CN114912546A - Energy data aggregation method and device - Google Patents
Energy data aggregation method and device Download PDFInfo
- Publication number
- CN114912546A CN114912546A CN202210668397.6A CN202210668397A CN114912546A CN 114912546 A CN114912546 A CN 114912546A CN 202210668397 A CN202210668397 A CN 202210668397A CN 114912546 A CN114912546 A CN 114912546A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- aggregation
- individual physical
- cluster model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002776 aggregation Effects 0.000 title claims abstract description 181
- 238000004220 aggregation Methods 0.000 title claims abstract description 181
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004138 cluster model Methods 0.000 claims abstract description 144
- 238000012549 training Methods 0.000 claims abstract description 96
- 238000012360 testing method Methods 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 238000003064 k means clustering Methods 0.000 claims abstract description 29
- 230000004931 aggregating effect Effects 0.000 claims abstract description 20
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000002349 favourable effect Effects 0.000 abstract 1
- 238000004146 energy storage Methods 0.000 description 18
- 230000004044 response Effects 0.000 description 18
- 230000033228 biological regulation Effects 0.000 description 10
- 238000010248 power generation Methods 0.000 description 9
- 238000009826 distribution Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 4
- 230000009194 climbing Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007599 discharging Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000003828 downregulation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000003827 upregulation Effects 0.000 description 1
- 239000002699 waste material 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
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for aggregating energy data, wherein the method comprises the following steps: the method comprises the steps of obtaining renewable energy data and energy data to be detected, establishing an individual physical model and an aggregation cluster model of renewable energy based on the renewable energy data, dividing the renewable energy data into training set data and testing set data, training and verifying the individual physical model and the aggregation cluster model based on a K-means clustering algorithm, the training set data and the testing set data to obtain a target individual physical model and a target aggregation cluster model, inputting the energy data to be detected into the target individual physical model and the target aggregation cluster model to obtain predicted aggregation index data of the energy data to be detected. The method is favorable for solving the technical problem that the social idle distributed renewable resources are difficult to assemble, and unifies the access standard of the renewable resources.
Description
Technical Field
The invention relates to the technical field of distributed energy of a power system, in particular to an energy data aggregation method and device.
Background
With the increasing demand of society on energy, the proposal of a double-carbon target promotes the structural transformation of energy, and distributed renewable energy also meets the mass growth. The distributed wind and light energy power generation system has the advantages that various heterogeneous mass distributed renewable resources including distributed photovoltaic, distributed fans, distributed energy storage, electric vehicles and flexible loads provide economic clean energy for a power grid, the advantages of wind and light resources specific to different regions can be fully exerted according to local conditions, and safe and economic operation of the power grid can be guaranteed through peak clipping, valley filling, frequency modulation and demand response. At present, the mass of distributed renewable energy sources is rapidly increased in energy ratio, and the distributed renewable energy sources are huge in quantity and various in variety. However, the geographic distribution is dispersed, the subordinate rights are not uniform, the power generation characteristics of the power generation system are uncertain due to climate and human factors, and if the power generation system is directly connected to a power grid in an unordered manner, on one hand, the management is difficult and impact is brought to the power grid, on the other hand, the waste of social idle resources is caused, and the full consumption of renewable resources cannot be guaranteed. In view of this, the characteristics of small amount, distributed dispersion and different subordination rights of the massive distributed renewable resources are combined, and the unified access can be realized by convergence of some intermediate mechanisms, so that the flexibility of the power system is enhanced.
Aiming at the convergence and access of massive distributed renewable resources, the current mainstream practice at home and abroad is mainly to access the resources in the forms of aggregators, virtual power plants and the like, and participate in the day-ahead plan overall response scheduling instruction in the form of a quasi-conventional power supply after convergence. For effective utilization of various distributed renewable energy sources, a standardized model needs to be established, which not only meets the requirement of shielding physical properties of bottom layers of various resources to ensure the externally controllable properties of openness properties, but also meets the self heterogeneous properties of various resources.
At present, distributed renewable energy accessed to a power grid for operation is mostly large wind power plants and photovoltaic units, and an effective utilization means is lacked for distributed resources which are idle in society and large in volume.
Therefore, in order to unify the access standard of renewable resources and solve the technical problem that the social idle distributed renewable resources are difficult to converge at present, it is urgently needed to construct an energy data aggregation method.
Disclosure of Invention
The invention provides an energy data aggregation method and device, and solves the technical problem that social idle distributed renewable resources are difficult to assemble at present.
