CN112419084A - Method and device for optimizing utilization rate of power distribution network equipment - Google Patents
Method and device for optimizing utilization rate of power distribution network equipment Download PDFInfo
- Publication number
- CN112419084A CN112419084A CN202011256534.2A CN202011256534A CN112419084A CN 112419084 A CN112419084 A CN 112419084A CN 202011256534 A CN202011256534 A CN 202011256534A CN 112419084 A CN112419084 A CN 112419084A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- power distribution
- load
- utilization rate
- electricity price
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000004044 response Effects 0.000 claims abstract description 116
- 238000005457 optimization Methods 0.000 claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 25
- 238000000605 extraction Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 20
- 230000005611 electricity Effects 0.000 claims description 112
- 238000011156 evaluation Methods 0.000 claims description 32
- 238000011478 gradient descent method Methods 0.000 claims description 6
- 150000001875 compounds Chemical class 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000009467 reduction Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 76
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000008901 benefit Effects 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
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006872 improvement 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
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000005612 types of electricity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method and a device for optimizing utilization rate of power distribution network equipment, wherein the method comprises the following steps: the method comprises the steps of establishing an LSTM self-editor through training, carrying out feature extraction on a daily load curve set of the power distribution network to obtain a deep characteristic load sequence of the power distribution network, achieving dimension reduction on a high-dimensional load curve, then clustering the deep characteristic load sequence by using an improved fuzzy C mean value clustering algorithm, achieving accurate classification on load characteristics of various power users, establishing a power distribution network equipment utilization rate optimization model which aims at the condition that the equipment utilization rate and the user satisfaction degree are the maximum and takes classified load time-sharing demand response into consideration based on a load sequence classification result, and accordingly accurately guiding users to use power by staggering peaks and further achieving peak clipping and valley filling of user load curves, effectively improving the equipment utilization rate of the power distribution network and solving the technical problem that the existing power distribution network equipment utilization rate is low.
Description
Technical Field
The application relates to the technical field of electric power, in particular to a method and a device for optimizing utilization rate of power distribution network equipment.
Background
In recent years, with the rapid development of social economy, the demand of social electricity consumption is increased rapidly, so that a large amount of power distribution network equipment is invested. The capacity of the distribution network equipment is usually determined according to the maximum value of the load actually carried by the equipment in an operation cycle and is an instantaneous value of a certain discontinuous surface, and in the actual operation of the system, the time period for the load to reach the peak value is very short, so that the equipment is in a light load state for a long time, the utilization rate of the distribution network equipment is improved, the power supply reliability is ensured, and the capacity is of great importance for improving the operation level and the power supply capacity of a power grid enterprise.
At present, measures for improving the utilization rate of power distribution network equipment mainly comprise management measures and technical measures, wherein the management measures mainly guide users to carry out peak load shifting power utilization to realize peak load shifting so as to improve the utilization rate of the power distribution network equipment; in the aspect of technical measures, the improvement of the equipment utilization rate of the power distribution network is mainly researched by means of response, but a specific quantitative scheme for improving the equipment utilization rate of the power distribution network is not provided, so that the equipment utilization rate of the power distribution network can be improved only through management measures, and the equipment utilization rate of the power distribution network is low.
Disclosure of Invention
The embodiment of the application provides a method and a device for optimizing the utilization rate of power distribution network equipment, which are used for solving the technical problem of low utilization rate of the existing power distribution network equipment.
In view of this, a first aspect of the present application provides a method for optimizing utilization rate of power distribution network devices, where the method includes:
s1, training the multiple layers of LSTMs, and establishing an LSTM self-editor of the power distribution network;
s2, performing feature extraction on the daily load curve set of the power distribution network through the LSTM self-editor to obtain a deep characteristic load sequence of the power distribution network;
s3, setting the distance index of the fuzzy C-means clustering algorithm as a comprehensive similar distance to obtain a target function of the fuzzy C-means clustering algorithm, and clustering the deep characteristic load sequence through the target function to obtain a classified load sequence of the power distribution network;
s4, establishing a classified load time-of-use electricity price demand response model of the power distribution network according to the classified load sequence of the power distribution network based on a response participation demand response model;
s5, after the constraint condition of the classified load time-of-use electricity price demand response model is set, calculating to obtain a capacity factor according to the electricity price of the classified load time-of-use electricity price demand response model, wherein the constraint condition comprises: single-period response load constraint, load response capacity constraint, time-of-use electricity price constraint and equipment load rate constraint;
s6, establishing an equipment utilization rate objective function of the power distribution network according to the capacity factor, and setting the equipment utilization rate objective function as an evaluation index model of the power distribution network.
Optionally, step S5 is followed by:
calculating to obtain an electricity consumption mode satisfaction index and a user electricity expense satisfaction index according to the electricity consumption and the user electricity expense of the classified load time-of-use electricity price demand response model;
establishing a user satisfaction objective function of the power distribution network according to the power utilization mode satisfaction index and the user power cost expenditure satisfaction index;
and respectively setting the weights of the user satisfaction degree objective function and the equipment utilization rate objective function, establishing a multi-objective optimization objective function of the power distribution network, and setting the multi-objective optimization objective function as an evaluation index model of the power distribution network.
Optionally, step S1 specifically includes:
and after the LSTM self-editor model is trained, calculating by a gradient descent method to obtain an optimal parameter set of the LSTM self-editor model, so that a cost function mean square error is obtained, and the LSTM self-editor is obtained.
