CN114498632A - Power distribution station load prediction method and device based on new energy and charging facility - Google Patents
Power distribution station load prediction method and device based on new energy and charging facility Download PDFInfo
- Publication number
- CN114498632A CN114498632A CN202210101087.6A CN202210101087A CN114498632A CN 114498632 A CN114498632 A CN 114498632A CN 202210101087 A CN202210101087 A CN 202210101087A CN 114498632 A CN114498632 A CN 114498632A
- Authority
- CN
- China
- Prior art keywords
- power
- photovoltaic
- output
- wind speed
- evaluation index
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 85
- 239000011159 matrix material Substances 0.000 claims abstract description 47
- 238000012546 transfer Methods 0.000 claims abstract description 14
- 230000007704 transition Effects 0.000 claims description 53
- 230000006870 function Effects 0.000 claims description 49
- 238000010248 power generation Methods 0.000 claims description 24
- 239000002245 particle Substances 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000010606 normalization Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
- G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power distribution station load prediction method and a power distribution station load prediction device based on new energy and charging facilities, wherein the method comprises the following steps: establishing a photovoltaic influence evaluation index and determining the weight of the photovoltaic influence evaluation index; acquiring meteorological data of a power distribution area, and calculating predicted photovoltaic output of the power distribution area according to the meteorological data and the weight of the photovoltaic influence evaluation index; acquiring wind speed of a power distribution area, and calculating predicted wind power output of the power distribution area according to the wind speed; establishing a space-time transfer state matrix of the electric automobile, and determining the charging load power of the electric automobile according to the space-time transfer state matrix; acquiring basic load power, and superposing the predicted photovoltaic output, the predicted wind power output, the charging load power and the basic load power to acquire a load prediction condition of a power distribution station area; the method can predict the load by considering the influence of the distributed power supply, and the prediction result is more accurate and reliable.
Description
Technical Field
The invention relates to the technical field of electric automobiles, in particular to a power distribution area load prediction method and device based on new energy and charging facilities.
Background
Along with the continuous development of science and technology and the continuous improvement of the attention of people to environmental protection, the number of urban electric vehicles is increasing year by year, and in addition, along with the development of cities, photovoltaic and wind power are common one of distributed power supplies, and can be combined with building facilities such as houses, commercial buildings and industrial parks to flexibly supplement the ground electric energy.
With the large-scale access of the distributed photovoltaic power generation and wind power generation system and the electric automobile to the urban power distribution network in the form of V2G, the proportion of distributed power sources in the power distribution network is greatly improved. The distributed power supply has the characteristics of randomness, volatility, dispersity and the like, and the existing power distribution network architecture mainly based on the power supply side leading and single radial power supply is difficult to meet the requirements of users on power supply reliability and power quality after the distributed power supply is connected in a large scale.
For example, patent document CN111008727A discloses a method and an apparatus for predicting load of a distribution substation, which obtains historical load data and related factor data of a set time period of the distribution substation, then establishes a prediction model including the historical load data, the related factor data, a date type weight, a temperature factor influence weight, and a power outage duration influence weight, and finally predicts a future load value according to the model. When the load of the distribution substation is predicted, the temperature, the date type and the power-off time duration can be comprehensively considered, but the influence of a distributed power supply is not considered, and the accuracy of the conventional space load prediction is difficult to meet.
Disclosure of Invention
The invention provides a power distribution area load prediction method and device based on new energy and charging facilities, which can predict loads by considering the influence of a distributed power supply and have more accurate and reliable prediction results.
A power distribution station load prediction method based on new energy and charging facilities comprises the following steps:
establishing a photovoltaic influence evaluation index and determining the weight of the photovoltaic influence evaluation index;
acquiring meteorological data of a power distribution area, and calculating predicted photovoltaic output of the power distribution area according to the meteorological data and the weight of the photovoltaic influence evaluation index;
acquiring the wind speed of a power distribution station area, and calculating the predicted wind power output of the power distribution station area according to the wind speed;
establishing a space-time transfer state matrix of the electric automobile, and determining the charging load power of the electric automobile according to the space-time transfer state matrix;
and acquiring basic load power, and superposing the predicted photovoltaic output, the predicted wind power output, the charging load power and the basic load power to acquire the load prediction condition of the power distribution station area.
Further, determining the weight of the photovoltaic influence evaluation index comprises:
dividing a power distribution station area into m planning areas;
respectively establishing membership functions of all photovoltaic influence evaluation indexes;
generating a membership function matrix according to membership functions of all photovoltaic influence evaluation indexes in all planning areas;
performing normalization processing on the membership function of each photovoltaic influence evaluation index by adopting weighted fuzzy calculation to obtain a total evaluation value;
and calculating the weight of the photovoltaic influence evaluation index according to the membership function matrix and the total evaluation value.