In a first aspect, the present invention provides a method for aggregating energy data, including:
acquiring renewable energy data and energy data to be detected;
establishing an individual physical model and an aggregation cluster model of renewable energy sources based on the renewable energy source data;
dividing the renewable energy data into training set data and test set data;
training and verifying the individual physical model and the aggregation cluster model based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregation cluster model;
and inputting the energy data to be detected into the target individual physical model and the target aggregation cluster model to obtain the predicted aggregation index data of the energy data to be detected.
Optionally, acquiring renewable energy data and energy data to be measured includes:
acquiring renewable energy source initial data;
and cleaning and repairing the renewable energy source initial data to obtain the renewable energy source data and the energy source data to be detected.
Optionally, training and verifying the individual physical model and the aggregation cluster model based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregation cluster model, including:
training the individual physical model and the aggregation cluster model by using the K-means clustering algorithm and combining the training set data to obtain a trained aggregation cluster model and a trained aggregation cluster model;
and verifying the trained aggregation cluster model and the trained aggregation cluster model based on the test set data to obtain the target individual physical model and the target aggregation cluster model.
Optionally, training the individual physical model and the aggregation cluster model by using the K-means clustering algorithm and combining with the training set data to obtain a trained aggregation cluster model and a trained aggregation cluster model, including:
inputting the training set data into the individual physical model and the aggregation cluster model to obtain a corresponding prediction aggregation value of the renewable energy data;
determining a training error according to a data label corresponding to the training set data and the prediction aggregation value;
based on the training error, the individual physical model and the aggregation cluster model are adjusted through the K-means clustering algorithm to obtain optimal parameters, and the individual physical model and the aggregation cluster model are optimized through the optimal parameters to obtain the trained aggregation cluster model and the trained aggregation cluster model.
Optionally, before inputting the training set data into the individual physical model and the aggregation cluster model to obtain the predicted aggregation value of the corresponding renewable energy data, the method further includes:
initializing parameters of the individual physical model and parameters of the aggregated cluster model.
In a second aspect, the present invention provides an apparatus for aggregating energy data, including:
the acquisition module is used for acquiring renewable energy data and energy data to be detected;
the establishing module is used for establishing an individual physical model and an aggregation cluster model of renewable energy sources based on the renewable energy source data;
the dividing module is used for dividing the renewable energy data into training set data and test set data;
the training module is used for training and verifying the individual physical model and the aggregation cluster model based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregation cluster model;
and the index module is used for inputting the energy data to be detected into the target individual physical model and the target aggregation cluster model to obtain the predicted aggregation index data of the energy data to be detected.
Optionally, the obtaining module includes:
the acquisition submodule is used for acquiring the initial data of the renewable energy source;
and the repairing submodule is used for cleaning and repairing the renewable energy source initial data to obtain the renewable energy source data and the energy source data to be detected.
Optionally, the training module comprises:
the training submodule is used for training the individual physical model and the aggregation cluster model by using the K-means clustering algorithm and combining the training set data to obtain a trained aggregation cluster model and a trained aggregation cluster model;
and the verification sub-module is used for verifying the trained aggregation cluster model and the trained aggregation cluster model based on the test set data to obtain the target individual physical model and the target aggregation cluster model.
Optionally, the training submodule includes:
the prediction unit is used for inputting the training set data into the individual physical model and the aggregation cluster model to obtain a prediction aggregation value of corresponding renewable energy data;
an error unit, configured to determine a training error according to a data label corresponding to the training set data and the prediction aggregation value;
and the optimization unit is used for adjusting the individual physical model and the aggregation cluster model through the K-means clustering algorithm based on the training error to obtain optimal parameters, and optimizing the individual physical model and the aggregation cluster model by adopting the optimal parameters to obtain the trained aggregation cluster model and the trained aggregation cluster model.
Optionally, the training sub-module further comprises:
a parameter unit for initializing parameters of the individual physical model and parameters of the aggregated cluster model.