Optionally, step S2 specifically includes:
inputting the daily load curve set of the power distribution network into the LSTM self-editor for training until a hidden layer load sequence of a k-th layer is output, setting the hidden layer load sequence of the middle layer of the LSTM self-editor as a deep layer characteristic load sequence, wherein k is the layer number (k >0) of the LSTM self-editor.
Optionally, the classified load time-of-use electricity price demand response model is:
in the formula (I), the compound is shown in the specification,
for the load amount m periods before the nth class user demand response,
the load variation quantity of m time periods obtained by adjusting the controllable load electricity utilization state after the Nth class user price type demand response,
for the electricity price variation amount of the m period after the demand response of the nth class user,
in response to the electricity price of the previous user in the period of m, E is an electricity price elastic coefficient matrix of the electricity quantity, deltaNDemand response models are the response engagement.
Optionally, the evaluation index model is:
in the formula, eta is a capacity factor; e is the actual electric quantity of the equipment evaluation period; c is the rated capacity of the equipment; t is an evaluation period.
This application second aspect provides an optimization device of distribution network equipment utilization ratio, the device includes:
the first establishing unit is used for training the multi-layer LSTM and establishing an LSTM self-editor of the power distribution network;
the extraction unit is used for carrying out feature extraction on the daily load curve set of the power distribution network through the LSTM self-editor to obtain a deep characteristic load sequence of the power distribution network;
the clustering unit is used for setting a distance index of a fuzzy C-means clustering algorithm as a comprehensive similar distance to obtain a target function of the fuzzy C-means clustering algorithm, and clustering the deep characteristic load sequence through the target function to obtain a classified load sequence of the power distribution network;
the second establishing unit is used for establishing a classified load time-of-use electricity price demand response model of the power distribution network according to the classified load sequence of the power distribution network based on the response participation demand response model;
the calculating unit is configured to calculate a capacity factor according to the electricity price of the classified load time-of-use electricity price demand response model after setting a constraint condition of the classified load time-of-use electricity price demand response model, where the constraint condition includes: single-period response load constraint, load response capacity constraint, time-of-use electricity price constraint and equipment load rate constraint;
and the third establishing unit is used for establishing an equipment utilization rate objective function of the power distribution network according to the capacity factor and setting the equipment utilization rate objective function as an evaluation index model of the power distribution network.
Optionally, the method further comprises: a fourth set-up unit for establishing a third set-up unit,
the system comprises a classification load time-of-use electricity price demand response model, a power consumption mode satisfaction index and a user electricity price expenditure satisfaction index, wherein the classification load time-of-use electricity price demand response model is used for calculating and obtaining the power consumption mode satisfaction index and the user electricity price expenditure satisfaction index respectively according to the power consumption and the user electricity price of the classification load time-of-use electricity price;
establishing a user satisfaction objective function of the power distribution network according to the power utilization mode satisfaction index and the user power cost expenditure satisfaction index;
and respectively setting the weights of the user satisfaction degree objective function and the equipment utilization rate objective function, establishing a multi-objective optimization objective function of the power distribution network, and setting the multi-objective optimization objective function as an evaluation index model of the power distribution network.
Optionally, the first establishing unit is specifically configured to:
and after the LSTM self-editor model is trained, calculating by a gradient descent method to obtain an optimal parameter set of the LSTM self-editor model, so that a cost function mean square error is obtained, and the LSTM self-editor is obtained.
Optionally, the extracting unit is specifically configured to:
inputting the daily load curve set of the power distribution network into the LSTM self-editor for training until a hidden layer load sequence of a k-th layer is output, setting the hidden layer load sequence of the middle layer of the LSTM self-editor as a deep layer characteristic load sequence, wherein k is the layer number (k >0) of the LSTM self-editor.
According to the technical scheme, the embodiment of the application has the following advantages:
in the embodiment of the application, a method for optimizing the utilization rate of power distribution network equipment is provided, which comprises the following steps: s1, training the multiple layers of LSTMs, and establishing an LSTM self-editor of the power distribution network; s2, performing feature extraction on the daily load curve set of the power distribution network through an LSTM self-editor to obtain a deep characteristic load sequence of the power distribution network; s3, setting the distance index of the fuzzy C-means clustering algorithm as a comprehensive similar distance to obtain a target function of the fuzzy C-means clustering algorithm, and clustering deep characteristic load sequences through the target function to obtain a classified load sequence of the power distribution network; s4, establishing a classified load time-of-use electricity price demand response model of the power distribution network according to the classified load sequence of the power distribution network based on the response participation demand response model; s5, after constraint conditions of the classified load time-of-use electricity price demand response model are set, capacity factors are obtained through electricity price calculation according to the classified load time-of-use electricity price demand response model, and the constraint conditions include: single-period response load constraint, load response capacity constraint, time-of-use electricity price constraint and equipment load rate constraint; s6, establishing an equipment utilization rate objective function of the power distribution network according to the capacity factor, and setting the equipment utilization rate objective function as an evaluation index model of the power distribution network.
According to the optimization method for the equipment utilization rate of the power distribution network, the LSTM self-editor is established to perform feature extraction on the daily load curve set of the power distribution network to obtain the deep characteristic load sequence of the power distribution network, dimension reduction of a high-dimensional load curve is achieved, then the deep characteristic load sequence is clustered by using an improved fuzzy C mean value clustering algorithm, accurate classification of load characteristics of various power users is achieved, a power distribution network equipment utilization rate objective function taking the equipment utilization rate as the maximum target is established based on a load sequence classification result, and finally the equipment utilization rate objective function is used as an evaluation index model of the power distribution network, so that the power utilization rate of the users can be accurately guided, the users can be guided to perform peak clipping and valley filling, the equipment utilization rate of the power distribution network is effectively improved, and the technical problem that the existing power distribution network equipment utilization rate is low.
