CN114006367A - Distributed power supply access capability prediction method and system - Google Patents
Distributed power supply access capability prediction method and system Download PDFInfo
- Publication number
- CN114006367A CN114006367A CN202111244102.4A CN202111244102A CN114006367A CN 114006367 A CN114006367 A CN 114006367A CN 202111244102 A CN202111244102 A CN 202111244102A CN 114006367 A CN114006367 A CN 114006367A
- Authority
- CN
- China
- Prior art keywords
- power supply
- power
- distributed power
- load
- charging
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004146 energy storage Methods 0.000 claims abstract description 19
- 238000012423 maintenance Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 6
- 229920006395 saturated elastomer Polymers 0.000 claims description 5
- 238000012549 training Methods 0.000 description 17
- 238000010248 power generation Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000009826 distribution Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 7
- 238000007599 discharging Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000010606 normalization Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
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
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/008—Circuit arrangements for ac mains or ac distribution networks involving trading of energy or energy transmission rights
-
- 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
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The utility model discloses a distributed power supply access capability prediction method and system, including: obtaining an active power and an equivalent load predicted value output by a conventional unit power supply in the system; inputting active power output by a conventional unit power supply and an equivalent load predicted value into a constructed distributed power supply access capability prediction model to obtain a distributed power supply access capability prediction result; the distributed power supply access capacity prediction model is constructed by taking the minimum comprehensive cost of initial investment, maintenance and operation of each power supply, the minimum comprehensive cost of system power balance, the constraint of active power output of each power supply, the constraint of charge and discharge power of an energy storage battery and the constraint of photovoltaic grid connection reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the access of the distributed power supply as a target. And the minimum peak-to-valley difference rate of the power grid is ensured after the distributed power supply is connected.
Description
Technical Field
The invention relates to the technical field of power grid planning, in particular to a method and a system for predicting the access capability of a distributed power supply.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Wind power generation and solar power generation are widely connected to a power system on a large scale, and the randomness and the fluctuation of the power generation cause the power system to face challenges. After the distributed power supply is connected to the power distribution network, the distributed power supply affects node voltage, line current, short-circuit current, reliability and the like of the power distribution network, new challenges are inevitably brought to power distribution network planning, uncertainty and randomness are obviously increased, and the influence of the distributed power supply on the power distribution network planning is also added when traditional factors of planning the power distribution network in the past are considered.
Different from the traditional power supply, part of the distributed power supply utilizes new energy sources for power generation (such as solar energy and wind energy), the output power of the distributed power supply is restricted by natural conditions, and stable output cannot be provided, so that the distributed power supply cannot be considered as the traditional power supply simply.
The inventor finds that the peak-valley difference rate after the distributed power supply is connected is not considered when the existing distributed power supply access capacity is predicted, so that the problem of unstable operation of a power grid is easily caused after the distributed power supply is connected, and meanwhile, the influence of unstable load factors such as charging load of an electric automobile is not considered when the distributed power supply access capacity is predicted, so that the prediction result of the distributed power supply access capacity is inaccurate.
Disclosure of Invention
The disclosure provides a method and a system for predicting the access capability of a distributed power supply to solve the above problems, and when the power magnitude of photovoltaic access is predicted, the minimum peak-to-valley difference rate is taken as a target, so that after the photovoltaic access, the peak-to-valley difference rate of a power grid is minimum, and the stable operation of the power grid is ensured.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
in a first aspect, a method for predicting distributed power access capability is provided, including:
obtaining an active power and an equivalent load predicted value output by a conventional unit power supply in the system;
inputting active power output by a conventional unit power supply and an equivalent load predicted value into a constructed distributed power supply access capacity prediction model to obtain a prediction result of the distributed power supply access capacity;
the distributed power supply access capacity prediction model is constructed by taking the minimum comprehensive cost of initial investment, maintenance and operation of each power supply, the minimum comprehensive cost of system power balance, the constraint of active power output of each power supply, the constraint of charging and discharging power of an energy storage battery and the constraint of photovoltaic grid connection reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the distributed power supply is accessed as a target.