According to the technical scheme, the invention has the following advantages: the invention provides an aggregation method of energy data, which comprises the steps of establishing an individual physical model and an aggregation cluster model of renewable energy sources based on renewable energy data by acquiring the renewable energy data and the energy data to be detected, dividing the renewable energy data into training set data and test set data, training and verifying the individual physical model and the aggregation cluster model based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregation cluster model, inputting the energy data to be detected into the target individual physical model and the target aggregation cluster model to obtain predicted aggregation index data of the energy data to be detected, and solving the technical problem that the social idle distributed renewable resources are difficult to aggregate by the aggregation method of the energy data, the access standard of renewable resources is unified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a flowchart illustrating a first embodiment of a method for aggregating energy data according to the present invention;
FIG. 2 is a flowchart illustrating a second embodiment of a method for aggregating energy data according to the present invention;
FIG. 3 is a flowchart illustrating a standardized model update for renewable energy according to the present invention;
fig. 4 is a block diagram illustrating an embodiment of an apparatus for aggregating energy data according to the present invention.
Detailed Description
The embodiment of the invention provides an energy data aggregation method and device, which are used for solving the technical problem that the social idle distributed renewable resources are difficult to converge at present.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In a first embodiment, referring to fig. 1, fig. 1 is a flowchart illustrating a first method for aggregating energy data according to a first embodiment of the present invention, including:
step S101, renewable energy data and energy data to be detected are obtained;
it should be noted that the energy data includes individual photovoltaic array data, wind turbine data, distributed energy storage data, electric vehicle data, flexibility load data, and in-cluster and out-cluster characterization data.
The intra-cluster characterization data includes capacity support capability (including a baseline value and upper and lower boundaries), power support capability (including a baseline value and upper and lower boundaries), dynamic response capability, and effective convergence time ratio.
The off-cluster characteristic data comprises a stability factor, a reliability factor, a network loss factor, a unit regulation power and a dynamic sensitivity factor.
In the embodiment of the invention, renewable energy source initial data is obtained, and the renewable energy source initial data is cleaned and repaired to obtain the renewable energy source data and the energy source data to be detected.
Step S102, establishing an individual physical model and an aggregation cluster model of renewable energy sources based on the renewable energy source data;
it should be noted that the individual physical model of the renewable energy source includes an individual photovoltaic array model, a wind turbine model, a distributed energy storage model, an electric vehicle model, and a flexible load model.
In the embodiment of the invention, an individual physical model and an aggregation cluster model of renewable energy are established according to the renewable energy data.
Step S103, dividing the renewable energy data into training set data and test set data;
step S104, training and verifying the individual physical model and the aggregation cluster model based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregation cluster model;
in the embodiment of the present invention, the K-means clustering algorithm is applied, the training set data is combined, the individual physical model and the aggregation cluster model are trained, a trained aggregation cluster model and a trained aggregation cluster model are obtained, and the trained aggregation cluster model are verified based on the test set data, so that the target individual physical model and the target aggregation cluster model are obtained.
Step S105, inputting the energy data to be measured into the target individual physical model and the target aggregation cluster model to obtain the prediction aggregation index data of the energy data to be measured.
In the energy data aggregation method provided by the embodiment of the invention, renewable energy data and energy data to be tested are obtained, an individual physical model and an aggregation cluster model of renewable energy are established based on the renewable energy data, the renewable energy data are divided into training set data and test set data, the individual physical model and the aggregation cluster model are trained and verified based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregation cluster model, the energy data to be tested are input into the target individual physical model and the target aggregation cluster model to obtain predicted aggregation index data of the energy data to be tested, and the technical problem that the existing social idle distributed renewable resources are difficult to aggregate is solved by the energy data aggregation method, the access standard of renewable resources is unified.
In a second embodiment, referring to fig. 2, fig. 2 is a flowchart illustrating a method for aggregating energy data according to the present invention, including:
step S201, acquiring renewable energy source initial data;
in the embodiment of the invention, the renewable energy source initial data is obtained and comprises individual photovoltaic array data, wind driven generator data, distributed energy storage data, electric vehicle data, flexible load data, in-cluster characteristic representation data and out-cluster characteristic representation data.
The intra-cluster characterization data includes capacity support capability (including a baseline value and upper and lower boundaries), power support capability (including a baseline value and upper and lower boundaries), dynamic response capability, and effective convergence time ratio.
The off-cluster characteristic data comprises a stability factor, a reliability factor, a network loss factor, a unit regulation power and a dynamic sensitivity factor.
Step S202, cleaning and repairing the renewable energy source initial data to obtain renewable energy source data and energy source data to be detected;
step S203, establishing an individual physical model and an aggregation cluster model of renewable energy sources based on the renewable energy source data;
in the embodiment of the invention, an individual physical model and an aggregation cluster model of renewable energy sources are established based on the renewable energy source data, and the individual physical model of the renewable energy sources comprises an individual photovoltaic array model, a wind power generator model, a distributed energy storage model, an electric automobile model and a flexible load model.