Drawings
Fig. 1 is a schematic flowchart of a first embodiment of a method for optimizing utilization of power distribution network equipment according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a second embodiment of a method for optimizing utilization of power distribution network equipment according to an embodiment of the present application;
fig. 3 is a structural diagram of an embodiment of an apparatus for optimizing utilization rate of power distribution network equipment according to an embodiment of the present application;
FIG. 4 is a graph of an iteration of a loss function for the training of the LSTM self-editor provided herein;
FIG. 5 is a diagram illustrating the classification result of deep feature loading sequences provided in the present application;
FIG. 6 is a graph of a load curve optimization result under a classified load time-sharing demand response provided by the present application;
fig. 7 is a comparison graph of user load curves under different target weights provided by the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
Referring to fig. 1, a first embodiment of a method for optimizing utilization of power distribution network equipment provided in the embodiment of the present application includes:
It can be understood that model training is carried out after multilayer LSTM superposition is adopted, so that the output bit number and the number of coding and decoding layers of an LSTM self-encoder model are determined, and further an LSTM self-encoder of the power distribution network is established.
And 102, carrying out feature extraction on the daily load curve set of the power distribution network through an LSTM self-editor to obtain a deep characteristic load sequence of the power distribution network.
In order to find out the rule and the characteristic of the power load and realize deep characteristic extraction of the time sequence characteristic of the load sequence, the implementation carries out characteristic extraction on a daily load curve set of the power distribution network through an LSTM self-editor to obtain a deep characteristic load sequence of the power distribution network.
103, setting the distance index of the fuzzy C-means clustering algorithm as a comprehensive similar distance to obtain a target function of the fuzzy C-means clustering algorithm, and clustering deep characteristic load sequences through the target function to obtain a classified load sequence of the power distribution network.
It should be noted that the fuzzy C-means clustering is a common load clustering algorithm, and generally, an euclidean distance is used as a distance index, and the euclidean distance is an index for judging a difference in magnitude of a numerical value, and has a limitation on the similarity measurement of a load curve, so that in the embodiment of the present application, the distance index in the fuzzy C-means is set as the comprehensive similar distance measurement to obtain a target function of the fuzzy C-means clustering algorithm, and deep characteristic load sequences are clustered by the target function to divide deep characteristic load sequences with the same load characteristics into the same class.
And step 104, establishing a classified load time-of-use electricity price demand response model of the power distribution network according to the classified load sequence of the power distribution network based on the response participation demand response model.
In consideration of the psychological influence of electricity consumption of the user, the load response quantity has certain uncertainty, and the uncertainty can be reflected as the user participation degree, so that the classified load time-of-use electricity price demand response model of the power distribution network is established based on the response participation degree demand response model in the embodiment of the application, a corresponding time-of-use electricity price demand response model is formulated, and peak clipping and valley filling of a load curve are realized.
After the constraint conditions of the class load time-of-use electricity price demand response model are set, it should be noted that, because the electricity price is a fundamental factor influencing a load curve, the capacity factor is obtained by calculating the electricity price of the class load time-of-use electricity price demand response model in the embodiment of the application and is used as an evaluation index of the equipment utilization rate of the power distribution network.
And 106, establishing an equipment utilization rate objective function of the power distribution network according to the capacity factor, and setting the equipment utilization rate objective function as an evaluation index model of the power distribution network.
The equipment utilization rate target function of the power distribution network is used as an evaluation index model of the power distribution network, so that peak load shifting and power utilization of a user can be guided, and peak load shifting of the user is further guided.
Wherein, the evaluation index model is as follows:
in the formula, eta is a capacity factor; e is the actual electric quantity of the equipment evaluation period; c is the rated capacity of the equipment; t is an evaluation period.
According to the optimization method for the equipment utilization rate of the power distribution network, the LSTM self-editor is established to perform feature extraction on the daily load curve set of the power distribution network to obtain the deep characteristic load sequence of the power distribution network, then the deep characteristic load sequence is clustered by using the improved fuzzy C mean value clustering algorithm, the load characteristics of various power users are accurately classified, the target function of the equipment utilization rate of the power distribution network, which takes the equipment utilization rate as the maximum target, is established based on the classification result of the load sequence, and finally the target function of the equipment utilization rate is used as the evaluation index model of the power distribution network, so that the peak load shifting of the users can be accurately guided, the peak clipping and valley filling of the users are further guided, the equipment utilization rate of the power distribution network is effectively improved, and the technical problem that the.
The foregoing is an embodiment one of a method for optimizing a utilization rate of power distribution network equipment provided in this embodiment of the application, and the following is an embodiment two of the method for optimizing a utilization rate of power distribution network equipment provided in this embodiment of the application.
Referring to fig. 2, a second embodiment of a method for optimizing utilization of power distribution network equipment according to an embodiment of the present application includes:
The LSTM self-editor model of the power distribution network is built by adopting multilayer LSTM superposition, then the output dimension of the LSTM self-editor model and the number of layers of coding and decoding are determined after the LSTM self-editor model is trained, and finally the optimal parameter set of the LSTM self-editor model is calculated by a gradient descent method so as to enable the mean square error of the cost function to be obtained, thereby building the LSTM self-editor of the power distribution network.
It can be understood that the daily load curve set of the power distribution network is input into the first layer of the LSTM self-editor for training, the load sequence of the hidden layer of the first layer is output, the load sequence of the hidden layer of the first layer is used as the input of the second layer, the process is repeated until the load sequence of the hidden layer of the last layer is output, and the load sequence of the hidden layer of the middle layer of the LSTM self-editor is set as the deep characteristic load sequence.