In a second aspect, a distributed power access capability prediction system is provided, including:
the data acquisition module is used for acquiring active power and equivalent load predicted values output by a conventional unit power supply in the system;
the charging load prediction module is used for inputting the active power output by the conventional unit power supply and the equivalent load prediction value into the constructed distributed power supply access capability prediction model to obtain a prediction result of the distributed power supply access capability;
the distributed power supply access capacity prediction model is constructed by taking the minimum comprehensive cost of initial investment, maintenance and operation of each power supply, the minimum comprehensive cost of system power balance, the constraint of active power output of each power supply, the constraint of charging and discharging power of an energy storage battery and the constraint of photovoltaic grid connection reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the distributed power supply is accessed as a target.
In a third aspect, an electronic device is provided, which includes a memory and a processor, and computer instructions stored in the memory and executed on the processor, where the computer instructions, when executed by the processor, perform the steps of the distributed power access capability prediction method.
In a fourth aspect, a computer-readable storage medium is provided for storing computer instructions, which when executed by a processor, perform the steps of a distributed power access capability prediction method.
Compared with the prior art, the beneficial effect of this disclosure is:
1. the method and the device aim at minimizing the peak-valley difference rate of the power grid after the distributed power supply is connected, and predict the connection capability of the distributed power supply by taking the minimum comprehensive cost of initial investment, maintenance and operation of the system as constraint, so that the peak-valley difference rate of the power grid is minimized after the distributed power supply is connected into the power grid, and the stable operation of the power grid is ensured.
2. According to the method and the device, when the access capability of the distributed power supply is predicted, the influence of the charging load of the electric automobile is considered, and the accuracy of the prediction of the access capability of the distributed power supply is guaranteed.
Advantages of additional aspects of the invention 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 invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application in a limiting sense.
Fig. 1 is a flow chart of a method disclosed in embodiment 1 of the present disclosure.
The specific implementation mode is as follows:
the present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an", and/or "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of the features, steps, operations, devices, components, and/or combinations thereof.
Example 1
In this embodiment, a method for predicting distributed power supply access capability is disclosed, which includes:
obtaining an active power and an equivalent load predicted value output by a conventional unit power supply in the system;
inputting active power output by a conventional unit power supply and an equivalent load predicted value into a constructed distributed power supply access capacity prediction model to obtain a prediction result of the distributed power supply access capacity;
the distributed power supply access capacity prediction model is constructed by taking the minimum comprehensive cost of initial investment, maintenance and operation of each power supply, the minimum comprehensive cost of system power balance, the constraint of active power output of each power supply, the constraint of charging and discharging power of an energy storage battery and the constraint of photovoltaic grid connection reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the distributed power supply is accessed as a target.
Further, the power supply in the system comprises a conventional unit and a distributed power supply; the equivalent load predicted value comprises a conventional load predicted value and an energy storage load.
Further, the specific process of obtaining the conventional load predicted value is as follows:
acquiring the average temperature, the average humidity, the holiday days, the GDP acceleration rate of the area, the industrial structure, the power utilization structure and the saturation load density of a time period to be predicted;
and inputting the obtained average temperature, average humidity, holiday days, regional GDP acceleration, industrial structure, power utilization structure and saturated load density of the date to be predicted into a trained conventional load prediction model to obtain a conventional load prediction value.
Further, the conventional load prediction model employs a deep neural network.
Further, the equivalent load predicted value comprises a conventional load predicted value and an electric vehicle charging load predicted value.
Furthermore, the distributed power supply access capability prediction model is constructed by taking the minimum comprehensive cost of initial investment, maintenance and operation of each power supply, the minimum comprehensive cost of system power balance, the constraint of active power output of each power supply, the power constraint during charging of the electric automobile and the constraint of photovoltaic grid-connected reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the distributed power supply is accessed as a target
Further, the process of obtaining the predicted value of the charging load of the electric vehicle is as follows:
acquiring the battery capacity and the rated charging power of the electric automobile, the charge state when the electric automobile is connected to a power grid, the charge state when the electric automobile is charged, the moment when the electric automobile is connected to the power grid and the moment when the electric automobile leaves the power grid;
determining the number of the electric automobiles in a certain time period according to the moment when the electric automobiles are connected into the power grid and leave the power grid;
determining the charging power of the electric automobile in a certain time period according to the battery capacity and the rated charging power of the electric automobile, the charging state when the electric automobile is connected to a power grid and the charging state when the charging is finished;
and determining a predicted value of the charging load of the electric automobile according to the number of the electric automobiles and the charging power of the electric automobiles.