In a concrete implementation, please refer to fig. 3, fig. 3 is a flowchart of a standardized model updating process of renewable energy according to the present invention, wherein t is a time, p is a power generation power, e is an accumulated power generation amount, r is a climbing speed, and D is an external characteristic factor;
the distributed renewable resources consider individual photovoltaic arrays, wind power generators, distributed energy storage, electric vehicles and flexible loads, and the content of modeling on the physical level mainly relates to the electrical quantity and constraint conditions of the individual photovoltaic arrays, and comprises the following steps:
the power generation characteristics of a universal flexible resource in the time period t can be combined by six elements
A description is given.
And the upper and lower bounds of the generated power, the accumulated generated energy and the climbing rate of the jth flexible resource of the jth class and numbered k in the t time period under the aggregation quotient node i are respectively.
For photovoltaicsFor a unit, a Maximum Power Point Tracking (MPPT) technology provided by the unit can ensure that parameters and loads of a photovoltaic cell are optimally matched, and output Power is always kept at a Maximum Power Point P m To (3). Based on this, P per period m The predicted value is considered as the maximum output prediction
By power electronics, can range from 0 to
The upper and lower bounds of the PV power and the accumulated generated energy are as follows:
the regulation and control characteristics of the wind turbine generator are similar to those of the photovoltaic generator and can be from 0 to
Continuously adjusting the output of the generator set, wherein the upper and lower bounds of the power of the wind turbine generator set and the accumulated generated energy are as follows:
compared with photovoltaic generator set power generation, the generator set output fluctuation is larger and irregular, and the generator set output fluctuation is more difficult to be adjusted
And (3) predicting, so that the wind power hour average output change rate is adopted as a measure:
wherein,
the output change rate of the wind power in hours,
the output fluctuation quantity of the wind power in hours,
the rated installed capacity of the wind power is obtained.
The energy storage operating characteristics may each be described based on a Charge amount (SOC) of the energy storage device at time t:
wherein, SOC (t) is the state of charge of the stored energy at the end of the tth period; eta c 、η d Respectively charging and discharging efficiency of energy storage; e r Rated capacity for stored energy; sigma is the energy storage self-discharge rate; p c 、P d Respectively, the charge and discharge power of the current period.
And (4) operation restraint of the energy storage device:
firstly, the charging and discharging power of the energy storage device is limited, and the stored energy charging and discharging within unit time is not more than 20% of the rated capacity of the energy storage device, namely:
in order to prevent the energy storage device from being charged and discharged excessively and have sufficient margin for emergency scheduling, the minimum charge quantity of the energy storage is set as SOC min The maximum charge is SOC max Namely:
SOC min ≤SOC ess (t)≤SOC max ；
usually taking SOC min Is 0.2, SOC max Is 0.9.
The charge-discharge power allowed by the energy storage device per unit time continuously changes along with the SOC, namely:
the essence of the electric automobile is still energy storage, but the energy storage is movable and has stronger user attributes, so that larger uncertainty is brought, the social attributes of the electric automobile are reflected by the user characteristics, the electric automobile is described through the angle of a charging pile, and the social attributes of the electric automobile are described through the travel rule of the electric automobile;
the probability distribution of the electric automobile leaving time and arriving time obeys generalized extreme value distribution, the probability distribution of the traveling distance obeys Weibull distribution, the traveling of the electric automobile can be randomly simulated by adopting a Monte Carlo random simulation mode, and the inverse function of the distribution function of the leaving time, arriving time and traveling distance of the electric automobile is as follows:
wherein x is out Is the electric automobile trip time, f PEV,out Is an inverse probability density function of the trip time of the electric automobile, y out Is the probability of the electric automobile going out at the moment mu PEV,out ，σ PEV,out ，ξ PEV,out Position parameters, scale parameters and shape parameters of the probability distribution at the trip time of the electric automobile; x is the number of in ，f PEV,in ，y in ，μ PEV,in ，σ PEV,in ，ξ PEV,in Corresponding probability density inverse functions of the arrival time and the arrival time of the electric vehicle, the arrival time probability, and the position parameters, the scale parameters and the shape parameters of the probability distribution of the arrival time of the electric vehicle are obtained; x is the number of dis ，f dis ，y dis ，k dis ，λ dis The shape and scale parameters of the travel distance, the inverse travel distance probability density function, the travel distance probability and the travel distance distribution function of the electric automobile are shown.