And 203, setting the distance index of the fuzzy C-means clustering algorithm as a comprehensive similar distance to obtain a target function of the fuzzy C-means clustering algorithm, and clustering deep characteristic load sequences through the target function to obtain a classified load sequence of the power distribution network.
Step 203 in this embodiment of the application is the same as step 103 in this embodiment, please refer to step 103 for description, which is not described herein again, and it should be noted that the objective function of the fuzzy C-means clustering algorithm is:
wherein the content of the first and second substances,
wherein c is the number of clustering centers; dwhole(ik)Represents the k data pointA composite similarity distance to the class i center; m is a weighting index; n is the total number of samples.
And step 204, establishing a classified load time-of-use electricity price demand response model of the power distribution network according to the classified load sequence of the power distribution network based on the response participation demand response model.
Step 204 in this embodiment of the present application is the same as the description of step 104 in this embodiment, please refer to step 104 for description, which is not described herein again, and it should be noted that the classification load time-of-use electricity price demand response model is:
in the formula (I), the compound is shown in the specification,
for the load amount m periods before the nth class user demand response,
the load variation quantity of m time periods obtained by adjusting the controllable load electricity utilization state after the Nth class user price type demand response,
for the electricity price variation amount of the m period after the demand response of the nth class user,
in response to the electricity price of the previous user in the period of m, E is an electricity price elastic coefficient matrix of the electricity quantity, deltaNA response model is required to respond to the engagement.
Step 205 in this embodiment is the same as the description of step 105 in this embodiment, please refer to step 105 for description, which is not described herein again, and it should be noted that:
the load available for flexible adjustment in each time interval is limited, and therefore, a single-time interval response load constraint is introduced, wherein the single-time interval response load constraint is as follows:
PHmin(t)≤ΔP(t)≤PHmax(t)；
in the formula, PHmax(t) and PHmin(t) represents an upper limit and a lower limit of the demand response load for the period t, respectively.
In order to ensure the balance of the whole power consumption of the users in the dispatching cycle, the load quantity of the demand response reduction or increase should be kept in a certain balance, and therefore, a load response capacity constraint is introduced, wherein the load response capacity constraint is as follows:
in the formula, SPmaxAnd SPminRespectively representing the upper and lower limits of the load response capacity in a scheduling period T, wherein SPmin＜0。
Considering the satisfaction degree of the user, the adjustment range of the electricity price needs to be limited within a reasonable interval, so that the adjustment range of the time-of-use electricity price is restricted, wherein the time-of-use electricity price restriction is as follows:
in the formula, QminAnd QmaxThe minimum value and the maximum value of the time-of-use electricity price are respectively.
The equipment utilization rate is improved, and meanwhile, the equipment overload is also avoided, so that the load rate of the equipment in a scheduling period is restrained, wherein the restraint of the load rate of the equipment is as follows:
in the formula etaminAnd ηmaxAre respectively provided withMinimum and maximum values of the load factor of the apparatus, Pt,maxIs the maximum load value in a period, and C is the equipment capacity.
It can be understood that, in the embodiment, besides improving the utilization rate of the equipment, the user satisfaction is also considered, and the balance between the utilization rate of the equipment and the user satisfaction is considered, so that the multi-objective optimization objective function is established by taking the objective function of the user satisfaction and the objective function of the utilization rate of the equipment and taking the weights of the objective function and the objective function of the utilization rate of the equipment into consideration, and is used as the evaluation index model of the power distribution network.
The evaluation index model is:
f＝αf1+βf2；
wherein:
in the formula, eta is a capacity factor; e is the actual electric quantity of the equipment evaluation period; c is the rated capacity of the equipment; t is an evaluation period.
In the formula, sloadFor the electricity usage satisfaction index, spriceFor the satisfaction index of the user electricity expense, alpha and beta respectively represent f1，f2The weight coefficient of (2). When alpha and beta are coefficients between 0 and 1, the comprehensive consideration of the user side and the power grid side is shown, so that the overall social benefit is optimal. When α is 1 and β is 0, it indicates that the objective function is onlyFrom the perspective of the user, the user benefit is maximized; when α is 0 and β is 1, the objective function is considered from the perspective of the grid only, and the utility equipment utilization rate is highest.
The optimization method of the power distribution network equipment utilization rate obtains deep characteristic load sequences of the power distribution network by establishing an LSTM self-editor to perform characteristic extraction on a daily load curve set of the power distribution network, realizes the dimension reduction of a high-dimensional load curve, then utilizes an improved fuzzy C-means clustering algorithm to cluster the deep characteristic load sequences, realizes the accurate classification of the load characteristics of various power users, establishes a power distribution network equipment utilization rate target function taking the equipment utilization rate as the maximum target based on the load sequence classification result, simultaneously establishes a target function with user satisfaction degree by considering the user satisfaction degree, and respectively sets the weights of the equipment utilization rate target function and the user satisfaction degree target function so as to establish a multi-target power distribution network evaluation index function, thereby accurately guiding the peak-shifting power consumption of the users and considering the user satisfaction degree, the balance of the equipment utilization rate and the user satisfaction degree of the power distribution network is realized, and the technical problem that the equipment utilization rate of the existing power distribution network is low is solved.
The second embodiment of the method for optimizing the utilization rate of the power distribution network equipment provided in the embodiment of the present application is as follows.