The method for predicting the charging load of the electric vehicle disclosed in this embodiment will be described in detail.
As shown in fig. 1, a method for predicting access capability of a distributed power supply includes:
s1: and obtaining the active power and equivalent load prediction values output by the conventional unit power supply in the system.
In specific implementation, the power supply in the power grid system comprises a conventional generator set and a distributed power supply, and the distributed power supply further comprises photovoltaic power generation, wind power generation, gas turbine power generation and the like.
Wherein, the obtained G for the generating power of the conventional generating setMachine setG represents generated power of distributed power supplyDistributed power supplyAnd (4) showing.
Acquiring the sunshine duration and the radiation intensity of sunlight of an area to be planned to obtain photovoltaic power generation power;
and obtaining the power of wind power generation by obtaining the wind speed of the area to be planned.
The equivalent load predicted value can be a conventional load predicted value and an energy storage load; when the charging of the electric automobile is considered, the predicted value of the charging load of the electric automobile is also included.
The conventional load predicted value obtaining process comprises the following steps:
acquiring the average temperature, the average humidity, the holiday days, the GDP acceleration rate of the area, the industrial structure, the power utilization structure and the saturation load density of a time period to be predicted;
and inputting the obtained average temperature, average humidity, holiday days, regional GDP acceleration, industrial structure, power utilization structure and saturated load density of the date to be predicted into a trained conventional load prediction model to obtain a conventional load prediction value.
The conventional load prediction model of the present embodiment employs a deep neural network.
Deep Neural Networks (DNNs) are multi-layer perceptrons that contain multiple hidden layers. The general deep neural network model is composed of an input layer, a plurality of intermediate layers and an output layer. A DNN network model adopts a hybrid training mode, a temporary output layer is stacked on a hidden layer to be trained in the process of training layer by layer, then the layer is trained by adopting a hybrid training method combining unsupervised training (reestablishing input) and supervised training (reducing prediction error), namely, an updated value of the weight of the hidden layer in the unsupervised training process is added with an updated value obtained by the supervised training to serve as a weight updated value, a radial basis function is adopted for the unsupervised training, and a sigmoid function is adopted for the supervised training.
The learning process of the deep neural network utilizes forward and backward propagation of signals to achieve learning training. In the forward propagation learning process, input information is propagated to the output layer after passing through the input layer, in the hidden layer learning training. In general, the predicted result cannot be achieved, so that the error change value is reversely propagated in the output layer, the hidden layer learning is re-entered, and the result is output when the predicted result reaches the expected value through repeated iteration of forward and reverse, and finally the learning training is completed.
For a DNN network, assuming that its input is X, the computation of activation values for its hidden and output layers can be represented by the following formula:
vk(x)＝∑wkjuj(x)+wk0
in the formula uj(x) Representing the output of the jth node in the hidden layer, mjRepresenting the center of the jth hidden layer node. | l | |, denotes the Euclidean norm, σjRepresenting the width of the Gauss distribution for node j.
Wherein wkjAnd wk0Respectively representing the weight and the offset vector of the k-th layer of the network, yk(x) Representing the output of the network. The forward propagation algorithm of DNN is to use several weight coefficient matrixes W to bias vectors Wk0And carrying out a series of nonlinear operations and activation operations on the incoming and incoming value vector x, starting from the input layer, calculating backwards layer by layer until the operation is carried out on the output layer, and obtaining an output result as a value.