Further, the weight of the photovoltaic influence evaluation index is calculated by the following formula:
wherein m represents the number of planning areas, n represents the number of photovoltaic influence evaluation indexes, and CkDenotes a ratio of a total evaluation value of the kth planned section, EiWeight representing the ith photovoltaic impact evaluation index, Ai,kAnd representing the membership degree of the ith photovoltaic influence evaluation index to the kth planning area.
Further, the meteorological data comprises the highest air temperature, the lowest air temperature, the average air temperature and the humidity within a preset time period;
according to the meteorological data and the weight of the photovoltaic influence evaluation index, calculating the predicted photovoltaic output of the distribution station area, wherein the method comprises the following steps:
normalizing the highest air temperature, the lowest air temperature, the average air temperature and the humidity in the preset time period;
determining a kernel function;
establishing a least square vector machine model, taking the highest air temperature, the lowest air temperature, the average air temperature and the humidity after normalization processing as particles, and calculating and obtaining parameters of the kernel function and the least square vector machine model based on a particle swarm algorithm;
and outputting the predicted photovoltaic output according to the kernel function and a least squares vector machine model.
Further, calculating a predicted wind power output of the distribution substation according to the wind speed includes:
establishing a relation between wind speed and power generation output power;
calculating the power generation output power at each wind speed according to the relation between the wind speed and the power generation output power;
determining a wind disturbance value;
and adding the electric output power and the wind power disturbance value to obtain predicted wind power output.
Further, the power generation output power at each wind speed is calculated by the following formula:
wherein v is wind speed, v isinFor cutting into the wind speed, voutTo cut out wind speed, vrFor rated wind speed, prIs the rated power output, and p is the power output.
Further, establishing an electric vehicle space-time transition state matrix, comprising:
dividing the state of the electric vehicle into various planning areas and on the road;
and according to the state of the electric automobile, simulating a transition state through a Markov chain, and generating a space-time transition state matrix.
Further, determining the charging load power of the electric automobile according to the space-time transition state matrix, comprising:
determining the initial state and the transition probability of the electric automobile according to the space-time transition state matrix;
determining the next state according to the initial state and the transition probability;
and judging whether the electric vehicle needs to be charged or not and calculating the charging load power of the electric vehicle according to the state, the quantity, the battery capacity, the charging power and the power consumption per kilometer of the electric vehicle.
A distribution substation load prediction device based on new energy and charging facilities comprises:
the photovoltaic weight calculation module is used for establishing a photovoltaic influence evaluation index and determining the weight of the photovoltaic influence evaluation index;
the photovoltaic prediction module is used for acquiring meteorological data of a power distribution station area and calculating the predicted photovoltaic output of the power distribution station area according to the meteorological data and the weight of the photovoltaic influence evaluation index;
the wind power prediction module is used for acquiring the wind speed of a power distribution station area and calculating the predicted wind power output of the power distribution station area according to the wind speed;
the electric vehicle load prediction module is used for establishing a space-time transfer state matrix of the electric vehicle and determining the charging load power of the electric vehicle according to the space-time transfer state matrix;
and the comprehensive prediction module is used for obtaining the basic load power, and superposing the predicted photovoltaic output, the predicted wind power output, the charging load power and the basic load power to obtain the load prediction condition of the power distribution station area.
An electronic device comprises a processor and a storage device, wherein the storage device stores a plurality of instructions, and the processor is used for reading the instructions and executing the method.
The power distribution station load prediction method and device based on the new energy and the charging facility, provided by the invention, at least have the following beneficial effects:
various factors involved in photovoltaic output are comprehensively considered, weighted fuzzy calculation is carried out on membership functions of all photovoltaic influence evaluation indexes, meteorological data are collected and used for calculating the predicted photovoltaic output of the power distribution area, and therefore the prediction result is more accurate;
uncertainty in the wind power generation process is considered, and a disturbance item is added to a wind power output predicted value to enable a result to be more fit for actual output, so that the predicted result is more accurate and reliable;
the influence of various distributed power sources is comprehensively considered, from the distribution characteristics of dual dimensions of time and space, the three factors of photovoltaic output, wind power output and electric automobile charging power are combined and superposed with the basic load power, and the accuracy of the load prediction of the power distribution station area is improved.
Drawings
Fig. 1 is a flowchart of an embodiment of a power distribution grid load prediction method based on a new energy source and a charging facility according to the present invention.
Fig. 2 is a functional relationship diagram of an embodiment of a relationship between wind power output power and wind speed in the power distribution grid load prediction method provided by the present invention.
Fig. 3 is a schematic structural diagram of an embodiment of a distribution substation load prediction apparatus based on a new energy source and a charging facility according to the present invention.
Fig. 4 is a schematic structural diagram of an embodiment of the power distribution substation load prediction electronic device based on a new energy source and a charging facility according to the present invention.
Reference numerals: 101-a processor, 102-a storage device, 201-a photovoltaic weight calculation module, 202-a photovoltaic prediction module, 203-a wind power prediction module, 204-an electric vehicle load prediction module and 205-a comprehensive prediction module.
Detailed Description
In order to better understand the technical scheme, the technical scheme is described in detail in the following with reference to the attached drawings of the specification and specific embodiments.
Referring to fig. 1, in some embodiments, there is provided a power distribution grid load prediction method based on new energy and a charging facility, including:
s1, establishing photovoltaic influence evaluation indexes and determining the weight of the indexes;
s2, collecting meteorological data of a power distribution area, and calculating the predicted photovoltaic output of the power distribution area according to the meteorological data and the weight of the photovoltaic influence evaluation index;
s3, collecting wind speed of a power distribution station area, and calculating predicted wind power output of the power distribution station area according to the wind speed;
s4, establishing a space-time transfer state matrix of the electric automobile, and determining the charging load power of the electric automobile according to the space-time transfer state matrix;
and S5, obtaining basic load power, and superposing the predicted photovoltaic output, the predicted wind power output, the charging load power and the basic load power to obtain the load prediction condition of the power distribution station area.
Specifically, in step S1, determining the weight of the photovoltaic influence evaluation index includes:
s11, dividing the power distribution station area into m planning areas;
s12, respectively establishing membership functions of each photovoltaic influence evaluation index;
s13, generating a membership function matrix according to the membership function of each photovoltaic influence evaluation index in each planning region;
s14, performing normalization processing on the membership function of each photovoltaic influence evaluation index by adopting weighted fuzzy calculation to obtain a total evaluation value;
and S15, calculating the weight of the photovoltaic influence evaluation index according to the membership function matrix and the total evaluation value.
In one embodiment, the photovoltaic impact evaluation index includes, but is not limited to, the indexes of base load density, sunshine duration, sunshine intensity, high-rise building ratio, photovoltaic internet price, photovoltaic financial subsidy, heat island effect, traffic flow grade and the like.
In one embodiment, the distribution grid is divided into 3 planning zones, namely residential, commercial and industrial zones. Dividing a power distribution station area into a residential area, a commercial area and an industrial area according to land types, and selecting 7 photovoltaic influence evaluation indexes to establish an evaluation set U ═ U ═1,u2,u3,u4,u5,u6,u7And establishing a comment set V ═ V { according to different regions1,v2,v3}。
In order to evaluate the merits of different evaluation indexes, it is necessary to unify all the factors by using a membership function, and respectively establish a membership function for each of the six photovoltaic influence evaluation indexes and generate a membership function matrix, for example, in some embodiments, the membership function of each photovoltaic influence evaluation index is represented by the following formula:
the membership function matrix is represented by the following formula:
wherein u is1—u6Respectively as basic load density index, sunshine duration index, sunshine intensity index, high-rise building ratio index, photovoltaic on-line electricity price index, photovoltaic financial subsidy index, heat island effect index, F1(u1)—F7(u7) The membership function matrix is a membership function corresponding to 7 different indexes, H represents the membership of a residential area, B represents the membership of a commercial area, I represents the membership of an industrial area, and A represents the generated membership function matrix.
In step S15, the weight of the photovoltaic influence evaluation index is calculated by the following formula:
wherein m represents the number of planning regions, n represents the number of photovoltaic influence evaluation indexes, CkDenotes a ratio of a total evaluation value of the kth planned section, EiWeight representing the ith photovoltaic impact evaluation index, Ai,kAnd representing the membership degree of the ith photovoltaic influence evaluation index to the kth planning area.
In order to determine the weight of each index, a matrix judgment scale is introduced, and the weight E of each photovoltaic influence evaluation index is determined by an analytic hierarchy process. In order to enable the obtained magnitude of the evaluation index weight E of the voltage influence to be more consistent with the actual condition of the area, the normalization processing is carried out by adopting weighted fuzzy calculation, and a total evaluation set C is obtained.
In step S2, the meteorological data includes a highest air temperature, a lowest air temperature, an average air temperature, and humidity within a preset time period;
according to the meteorological data and the weight of the photovoltaic influence evaluation index, calculating the predicted photovoltaic output of the distribution station area, wherein the method comprises the following steps:
s21, carrying out normalization processing on the highest air temperature, the lowest air temperature, the average air temperature and the humidity in the preset time period;
s22, determining a kernel function;
s23, establishing a least square vector machine model, taking the highest air temperature, the lowest air temperature, the average air temperature and the humidity after normalization processing as particles, and calculating and obtaining parameters of the kernel function and the least square vector machine model based on a particle swarm algorithm;
and S24, outputting the predicted photovoltaic output according to the kernel function and the least square vector machine model.
The photovoltaic output size is greatly influenced by seasons and weather, in order to ensure that a prediction result is reliable and accurate, data of a certain day in a certain season are selected as samples, specific data comprise the highest, lowest and average air temperature and humidity conditions and the photovoltaic output condition, various data of the day and the last two days are required to be selected, a model comprising space and time prediction is established, specific indexes influencing the output of the model are determined by adopting an analytic hierarchy process, weight distribution is carried out according to the influence size, a specific index set is determined by adopting fuzzy evaluation, each data is processed in a normalization mode, and the obtained indexes are combined with the prediction result of the minimum two-component vector machine model to be calculated. Meanwhile, in order to optimize the particle swarm optimization, a kernel function is determined through a radial basis function, the average percentage error is used as a target function, the prediction precision is improved, and the final photovoltaic output size in the power distribution area is obtained.
Specifically, the highest, lowest and average air temperature and humidity and photovoltaic output conditions of one day and two days before are selected, the temperature and humidity are normalized, and the load output is logarithmically normalized. In order to process the nonlinear relation between input and output, a radial basis function with simple parameters and good accuracy is adopted, and the radial basis function is expressed by the following formula:
where x is the input vector, xiBeing the center of the radial basis function,
the width of the nucleus is the width of the nucleus,
the method needs to be obtained through a particle swarm algorithm.
The least squares vector machine model is represented by the following formula:
wherein, yiRepresenting the predicted photovoltaic output, ω being the inertial weight, xiIs the center of the radial basis function, b is a constant, e represents the error vector, eiAnd expressing errors, wherein gamma expresses a regularization parameter, and needs to be obtained through a particle swarm algorithm.
The particle swarm algorithm is expressed by the following formula:
vid k+1＝ωvid k+c1ζ(pid k-xid k)+c2η(pgd k-xid k)；
xid k+1＝xid k+εvid k+1；
wherein v isid k+1Denotes the velocity, v, of the ith particle at the k +1 th iterationid kRepresenting the velocity, p, of the ith particle at the kth iterationid kRepresents the individual optimum value, p, of the ith particle at k iterationsgd kRepresents the global optimum at the k-th iteration, xid kPosition of ith particle, x, at kth iterationid k+1The position of the ith particle in the (k + 1) th iteration is shown, omega is the inertia weight, c1 and c2 are learning factors, zeta and eta are random numbers of 0-1, and epsilon represents the velocity coefficient.
In step S3, calculating a predicted wind power output of the distribution grid according to the wind speed includes:
s31, establishing a relation between wind speed and power generation output power;
s32, calculating the power generation output power at each wind speed according to the relation between the wind speed and the power generation output power;
s33, determining a wind disturbance value;
and S34, adding the electric output power and the wind power disturbance value to obtain predicted wind power output.
In step S31, when the actual wind speed is lower than the cut-in wind speed vinWhen the power is generated, the output power is 0; when the actual wind speed is greater than the cut-in wind speed vinLess than rated wind speed vrMeanwhile, the relation between the power generation output power and the wind speed is a curve; when the actual wind speed is greater than the rated wind speed vrBut less than cut-out wind speed voutOutputting rated power; when the actual wind speed is greater than the cut-out wind speed voutIn time, in order to prevent the blade from stalling and stopping due to safety failure, the power generation output power is also 0.
In step S32, the power generation output power at each wind speed is calculated by the following equation:
wherein v is wind speed, v is wind speedinFor cutting into the wind speed, voutTo cut out wind speed, vrAt rated wind speed, prIs the rated power output, and p is the power output.
The relation between the wind power output and the wind speed refers to fig. 2.
In step S33, since wind power generation is random and there is always a certain error in the prediction of wind power generation, it is considered to simulate the actual generated power by adding one disturbance term Δ p. Uncertainty of the wind power output is considered, and a disturbance item is added, so that the wind power output is more fit for actual output.
The actual wind power output is obtained by adding the predicted value calculated in step S32 and the disturbance term Δ p.
In step S4, establishing a space-time transition state matrix of the electric vehicle, including:
s41, dividing the state of the electric automobile into various planning areas and on the road;
and S42, simulating the transition state through a Markov chain according to the state of the electric automobile, and generating a space-time transition state matrix.
In a markov chain, a change of state is called a transition and the probability associated with a different state change is called a transition probability. Markov chains are typically represented by a conditional distribution probability. Assume that the state at the current time t is Si，tThe state at the next time is Sj,t+1，Pij,tFor time t slave state Si,tTransition to State Sj,t+1The Markov chain can be represented as P by a conditional distribution probabilityij,t＝P(Si,t→Sj,t+1)＝P(Sj,t+1|Si,t) The sum of the transition probabilities is 1 for any one of the traveling states.
In one embodiment, the power distribution station area is divided into three areas, namely, a residential area, a commercial area and an industrial area according to the land type, so that the electric vehicle has only four states, namely, in the residential area, in the commercial area, in the industrial area and in driving. Since the transition state of the electric vehicle is related to only the last state, the markov chain can be used to represent the spatio-temporal transition state of the electric vehicle. The state transition matrix of the electric vehicle can be obtained according to the Markov chain, and is expressed by the following formula:
wherein H represents a residential district, B represents a business district, I represents an industrial district, D represents a state transition matrix of the electric vehicle during driving, P represents a state transition matrix of the electric vehicle, and P represents a state transition matrix of the electric vehicleHHProbability of transition of electric vehicle from state in residence district to state in residence district, PHBProbability of transition of electric vehicle from state in residential district to state in business district, PHIProbability of transition of electric vehicle from state in residential district to state in industrial district, PHDProbability of transition of electric vehicle from the state of residence to the state of driving, PBHProbability of transition of electric vehicle from state in business district to state in residential district, PBBFor the transition probability, P, of an electric vehicle from a state in a commercial district to a state in a commercial districtBIFor the transition probability, P, of an electric vehicle from a state in a commercial district to a state in an industrial districtBDFor the transition probability of an electric vehicle from the state in the commercial district to the state in operation, PIHProbability of transition of electric vehicle from state in industrial district to state in residential district, PIBFor the transition probability, P, of an electric vehicle from an in-industry state to an in-business stateIIFor the transition probability, P, of an electric vehicle from a state in the industrial area to a state in the industrial areaIDFor the transition probability of an electric vehicle from the state in the industrial area to the state in driving, PDHFor the transition probability of an electric vehicle from a state in driving to a state in a residential area, PDBFor the transition probability, P, of an electric vehicle from a driving state to a state in a commercial districtDIFor the transition probability of an electric vehicle from a state in driving to a state in the industrial area, PDDIs powered electricallyProbability of transition of the vehicle from the on-board state to the on-board state.
In step S4, determining the charging load power of the electric vehicle according to the space-time transition state matrix includes:
s43, determining the initial state and the transition probability of the electric automobile according to the space-time transition state matrix;
s44, determining the next state according to the initial state and the transition probability;
and S45, judging whether the electric vehicle needs to be charged or not according to the state, the quantity, the battery capacity, the charging power and the power consumption per kilometer of the electric vehicle, and calculating the charging load power of the electric vehicle.
In order to predict the charging load of the electric vehicle, some photovoltaic influence evaluation indexes of the charging load, such as trip probability, vehicle driving distance, charging decision of a vehicle owner, and the like, need to be considered. Wherein the daily driving mileage of the vehicle is approximately in accordance with a lognormal distribution.
In a specific implementation mode, a charging decision assumes that charging is needed when the remaining electric quantity of a vehicle is lower than 20%, firstly, evaluation indexes such as the total simulation number N of the electric vehicle, the battery capacity and the charging power level of the vehicle, the power consumption per kilometer and the like are input into a system, then, the time-space distribution of a trip chain of each vehicle is obtained according to the initial state probability and the probability transition matrix, then, the decision of charging and the calculation and the updating of an SOC value are determined according to whether the electric quantity is lower than 20%, and finally, charging load distribution of different areas is obtained through accumulation.
Referring to fig. 3, in some embodiments, there is provided a distribution substation load prediction apparatus based on a new energy source and a charging facility, including:
a photovoltaic weight calculation module 201, configured to establish a photovoltaic impact evaluation index and determine a weight of the photovoltaic impact evaluation index;
the photovoltaic prediction module 202 is used for acquiring meteorological data of a power distribution station area and calculating predicted photovoltaic output of the power distribution station area according to the meteorological data and the weight of the photovoltaic influence evaluation index;
the wind power prediction module 203 is used for acquiring the wind speed of a power distribution station area and calculating the predicted wind power output of the power distribution station area according to the wind speed;
the electric vehicle load prediction module 204 is used for establishing a space-time transfer state matrix of the electric vehicle and determining the charging load power of the electric vehicle according to the space-time transfer state matrix;
and the comprehensive prediction module 205 is configured to obtain a base load power, and superimpose the predicted photovoltaic output, the predicted wind power output, the charging load power, and the base load power to obtain a load prediction situation of the power distribution substation.
Specifically, the photovoltaic weight calculation module 201 is further configured to:
dividing a power distribution station area into m planning areas; respectively establishing membership functions of all photovoltaic influence evaluation indexes; generating a membership function matrix according to membership functions of all photovoltaic influence evaluation indexes in all planning areas; performing normalization processing on the membership function of each photovoltaic influence evaluation index by adopting weighted fuzzy calculation to obtain a total evaluation value; and calculating the weight of the photovoltaic influence evaluation index according to the membership function matrix and the total evaluation value.
The weight of the photovoltaic influence evaluation index in the photovoltaic weight calculation module 201 is calculated by the following formula:
wherein m represents the number of planning regions, n represents the number of photovoltaic influence evaluation indexes, CkDenotes a ratio of a total evaluation value of the kth planned section, EiWeight representing the ith photovoltaic impact evaluation index, Ai,kAnd representing the membership degree of the ith photovoltaic influence evaluation index to the kth planning area.
The meteorological data acquired by the photovoltaic prediction module 202 include the highest air temperature, the lowest air temperature, the average air temperature and the humidity within a preset time period;
according to the meteorological data and the weight of the photovoltaic influence evaluation index, calculating the predicted photovoltaic output of the distribution station area, wherein the method comprises the following steps:
normalizing the highest air temperature, the lowest air temperature, the average air temperature and the humidity in the preset time period;
determining a kernel function;
establishing a least square vector machine model, taking the highest air temperature, the lowest air temperature, the average air temperature and the humidity after normalization processing as particles, and calculating and obtaining parameters of the kernel function and the least square vector machine model based on a particle swarm algorithm;
and outputting the predicted photovoltaic output according to the kernel function and a least squares vector machine model.
The wind power prediction module 203 is further configured to:
establishing a relation between wind speed and power generation output power; calculating the power generation output power at each wind speed according to the relation between the wind speed and the power generation output power; determining a wind disturbance value; and adding the electric output power and the wind power disturbance value to obtain predicted wind power output.
The power generation output power at each wind speed is calculated by the following formula:
wherein v is wind speed, v is wind speedinFor cutting into the wind speed, voutTo cut out wind speed, vrAt rated wind speed, prIs the rated power output, and p is the power output.
The electric vehicle load prediction module 204 is further configured to:
dividing the state of the electric vehicle into various planning areas and on the road; and according to the state of the electric automobile, simulating a transition state through a Markov chain, and generating a space-time transition state matrix.
Determining the charging load power of the electric automobile according to the space-time transition state matrix, comprising the following steps:
determining the initial state and the transition probability of the electric automobile according to the space-time transition state matrix;
determining the next state according to the initial state and the transition probability;
and judging whether the electric vehicle needs to be charged or not and calculating the charging load power of the electric vehicle according to the state, the quantity, the battery capacity, the charging power and the power consumption per kilometer of the electric vehicle.
Referring to fig. 4, in some embodiments, an electronic device is provided and includes a processor 101 and a storage device 102, where the storage device 102 stores a plurality of instructions, and the processor 101 is configured to read the instructions and execute the method described above.
According to the power distribution area load prediction method and device based on the new energy and the charging facility, various factors involved in photovoltaic output are comprehensively considered, weighted fuzzy calculation is performed on membership functions of all photovoltaic influence evaluation indexes, meteorological data are collected and used for calculating the predicted photovoltaic output of the power distribution area, and therefore the prediction result is more accurate; uncertainty in the wind power generation process is considered, and a disturbance item is added to a wind power output predicted value to enable a result to be more fit for actual output, so that the predicted result is more accurate and reliable; the influence of various distributed power sources is comprehensively considered, from the distribution characteristics of dual dimensions of time and space, the three factors of photovoltaic output, wind power output and electric automobile charging power are combined and superposed with the basic load power, and the accuracy of the load prediction of the power distribution station area is improved.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention. It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A power distribution station load prediction method based on new energy and charging facilities is characterized by comprising the following steps:
establishing a photovoltaic influence evaluation index and determining the weight of the photovoltaic influence evaluation index;
acquiring meteorological data of a power distribution area, and calculating predicted photovoltaic output of the power distribution area according to the meteorological data and the weight of the photovoltaic influence evaluation index;
acquiring wind speed of a power distribution area, and calculating predicted wind power output of the power distribution area according to the wind speed;
establishing a space-time transfer state matrix of the electric automobile, and determining the charging load power of the electric automobile according to the space-time transfer state matrix;
and acquiring basic load power, and superposing the predicted photovoltaic output, the predicted wind power output, the charging load power and the basic load power to acquire the load prediction condition of the power distribution station area.
2. The method of claim 1, wherein determining the weight of the photovoltaic impact evaluation index comprises:
dividing a power distribution station area into m planning areas;
respectively establishing membership functions of all photovoltaic influence evaluation indexes;
generating a membership function matrix according to membership functions of all photovoltaic influence evaluation indexes in all planning areas;
performing normalization processing on the membership function of each photovoltaic influence evaluation index by adopting weighted fuzzy calculation to obtain a total evaluation value;
and calculating the weight of the photovoltaic influence evaluation index according to the membership function matrix and the total evaluation value.
3. The method according to claim 2, wherein the weight of the photovoltaic impact evaluation index is calculated by the following formula:
wherein m represents the number of planning regions, n represents the number of photovoltaic influence evaluation indexes, CkTo representRatio of the k-th planned area to the total evaluation value, EiWeight representing the ith photovoltaic impact evaluation index, Ai,kAnd representing the membership degree of the ith photovoltaic influence evaluation index to the kth planning area.
4. The method of claim 1, wherein the meteorological data includes a maximum air temperature, a minimum air temperature, an average air temperature, and a humidity for a preset time period;
according to the meteorological data and the weight of the photovoltaic influence evaluation index, calculating the predicted photovoltaic output of the distribution station area, wherein the method comprises the following steps:
normalizing the highest air temperature, the lowest air temperature, the average air temperature and the humidity in the preset time period;
determining a kernel function;
establishing a least square vector machine model, taking the highest air temperature, the lowest air temperature, the average air temperature and the humidity after normalization processing as particles, and calculating and obtaining parameters of the kernel function and the least square vector machine model based on a particle swarm algorithm;
and outputting the predicted photovoltaic output according to the kernel function and a least squares vector machine model.
5. The method of claim 1, wherein calculating a predicted wind power output for a distribution grid based on the wind speed comprises:
establishing a relation between wind speed and power generation output power;
calculating the power generation output power at each wind speed according to the relation between the wind speed and the power generation output power;
determining a wind disturbance value;
and adding the electric output power and the wind power disturbance value to obtain predicted wind power output.
6. The method of claim 5, wherein the power generation output power at each wind speed is calculated by the following formula:
wherein v is wind speed, v is wind speedinFor cutting into the wind speed, voutTo cut out wind speed, vrAt rated wind speed, prIs the rated power output, and p is the power output.
7. The method of claim 1, wherein establishing an electric vehicle spatiotemporal transition state matrix comprises:
dividing the state of the electric vehicle into various planning areas and on the road;
and according to the state of the electric automobile, simulating a transition state through a Markov chain, and generating a space-time transition state matrix.
8. The method of claim 7, wherein determining a charging load power of the electric vehicle based on the spatiotemporal transition state matrix comprises:
determining the initial state and the transition probability of the electric automobile according to the space-time transition state matrix;
determining the next state according to the initial state and the transition probability;
and judging whether the electric vehicle needs to be charged or not and calculating the charging load power of the electric vehicle according to the state, the quantity, the battery capacity, the charging power and the power consumption per kilometer of the electric vehicle.
9. A distribution grid load prediction device based on new energy and a charging facility is characterized by comprising:
the photovoltaic weight calculation module is used for establishing a photovoltaic influence evaluation index and determining the weight of the photovoltaic influence evaluation index;
the photovoltaic prediction module is used for acquiring meteorological data of the distribution substation area and calculating the predicted photovoltaic output of the distribution substation area according to the meteorological data and the weight of the photovoltaic influence evaluation index;
the wind power prediction module is used for acquiring the wind speed of a power distribution station area and calculating the predicted wind power output of the power distribution station area according to the wind speed;
the electric vehicle load prediction module is used for establishing a space-time transfer state matrix of the electric vehicle and determining the charging load power of the electric vehicle according to the space-time transfer state matrix;
and the comprehensive prediction module is used for obtaining the basic load power, and superposing the predicted photovoltaic output, the predicted wind power output, the charging load power and the basic load power to obtain the load prediction condition of the power distribution station area.
10. An electronic device comprising a processor and a storage device, the storage device storing a plurality of instructions, the processor being configured to read the instructions and perform the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210101087.6A CN114498632A (en) | 2022-01-27 | 2022-01-27 | Power distribution station load prediction method and device based on new energy and charging facility |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210101087.6A CN114498632A (en) | 2022-01-27 | 2022-01-27 | Power distribution station load prediction method and device based on new energy and charging facility |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114498632A true CN114498632A (en) | 2022-05-13 |
Family
ID=81476399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210101087.6A Pending CN114498632A (en) | 2022-01-27 | 2022-01-27 | Power distribution station load prediction method and device based on new energy and charging facility |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114498632A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116258355A (en) * | 2023-05-15 | 2023-06-13 | 国网浙江省电力有限公司永康市供电公司 | Distribution area load curve decomposition method and device suitable for multipoint power estimation |
| CN117040028A (en) * | 2023-09-28 | 2023-11-10 | 泰豪科技(深圳)电力技术有限公司 | Control strategy optimization method and system for optical storage and charging micro-grid of industrial and commercial park |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514487A (en) * | 2013-07-15 | 2014-01-15 | 国家电网公司 | Load forecasting method of power distribution network with distributed power supply |
| CN105305488A (en) * | 2015-10-13 | 2016-02-03 | 国家电网公司 | Evaluation method considering influence of new energy grid connection on utilization rate of transmission network |
| US20160169202A1 (en) * | 2013-05-03 | 2016-06-16 | State Grid Corporation Of China | Short-term operation optimization method of electric power system including large-scale wind power |
| CN109167387A (en) * | 2018-09-14 | 2019-01-08 | 大唐新疆清洁能源有限公司 | Wind field wind power forecasting method |
| CN110956329A (en) * | 2019-12-02 | 2020-04-03 | 国网浙江省电力有限公司绍兴供电公司 | Load prediction method based on distributed photovoltaic and electric vehicle space-time distribution |
| CN112736926A (en) * | 2020-12-25 | 2021-04-30 | 华北电力大学 | Interval affine power flow dynamic optimization method for distributed new energy access power distribution network |
-
2022
- 2022-01-27 CN CN202210101087.6A patent/CN114498632A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160169202A1 (en) * | 2013-05-03 | 2016-06-16 | State Grid Corporation Of China | Short-term operation optimization method of electric power system including large-scale wind power |
| CN103514487A (en) * | 2013-07-15 | 2014-01-15 | 国家电网公司 | Load forecasting method of power distribution network with distributed power supply |
| CN105305488A (en) * | 2015-10-13 | 2016-02-03 | 国家电网公司 | Evaluation method considering influence of new energy grid connection on utilization rate of transmission network |
| CN109167387A (en) * | 2018-09-14 | 2019-01-08 | 大唐新疆清洁能源有限公司 | Wind field wind power forecasting method |
| CN110956329A (en) * | 2019-12-02 | 2020-04-03 | 国网浙江省电力有限公司绍兴供电公司 | Load prediction method based on distributed photovoltaic and electric vehicle space-time distribution |
| CN112736926A (en) * | 2020-12-25 | 2021-04-30 | 华北电力大学 | Interval affine power flow dynamic optimization method for distributed new energy access power distribution network |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116258355A (en) * | 2023-05-15 | 2023-06-13 | 国网浙江省电力有限公司永康市供电公司 | Distribution area load curve decomposition method and device suitable for multipoint power estimation |
| CN116258355B (en) * | 2023-05-15 | 2023-08-11 | 国网浙江省电力有限公司永康市供电公司 | Distribution area load curve decomposition method and device suitable for multipoint power estimation |
| CN117040028A (en) * | 2023-09-28 | 2023-11-10 | 泰豪科技(深圳)电力技术有限公司 | Control strategy optimization method and system for optical storage and charging micro-grid of industrial and commercial park |
| CN117040028B (en) * | 2023-09-28 | 2024-01-09 | 泰豪科技(深圳)电力技术有限公司 | Control strategy optimization method and system for optical storage and charging micro-grid of industrial and commercial park |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288212B (en) | Improved MOPSO-based electric taxi newly-built charging station site selection method | |
| CN103241130B (en) | Energy management method and system for electric bus charging and swap station | |
| US20220410750A1 (en) | System and method for smart charging management of electric vehicle fleets | |
| Li et al. | Prediction of electric bus energy consumption with stochastic speed profile generation modelling and data driven method based on real-world big data | |
| CN114498632A (en) | Power distribution station load prediction method and device based on new energy and charging facility | |
| CN103745110B (en) | Method of estimating operational driving range of all-electric buses | |
| Kim et al. | Idle vehicle relocation strategy through deep learning for shared autonomous electric vehicle system optimization | |
| Fotouhi et al. | Electric vehicle energy consumption estimation for a fleet management system | |
| Liu et al. | Optimal location planning of electric bus charging stations with integrated photovoltaic and energy storage system | |
| CN114048920A (en) | Site selection layout method, device, equipment and storage medium for charging facility construction | |
| Liu et al. | Building-centric investigation into electric vehicle behavior: A survey-based simulation method for charging system design | |
| CN110210670A (en) | A kind of prediction technique based on power-system short-term load | |
| CN116523093A (en) | Grid demand sensing system and method of energy system based on random source load prediction | |
| CN114169609A (en) | Photovoltaic coupling-considered electric vehicle charging station planning method | |
| Jiang et al. | Optimal configuration of electric vehicles for charging stations under the fast power supplement mode | |
| Abbas et al. | An improved optimal forecasting algorithm for comprehensive electric vehicle charging allocation | |
| CN115330267A (en) | Battery charging and replacing facility layout method, device, equipment and medium based on demand behaviors | |
| Pan et al. | Development of an energy consumption prediction model for battery electric vehicles in real-world driving: a combined approach of short-trip segment division and deep learning | |
| CN117057533A (en) | Method and device for optimizing subdivision period ordered charging strategy based on load evaluation | |
| Liu et al. | Impacts of photovoltaic and energy storage system adoption on public transport: A simulation-based optimization approach | |
| El-Azab et al. | Seasonal electric vehicle forecasting model based on machine learning and deep learning techniques | |
| Farhadi et al. | Data-driven multi-objective optimization for electric vehicle charging infrastructure | |
| CN111784027A (en) | Urban range electric vehicle charging demand prediction method considering geographic information | |
| CN110674988A (en) | Urban charging station planning method based on electric vehicle travel big data | |
| Schwenk | A smart charging assistant for electric vehicles considering battery degradation, power grid and user constraints |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220513 |
|
| RJ01 | Rejection of invention patent application after publication |