Referring to fig. 3, an apparatus for optimizing utilization of power distribution network equipment provided in an embodiment of the present application includes:
the first establishing unit 301 is configured to train multiple layers of LSTM and establish an LSTM self-editor of the power distribution network;
an extraction unit 302, configured to perform feature extraction on a daily load curve set of the power distribution network through an LSTM self-editor to obtain a deep characteristic load sequence of the power distribution network;
the clustering unit 303 is configured to set a distance index of the fuzzy C-means clustering algorithm to be a comprehensive similar distance, obtain a target function of the fuzzy C-means clustering algorithm, and obtain a classified load sequence of the power distribution network after clustering the deep characteristic load sequence through the target function;
a second establishing unit 304, configured to establish a classified load time-of-use electricity price demand response model of the power distribution network according to the classified load sequence of the power distribution network based on the response participation demand response model;
the calculating unit 305 is configured to obtain a capacity factor by calculating the electricity price of the classified load time-of-use electricity price demand response model after setting a constraint condition of the classified load time-of-use electricity price demand response model, where the constraint condition includes: single-period response load constraint, load response capacity constraint, time-of-use electricity price constraint and equipment load rate constraint;
and a third establishing unit 306, configured to establish an equipment utilization rate objective function of the power distribution network according to the capacity factor, and set the equipment utilization rate objective function as an evaluation index model of the power distribution network.
A fourth establishing unit 307, configured to calculate a power consumption mode satisfaction index and a user electricity fee expenditure satisfaction index according to the power consumption and the user electricity fee of the classified load time-of-use electricity price response model; establishing a user satisfaction target function of the power distribution network according to the power utilization mode satisfaction index and the user power expense satisfaction index; and respectively setting the weights of the user satisfaction degree objective function and the equipment utilization rate objective function, establishing a multi-objective optimization objective function of the power distribution network, and setting the multi-objective optimization objective function as an evaluation index model of the power distribution network.
The optimizing device for the equipment utilization rate of the power distribution network obtains deep characteristic load sequences of the power distribution network by establishing an LSTM self-editor to perform characteristic extraction on a daily load curve set of the power distribution network, realizes dimension reduction on a high-dimensional load curve, then clusters the deep characteristic load sequences by using an improved fuzzy C-means clustering algorithm, realizes accurate classification on load characteristics of various power users, establishes a target function of the equipment utilization rate of the power distribution network taking the equipment utilization rate as a maximum target based on a load sequence classification result, simultaneously establishes a target function with user satisfaction degree by considering the user satisfaction degree, and respectively sets weights of the target function of the equipment utilization rate and the target function of the user satisfaction degree so as to establish a multi-target evaluation index function of the power distribution network, thereby accurately guiding the peak-shifting power consumption of the user and considering the user satisfaction degree, the balance of the equipment utilization rate and the user satisfaction degree of the power distribution network is realized, and the technical problem that the equipment utilization rate of the existing power distribution network is low is solved.
The application also provides an optimization method and an optimization device for the utilization rate of the power distribution network equipment, and experimental results and analysis of the optimization method and the optimization device are as follows:
1. examples and parameter settings
The LSTM self-editor was trained using 10000 commercial and industrial users daily load data in a certain area, 8000 as a training set and 2000 as a test set. The LSTM self-editor parameters are shown in table 1, and time-series deep characteristic parameters of the electrical load can be extracted by the LSTM self-editor. On the basis of a trained LSTM self-editor, the load data sets of 1200 users in total in the region of business and industry are subjected to cluster analysis, the daily load sampling interval is 15min, 96 data points are counted each day, the typical daily user load sequence set samples are normalized, and a table 2 shows the peak-valley bisection time electricity price parameters.
| Parameter(s) | Value of |
| Optimization method | |
| Learning rate | |
| 10-3 | |
| Activating a function | GELU |
TABLE 1
TABLE 2
2. Load clustering result analysis
1) Training results of LSTM self-editor
In order to test the effect of the LSTM self-editor on the deep feature extraction of the load curve, the actual daily load curves of 200 users are taken as a test set in a typical daily user load sequence set, and compared with the daily load curves output after each layer of LSTM encoding and decoding, the respective cost function Mean Square Error (MSE) is shown in fig. 4.
Fig. 4 shows a loss function iteration diagram of the training of the LSTM self-editor, and it can be seen from the diagram that the training set and the test set of the model both reach the same convergence degree quickly, and the final error of the model is also low, which fully indicates that the LSTM self-editor model can reconstruct the sequence well, so the information of the middle layer is also an effective feature.
2) Load clustering results
On the basis of using an LSTM self-editor to perform feature extraction on the load curve to obtain a dimension reduction feature sequence, an improved fuzzy C-means algorithm is used to cluster deep feature load sequences, and the load classification result is shown in FIG. 5.
The deep characteristic load sequences are divided into 6 categories through clustering, wherein the category 1, the category 2 and the category 3 have the characteristics of all-weather power utilization, have high fluctuation in the power utilization process and have high demand response potential; the category 4 shows all-weather electricity utilization and stable electricity utilization process, while the categories 5 and 6 show typical electricity utilization characteristics of day-night electricity utilization or day-night electricity utilization, and the three types of electricity utilization characteristics have strong regularity and weak load transferability and basically have no demand response potential.
3. Optimization result of utilization rate of classified load demand response equipment
Based on the analysis, the categories 1, 2 and 3 with large demand response potential are selected, the response characteristics of the electricity consumption to the time-of-use electricity price are considered for optimizing the equipment utilization rate, and the optimization result is shown in table 3.