In the neural network input quantity, the magnitude of the unit difference is large because of different units of each input quantity. If direct input quantity input is adopted, the neuron training is saturated, so that before input training, normalization processing must be carried out on data to enable the data to be in the same quantity level, neural network convergence is accelerated, and finally a real numerical value is obtained through inverse normalization processing. The normalization method employed in this embodiment normalizes the data to [0, 1 ]]The formula is as follows:
reverse normalization: x is the number ofi＝(xmax-xmin)yi+xmin. Wherein xmax、xminFor training the maximum and minimum values of the sample input, xi、yiValues before and after normalization for the input samples.
Factors affecting the power load are many and generally include economic factors, time factors, climate factors and random factors. The factors that have the greatest influence on the short-term load forecasting are generally weather and holidays, while the medium-term and long-term load forecasting mainly needs to consider the development of socioeconomic performance, the change of population volume and the change of geographical climate.
The monthly load of the grid has obvious seasonal characteristics. The load is generally low when the month 11, 12 and 1 is the winter month, and the industrial load is greatly reduced and the total load is reduced to the lowest point when the spring holiday comes at the end of the month 1 in the lunar calendar 12. In the 7 and 8 months, which belong to the summer months, the load of the air conditioner is greatly increased, the occupied proportion is high, the total load of the power grid is also greatly increased, and the annual maximum load value is reached. 3. In months 4, 5, 10 and 11, the load of the power grid is smaller due to meteorological factors, and the load is more stable. The influence on the monthly load is therefore mainly due to weather factors, climate factors, historical and economic factors, industrial and electrical structures. The corresponding factor indexes are respectively as follows: average air temperature, average humidity, holiday days, GDP acceleration rate, industrial structure, power structure and saturated load density.
The training process of the deep neural network comprises the following steps:
acquiring historical sample data of a time period to be predicted;
inputting the acquired historical sample data into the constructed deep neural network, and performing partial supervised training to acquire the trained deep neural network.
The acquired historical sample data comprises: average air temperature, average humidity, holiday days, regional GDP acceleration, industrial structure, power utilization structure, saturation load density and corresponding conventional load data of a time period to be predicted.
The specific process for obtaining the predicted value of the charging load of the electric automobile comprises the following steps:
acquiring the battery capacity and the rated charging power of the electric automobile, the charge state when the electric automobile is connected to a power grid, the charge state when the electric automobile is charged, the moment when the electric automobile is connected to the power grid and the moment when the electric automobile leaves the power grid;
determining the number of the electric automobiles in a certain time period according to the moment when the electric automobiles are connected into the power grid and leave the power grid;
determining the charging power of the electric automobile in a certain time period according to the battery capacity and the rated charging power of the electric automobile, the charging state when the electric automobile is connected to a power grid and the charging state when the charging is finished;
and determining a predicted value of the charging load of the electric automobile according to the number of the electric automobiles and the charging power of the electric automobiles.
In specific implementation, the driving mileage of the electric vehicle is different every day, the battery capacity and the state of the electric vehicle connected to the power grid at the same time are different, and the quantity of the electric vehicles, the driving mileage distribution, the battery capacity and charging and discharging power curves and the use habits of drivers need to be considered when the charging load model of the electric vehicle is established. Under different charging modes, the influence of charging of the electric automobile on daily load curves is different, the maximum load of a power grid at a peak at night can be increased by free charging, and the peak-valley difference of the load of the power grid is increased.
The method is characterized in that a private car is taken as a research object, the charging mode is a slow charging mode, charging loss is not considered, charging is carried out at constant power, and variables related to a charging load model of a single electric car are listed in table 1.
TABLE 1 Single electric vehicle Charge load model variables
Because the market penetration rate of the current private electric vehicle is low and statistical data for the rule of private electric vehicle traveling is lacked, on the premise that the electric vehicle replaces the traditional fuel oil vehicle and the traveling habit of the private vehicle is not changed,the simulation research can be carried out by utilizing the traveling statistical data of the traditional fuel automobile. According to the 2015 year Beijing annual newspaper for traffic development published by the Beijing institute of traffic development, statistical data of the time when a private car in the Beijing area finally returns home, the first trip time and daily mileage can be obtained. Selecting a Gaussian function to fit the probability distribution graph to obtain the time T of accessing the private electric vehicle to the power gridaThe fitted probability density function of (a) is:
in the formula, mus＝b1＝18.62；
Private electric automobile leaves electric wire netting moment TaThe fitted probability density function of (a) is:
in the formula, mud＝b2＝7.901；
And determining the number of the electric automobiles connected to the power grid in a certain time period according to the moment when the private electric automobiles are connected to the power grid and the moment when the private electric automobiles leave the power grid.