The flexible load is characterized from an interruptible and translatable perspective:
mathematical model of interruptible load resources:
and (3) constraint of maximum calling times of resources:
resource available period constraint:
minimum resource, maximum usage duration constraint:
relationship between actual operating power of the resource and whether to initiate a response:
response cost of interruptible load resource:
wherein S is DR Is a set of interruptible load resources; y is i,t The use state of interruptible load resources; z is a radical of i,t The two groups of variables are both variables of 0 to 1 and are starting variables of the resource; n is the maximum response times of the resource; Ψ use A set of available time instants; t is min And T max Resource minimum and maximum response times, respectively; p is a radical of DR,i,t Is the actual power of resource i; p is a radical of formula i,t,0 And P DR,i,t The initial power and the response power of the resource are respectively; c. C i Is the cost per power response of the interruptible load resource.
Mathematical model of translatable load resources:
and (3) constraint of maximum calling times of resources:
resource available period constraint:
the relationship between the shifting-out amount and the shifting-in amount of the load resource can be translated:
resource movable period constraint:
actual operating power of resources:
immigration variable and response variable relationships:
response cost of translatable load resources:
wherein S is TR A set of translatable load resources; y is i,OUT,t The use state of the translatable load resource i; z is a radical of i,OUT,t For the starting variable of the resource, y i,IN,t Representing whether the load is moved in the period, wherein the three groups of variables are all variables of 0-1; Ψ in A set of time-shifted instances; p is a radical of TR,i,t Is the actual power of resource i; p is a radical of i,t,0 And P TR,i The initial power and the response power of the resource, respectively.
The cluster model has a two-layer property that faces down to the properties of the individual aggregates, similar to the individual models. However, the cluster layer does not distinguish the source load and the load, so the lower layer model is the unity of the source load and the load. The physical part of the upper layer, facing the cluster properties of the scheduling or market, should be characterized by its internal characteristics, i.e. the power up and down capability and the power baseline for the aggregate virtual power.
By using
And the generated power of the flexible resource of the jth class and the number k under the access cluster node i in the t time period is shown. If the power value is positive, the resource sends active power to the power grid, and if the power value is negative, the resource absorbs active power from the power grid. By using
And the accumulated power generation amount of the flexible resource of the jth class and the number k under the access cluster node i in the 1 st to the t th time periods is shown. The concrete behavior is shown in the following table:
the six-tuple parameters respectively represent the active power boundary, the accumulated generating capacity boundary and the climbing rate boundary of the flexible resource from t to t +1 in a time period t, namely:
wherein,
and the upper and lower bounds of the generated power, the accumulated generated energy and the climbing rate of the jth flexible resource of the jth class and the serial number k in the t-th time period are respectively set under the cluster node i.
The baseline power is the aggregation power of the cluster when no regulation and control means are adopted, is used for confirming the regulation and control effect of the cluster, and needs to be calculated in a rolling mode in a period of 5-30 min. And the up-regulation and down-regulation boundaries adopt an individual model boundary calculation method. Meanwhile, the external characteristics are formed by considering cluster aggregation evaluation and cluster social attributes, and finally the characteristics are unified as follows:
A＝{C,P,D,T,Sta,Se,L,K,Sen,…}
Sta＝f 1 (C,D,P,T)
Se＝f 2 (C,D,P,T)
L＝f 3 (C,D,P,T,Site(Z))
K＝f 4 (C,D,P,T,Site(Z))；
wherein, C, P, D, and T are internal characteristic representations of the cluster, and are respectively capacity support capacity (including a reference value and upper and lower boundaries), power support capacity (including a reference value and upper and lower boundaries), dynamic response capacity, and effective convergence time ratio. St, Se, L, K and Sen are characteristic characteristics outside the cluster, and are respectively a stability factor, a reliability factor, a network loss factor, unit regulation power and a dynamic sensitivity factor.
Step S204, dividing the renewable energy data into training set data and test set data;
step S205, training the individual physical model and the aggregation cluster model by using the K-means clustering algorithm and combining the training set data to obtain a trained aggregation cluster model and a trained aggregation cluster model;
in an optional embodiment, the training of the individual physical model and the aggregation cluster model by using the K-means clustering algorithm and combining with the training set data to obtain a trained aggregation cluster model and a trained aggregation cluster model includes:
initializing parameters of the individual physical model and parameters of the aggregated cluster model;
inputting the training set data into the individual physical model and the aggregation cluster model to obtain a corresponding prediction aggregation value of the renewable energy data;
determining a training error according to the data label corresponding to the training set data and the prediction aggregation value;
based on the training error, the individual physical model and the aggregation cluster model are adjusted through the K-means clustering algorithm to obtain optimal parameters, and the individual physical model and the aggregation cluster model are optimized through the optimal parameters to obtain the trained aggregation cluster model and the trained aggregation cluster model.