As can be seen from fig. 6, the load curves of the three types of loads are subjected to peak clipping and valley filling under the action of the time-of-use electricity prices of the three types of loads, the classified time-of-use electricity prices of the various types of loads are shown in table 3, and the peak-to-valley difference of the total load curve after response is greatly reduced compared with the original load curve. From the analysis of table 4, it can be seen that the system equipment utilization rate after the classified time-of-use electricity price response is performed is improved from 32.31% to 65.83% before the response. Meanwhile, although the load adjustment reduces the satisfaction degree of the electricity utilization mode of the user, the user adjusts the load by reasonably utilizing the time-of-use electricity price, so that the electricity charge is reduced, the overall satisfaction degree of the user is not greatly influenced by the demand response, and the satisfaction degree of the user is still 91.21 percent after the response. And the comprehensive satisfaction degree after response is improved from 66.155 percent before response to 78.515 percent. Therefore, the equipment utilization rate is optimized through classified load demand response, the equipment utilization rate can be effectively improved, and the user satisfaction degree is better considered.
TABLE 3
| Utilization of equipment | Degree of satisfaction of user | Comprehensive results | |
| Before response | 32.31％ | 100％ | 66.155％ |
| After responding | 65.83％ | 91.21％ | 78.515％ |
TABLE 4
4. Effect of weight parameters on Equipment utilization
To verify the objective function f1、f2Selecting the influence of the weight parameters alpha and beta on the utilization rate of equipment, and selecting three different weight parameter combination modes, namely: α, β ═ 0.5, mode two: α is 0.3, β is 0.7, manner three: α ═ 0.7 and β ═ 0.3, and the comparisons were under different target weights, as shown in fig. 7.
The simulation result is analyzed, and under the condition of classified time-of-use electricity price demand response, the load curves in the three modes have obvious phenomena of peak clipping, valley filling and load transfer, wherein the load curve in the third mode has the minimum peak-valley difference, and the load curve in the second mode has the maximum peak-valley difference. Analyzing the data in table 5, the system equipment utilization rate is highest in the third mode, and is 69.83%, and the user satisfaction is lowest, and is 89.32%; in the second mode, the utilization rate of the system equipment is the lowest and is 60.20%, and the user satisfaction is the highest and is 95.42%. This is because the target weight α of the device utilization ratio is 0.7 in the third mode, which has a large value, and the user satisfaction β is 0.3, which has a small value, so that the system sacrifices a part of the user satisfaction, and performs load adjustment to a greater extent to ensure a high device utilization ratio, and vice versa in the second mode. Therefore, the optimization result of the power distribution network system is related to the selection of the equipment utilization rate and the user satisfaction degree weight, and reference basis can be provided for decision-making personnel in the process of balancing the equipment utilization rate and the user satisfaction degree by reasonably setting the weight parameters.
| Utilization of equipment | Degree of satisfaction of user | |
| In a first mode | 65.83％ | 91.21％ |
| Mode two | 60.20％ | 95.42％ |
TABLE 5
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The terms "first," "second," "third," "fourth," and the like in the description of the present application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. 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 application 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 application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing 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 application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should 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 in the embodiments of the present application.
Claims (10)
1. A method for optimizing utilization rate of power distribution network equipment is characterized by comprising the following steps:
s1, training the multiple layers of LSTMs, and establishing an LSTM self-editor of the power distribution network;
s2, performing feature extraction on the daily load curve set of the power distribution network through the LSTM self-editor to obtain a deep characteristic load sequence of the power distribution network;
s3, setting the distance index of the fuzzy C-means clustering algorithm as a comprehensive similar distance to obtain a target function of the fuzzy C-means clustering algorithm, and clustering the deep characteristic load sequence through the target function to obtain a classified load sequence of the power distribution network;
s4, establishing a classified load time-of-use electricity price demand response model of the power distribution network according to the classified load sequence of the power distribution network based on a response participation demand response model;
s5, after the constraint condition of the classified load time-of-use electricity price demand response model is set, calculating to obtain a capacity factor according to the electricity price of the classified load time-of-use electricity price demand response model, wherein the constraint condition comprises: single-period response load constraint, load response capacity constraint, time-of-use electricity price constraint and equipment load rate constraint;
s6, establishing an equipment utilization rate objective function of the power distribution network according to the capacity factor, and setting the equipment utilization rate objective function as an evaluation index model of the power distribution network.
2. The method for optimizing the utilization ratio of the power distribution network equipment according to claim 1, wherein step S5 is followed by further comprising:
calculating to obtain an electricity consumption mode satisfaction index and a user electricity expense satisfaction index according to the electricity consumption and the user electricity expense of the classified load time-of-use electricity price demand response model;
establishing a user satisfaction objective function of the power distribution network according to the power utilization mode satisfaction index and the user power cost expenditure satisfaction index;
and respectively setting the weights of the user satisfaction degree objective function and the equipment utilization rate objective function, establishing a multi-objective optimization objective function of the power distribution network, and setting the multi-objective optimization objective function as an evaluation index model of the power distribution network.
3. The method for optimizing the utilization rate of the power distribution network equipment according to claim 1, wherein the step S1 specifically includes:
and after the LSTM self-editor model is trained, calculating by a gradient descent method to obtain an optimal parameter set of the LSTM self-editor model, so that a cost function mean square error is obtained, and the LSTM self-editor is obtained.
4. The method for optimizing the utilization rate of the power distribution network equipment according to claim 1, wherein the step S2 specifically includes:
inputting the daily load curve set of the power distribution network into the LSTM self-editor for training until a hidden layer load sequence of a k-th layer is output, setting the hidden layer load sequence of the middle layer of the LSTM self-editor as a deep layer characteristic load sequence, wherein k is the layer number (k >0) of the LSTM self-editor.