The total charging load of the t-th time period is the sum P of the charging loads of all the current electric vehiclesEV1It can be expressed as:
wherein N represents the number of electric vehicles, Pn，tRepresents the charging power of the electric vehicle n during the t-th period.
S2: and inputting the active power output by the conventional unit power supply and the equivalent load predicted value into the constructed distributed power supply access capability prediction model to obtain the prediction result of the distributed power supply access capability.
The distributed power supply access capacity prediction model is constructed by taking the minimum comprehensive cost of initial investment, maintenance and operation of each power supply, the minimum comprehensive cost of system power balance, the constraint of active power output of each power supply, the constraint of charging and discharging power of an energy storage battery and the constraint of photovoltaic grid connection reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the distributed power supply is accessed as a target.
In specific implementation, when the peak-clipping and valley-filling effects of the charging load scheduling of the electric vehicle on the equivalent load are not considered, the magnitude of the power accessed by the photovoltaic power generation and the local energy storage are determined through the cooperative scheduling of the photovoltaic power generation and the local energy storage, and a distributed power supply access capacity prediction model constructed by taking the minimum peak-valley difference rate as a target is as follows:
the constraint conditions are as follows:
Gdistributed power supply+GMachine set＝Peq
GMachine set＝PNormal load
0≤Pscharge(i)≤Pscharmax
-Psdischarmax≤Psdischarge(i)≤0
Wherein f isiIs the peak-to-valley difference rate, i is time, Pmax、PminThe maximum value and the minimum value of the power grid load are respectively, wherein the power grid load P is P ═ Peq；
The power supply of the conventional generator set is active power,
the power generation cost of each conventional generator set power supply i,
active power for distributed power generation, including photovoltaic, wind, gas turbines, etc.,
the active load of the power grid comprises the response load of the demand side such as the conventional load, the charging and the energy storage of the electric automobile and the like,
and
respectively the maximum and minimum active power, P, of the conventional unit power supplyeqEquivalent load (MW); pavIs the average value (MW) of the equivalent load,
is the maximum active power of the regional photovoltaic power; pscharmaxMaximum charging power (MW) for the energy storage battery; psdischarmaxMaximum discharge power (MW) for the energy storage cell; pscharge(i) Charging power (MW) of the energy storage battery for a certain time; psdischarge(i) The discharge power (MW) of the energy storage battery at a certain time; and lambda is the reliability coefficient of the photovoltaic grid connection.
When the resource complementary action of the electric automobile charging and the distributed power supply is considered, the photovoltaic power generation is locally consumed through the coordination control of the distributed power supply such as the charging and the photovoltaic power generation, and the maximum capacity of the regional electric automobile and the photovoltaic access is determined.
Considering two conditions of orderly charging and unordered charging of the electric automobile, PEV1Expressed as a disordered charge load, the ordered charge load is the adjustable load PEV2Then the equivalent load is Peq＝PEV1+PGeneral of(ii) a At the moment, the constraint condition of the distributed power supply access capability prediction model constructed by taking the minimum peak-to-valley difference rate as a target is changed into:
CPV-PEV2+Gmachine set＝PEV1+PGeneral of
GMachine set＝PGeneral of+PEV1
At this time, the grid load P is: p ═ PEV1+PGeneral of
The adjustable load can be regarded as negative generated output, and a part of photovoltaic generated output is equivalently absorbed in the charging process. When the electric automobile is charged in a valley, the peak load of the power grid cannot be increased, the photovoltaic power, the wind power fluctuation and the synergy among the electric automobile charging are further utilized, the electric automobile is dispatched to locally absorb the photovoltaic power, and the photovoltaic capacity of the power grid is improved under the condition that the conventional peak regulation capacity is not increased.
