each distributed power supply cluster and the standard value of the meteorological condition value into a trained extreme learning machine to obtain the output predicted value of each distributed power supply cluster.
The input parameters of the extreme learning machine comprise a standard value of the output value of the distributed power supply on the day before the predicted target day and a standard value of the meteorological condition value on the predicted target day, and correspondingly, the extreme learning machine outputs the output predicted value of the distributed power supply on the predicted target day.
S105: and processing the target load value and the meteorological condition value corresponding to the corresponding load cluster by using each prediction model to determine the load prediction value of each load cluster.
In specific implementation, characteristic value extraction can be performed on each load cluster; the characteristic values comprise a load historical value corresponding to the current day, a historical meteorological condition value corresponding to the current day and a load historical value corresponding to the previous day; converting each characteristic value into standard data; training a pre-established extreme learning machine by using standard data; and inputting the target load value and the meteorological condition value corresponding to each load cluster into the trained extreme learning machine to obtain the load predicted value of each load cluster.
The process of determining the load predicted value of each load cluster is similar to the process of determining the output predicted value of each distributed power supply cluster, and the process of determining the load predicted value may specifically refer to the process of determining the output predicted value of the distributed power supply cluster, and is not described herein again.
S106: and establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition according to the output predicted value, the load predicted value and the costs of various power distribution networks.
In the embodiment of the invention, an active power distribution network scheduling model based on a predicted value and considering distributed output and load randomness is established, wherein the active power distribution network scheduling model is composed of a target function and constraint conditions.
The method comprises the following steps that the cost of purchasing power from a main network, the flexible load scheduling cost, the storage battery energy storage scheduling cost and the distributed power supply scheduling cost are considered in an objective function, linear weighting of the costs is used as a single target to be optimized, and the established objective function formula is as follows:
wherein F represents the scheduling total cost, T is the optimized scheduling period, Pgrid(t) represents the amount of power purchased from the grid company at time t, cgrid(t) represents the purchase price of electricity from the large power grid at time t, m represents the number of flexible loads, NS represents the number of energy storage devices, NG represents the number of distributed power sources, Cloadi(t) represents the scheduling cost of the flexible load, Cstorj(t) represents the scheduling cost of the energy storage device, CDGk(t) represents the scheduling cost of the distributed power supply,
each scheduling cost formula is as follows:
in the formula, alphai,βiRespectively scheduling cost coefficients for the flexible load; pload0An active initial value before flexible load scheduling is obtained; delta PloadiIs the flexible load power variation; lambda [ alpha ]essRepresenting the cost factor, P, of the storage batterystorj(t) represents the discharge capacity of the jth energy storage device at time t, ak,bk,ckRespectively, the cost factor, P, of the distributed power supplyDGk(t) represents a force output value of the kth distributed device at the time t;
the constraints include active power balance constraints and system standby constraints,
the active power balance constraint formula is as follows:
in the formula, Pd(t) load demand for a period t;
the system standby constraint equation is as follows:
in the formula (I), the compound is shown in the specification,maximum adjustment of compliant load, PresFor system backup requirements, β is the confidence that the inequality holds.
In the embodiment of the invention, an active power distribution network random optimization scheduling model which fully considers the output of the distributed power supply and the randomness and the volatility of the load is established, the model meets the system standby constraint based on certain confidence coefficient, the standby cost can be greatly reduced in a smaller risk range, and the safe and economic operation of the power distribution network can be better met.
S107: and solving the objective function under each constraint condition by using a hybrid intelligent algorithm to obtain a power distribution network scheduling result.
In the embodiment of the invention, the objective function is solved by combining random simulation, an extreme learning machine and a hybrid intelligent algorithm of a genetic algorithm. The algorithm can better solve the problem of random planning, can better adapt to uncertain variables and approach uncertain functions, and has stronger convergence.
The concrete solving steps of the hybrid intelligent algorithm are as follows:
step 1: and generating input and output samples for the uncertain function through random simulation, namely respectively taking the output predicted value of the distributed power supply divided by the cluster and the load predicted value divided by the cluster as the random simulation sample values of the expected distributed power supply output and load.
Step 2: and training the extreme learning machine according to the training samples generated by the simulation to approximate an uncertain function, namely, utilizing the extreme learning machine to approximate the system standby constraint condition.
Step 3: 100 chromosomes were initialized and examined for feasibility using an extreme learning machine.
Step 4: and carrying out cross mutation operation on the chromosome, and verifying the feasibility of the offspring chromosome by using a trained extreme learning machine.
Step 5: the objective function values of all chromosomes are calculated, and the optimal individual is selected as the parent of the next generation through roulette.
Step 6: and repeating the Step4 and the Step5 until convergence.
Combining the constraint formula, solving the objective function under each constraint condition, and obtaining a distribution network scheduling result including delta Ploadi(t)、Pstorj(t)、PDGk(t) and Pgrid(t) specific values of the parameters.
According to the technical scheme, historical data of the power distribution network are obtained; the historical data comprises a load historical value, a distributed power supply historical force output value and a historical meteorological condition value; performing cluster division on the distributed power supplies based on fuzzy clustering to obtain a plurality of distributed power supply clusters; performing cluster division on the load based on the fuzzy clustering to obtain a plurality of load clusters; processing the output value of the target distributed power supply and the meteorological condition value corresponding to the corresponding distributed power supply cluster by using each prediction model, and determining the output prediction value of each distributed power supply cluster; processing the target load value and the meteorological condition value corresponding to the corresponding load cluster by using each prediction model, and determining the load prediction value of each load cluster; after the cluster is divided, the sample characteristics are more obvious, and the obtained prediction result is more accurate. According to the output predicted value, the load predicted value and various power distribution network costs, establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition; and solving the objective function under the constraint condition by using a hybrid intelligent algorithm to obtain a distribution network scheduling result. The constraint conditions fully consider the output of the distributed power supply and the randomness of the load, and can better meet the safe and stable operation of the power distribution network.
Fig. 2 is a schematic structural diagram of a device for randomly optimizing and scheduling a power distribution network according to an embodiment of the present invention, including an obtaining unit 21, a distributed power source dividing unit 22, a load dividing unit 23, a distributed power source predicting unit 24, a load predicting unit 25, an establishing unit 26, and a solving unit 27;
an obtaining unit 21, configured to obtain historical data of a power distribution network; the historical data comprises a load historical value, a distributed power supply historical output value and a historical meteorological condition value;
the distributed power supply dividing unit 22 is configured to perform cluster division on the distributed power supplies based on fuzzy clustering to obtain a plurality of distributed power supply clusters;
the load dividing unit 23 is configured to perform cluster division on the load based on the fuzzy clustering to obtain a plurality of load clusters;
the distributed power supply prediction unit 24 is configured to process the target distributed power supply output value and the meteorological condition value corresponding to the corresponding distributed power supply cluster by using each prediction model, and determine the output prediction value of each distributed power supply cluster;
the load prediction unit 25 is configured to process the target load value and the meteorological condition value corresponding to the corresponding load cluster by using each prediction model, and determine a load prediction value of each load cluster;
the establishing unit 26 is configured to establish a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition according to the output predicted value, the load predicted value and various power distribution network costs;
and the solving unit 27 is used for solving the objective function under each constraint condition by using a hybrid intelligent algorithm to obtain a power distribution network scheduling result.
Optionally, the distributed power supply partitioning unit includes a matrix establishing subunit and a cluster partitioning subunit;
the matrix establishing subunit is used for establishing a distributed output observation data matrix corresponding to the historical output value of the distributed power supply;
and the cluster dividing subunit is used for dividing the clusters of the distributed output observation data matrix according to each preset initial membership matrix and the corresponding initial clustering center thereof so as to obtain a plurality of distributed power supply clusters.
Optionally, the load dividing unit includes a matrix establishing subunit and a cluster dividing subunit;
the matrix establishing subunit is used for establishing a load observation data matrix corresponding to the load historical value;
and the cluster division subunit is used for carrying out cluster division on the load observation data matrix according to each preset initial membership matrix and the corresponding initial clustering center thereof so as to obtain a plurality of load clusters.
Optionally, the distributed power supply prediction unit includes an extraction subunit, a transformation subunit, a training subunit and an obtaining subunit;
the extraction subunit is used for extracting the characteristic values of all the distributed power supply clusters; the characteristic values comprise historical output values of the distributed power supplies corresponding to the current day, historical meteorological condition values corresponding to the current day and historical output values of the distributed power supplies corresponding to the previous day;
the transformation unit is used for transforming each characteristic value into standard data;
the training subunit is used for training the pre-established extreme learning machine by using the standard data;
and the obtaining subunit is used for inputting the standard value of the output value of the target distributed power supply corresponding to each distributed power supply cluster and the standard value of the meteorological condition value into the trained extreme learning machine so as to obtain the output predicted value of each distributed power supply cluster.
Optionally, the load prediction unit comprises an extraction subunit, a transformation subunit, a training subunit and an obtaining subunit;
the extraction subunit is used for extracting the characteristic value of each load cluster; the characteristic values comprise a load historical value corresponding to the current day, a historical meteorological condition value corresponding to the current day and a load historical value corresponding to the previous day;
the transformation unit is used for transforming each characteristic value into standard data;
the training subunit is used for training the pre-established extreme learning machine by using the standard data;
and the obtaining subunit is used for inputting the target load value and the meteorological condition value corresponding to each load cluster into the trained extreme learning machine so as to obtain the load predicted value of each load cluster.
Optionally, the establishing unit is specifically configured to establish the objective function according to the following formula,
wherein F represents the scheduling total cost, T is the optimized scheduling period, Pgrid(t) represents the amount of power purchased from the grid company at time t, cgrid(t) represents the purchase price of electricity from the large power grid at time t, m represents the number of flexible loads, NS represents the number of energy storage devices, NG represents the number of distributed power sources, Cloadi(t) represents the scheduling cost of the flexible load, Cstorj(t) represents the scheduling cost of the energy storage device, CDGk(t) represents the scheduling cost of the distributed power supply,
each scheduling cost may be represented as:
in the formula, alphai,βiRespectively scheduling cost coefficients for the flexible load; pload0An active initial value before flexible load scheduling is obtained; delta PloadiIs the flexible load power variation; lambda [ alpha ]essRepresenting the cost factor, P, of the storage batterystorj(t) represents the discharge capacity of the jth energy storage device at time t, ak,bk,ckRespectively, the cost factor, P, of the distributed power supplyDGk(t) represents a force output value of the kth distributed device at the time t;
the constraints include active power balance constraints and system standby constraints,
the active power balance constraint formula is as follows:
in the formula, Pd(t) load demand for a period t;
the system standby constraint equation is as follows:
in the formula (I), the compound is shown in the specification,maximum adjustment of compliant load, PresFor system backup requirements, β is the confidence that the inequality holds.
The description of the features in the embodiment corresponding to fig. 2 may refer to the related description of the embodiment corresponding to fig. 1, and is not repeated here.
According to the technical scheme, historical data of the power distribution network are obtained; the historical data comprises a load historical value, a distributed power supply historical force output value and a historical meteorological condition value; performing cluster division on the distributed power supplies based on fuzzy clustering to obtain a plurality of distributed power supply clusters; performing cluster division on the load based on the fuzzy clustering to obtain a plurality of load clusters; processing the output value of the target distributed power supply and the meteorological condition value corresponding to the corresponding distributed power supply cluster by using each prediction model, and determining the output prediction value of each distributed power supply cluster; processing the target load value and the meteorological condition value corresponding to the corresponding load cluster by using each prediction model, and determining the load prediction value of each load cluster; after the cluster is divided, the sample characteristics are more obvious, and the obtained prediction result is more accurate. According to the output predicted value, the load predicted value and various power distribution network costs, establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition; and solving the objective function under the constraint condition by using a hybrid intelligent algorithm to obtain a distribution network scheduling result. The constraint conditions fully consider the output of the distributed power supply and the randomness of the load, and can better meet the safe and stable operation of the power distribution network.
Fig. 3 is a schematic hardware structure diagram of a device 30 for randomly optimizing and scheduling a power distribution network according to an embodiment of the present invention, where the device includes:
a memory 31 for storing a computer program;
a processor 32 for executing a computer program for implementing the steps of the method for stochastic optimal scheduling of a power distribution network as described above.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when being executed by a processor, the computer program realizes the steps of the method for the random optimal scheduling of the power distribution network.
The method, the device and the computer-readable storage medium for the random optimal scheduling of the power distribution network provided by the embodiment of the invention are described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Claims (8)
1. A method for randomly optimizing and scheduling a power distribution network is characterized by comprising the following steps:
acquiring historical data of the power distribution network; the historical data comprises a load historical value, a distributed power supply historical output value and a historical meteorological condition value;
performing cluster division on the distributed power supplies based on fuzzy clustering to obtain a plurality of distributed power supply clusters;
performing cluster division on the load based on the fuzzy clustering to obtain a plurality of load clusters;
processing the output value of the target distributed power supply and the meteorological condition value corresponding to the corresponding distributed power supply cluster by using each prediction model, and determining the output prediction value of each distributed power supply cluster;
processing a target load value and a meteorological condition value corresponding to a corresponding load cluster by using each prediction model, and determining a load prediction value of each load cluster;
establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition according to the output predicted value, the load predicted value and various power distribution network costs;
solving the objective function under each constraint condition by using a hybrid intelligent algorithm to obtain a distribution network scheduling result;
the step of establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition according to the output predicted value, the load predicted value and various power distribution network costs comprises the following steps:
the objective function is established according to the following formula,
wherein F represents the scheduling total cost, T is the optimized scheduling period, Pgrid(t) represents the amount of power purchased from the grid company at time t, cgrid(t) represents the purchase price of electricity from the large power grid at time t, m represents the number of flexible loads, NS represents the number of energy storage devices, NG represents the number of distributed power sources, Cloadi(t) represents the scheduling cost of the flexible load, Cstorj(t) represents the scheduling cost of the energy storage device, CDGk(t) represents the scheduling cost of the distributed power supply,
each scheduling cost formula is as follows:
in the formula, alphai,βiRespectively scheduling cost coefficients for the flexible load; pload0An active initial value before flexible load scheduling is obtained; delta PloadiIs the flexible load power variation; lambda [ alpha ]essRepresenting the cost factor, P, of the storage batterystorj(t) represents the discharge capacity of the jth energy storage device at time t, ak,bk,ckRespectively, the cost factor, P, of the distributed power supplyDGk(t) represents a force output value of the kth distributed device at the time t;
the constraints include active power balance constraints and system standby constraints,
the active power balance constraint formula is as follows:
in the formula, Pd(t) load demand for a period t;
the system standby constraint equation is as follows:
2. The method of claim 1, wherein the clustering the distributed power sources based on fuzzy clustering to obtain a plurality of distributed power source clusters comprises:
establishing a distributed output observation data matrix corresponding to the historical output value of the distributed power supply;
and according to the preset initial membership degree matrixes and the corresponding initial clustering centers thereof, carrying out cluster division on the distributed output observation data matrix to obtain a plurality of distributed power supply clusters.
3. The method of claim 1, wherein the clustering the load based on fuzzy clustering to obtain a plurality of load clusters comprises:
establishing a load observation data matrix corresponding to the load historical value;
and according to the preset initial membership degree matrixes and the corresponding initial clustering centers thereof, carrying out cluster division on the load observation data matrix to obtain a plurality of load clusters.
4. The method of claim 1, wherein the processing the target distributed power output value and the meteorological condition value corresponding to the corresponding distributed power cluster using each prediction model to determine the output predicted value for each distributed power cluster comprises:
extracting characteristic values of each distributed power supply cluster; the characteristic values comprise historical output values of the distributed power supplies corresponding to the current day, historical meteorological condition values corresponding to the current day and historical output values of the distributed power supplies corresponding to the previous day;
converting each characteristic value into standard data;
training a pre-established extreme learning machine by using the standard data;
and inputting the standard value of the output value of the target distributed power supply corresponding to each distributed power supply cluster and the standard value of the meteorological condition value into a trained extreme learning machine to obtain the output predicted value of each distributed power supply cluster.
5. The method of claim 1, wherein the processing the target load values and the meteorological conditions values corresponding to the respective load clusters using the respective prediction models, and determining the predicted load values for the respective load clusters comprises:
extracting characteristic values of each load cluster; the characteristic values comprise a load historical value corresponding to the current day, a historical meteorological condition value corresponding to the current day and a load historical value corresponding to the previous day;
converting each characteristic value into standard data;
training a pre-established extreme learning machine by using the standard data;
and inputting the target load value and the meteorological condition value corresponding to each load cluster into a trained extreme learning machine to obtain a load predicted value of each load cluster.
6. A device for randomly optimizing and scheduling a power distribution network is characterized by comprising an acquisition unit, a distributed power supply dividing unit, a load dividing unit, a distributed power supply prediction unit, a load prediction unit, an establishing unit and a solving unit;
the acquisition unit is used for acquiring historical data of the power distribution network; the historical data comprises a load historical value, a distributed power supply historical output value and a historical meteorological condition value;
the distributed power supply dividing unit is used for carrying out cluster division on the distributed power supplies based on fuzzy clustering to obtain a plurality of distributed power supply clusters;
the load dividing unit is used for carrying out cluster division on the load based on fuzzy clustering to obtain a plurality of load clusters;
the distributed power supply prediction unit is used for processing a target distributed power supply output value and a meteorological condition value corresponding to a corresponding distributed power supply cluster by using each prediction model to determine an output prediction value of each distributed power supply cluster;
the load prediction unit is used for processing a target load value and a meteorological condition value corresponding to the corresponding load cluster by using each prediction model to determine a load prediction value of each load cluster;
the establishing unit is used for establishing a target function with the minimum active scheduling cost, an active power balance constraint condition and a system standby constraint condition according to the output predicted value, the load predicted value and various power distribution network costs;
the solving unit is used for solving the objective function under each constraint condition by using a hybrid intelligent algorithm to obtain a distribution network scheduling result;
the establishing unit is specifically configured to establish the objective function according to the following formula,
wherein F represents the scheduling total cost, T is the optimized scheduling period, Pgrid(t) represents the amount of power purchased from the grid company at time t, cgrid(t) represents the purchase price of electricity from the large power grid at time t, m represents the number of flexible loads, NS represents the number of energy storage devices, NG represents the number of distributed power sources, Cloadi(t) represents the scheduling cost of the flexible load, Cstorj(t) represents scheduling of energy storage devicesThis, CDGk(t) represents the scheduling cost of the distributed power supply,
each scheduling cost may be represented as:
in the formula, alphai,βiRespectively scheduling cost coefficients for the flexible load; pload0An active initial value before flexible load scheduling is obtained; delta PloadiIs the flexible load power variation; lambda [ alpha ]essRepresenting the cost factor, P, of the storage batterystorj(t) represents the discharge capacity of the jth energy storage device at time t, ak,bk,ckRespectively, the cost factor, P, of the distributed power supplyDGk(t) represents a force output value of the kth distributed device at the time t;
the constraints include active power balance constraints and system standby constraints,
the active power balance constraint formula is as follows:
in the formula, Pd(t) load demand for a period t;
the system standby constraint equation is as follows:
7. The utility model provides a device of distribution network random optimization dispatch which characterized in that includes:
a memory for storing a computer program;
a processor for executing said computer program for carrying out the steps of the method for stochastic optimized scheduling of power distribution networks according to any of claims 1 to 5.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for stochastic optimized scheduling of an electrical distribution network according to any of the claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910402407.XA CN110048420B (en) | 2019-05-15 | 2019-05-15 | Method, device and medium for random optimal scheduling of power distribution network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910402407.XA CN110048420B (en) | 2019-05-15 | 2019-05-15 | Method, device and medium for random optimal scheduling of power distribution network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110048420A CN110048420A (en) | 2019-07-23 |
CN110048420B true CN110048420B (en) | 2021-08-13 |
Family
ID=67281924
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910402407.XA Active CN110048420B (en) | 2019-05-15 | 2019-05-15 | Method, device and medium for random optimal scheduling of power distribution network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110048420B (en) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110648248B (en) * | 2019-09-05 | 2023-04-07 | 广东电网有限责任公司 | Control method, device and equipment for power station |
CN110729768A (en) * | 2019-10-09 | 2020-01-24 | 南方电网能源发展研究院有限责任公司 | Incremental power distribution network time-sharing power distribution method for distributed power supply output characteristics |
CN111507510A (en) * | 2020-04-08 | 2020-08-07 | 广东电网有限责任公司电力调度控制中心 | Optimization method, device, equipment and storage medium for self-healing scheme of power distribution network |
CN111709574B (en) * | 2020-06-16 | 2022-02-22 | 广东电网有限责任公司 | Distributed cluster configuration scheduling method, computer equipment and storage medium |
CN112329995B (en) * | 2020-10-23 | 2023-05-30 | 南方电网调峰调频发电有限公司 | Optimized scheduling method and device for distributed energy storage cluster and computer equipment |
CN112884221B (en) * | 2021-02-10 | 2024-07-19 | 中青云智科技(浙江)有限公司 | Local area network multi-function mutual-aid optimizing scheduling method and device |
CN113592528A (en) * | 2021-06-22 | 2021-11-02 | 国网河北省电力有限公司营销服务中心 | Baseline load estimation method and device and terminal equipment |
CN113300416B (en) * | 2021-07-07 | 2022-10-21 | 广东电网有限责任公司 | Power grid standby capacity configuration method, system, equipment and computer medium |
CN113644682B (en) * | 2021-07-14 | 2023-08-25 | 国网河北省电力有限公司电力科学研究院 | Multi-zone collaborative management and control method and device for high-permeability active power distribution network and terminal equipment |
CN113962429B (en) * | 2021-09-03 | 2024-04-05 | 华南理工大学 | Optimization method, system, device and medium for solving load replacement |
CN113887809A (en) * | 2021-10-11 | 2022-01-04 | 国网新疆电力有限公司巴州供电公司 | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target |
CN113902315A (en) * | 2021-10-13 | 2022-01-07 | 四川才能科技有限公司 | Intelligent life service system and method |
CN115511384B (en) * | 2022-11-03 | 2023-06-06 | 武汉域弘信息技术有限公司 | Power scheduling method, device, equipment and medium for distributed solar power generation |
CN115566740B (en) * | 2022-12-05 | 2023-04-07 | 广东电网有限责任公司江门供电局 | Distributed renewable energy cluster aggregation regulation potential evaluation method and device |
CN115796393B (en) * | 2023-01-31 | 2023-05-05 | 深圳市三和电力科技有限公司 | Energy management optimization method, system and storage medium based on multi-energy interaction |
CN117114363B (en) * | 2023-10-19 | 2024-02-06 | 北京国电通网络技术有限公司 | Power distribution network regulation and control method, device, electronic equipment and computer readable medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104600713A (en) * | 2014-12-25 | 2015-05-06 | 国家电网公司 | Device and method for generating day-ahead reactive power dispatch of power distribution network containing wind/photovoltaic power generation |
CN107464048A (en) * | 2017-07-26 | 2017-12-12 | 广东电网有限责任公司电力调度控制中心 | A kind of plan security check method a few days ago based on research state |
CN107516150A (en) * | 2017-08-25 | 2017-12-26 | 广东工业大学 | A kind of Forecasting Methodology of short-term wind-electricity power, apparatus and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10103548B2 (en) * | 2015-10-23 | 2018-10-16 | Fujitsu Limited | Operating a solar power generating system |
-
2019
- 2019-05-15 CN CN201910402407.XA patent/CN110048420B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104600713A (en) * | 2014-12-25 | 2015-05-06 | 国家电网公司 | Device and method for generating day-ahead reactive power dispatch of power distribution network containing wind/photovoltaic power generation |
CN107464048A (en) * | 2017-07-26 | 2017-12-12 | 广东电网有限责任公司电力调度控制中心 | A kind of plan security check method a few days ago based on research state |
CN107516150A (en) * | 2017-08-25 | 2017-12-26 | 广东工业大学 | A kind of Forecasting Methodology of short-term wind-electricity power, apparatus and system |
Also Published As
Publication number | Publication date |
---|---|
CN110048420A (en) | 2019-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110048420B (en) | Method, device and medium for random optimal scheduling of power distribution network | |
CN108306303B (en) | Voltage stability evaluation method considering load increase and new energy output randomness | |
CN110298138B (en) | Comprehensive energy system optimization method, device, equipment and readable storage medium | |
Mohan et al. | An efficient two stage stochastic optimal energy and reserve management in a microgrid | |
CN104376410B (en) | A kind of planing method of Distributed Generation in Distribution System | |
CN110738344B (en) | Distributed reactive power optimization method and device for load prediction of power system | |
CN107749638B (en) | Multi-microgrid combined virtual power plant distributed random non-overlapping sampling centerless optimization method | |
CN115796393B (en) | Energy management optimization method, system and storage medium based on multi-energy interaction | |
CN105207573A (en) | Quantitative optimal configuration method of wind-solar hybrid power system based on discrete probability model | |
CN112994092B (en) | Independent wind-solar storage micro-grid system size planning method based on power prediction | |
KR20200119367A (en) | Demand power prediction device for energy storage system and method for predicting demand power using the same | |
CN115689253B (en) | Comprehensive energy scheduling optimization method taking total building carbon emission as target | |
Feng et al. | Scenario reduction for stochastic unit commitment with wind penetration | |
Javidsharifi et al. | Probabilistic model for microgrids optimal energy management considering AC network constraints | |
Gazijahani et al. | Optimal multi-objective operation of multi microgrids with considering uncertainty | |
CN115689017A (en) | Photovoltaic power generation capacity prediction method, device, equipment and storage medium | |
CN113536694B (en) | Robust optimization operation method, system and device for comprehensive energy system and storage medium | |
Zhao et al. | Probabilistic voltage stability assessment considering stochastic load growth direction and renewable energy generation | |
Buonanno et al. | Comprehensive method for modeling uncertainties of solar irradiance for PV power generation in smart grids | |
CN112215478B (en) | Power coordination control method and device for optical storage station and storage medium | |
CN108846529A (en) | A kind of generated energy forecasting system | |
CN117595231A (en) | Intelligent power grid distribution management system and method thereof | |
CN110489893B (en) | Variable weight-based bus load prediction method and system | |
CN116054241B (en) | Robust energy management method for new energy micro-grid group system | |
CN110991519A (en) | Intelligent switch state analysis and adjustment method and 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 |