5. The method for optimizing the utilization rate of the power distribution network equipment according to claim 1, wherein the classified load time-of-use electricity price demand response model is as follows:
in the formula (I), the compound is shown in the specification,
for the load amount m periods before the nth class user demand response,
the load variation quantity of m time periods obtained by adjusting the controllable load electricity utilization state after the Nth class user price type demand response,
for the electricity price variation amount of the m period after the demand response of the nth class user,
in response to the electricity price of the previous user in the period of m, E is an electricity price elastic coefficient matrix of the electricity quantity, deltaNThe above-mentionedA response engagement demand response model.
6. The method for optimizing the utilization rate of the power distribution network equipment according to claim 1, wherein the evaluation index model is as follows:
in the formula, eta is a capacity factor; e is the actual electric quantity of the equipment evaluation period; c is the rated capacity of the equipment; t is an evaluation period.
7. An optimization device for utilization rate of power distribution network equipment is characterized by comprising:
the first establishing unit is used for training the multi-layer LSTM and establishing an LSTM self-editor of the power distribution network;
the extraction unit is used for carrying out feature extraction on the daily load curve set of the power distribution network through the LSTM self-editor to obtain a deep characteristic load sequence of the power distribution network;
the clustering unit is used for setting a distance index of a fuzzy C-means clustering algorithm as a comprehensive similar distance to obtain a target function of the fuzzy C-means clustering algorithm, and clustering the deep characteristic load sequence through the target function to obtain a classified load sequence of the power distribution network;
the second establishing unit is used for establishing a classified load time-of-use electricity price demand response model of the power distribution network according to the classified load sequence of the power distribution network based on the response participation demand response model;
the calculating unit is configured to calculate a capacity factor according to the electricity price of the classified load time-of-use electricity price demand response model after setting a constraint condition of the classified load time-of-use electricity price demand response model, where the constraint condition includes: single-period response load constraint, load response capacity constraint, time-of-use electricity price constraint and equipment load rate constraint;
and the third establishing unit is used for establishing an equipment utilization rate objective function of the power distribution network according to the capacity factor and setting the equipment utilization rate objective function as an evaluation index model of the power distribution network.
8. The apparatus for optimizing utilization of power distribution network equipment according to claim 7, further comprising: a fourth set-up unit for establishing a third set-up unit,
the system comprises a classification load time-of-use electricity price demand response model, a power consumption mode satisfaction index and a user electricity price expenditure satisfaction index, wherein the classification load time-of-use electricity price demand response model is used for calculating and obtaining the power consumption mode satisfaction index and the user electricity price expenditure satisfaction index respectively according to the power consumption and the user electricity price of the classification load time-of-use electricity price;
establishing a user satisfaction objective function of the power distribution network according to the power utilization mode satisfaction index and the user power cost expenditure satisfaction index;
and respectively setting the weights of the user satisfaction degree objective function and the equipment utilization rate objective function, establishing a multi-objective optimization objective function of the power distribution network, and setting the multi-objective optimization objective function as an evaluation index model of the power distribution network.
9. The apparatus for optimizing utilization of power distribution network equipment according to claim 7, wherein the first establishing unit is specifically configured to:
and after the LSTM self-editor model is trained, calculating by a gradient descent method to obtain an optimal parameter set of the LSTM self-editor model, so that a cost function mean square error is obtained, and the LSTM self-editor is obtained.
10. The device for optimizing utilization of power distribution network equipment according to claim 7, wherein the extraction unit is specifically configured to:
inputting the daily load curve set of the power distribution network into the LSTM self-editor for training until a hidden layer load sequence of a k-th layer is output, setting the hidden layer load sequence of the middle layer of the LSTM self-editor as a deep layer characteristic load sequence, wherein k is the layer number (k >0) of the LSTM self-editor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011256534.2A CN112419084B (en) | 2020-11-11 | 2020-11-11 | Method and device for optimizing utilization rate of power distribution network equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011256534.2A CN112419084B (en) | 2020-11-11 | 2020-11-11 | Method and device for optimizing utilization rate of power distribution network equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112419084A true CN112419084A (en) | 2021-02-26 |
| CN112419084B CN112419084B (en) | 2022-11-29 |
Family
ID=74781651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011256534.2A Active CN112419084B (en) | 2020-11-11 | 2020-11-11 | Method and device for optimizing utilization rate of power distribution network equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112419084B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114268097A (en) * | 2021-12-28 | 2022-04-01 | 国网上海市电力公司 | Method and system for analyzing influence of user side energy management system access on power distribution network |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105469194A (en) * | 2015-11-18 | 2016-04-06 | 中国电力科学研究院 | Power distribution network main equipment operation efficiency evaluation method based on load duration curve |
| CN107944630A (en) * | 2017-12-01 | 2018-04-20 | 华北电力大学 | A kind of seasonality tou power price optimization formulating method |