The maximum charging power of the electric automobile is determined according to the maximum charging power P of a charging and replacing power station to which a bus in the area can be connectedmaxCharging power P for charging electric vehicles with the maximum number of charging piles in region simultaneouslyEVAnd (4) determining.
The quantity of the charging piles is determined according to the areas where the charging piles are located, the building type configuration indexes and the building area.
Electric vehicle charging load P that hypothesis can be insertedEVAll as interruptible loads to participate in the regulation and control of the power grid, the electric automobile is charged in the off-peak period, and the peak load Peq＝PNormal load. The size of the electric automobile access load is determined by the planned number of regional charging piles, the capacity of transformers and lines, the load rate and the power factor. The method specifically comprises the following steps:
pEV＝n*Pcharging deviceSimultaneous rate of change
Pmax＝βSN cosθ/ks-PH
PmaxThe maximum charging power (kW) of a charging and replacing power station which can be accessed by a 10kV bus; beta is the load factor of the transformer; sNTransformer capacity (kVA); pHActive power (kW) for the conventional load carried by the transformer; k is a radical ofsSimultaneous coefficient of electrical load for the user; cos θ is the power factor.
PEV＝n*PCharging deviceIn the simultaneous rate, n is the number of regional charging piles and is limited by the area of regional construction, PCharging deviceThe charging power of a single electric automobile.
The construction quantity and the construction area of the regional charging pile are related. And the quantity N of the construction project configuration parking spaces is determined according to the area where the construction project is located, the configuration indexes of the building types and the building area. According to the temporary regulations on the planning and construction of charging facilities of units, residential areas and parking lots, the construction proportion or the reserved proportion of the charging facilities of the electric vehicles in the parking lots is not less than 10%, and the number of charging piles in the planning area is N-10%.
Referring to special plans of charging infrastructures of other provincial electric automobiles, the simultaneous rate of charging piles of the electric automobiles can be 0.7.
And inputting the active power output by the conventional unit power supply and the equivalent load predicted value into the constructed distributed power supply access capability prediction model so as to obtain a distributed power supply access capability prediction result.
According to the method for predicting the access capability of the distributed power supply, when the access capability of the distributed power supply is predicted, the peak-to-valley difference rate of a power grid is fully considered, the minimum peak-to-valley difference rate after the distributed power supply is accessed is taken as a target, the prediction result of the access capability of the distributed power supply is obtained, and when the distributed power supply is accessed to the power grid, the minimum peak-to-valley difference rate of the power grid is obtained, so that the stable operation of the power grid is ensured.
In addition, when the access capability of the distributed power supply is predicted, not only the conventional load but also the influence of the charging load and the energy storage load of the electric automobile on the equivalent load are fully considered, so that the accuracy of the prediction of the access capability of the distributed power supply can be improved.
Example 2
In this embodiment, a distributed power source access capability prediction system is disclosed, which includes:
the data acquisition module is used for acquiring active power and equivalent load predicted values output by a conventional unit power supply in the system;
the charging load prediction module is used for inputting the active power output by the conventional unit power supply and the equivalent load prediction value into the constructed distributed power supply access capability prediction model to obtain a prediction result of the distributed power supply access capability;
the distributed power supply access capacity prediction model is constructed by taking the minimum comprehensive cost of initial investment, maintenance and operation of each power supply, the minimum comprehensive cost of system power balance, the constraint of active power output of each power supply, the constraint of charging and discharging power of an energy storage battery and the constraint of photovoltaic grid connection reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the distributed power supply is accessed as a target.
Example 3
In this embodiment, an electronic device is disclosed, which includes a memory, a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the method for predicting the distributed power access capability disclosed in embodiment 1.
Example 4
In this embodiment, a computer readable storage medium is disclosed for storing computer instructions which, when executed by a processor, perform the steps of a distributed power access capability prediction method disclosed in embodiment 1.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above examples are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above examples, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A method for predicting the access capability of a distributed power supply is characterized by comprising the following steps:
obtaining an active power and an equivalent load predicted value output by a conventional unit power supply in the system;
inputting active power output by a conventional unit power supply and an equivalent load predicted value into a constructed distributed power supply access capability prediction model to obtain a distributed power supply access capability prediction result;
the distributed power supply access capacity prediction model is constructed by taking the minimum comprehensive cost of initial investment, maintenance and operation of each power supply, the minimum comprehensive cost of system power balance, the constraint of active power output of each power supply, the constraint of charge and discharge power of an energy storage battery and the constraint of photovoltaic grid connection reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the access of the distributed power supply as a target.
2. The method for predicting the access capability of the distributed power supply of claim 1, wherein the power supply in the system comprises a conventional unit and the distributed power supply; the equivalent load predicted value comprises a conventional load predicted value and an energy storage load.
3. The method for predicting the access capability of the distributed power supply according to claim 2, wherein the specific process for obtaining the conventional load prediction value is as follows:
acquiring the average temperature, the average humidity, the holiday days, the GDP acceleration rate of the area, the industrial structure, the power utilization structure and the saturation load density of a time period to be predicted;
and inputting the obtained average temperature, average humidity, holiday days, regional GDP acceleration, industrial structure, power utilization structure and saturated load density of the date to be predicted into a trained conventional load prediction model to obtain a conventional load prediction value.
4. The method according to claim 3, wherein the conventional load prediction model employs a deep neural network.
5. The method for predicting the access capability of the distributed power supply according to claim 1, wherein the equivalent load prediction value comprises a conventional load prediction value and an electric vehicle charging load prediction value.
6. The method for predicting the access capability of the distributed power supplies according to claim 5, wherein the model for predicting the access capability of the distributed power supplies is constructed by taking the minimum integrated cost of initial investment, maintenance and operation of each power supply, the minimum integrated cost of system power balance, the constraint of active power output of each power supply, the constraint of power during charging of the electric automobile and the constraint of photovoltaic grid-connected reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the access of the distributed power supplies as a target.
7. The method for predicting the access capability of the distributed power supply according to claim 5, wherein the obtaining process of the predicted value of the charging load of the electric vehicle is as follows:
acquiring the battery capacity, the rated charging power, the state of charge when the electric automobile is connected to a power grid, the state of charge when the electric automobile is charged, the moment when the electric automobile is connected to the power grid and the moment when the electric automobile leaves the power grid;
determining the number of the electric automobiles in a certain time period according to the moment when the electric automobiles are connected to a power grid and leave the power grid;
determining the charging power of the electric automobile in a certain time period according to the battery capacity and the rated charging power of the electric automobile, the state of charge when the electric automobile is connected to a power grid and the state of charge when the charging is finished;
and determining a predicted value of the charging load of the electric automobiles according to the number of the electric automobiles and the charging power of the electric automobiles.
8. A distributed power source access capability prediction system, comprising:
the data acquisition module is used for acquiring active power and equivalent load predicted values output by a conventional unit power supply in the system;
the charging load prediction module is used for inputting the active power output by the conventional unit power supply and the equivalent load prediction value into the constructed distributed power supply access capability prediction model to obtain a prediction result of the distributed power supply access capability;
the distributed power supply access capacity prediction model is constructed by taking the minimum comprehensive cost of initial investment, maintenance and operation of each power supply, the minimum comprehensive cost of system power balance, the constraint of active power output of each power supply, the constraint of charge and discharge power of an energy storage battery and the constraint of photovoltaic grid connection reliability as constraint conditions and taking the minimum peak-to-valley difference rate of a power grid after the access of the distributed power supply as a target.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executed on the processor, the computer instructions when executed by the processor performing the steps of a distributed power access capability prediction method according to any one of claims 1-7.
10. A computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of a distributed power access capability prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111244102.4A CN114006367A (en) | 2021-10-25 | 2021-10-25 | Distributed power supply access capability prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111244102.4A CN114006367A (en) | 2021-10-25 | 2021-10-25 | Distributed power supply access capability prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114006367A true CN114006367A (en) | 2022-02-01 |
Family
ID=79923993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111244102.4A Pending CN114006367A (en) | 2021-10-25 | 2021-10-25 | Distributed power supply access capability prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114006367A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734098A (en) * | 2020-12-31 | 2021-04-30 | 国网山东省电力公司青岛供电公司 | Power distribution network power dispatching method and system based on source-load-network balance |
| WO2021143075A1 (en) * | 2020-01-17 | 2021-07-22 | 南京东博智慧能源研究院有限公司 | Demand response method taking space-time distribution of electric vehicle charging loads into consideration |
-
2021
- 2021-10-25 CN CN202111244102.4A patent/CN114006367A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021143075A1 (en) * | 2020-01-17 | 2021-07-22 | 南京东博智慧能源研究院有限公司 | Demand response method taking space-time distribution of electric vehicle charging loads into consideration |
| CN112734098A (en) * | 2020-12-31 | 2021-04-30 | 国网山东省电力公司青岛供电公司 | Power distribution network power dispatching method and system based on source-load-network balance |
Non-Patent Citations (1)
| Title |
|---|
| 贵州电网有限责任公司: "《电动汽车充电管理云平台与智能充电技术》", 30 June 2020, 机械工业出版社, pages: 248 - 252 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109462231B (en) | Load optimization scheduling method, system and storage medium for residential micro-grid | |
| CN110895638B (en) | Active power distribution network model establishment method considering electric vehicle charging station site selection and volume fixing | |
| CN110119886B (en) | Active distribution network dynamic planning method | |
| CN109359389B (en) | Urban electric vehicle charging decision method based on typical load dynamic game | |
| CN107147152B (en) | new energy power distribution network multi-type active and reactive power source collaborative optimization configuration method and system | |
| CN109599861B (en) | Power supply structure planning method of power supply of transmission-end power grid considering local load peak regulation capacity | |
| CN105071389B (en) | The alternating current-direct current mixing micro-capacitance sensor optimizing operation method and device of meter and source net load interaction | |
| CN112734098B (en) | Power distribution network power dispatching method and system based on source-load-network balance | |
| CN111178619A (en) | Multi-objective optimization method considering distributed power supply and charging station joint planning | |
| CN106602557A (en) | Multi-period optimization reconstruction method of active power distribution network comprising electric automobiles | |
| CN107590607A (en) | A kind of micro-capacitance sensor Optimal Scheduling and method based on photovoltaic prediction | |
| CN103997091A (en) | Scale electric automobile intelligent charging control method | |
| CN111799786B (en) | Game theory-based capacity configuration method for new energy hybrid power system | |
| CN110138006A (en) | Consider more micro electric network coordination Optimization Schedulings containing New-energy electric vehicle | |
| Sun et al. | Data enabled predictive energy management of a PV-battery smart home nanogrid | |
| CN113859018B (en) | Hierarchical charge-discharge optimization control method for large-scale electric automobile group | |
| CN113326467B (en) | Multi-target optimization method, storage medium and optimization system for multi-station fusion comprehensive energy system based on multiple uncertainties | |
| CN108921331A (en) | It is a kind of meter and V2G function electric car and new energy optimizing scheduling modeling and algorithm | |
| CN112238781A (en) | Electric automobile ordered charging control method based on layered architecture | |
| CN114583729A (en) | Light-storage electric vehicle charging station scheduling method considering full-life-cycle carbon emission | |
| CN116402307A (en) | Power grid planning capacity analysis method considering operation characteristics of schedulable flexible resources | |
| CN106096807A (en) | A kind of complementary microgrid economical operation evaluation methodology considering small power station | |
| CN113500940B (en) | Electric automobile ordered charging and discharging dynamic optimization strategy based on particle swarm optimization | |
| CN114462854A (en) | Hierarchical scheduling method and system containing new energy and electric vehicle grid connection | |
| CN117595392A (en) | Power distribution network joint optimization method and system considering light Fu Xiaona and light storage and charge configuration |
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 |