In the embodiment of the present invention, parameters of the individual physical model and parameters of the aggregation cluster model are initialized, the training set data is input into the individual physical model and the aggregation cluster model to obtain a predicted aggregation value of corresponding renewable energy data, a training error is determined according to a data label corresponding to the training set data and the predicted aggregation value, the individual physical model and the aggregation cluster model are adjusted by the K-means clustering algorithm based on the training error to obtain an optimal parameter, and the individual physical model and the aggregation cluster model are optimized by using the optimal parameter to obtain the trained aggregation cluster model and the trained aggregation cluster model.
Step S206, verifying the trained aggregation cluster model and the trained aggregation cluster model based on the test set data to obtain the target individual physical model and the target aggregation cluster model;
step S207, inputting the energy data to be detected into the target individual physical model and the target aggregation cluster model to obtain the predicted aggregation index data of the energy data to be detected;
in the embodiment of the invention, the energy data to be detected is input into the target individual physical model and the target aggregation cluster model to obtain the predicted aggregation index data of the energy data to be detected, and the aggregation degree of the energy corresponding to the energy data to be detected is determined.
In a specific implementation, the aggregation characteristic of the cluster depends on the characteristics of various distributed resources participating in the combination and the resource regulation and control strategy inside the cluster. The cluster server needs to adjust the output or working state of the interactive resources within an allowable range, so that the overall power of the system approaches to a target curve. Because the interactive resources respond to the regulation and control instruction of the cluster and have certain power regulation characteristics, after aggregation, the cluster power regulation capability can generate a large-scale effect, and the power curve is smoother.
Dividing the spatial region to which the user belongs by taking the point of connection as a unit to obtain the spatial aggregation characteristic of the cluster:
after aggregating the response characteristics distributed at different geographical locations, obtaining the time aggregation characteristics of the cluster:
in the formula, V i,j,k Is a variable of 0 to 1, when V i,j,k A value of 1 indicates a participation response,. DELTA.P Group,t Indicating the response value, P, provided by the cluster during the period t Group,t Indicating the cluster actually aggregated load value in the period t after the response.
In the energy data aggregation method provided by the embodiment of the invention, renewable energy data and energy data to be tested are obtained, an individual physical model and an aggregation cluster model of renewable energy are established based on the renewable energy data, the renewable energy data are divided into training set data and test set data, the individual physical model and the aggregation cluster model are trained and verified based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregation cluster model, the energy data to be tested are input into the target individual physical model and the target aggregation cluster model to obtain predicted aggregation index data of the energy data to be tested, and the technical problem that the existing social idle distributed renewable resources are difficult to aggregate is solved by the energy data aggregation method, the access standard of renewable resources is unified.
Referring to fig. 4, fig. 4 is a block diagram illustrating an embodiment of an apparatus for aggregating energy data according to the present invention, including:
an obtaining module 401, configured to obtain renewable energy data and energy data to be detected;
an establishing module 402, configured to establish an individual physical model and an aggregation cluster model of renewable energy based on the renewable energy data;
a dividing module 403, configured to divide the renewable energy data into training set data and test set data;
a training module 404, configured to train and verify the individual physical model and the aggregate cluster model based on a K-means clustering algorithm, the training set data, and the test set data, so as to obtain a target individual physical model and a target aggregate cluster model;
an index module 405, configured to input the energy data to be detected into the target individual physical model and the target aggregation cluster model, so as to obtain predicted aggregation index data of the energy data to be detected.
In an optional embodiment, the obtaining module 401 includes:
the acquisition submodule is used for acquiring renewable energy source initial data;
and the repairing submodule is used for cleaning and repairing the renewable energy source initial data to obtain the renewable energy source data and the energy source data to be detected.
In an optional embodiment, the training module 404 includes:
the training submodule is used for training the individual physical model and the aggregation cluster model by using the K-means clustering algorithm and combining the training set data to obtain a trained aggregation cluster model and a trained aggregation cluster model;
and the verification sub-module is used for verifying the trained aggregation cluster model and the trained aggregation cluster model based on the test set data to obtain the target individual physical model and the target aggregation cluster model.
In an alternative embodiment, the training submodule includes:
the prediction unit is used for inputting the training set data into the individual physical model and the aggregation cluster model to obtain a prediction aggregation value of corresponding renewable energy data;
the error unit is used for determining a training error according to the data label corresponding to the training set data and the prediction aggregation value;
and the optimization unit is used for adjusting the individual physical model and the aggregation cluster model through the K-means clustering algorithm based on the training error to obtain optimal parameters, and optimizing the individual physical model and the aggregation cluster model by adopting the optimal parameters to obtain the trained aggregation cluster model and the trained aggregation cluster model.
In an optional embodiment, the training submodule further comprises:
a parameter unit for initializing parameters of the individual physical model and parameters of the aggregated cluster model.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present application, it should be understood that the method and apparatus disclosed in the present invention can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention, which is substantially or partly contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a readable storage medium and includes several instructions, so as to enable a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned readable storage medium comprises: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for aggregating energy data, comprising:
acquiring renewable energy data and energy data to be detected;
establishing an individual physical model and an aggregation cluster model of renewable energy sources based on the renewable energy source data;
dividing the renewable energy data into training set data and test set data;
training and verifying the individual physical model and the aggregation cluster model based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregation cluster model;
and inputting the energy data to be detected into the target individual physical model and the target aggregation cluster model to obtain the predicted aggregation index data of the energy data to be detected.
2. The method for aggregating energy data according to claim 1, wherein the acquiring renewable energy data and energy data to be measured comprises:
acquiring renewable energy source initial data;
and cleaning and repairing the renewable energy source initial data to obtain the renewable energy source data and the energy source data to be detected.
3. The method for aggregating energy data according to claim 1, wherein training and verifying the individual physical model and the aggregate cluster model based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregate cluster model comprises:
training the individual physical model and the aggregation cluster model by using the K-means clustering algorithm and combining the training set data to obtain a trained aggregation cluster model and a trained aggregation cluster model;
and verifying the trained aggregation cluster model and the trained aggregation cluster model based on the test set data to obtain the target individual physical model and the target aggregation cluster model.
4. The method for aggregating energy data according to claim 3, wherein the training of the individual physical model and the aggregation cluster model by using the K-means clustering algorithm in combination with the training set data to obtain a trained aggregation cluster model and a trained aggregation cluster model comprises:
inputting the training set data into the individual physical model and the aggregation cluster model to obtain a corresponding prediction aggregation value of the renewable energy data;
determining a training error according to the data label corresponding to the training set data and the prediction aggregation value;
based on the training errors, the individual physical model and the aggregation cluster model are adjusted through the K-means clustering algorithm to obtain optimal parameters, and the individual physical model and the aggregation cluster model are optimized through the optimal parameters to obtain the trained aggregation cluster model and the trained aggregation cluster model.
5. The method of aggregating energy data according to claim 4, wherein before inputting the training set data into the individual physical models and the aggregation cluster model to obtain the corresponding predicted aggregation value of renewable energy data, further comprising:
initializing parameters of the individual physical model and parameters of the aggregated cluster model.
6. An apparatus for aggregating energy data, comprising:
the acquisition module is used for acquiring renewable energy data and energy data to be detected;
the establishing module is used for establishing an individual physical model and an aggregation cluster model of renewable energy sources based on the renewable energy source data;
the dividing module is used for dividing the renewable energy data into training set data and test set data;
the training module is used for training and verifying the individual physical model and the aggregation cluster model based on a K-means clustering algorithm, the training set data and the test set data to obtain a target individual physical model and a target aggregation cluster model;
and the index module is used for inputting the energy data to be detected into the target individual physical model and the target aggregation cluster model to obtain the predicted aggregation index data of the energy data to be detected.
7. The apparatus for aggregating energy data as recited in claim 6, wherein the acquiring module comprises:
the acquisition submodule is used for acquiring renewable energy source initial data;
and the repairing submodule is used for cleaning and repairing the renewable energy source initial data to obtain the renewable energy source data and the energy source data to be detected.
8. The apparatus for aggregating energy data as recited in claim 6, wherein the training module comprises:
the training submodule is used for training the individual physical model and the aggregation cluster model by using the K-means clustering algorithm and combining the training set data to obtain a trained aggregation cluster model and a trained aggregation cluster model;
and the verification sub-module is used for verifying the trained aggregation cluster model and the trained aggregation cluster model based on the test set data to obtain the target individual physical model and the target aggregation cluster model.
9. The apparatus for aggregating energy data as recited in claim 8, wherein the training submodule includes:
the prediction unit is used for inputting the training set data into the individual physical model and the aggregation cluster model to obtain a prediction aggregation value of corresponding renewable energy data;
the error unit is used for determining a training error according to the data label corresponding to the training set data and the prediction aggregation value;
and the optimization unit is used for adjusting the individual physical model and the aggregation cluster model through the K-means clustering algorithm based on the training error to obtain optimal parameters, and optimizing the individual physical model and the aggregation cluster model by adopting the optimal parameters to obtain the trained aggregation cluster model and the trained aggregation cluster model.
10. The apparatus for aggregating energy data as recited in claim 9, wherein the training sub-module further comprises:
a parameter unit for initializing parameters of the individual physical model and parameters of the aggregated cluster model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210668397.6A CN114912546A (en) | 2022-06-14 | 2022-06-14 | Energy data aggregation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210668397.6A CN114912546A (en) | 2022-06-14 | 2022-06-14 | Energy data aggregation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114912546A true CN114912546A (en) | 2022-08-16 |
Family
ID=82771607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210668397.6A Pending CN114912546A (en) | 2022-06-14 | 2022-06-14 | Energy data aggregation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114912546A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094613A (en) * | 2023-08-14 | 2023-11-21 | 华北电力大学 | Model construction method and device applied to comprehensive energy system |
-
2022
- 2022-06-14 CN CN202210668397.6A patent/CN114912546A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094613A (en) * | 2023-08-14 | 2023-11-21 | 华北电力大学 | Model construction method and device applied to comprehensive energy system |
| CN117094613B (en) * | 2023-08-14 | 2024-05-10 | 华北电力大学 | Model construction method and device applied to comprehensive energy system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Salkuti | Day-ahead thermal and renewable power generation scheduling considering uncertainty | |
| CN108306285B (en) | Reliability evaluation method for active power distribution network containing distributed power supply based on TOPSIS method | |
| CN112131733B (en) | Distributed power supply planning method considering influence of charging load of electric automobile | |
| Ghanbarzadeh et al. | Reliability constrained unit commitment with electric vehicle to grid using hybrid particle swarm optimization and ant colony optimization | |
| CN104156892A (en) | Active distribution network voltage drop simulation and evaluation method | |
| CN110061524B (en) | Active power dispatching equivalent aggregation method and system for distributed power supply virtual power plant based on deep neural network | |
| CN104077664B (en) | Confidence capacity assessment method of energy storage and generation system of wind power | |
| CN102509027B (en) | Wind powder combined predication method based on cross entropy theory | |
| CN105226650A (en) | Based on the micro-capacitance sensor reliability calculation method of miniature combustion engine-energy storage cooperation strategy | |
| CN106786977B (en) | Charging scheduling method of electric vehicle charging station | |
| CN113326467B (en) | Multi-target optimization method, storage medium and optimization system for multi-station fusion comprehensive energy system based on multiple uncertainties | |
| CN111181201B (en) | Multi-energy park scheduling method and system based on double-layer reinforcement learning | |
| CN110460038A (en) | It is a kind of to be related to more scene method for expansion planning of power transmission network of new-energy grid-connected | |
| CN114595891A (en) | Power distribution network voltage and power flow boundary crossing risk assessment method, system and equipment | |
| CN114912546A (en) | Energy data aggregation method and device | |
| Hutchinson et al. | Verification and analysis of a Battery Energy Storage System model | |
| CN115187018A (en) | Double-layer optimized scheduling method and device for park comprehensive energy system | |
| CN113536581A (en) | Energy storage system multi-state reliability modeling method considering operation strategy | |
| Zhu et al. | Dynamic multi-objective dispatch considering wind power and electric vehicles with probabilistic characteristics | |
| CN117196668A (en) | Large-scale new energy base access planning method and system based on marginal benefit | |
| CN116316588A (en) | Optimized dispatching method and device for micro-grid, computer equipment and storage medium | |
| CN109214624B (en) | Energy storage capacity optimization method, device and system based on Monte Carlo method | |
| CN115271220A (en) | Method and terminal for configuring electric heating energy storage capacity of comprehensive energy system | |
| CN114256865A (en) | Wind power installed capacity calculation method considering load increase direction randomness | |
| Ghaedi et al. | Reliability analysis of power system considering renewable resources, chp units, energy storage devices and demand response program |
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 |