| CN108390421A (en) * | 2018-01-19 | 2018-08-10 | 上海电力学院 | Meter and the double scale charging bootstrap techniques of the electric vehicle of user satisfaction and system |
| CN108604310A (en) * | 2015-12-31 | 2018-09-28 | 威拓股份有限公司 | Method, controller and the system of distribution system are controlled for using neural network framework |
| CN110288145A (en) * | 2019-06-20 | 2019-09-27 | 华北电力大学 | It is a kind of meter and demand response resource microgrid planing method and calculate equipment |
| US20200073342A1 (en) * | 2018-08-28 | 2020-03-05 | Johnson Controls Technology Company | Cloud based building energy optimization system with a dynamically trained load prediction model |
| CN111724210A (en) * | 2020-06-23 | 2020-09-29 | 华中科技大学 | Power demand response regulation and control method based on price elastic coefficient matrix |
| CN111832861A (en) * | 2019-04-19 | 2020-10-27 | 广州供电局有限公司 | Resident load variable-scale portrait method and system based on big data platform |
| CN111864758A (en) * | 2020-07-29 | 2020-10-30 | 合肥工业大学 | Energy storage system operation scheduling method considering load demand difference |
-
2020
- 2020-11-11 CN CN202011256534.2A patent/CN112419084B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105469194A (en) * | 2015-11-18 | 2016-04-06 | 中国电力科学研究院 | Power distribution network main equipment operation efficiency evaluation method based on load duration curve |
| CN108604310A (en) * | 2015-12-31 | 2018-09-28 | 威拓股份有限公司 | Method, controller and the system of distribution system are controlled for using neural network framework |
| CN107944630A (en) * | 2017-12-01 | 2018-04-20 | 华北电力大学 | A kind of seasonality tou power price optimization formulating method |
| CN108390421A (en) * | 2018-01-19 | 2018-08-10 | 上海电力学院 | Meter and the double scale charging bootstrap techniques of the electric vehicle of user satisfaction and system |
| US20200073342A1 (en) * | 2018-08-28 | 2020-03-05 | Johnson Controls Technology Company | Cloud based building energy optimization system with a dynamically trained load prediction model |
| CN111832861A (en) * | 2019-04-19 | 2020-10-27 | 广州供电局有限公司 | Resident load variable-scale portrait method and system based on big data platform |
| CN110288145A (en) * | 2019-06-20 | 2019-09-27 | 华北电力大学 | It is a kind of meter and demand response resource microgrid planing method and calculate equipment |
| CN111724210A (en) * | 2020-06-23 | 2020-09-29 | 华中科技大学 | Power demand response regulation and control method based on price elastic coefficient matrix |
| CN111864758A (en) * | 2020-07-29 | 2020-10-30 | 合肥工业大学 | Energy storage system operation scheduling method considering load demand difference |
Non-Patent Citations (5)
| Title |
|---|
| DAWEI GENG 等: "Effective LSTM with K-means Clustering Algorithm for Electricity Load Prediction", 《RICAI 2019》 * |
| KESHAV ADITYA R. PREMKUMAR 等: "Riboflow: Using Deep Learning to Classify Riboswitches With -99% Accuracy", 《FRONTIER IN BIOENGINEERING AND BIOTECHNOLOGY》 * |
| LONGMAO FAN 等: "Load prediction methods using machine learning for home energy management systems based on human behavior patterns recognition", 《CSEE JOURNAL OF POWER AND ENERGY SYSTEMS》 * |
| 周任军 等: "多功率曲线协整度约束下的源-荷-储优化协整模型", 《中国电机工程学报》 * |
| 彭曙蓉 等: "基于风电功率预测的电动汽车调价策略", 《电力科学与技术学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114268097A (en) * | 2021-12-28 | 2022-04-01 | 国网上海市电力公司 | Method and system for analyzing influence of user side energy management system access on power distribution network |
| CN114268097B (en) * | 2021-12-28 | 2023-12-19 | 国网上海市电力公司 | Analysis method and system for influence of access of user side energy management system on power distribution network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112419084B (en) | 2022-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110738435A (en) | distribution network project investment decision evaluation method | |
| CN106779277B (en) | Classified evaluation method and device for network loss of power distribution network | |
| CN109636146A (en) | A kind of user demand response potentiality portrait method | |
| CN108345908A (en) | Sorting technique, sorting device and the storage medium of electric network data | |
| CN110109971A (en) | A kind of low-voltage platform area user power utilization Load Characteristic Analysis method | |
| CN104537433A (en) | Sold electricity quantity prediction method based on inventory capacities and business expansion characteristics | |
| CN108389069A (en) | Top-tier customer recognition methods based on random forest and logistic regression and device | |
| CN111815060A (en) | Short-term load prediction method and device for power utilization area | |
| CN111126499A (en) | Secondary clustering-based power consumption behavior pattern classification method | |
| CN113902304A (en) | Controllable load screening method based on total load curve similarity | |
| CN112884590A (en) | Power grid enterprise financing decision method based on machine learning algorithm | |
| CN109389272A (en) | A kind of comprehensive estimation method and system for voltage coordination control strategy effect | |
| CN111553568A (en) | Line loss management method based on data mining technology | |
| Justo et al. | Behavioral similarity of residential customers using a neural network based on adaptive resonance theory | |
| CN112419084B (en) | Method and device for optimizing utilization rate of power distribution network equipment | |
| CN115496627A (en) | Method and system for evaluating response potential of adjustable resource | |
| CN111798333A (en) | Energy utilization evaluation and electricity utilization safety analysis method and system | |
| CN112614004A (en) | Method and device for processing power utilization information | |
| CN116701965A (en) | BIRCH clustering algorithm-based panoramic carbon representation method for enterprise users | |
| CN113450031B (en) | Method and device for selecting intelligent energy consumption service potential transformer area of residents | |
| CN111724049A (en) | Research and judgment method for potential power energy efficiency service customer | |
| CN111339167A (en) | Method for analyzing influence factors of transformer area line loss rate based on K-means and principal component linear regression | |
| CN109784748B (en) | User electricity consumption behavior identification method and device under market competition mechanism | |
| CN115566740B (en) | Distributed renewable energy cluster aggregation regulation potential evaluation method and device | |
| Lu et al. | Research on creating multi-attribute power consumption behavior portraits for massive users |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |