CN114742410A - Pso-CNN-based regenerative electric heating power utilization control decision method and system - Google Patents
Pso-CNN-based regenerative electric heating power utilization control decision method and system Download PDFInfo
- Publication number
- CN114742410A CN114742410A CN202210380057.3A CN202210380057A CN114742410A CN 114742410 A CN114742410 A CN 114742410A CN 202210380057 A CN202210380057 A CN 202210380057A CN 114742410 A CN114742410 A CN 114742410A
- Authority
- CN
- China
- Prior art keywords
- electric heating
- type electric
- heat accumulating
- accumulating type
- cluster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005485 electric heating Methods 0.000 title claims abstract description 204
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000001172 regenerating effect Effects 0.000 title abstract description 8
- 238000013486 operation strategy Methods 0.000 claims abstract description 45
- 238000013507 mapping Methods 0.000 claims abstract description 44
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 42
- 238000004146 energy storage Methods 0.000 claims abstract description 40
- 230000006870 function Effects 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 238000013178 mathematical model Methods 0.000 claims abstract description 25
- 239000002245 particle Substances 0.000 claims abstract description 23
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 230000033228 biological regulation Effects 0.000 claims description 18
- 230000005611 electricity Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000009825 accumulation Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000005338 heat storage Methods 0.000 claims description 7
- 230000002068 genetic effect Effects 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 230000017525 heat dissipation Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 claims description 3
- 230000001737 promoting effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 238000005065 mining Methods 0.000 claims description 2
- 238000011217 control strategy Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000002787 reinforcement Effects 0.000 description 3
- 238000007599 discharging Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004138 cluster model Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010200 validation analysis Methods 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Power Engineering (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
Abstract
The invention relates to a Pso-CNN-based regenerative electric heating power utilization control decision method and a system, wherein the method comprises the following steps: step S1: collecting all heat accumulating type electric heating load data in the area, and clustering the data to obtain a clustering result; step S2: establishing a dynamic mathematical model of the heat accumulating type electric heating temperature and the heat accumulating type electric heating energy storage device, and determining model parameters; step S3: constructing an objective function to enable the objective function to meet a dynamic mathematical model and constraint conditions thereof; initializing each cluster operation strategy, calculating a target function value based on a particle swarm optimization algorithm, and iteratively optimizing the heat accumulating type electric heating operation strategy of each cluster; step S4: and (4) constructing a state information mapping curve graph, inputting the state information mapping curve graph into a convolutional neural network for learning, and predicting the heat accumulating type electric heating operation strategy of each clustering group in each period in the future. The method provided by the invention is based on historical data, solves the optimal operation strategy of heat accumulating type electric heating by using a Pso algorithm, and predicts the future power utilization control strategy by using a CNN.
Description
Technical Field
The invention relates to the field of electric control decision-making of heat accumulating type electric heating, in particular to a method and a system for electric control decision-making of heat accumulating type electric heating based on Pso-CNN.
Background
With the further improvement of the power system, the infrastructure and policy of 'coal to electricity' and the like are gradually perfected, and the interaction between the user side load and the power grid side is enhanced. The heat accumulating type electric heating device is a novel load, and can store electric energy by using the energy storage device when the demand of the load side is small at night and the wind-light output is large, and release the electric energy by using the energy storage device when the demand of the wind-light load side is large at day and the light-splitting output is relatively insufficient, so that the aims of cutting peaks and filling valleys, stabilizing load fluctuation and promoting new energy consumption are achieved.
The heat accumulating type electric heating is different from other energy storage devices, firstly, the comfort level of users needs to be met when the heat accumulating type electric heating participates in regulation and control, and secondly, the regulation and control capacity of the heat accumulating type electric heating needs to be considered and the control strategy dimensionality of the heat accumulating type electric heating needs to be optimized because the heat accumulating type electric heating is distributed in each user family. In addition, factors such as uncertainty of wind and light output and fluctuation of a load side need to be considered.
Under actual conditions, the accuracy of power prediction and load prediction is reduced along with the increase of prediction time, so that certain deviation can be generated between the current control strategy formulation based on prediction data and the actual situation, a large amount of calculation is needed in a two-stage optimization method in the current day, and the real-time performance of the control strategy cannot be met. In recent years, many scholars adopt a deep reinforcement learning method based on data driving to solve a complex optimization problem, and obtain an optimal charging and discharging plan based on an actual state without prior knowledge of a system. However, the heat accumulating type electric heating is distributed in a user family, the quantity is large, the types are different, dimension explosion can be generated when the deep reinforcement learning method is used for processing the problems, and the optimization problems can not be solved.
Disclosure of Invention
In order to solve the technical problems, the invention provides a regenerative electric heating power utilization control decision method and system based on Pso-CNN.
The power utilization control decision method for the heat accumulating type electric heating is suitable for being used in a high-proportion new energy grid-connected scene, all heat accumulating type electric heating in a certain area is regarded as adjustable loads, and other loads (such as televisions, refrigerators and the like) are regarded as background loads. When wind and light output, namely new energy output, is excessive compared with the electric quantity required by a user, the electric heating absorbs energy from the power grid, and the heat storage device is used for storing electric energy besides normal heat supply. When the wind power and the solar power are insufficient compared with the electric quantity required by a user, the electric heating stops absorbing energy from the power grid and releases electric energy by using the heat storage device. The method can promote the consumption of new energy and stabilize the fluctuation of load while ensuring the comfort of users in winter, and meanwhile, the users participating in the adjustment can reduce the electricity consumption cost.
The technical solution of the invention is as follows: a heat accumulating type electric heating power utilization control decision method based on Pso-CNN comprises the following steps:
step S1: collecting all heat accumulating type electric heating load data in an area, determining the clustering characteristics of the heat accumulating type electric heating load, and clustering the heat accumulating type electric heating load according to the clustering characteristics based on a K-means algorithm to obtain a clustering result;
step S2: establishing a heat accumulating type electric heating temperature dynamic model and a dynamic mathematical model of a heat accumulating type electric heating energy storage device, and determining a model parameter of each cluster according to the cluster result;
step S3: constructing an objective function to meet the dynamic model of the heat accumulating type electric heating temperature and the dynamic mathematical model of the heat accumulating type electric heating energy storage device and constraint conditions thereof; initializing each cluster operation strategy, calculating a target function value based on a particle swarm optimization algorithm, and iteratively optimizing the heat accumulating type electric heating operation strategy of each cluster;
step S4: and respectively constructing a mapping of new energy output and background load requirements, a mapping of heat accumulating type electric heating regulation and control capacity and a mapping curve of heat accumulating type electric heating state data, converting the mapping curves into corresponding images, inputting the images into a convolutional neural network, and predicting heat accumulating type electric heating operation strategies of each clustering cluster in each period of time in the future.
Compared with the prior art, the invention has the following advantages:
1. the invention discloses a Pso-CNN-based heat accumulating type electric heating power utilization control decision method, which aims to solve the problem of overlarge resident load control dimension, and provides the steps of clustering heat accumulating type electric heating with similar regulation capacity according to different characteristics, determining model parameters of each clustering cluster according to clustering results, and adopting the same power utilization control strategy for loads in each clustering cluster.
2. The invention solves the optimal operation strategy of heat accumulating type electric heating by using the user comfort level as the constraint condition and based on the optimization method of all known states.
3. The method maps the state information of the power grid and the cluster heat accumulating type electric heating load in each time period to an image, and then provides the image to a convolution neural network of 3 channels for learning a control strategy; in addition, the invention also introduces a prediction error, solves the problem that the prediction precision is reduced along with the lengthening of the prediction time when the power prediction and the load prediction are carried out at present, and is more suitable for the actual scene; the method starts from the perspective of maximally consuming new energy, takes the electric charge saved by the user as an evaluation index of a future power utilization control strategy predicted by a convolutional neural network, and solves the problem that a demand response method based on the electricity price information can generate a new load peak in a valley period.
Drawings
Fig. 1 is a flow chart of a regenerative electric heating power utilization control decision method based on Pso-CNN in an embodiment of the present invention;
FIG. 2 is a diagram illustrating a mapping between new energy output and background load requirements according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a mapping picture of the regulation and control capability of the heat accumulating type electric heating system in the embodiment of the invention;
fig. 4 is a schematic diagram of a mapping picture of a heat accumulating type electric heating state in the embodiment of the invention;
fig. 5 is a schematic diagram of an input picture of a CNN convolutional neural network in the embodiment of the present invention;
fig. 6 is a structural block diagram of an electric control decision system for regenerative electric heating based on Pso-CNN in an embodiment of the present invention.
Detailed Description
The invention provides a PSo-CNN-based heat accumulating type electric heating power utilization control decision method, which is characterized in that based on historical data, a particle swarm optimization Pso algorithm is utilized to solve an optimal operation strategy of heat accumulating type electric heating, and a CNN convolution neural network is utilized to learn and predict a future power utilization control strategy.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings.
Example one
As shown in fig. 1, an electric control decision method for regenerative electric heating based on Pso-CNN provided in an embodiment of the present invention includes the following steps:
step S1: collecting all heat accumulating type electric heating load data in the area, determining the clustering characteristics of the heat accumulating type electric heating loads, and clustering the heat accumulating type electric heating loads according to the clustering characteristics based on a K-means algorithm to obtain clustering results;
step S2: establishing a heat accumulating type electric heating temperature dynamic model and a dynamic mathematical model of a heat accumulating type electric heating energy storage device, and determining a model parameter of each cluster according to a cluster result;
step S3: constructing an objective function to meet a heat accumulating type electric heating temperature dynamic model, a heat accumulating type electric heating energy storage device dynamic mathematical model and constraint conditions thereof; initializing each cluster operation strategy, calculating a target function value based on a particle swarm optimization algorithm, and iteratively optimizing the heat accumulating type electric heating operation strategy of each cluster;
step S4: and respectively constructing a mapping of new energy output and background load requirements, a mapping of heat accumulating type electric heating regulation and control capacity and a mapping curve of heat accumulating type electric heating state data, converting the mapping curves into corresponding images, inputting the images into a convolutional neural network, and predicting heat accumulating type electric heating operation strategies of each cluster at each time interval in the future.
In one embodiment, the step S1: collecting all heat accumulating type electric heating load data in an area, determining the clustering characteristics of the heat accumulating type electric heating loads, clustering the heat accumulating type electric heating loads according to the clustering characteristics based on a K-means algorithm to obtain clustering results, and concretely comprising the following steps:
step S11: collecting all heat accumulating type electric heating load data in the region, and determining the clustering characteristics of the heat accumulating type electric heating load as follows:
energy storage capacity S of heat accumulation type electric heatingtorThe unit kw · h;
charging rated power P of heat accumulating type electric heating heat accumulation elementinUnit kw;
discharge rated power P of heat accumulating type electric heating heat accumulation elementoutUnit kw;
the electric heat conversion efficiency eta of the heat accumulating type electric heating system;
the heat accumulating type electric heating rated power P is in unit kw;
efficiency eta of heat accumulating type electric heating energy storage elementin；
Step S12: randomly initializing the clustering center and the number of central points of the heat accumulating type electric heating load data;
step S13: calculating the Euclidean distance from each point to a clustering center according to clustering characteristics based on a K-means algorithm so as to cluster the heat accumulating type electric heating loads;
step S14: calculating an evaluation index a according to formula (1) to evaluate the clustering result;
wherein n is the number of the clustering central points, CiThe quantity R of the heat accumulating type electric heating loads belonging to the ith class in the clustering resultiThe Euclidean distance from the data point farthest from the clustering center to the clustering center in the ith class, and m represents the number of the selected clustering features;
step S15: based on a elimination rule in a genetic algorithm, sorting the cluster clusters from large fitness to small fitness, eliminating the cluster clusters with the fitness smaller than a threshold value, generating a new cluster from two cluster clusters with the highest fitness, and randomly selecting a new cluster center and the number of central points;
step S16: and judging whether the preset iteration frequency is reached, if not, repeating the steps S13-S15, otherwise, finishing the iteration, and selecting the clustering result which enables the evaluation index a to be the maximum as the clustering result.
Through the step S1, the heat accumulating type electric heating loads in the region are analyzed and clustered, the heat accumulating type electric heating loads with similar adjusting capacity are classified into the same cluster, and a uniform heat accumulating type electric heating operation strategy is adopted for each cluster.
In one embodiment, the step S2: establishing a heat accumulating type electric heating temperature dynamic model and a heat accumulating type electric heating energy storage device dynamic mathematical model, and determining the model parameters of each cluster according to the cluster result, wherein the method specifically comprises the following steps:
step S21: establishing a heat accumulating type electric heating temperature dynamic mathematical model as shown in a formula (2):
wherein, Tin(T) is the user's indoor temperature at time T, Tout(t) is the outdoor temperature at the moment t, delta is the heat dissipation coefficient of the user house, gamma is the temperature rise coefficient of the user house, and P (t) is the power absorbed by the heat accumulating type electric heating from the power grid at the moment t; pa(t) is the charging power of the heat accumulating type electric heating energy storage element at t moment, Pr(t) is the discharge power of the heat accumulating type electric heating energy storage element at the moment t; Δ t represents the duration of a time period, e.g., 24 × 60/96 if 24 hours a day is divided into 96 segments; the lambda value is 0 or 1, which indicates that the heat accumulating type electric mining and energy storing device can only take one action in the same time period, namely a discharging or charging action;
step S22: establishing a dynamic mathematical model of the heat accumulating type electric heating energy storage device, as shown in formula (3):
wherein S (t) is the energy stored by the heat accumulating type electric heating energy storage element at the time t, and mu is the heat dissipation coefficient of the heat accumulating type electric heating energy storage device per se;
step S23: according to the clustering result, determining the mathematical model parameter of each clustering cluster, as shown in formula (4):
wherein Q is a mathematical model parameter of the cluster, b is the number of heat accumulating type electric heating in the cluster, and Q isiPooling for the ith clusterModel parameters of thermal electric heating load.
In one embodiment, the step S3: constructing an objective function to meet a heat accumulating type electric heating temperature dynamic model, a heat accumulating type electric heating energy storage device dynamic mathematical model and constraint conditions thereof; initializing each cluster operation strategy, calculating a target function value based on a particle swarm optimization algorithm, and iteratively optimizing the heat accumulating type electric heating operation strategy of each cluster, wherein the strategy specifically comprises the following steps:
step S31: dividing 1 day into k time periods, and obtaining the difference value P between the output of new energy and the demand of the heat accumulating type electric heating load in each time period based on historical datavalAs shown in equation (5):
Pval(i)＝Pnew(i)-Pload(i) (5)
wherein P isnew(i) Is the output of new energy in the ith period, Pload(i) Demand for background load for the ith time period;
according to PvalAnd initializing the heat accumulating type electric heating operation strategy at the value of the time interval i as follows:
when new energy overflows, i.e. Pval(i)>0, order P (i)>0、Pa(i)＝0.5Pin、Pr(i)＝0；
When new energy is deficient, i.e. Pval(i)<0, let P (i) equal to 0, Pa(i)＝0、Pr(i)＝0.5Pout；
Wherein, P (i) the power absorbed by the heat accumulating type electric heating from the power grid in the ith period, Pa(i) For charging power, P, of the heat accumulating type electric heating energy storage device in the ith periodr(i) The discharge power of the heat accumulating type electric heating energy storage device is the ith time period;
in the embodiment of the present invention, one day is divided into 96 periods, i.e., k is 96;
step S32: the constraint conditions of the optimization equations (2) to (3) are set as shown in equations (6) to (10):
0.1Stor<S(t)<0.9Stor (6)
0≤Pa(t)<Pin (7)
0≤Pr(t)<Pout (8)
Tset-△t≤Tin(t)<Tset+△t (9)
λ 0 or λ 1 (10)
Wherein, TsetIs an indoor temperature value set by a user;
step S33: updating the total demand of background load of each time period according to the power utilization strategy of each cluster heat accumulation type electric heating of each time period, as shown in a formula (11):
Pload(i)＝Pload(i)+P(i) (11)
step S34: an objective function in a peak clipping and valley filling scene is set, as shown in formula (12):
wherein, Pload(i) The power requirement of the background load in the ith time period is shown, and k is the number of the time periods;
setting an objective function in a scene of promoting new energy consumption, as shown in equation (13):
wherein, Pnew(i) The output of new energy in the ith time period;
step S35: according to the power utilization strategy of each cluster heat accumulation type electric heating in each time period, the indoor temperature T of the user in each stage is calculated according to the formulas (2) and (3)inAnd the heat accumulating type electric heating energy storage capacity StorIf the constraint conditions (6) and (9) are not satisfied, adding penalty terms M1 and M2 to the objective function, as shown in equations (14) to (15):
step S36: solving a heat accumulating type electric heating operation strategy based on a particle swarm optimization algorithm, comprising the following steps of:
1) initialization particles P (i), Pa(i)、Pr(i) Obtaining an initial heat accumulating type electric heating operation strategy and generating an initial search speed V, Vr、Va；
2) Calculating objective function values of all clustering groups to obtain initial historical optimal points and global optimal points; the historical optimal point is an optimal point in each particle swarm, and the global optimal point is an optimal point in all the particle swarms;
3) updating the velocity and position of each particle as shown in equations (16) to (17):
P＝P+V (16)
P＝ω*P+c1*rand()*(Pbest-P)+c2*rand()*(Gbest-p) (17)
wherein P represents P (i), Pa(i)、Pr(i) And V represents V, Vr、Va(ii) a Omega is the inertia factor, c1、c2As a learning factor, PbestFor the particle history optimum, GbestIs a global optimum point; rand () is a random function;
4) calculating an objective function value of each particle, and updating a historical optimal point and a global optimal point of each particle;
5) judging whether the iteration times are reached, if the iteration times are the maximum, stopping iteration, and outputting a global optimal point as a heat accumulating type electric heating operation strategy; and if the maximum iteration times are not reached, repeating the steps 3) to 5).
Through the steps, the embodiment of the invention solves the problem of the optimal operation strategy of the heat accumulating type electric heating based on the historical dataThe problem is regarded as an optimization problem rather than an interaction process with the environment, so that a particle swarm optimization algorithm is adopted rather than a reinforcement learning algorithm, the solving process is simplified, and the operation strategy of each cluster heat accumulating type electric heating in each time period is obtained and comprises three parts, namely [ P (i), P: (P (i) ]a(i)，Pr(i)]The heat storage type heat storage medium is input into a CNN network for learning and can predict the heat storage type of a future period
And (4) an optimal strategy for electric heating operation.
In one embodiment, the step S4: respectively constructing a mapping graph of new energy output and background load requirements, a mapping graph of heat accumulating type electric heating regulation and control capacity and a mapping graph of heat accumulating type electric heating state data, converting the mapping graphs into corresponding images, inputting the images into a convolutional neural network, and predicting heat accumulating type electric heating operation strategies of each cluster at each time period in the future, wherein the mapping graph specifically comprises the following steps:
s41: respectively constructing a mapping of new energy output and background load requirements, a mapping of heat accumulating type electric heating regulation and control capacity and a mapping curve chart of heat accumulating type electric heating state data, converting the curve chart into pictures, and dividing the pictures into a training set and a verification set according to a preset proportion, wherein the method comprises the following steps:
1) constructing a graph of the mapping of the new energy output and the background load demand, and drawing a curve P according to the following formula (18)val:
Pval＝Pnew-Pload (18)
In the embodiment of the present invention, in order to completely reflect all the state information, the image should include new energy output data and background load demand data in the next 24 hours, that is, in 96 time periods, and the size of the image is set to 96 × 96. The image adopts a binarization method, namely when the curve passes through the pixel point, the weight of the pixel point is 255, if the curve does not pass through the pixel point, the weight of the pixel is 0, and in consideration of the problem that the prediction precision is reduced along with the increase of the prediction time, the embodiment of the invention introduces an error function ferror，ferrorIs a function of a randomly generated mean value alpha and a variance delta, wherein delta is a constant value, and alpha increases with the increase of the prediction timeLarge, two new curves are generated
As shown in equations (19) to (20):
Curve
enclosing into a region, wherein the weight of the pixel points in the region is set to be 127;
as shown in fig. 2, a diagram of a mapping between new energy output and background load demand is constructed.
2) The regulation and control capability of the heat accumulating type electric heating is related to the cluster type thereof, so that the codes corresponding to the type are set as the weight of the image, as shown in fig. 3.
3) The heat accumulating type electric heating state data mainly comprises the indoor temperature T of a userinUser-set temperature TsetOutdoor temperature ToutThe state of charge Soc of the energy storage element, dividing the 96 × 96 image into four regions with the size of 48 × 48, each region mapping one item of information, as shown in fig. 4;
4) taking the pictures as a unit of day according to the weight ratio of 7: 3 into a training set and a validation set.
S42: training the convolutional neural network by using a training set, optimizing the convolutional neural network based on a genetic algorithm, predicting a heat accumulating type electric heating operation strategy of each clustering cluster in each period in the future, and verifying an output result on a verification set according to the additional consumption of new energy and the electric charge saved by a user as indexes, wherein the method comprises the following steps:
1) on a training set, superposing the three mapping pictures to obtain an input picture shown in fig. 5, inputting the input picture into a 3-channel CNN (convolutional neural network), and optimizing the structure of the CNN convolutional neural network through a genetic algorithm, wherein optimized hyper-parameters comprise the number of convolutional kernels, the type of an activation function, the number of hidden layer layers and the number of hidden layer neurons, and an optimized target function is a loss value;
2) evaluating the output prediction result of the CNN network based on a verification set, wherein evaluation indexes comprise: additional consumption W of new energynewAnd the electricity cost M saved at the user sideelecAs shown in equations (21) to (22):
Wnew＝Wreg-Wnor (21)
wherein, WregShows the consumption of new energy after the heat accumulating type electric heating participates in the regulation and control, WnorShows that the heat accumulating type electric heating does not participate in regulating and controlling the consumption of new energy, Mnor(i) Represents the electricity consumption cost required by the heat accumulating type electric heating cluster i not participating in regulation and control, Mreg(i) And (4) representing the electricity consumption cost required by the participation of the heat accumulating type electric heating cluster i in regulation and control.
The invention discloses a Pso-CNN-based heat accumulating type electric heating power utilization control decision method, which aims to solve the problem of overlarge resident load control dimension, and provides the steps of clustering heat accumulating type electric heating with similar regulation capacity according to different characteristics, determining model parameters of each clustering cluster according to clustering results, and adopting the same power utilization control strategy for loads in each clustering cluster. The invention solves the optimal operation strategy of heat accumulating type electric heating by using the user comfort level as the constraint condition and based on the optimization method of all known states. The method maps the state information of the power grid and the cluster heat accumulating type electric heating load in each time period to an image, and then provides the image to a convolution neural network of 3 channels for learning a control strategy; in addition, the invention also introduces a prediction error, solves the problem that the prediction precision is reduced along with the lengthening of the prediction time when the power prediction and the load prediction are carried out at present, and is more suitable for the actual scene; the method starts from the perspective of maximally consuming new energy, takes the electric charge saved by the user as an evaluation index of a future power utilization control strategy predicted by a convolutional neural network, and solves the problem that a demand response method based on the electricity price information can generate a new load peak in a valley period.
Example two
As shown in fig. 6, an embodiment of the present invention provides an electricity control decision system for regenerative electric heating based on Pso-CNN, including the following modules:
the load clustering module 51 is used for collecting all heat accumulating type electric heating load data in the region, determining the clustering characteristics of the heat accumulating type electric heating loads, and clustering the heat accumulating type electric heating loads according to the clustering characteristics based on a K-means algorithm to obtain a clustering result;
the dynamic model establishing module 52 is used for establishing a heat accumulating type electric heating temperature dynamic model and a dynamic mathematical model of a heat accumulating type electric heating energy storage device, and determining a model parameter of each clustering cluster according to a clustering cluster result;
the operation strategy obtaining module 53 is used for constructing a target function so as to meet a heat accumulating type electric heating temperature dynamic model, a heat accumulating type electric heating energy storage device dynamic mathematical model and constraint conditions thereof; initializing each cluster operation strategy, calculating a target function value based on a particle swarm optimization algorithm, and iteratively optimizing the heat accumulating type electric heating operation strategy of each cluster;
and the prediction future operation strategy module 54 is used for respectively constructing a mapping of new energy output and background load requirements, a mapping of heat accumulating type electric heating regulation and control capacity and a mapping curve of heat accumulating type electric heating state data, converting the mapping curves into corresponding images, inputting the images into a convolutional neural network, and predicting the heat accumulating type electric heating operation strategy of each cluster at each period in the future.
The above examples are provided only for the purpose of describing the present invention, and are not intended to limit the scope of the present invention. The scope of the invention is defined by the appended claims. Various equivalent substitutions and modifications can be made without departing from the spirit and principles of the invention, and are intended to be within the scope of the invention.
Claims (6)
1. A heat accumulating type electric heating power utilization control decision method based on Pso-CNN is characterized by comprising the following steps:
step S1: collecting all heat accumulating type electric heating load data in an area, determining the clustering characteristics of the heat accumulating type electric heating loads, and clustering the heat accumulating type electric heating loads according to the clustering characteristics based on a K-means algorithm to obtain clustering results;
step S2: establishing a heat accumulating type electric heating temperature dynamic model and a heat accumulating type electric heating energy storage device dynamic mathematical model, and determining the model parameters of each cluster according to the cluster results;
step S3: constructing an objective function to meet the dynamic model of the heat accumulating type electric heating temperature and the dynamic mathematical model of the heat accumulating type electric heating energy storage device and constraint conditions thereof; initializing each cluster operation strategy, calculating a target function value based on a particle swarm optimization algorithm, and iteratively optimizing the heat accumulating type electric heating operation strategy of each cluster;
step S4: and respectively constructing a mapping of new energy output and background load requirements, a mapping of heat accumulating type electric heating regulation and control capacity and a mapping curve of heat accumulating type electric heating state data, converting the mapping curves into corresponding images, inputting the images into a convolutional neural network, and predicting heat accumulating type electric heating operation strategies of each clustering cluster in each period of time in the future.
2. The electric control decision method for heat accumulating type electric heating based on Pso-CNN as claimed in claim 1, wherein the step S1: collecting all heat accumulating type electric heating load data in an area, determining the clustering characteristics of the heat accumulating type electric heating load, clustering the heat accumulating type electric heating load according to the clustering characteristics based on a K-means algorithm to obtain a clustering result, and specifically comprising the following steps:
step S11: collecting all heat accumulating type electric heating load data in an area, and determining the clustering characteristics of the heat accumulating type electric heating load as follows:
energy storage capacity S of heat accumulation type electric heatingtorThe unit kw · h;
charging rated power P of heat accumulating type electric heating heat accumulation elementinThe unit kw;
discharge rated power P of heat accumulating type electric heating heat accumulating elementoutUnit kw;
the electric heat conversion efficiency eta of the heat accumulating type electric heating system;
the heat accumulating type electric heating rated power P is in unit kw;
efficiency eta of heat accumulating type electric heating energy storage elementin；
Step S12: randomly initializing the cluster centers and the number of central points of the heat accumulating type electric heating load data;
step S13: based on a K-means algorithm, according to the clustering characteristics, calculating Euclidean distances from each point to a clustering center so as to cluster the heat accumulating type electric heating loads;
step S14: calculating an evaluation index a according to formula (1) to evaluate the clustering result;
wherein n is the number of the clustering central points, CiThe quantity of the heat accumulating type electric heating loads belonging to the ith class in the clustering result, RiThe Euclidean distance from the data point farthest from the clustering center to the clustering center in the ith class is defined, and m represents the number of the selected clustering features;
step S15: based on a elimination rule in a genetic algorithm, sorting the cluster clusters from large fitness to small fitness, eliminating clusters with fitness smaller than a threshold value, generating a new cluster from two cluster clusters with highest fitness, and randomly selecting new cluster centers and the number of central points;
step S16: and judging whether the preset iteration frequency is reached, if not, repeating the steps S13-S15, otherwise, finishing the iteration, and selecting the clustering result which enables the evaluation index a to be the maximum as a clustering result.
3. The Pso-CNN-based heat storage type electric heating power utilization control decision method according to claim 2, wherein the step S2: establishing a heat accumulating type electric heating temperature dynamic model and a heat accumulating type electric heating energy storage device dynamic mathematical model, and determining the model parameters of each cluster according to the cluster results, wherein the heat accumulating type electric heating temperature dynamic model specifically comprises the following steps:
step S21: establishing a heat accumulating type electric heating temperature dynamic mathematical model as shown in a formula (2):
wherein, Tin(T) is the user's indoor temperature at time T, Tout(t) is the outdoor temperature at the moment t, delta is the heat dissipation coefficient of a user house, gamma is the temperature rise coefficient of the user house, and P (t) is the power absorbed by the heat accumulating type electric heating from the power grid at the moment t; p isa(t) is the charging power of the heat accumulating type electric heating energy storage element at t moment, Pr(t) is the discharge power of the heat accumulating type electric heating energy storage element at the moment t; Δ t represents the duration of a time period; the lambda value is 0 or 1, which indicates that the heat accumulating type electric mining energy storage device can only take one action in the same time period;
step S22: establishing a dynamic mathematical model of the heat accumulating type electric heating energy storage device, as shown in formula (3):
wherein, S (t) is the energy stored by the heat accumulating type electric heating energy storage element at the moment t, and mu is the self heat dissipation coefficient of the heat accumulating type electric heating energy storage device;
step S23: determining mathematical model parameters of each clustering cluster according to the clustering result, as shown in formula (4):
wherein Q is a mathematical model parameter of the cluster, n is the number of heat accumulating type electric heating in the cluster, and Q isiAnd the model parameters are the model parameters of the heat accumulating type electric heating load of the ith cluster.
4. The electric control decision method for heat accumulating type electric heating based on Pso-CNN as claimed in claim 3, wherein the step S3: constructing an objective function to meet the dynamic model of the heat accumulating type electric heating temperature and the dynamic mathematical model of the heat accumulating type electric heating energy storage device and constraint conditions thereof; initializing each cluster operation strategy, calculating an objective function value based on a particle swarm optimization algorithm, and iteratively optimizing the heat storage type electric heating operation strategy of each cluster, specifically comprising the following steps:
step S31: dividing 1 day into k time periods, and obtaining a difference value P between the output of new energy and the demand of the heat accumulating type electric heating load in each time period based on historical datavalAs shown in equation (5):
Pval(i)＝Pnew(i)-Pload(i) (5)
wherein P isnew(i) Is the output of new energy in the ith period, Pload(i) Demand for background load for the ith time period;
according to PvalAnd initializing the heat accumulating type electric heating operation strategy at the value of the time interval i as follows:
if Pval(i)>0, order P (i)>0、Pa(i)＝0.5Pin、Pr(i)＝0；
If Pval(i)<0, let P (i) equal to 0, Pa(i)＝0、Pr(i)＝0.5Pout；
Wherein, P (i) the power absorbed by the heat accumulating type electric heating from the power grid in the ith period, Pa(i) Charging power, P, of the heat accumulating type electric heating energy storage device in the ith time periodr(i) The discharge power of the heat accumulating type electric heating energy storage device is the ith time period;
step S32: the constraint conditions of the optimization equations (2) to (3) are set as shown in equations (6) to (10):
0.1Stor<S(t)<0.9Stor (6)
0≤Pa(t)<Pin (7)
0≤Pr(t)<Pout (8)
Tset-△t≤Tin(t)<Tset+△t (9)
λ 0 or λ 1 (10)
Wherein, TsetIs an indoor temperature value set by a user;
step S33: updating the total demand of the background load in each time period according to the power utilization strategy of each cluster heat accumulating type electric heating in each time period, as shown in a formula (11):
Pload(i)＝Pload(i)+P(i) (11)
step S34: setting an objective function in a peak clipping and valley filling scene as shown in formula (12):
wherein, Pload(i) The power requirement of the background load in the ith time period is defined, and k is the number of the time periods;
setting an objective function in a scene of promoting new energy consumption, as shown in equation (13):
wherein, Pnew(i) The output of new energy in the ith time period;
step S35: according to the electricity utilization strategy of each cluster heat accumulating type electric heating in each time period, the indoor temperature T of the user in each stage is calculated according to the formulas (2) and (3)inAnd the heat accumulating type electric heating energy storage capacity StorIf the constraint conditions (6) and (9) are not satisfied, adding a penalty term to the objective functionM1 and M2 are represented by the following formulas (14) to (15):
step S36: solving a heat accumulating type electric heating operation strategy based on a particle swarm optimization algorithm, comprising the following steps of:
1) initialization of P (i), Pa(i)、Pr(i) Obtaining an initial heat accumulating type electric heating operation strategy and generating an initial search speed V, Vr、Va；
2) Calculating objective function values of all the cluster groups to obtain initial historical optimal points and global optimal points;
3) updating the velocity and position of each particle as shown in equations (16) to (17):
P＝P+V (16)
P＝ω*P+c1*rand()*(Pbest-P)+c2*rand()*(Gbest-p) (17)
wherein P represents P (i), Pa(i)、Pr(i) And V represents V, Vr、Va(ii) a Omega is the inertia factor, c1、c2As a learning factor, PbestFor the particle history optimum, GbestIs a global optimum point; rand () is a random function;
4) calculating an objective function value of each particle, and updating a historical optimal point and a global optimal point of each particle;
5) judging whether the iteration times are reached, if the iteration times are the maximum, stopping iteration, and outputting a global optimal point as a heat accumulating type electric heating operation strategy; and if the maximum iteration times are not reached, repeating the steps 3) to 5).
5. The electric control decision method for heat accumulating type electric heating based on Pso-CNN as claimed in claim 3, wherein the step S4: respectively constructing a mapping graph of new energy output and background load requirements, a mapping graph of heat accumulating type electric heating regulation and control capacity and a mapping graph of heat accumulating type electric heating state data, converting the mapping graphs into corresponding images, inputting the images into a convolutional neural network, and predicting heat accumulating type electric heating operation strategies of each cluster at each time period in the future, wherein the method specifically comprises the following steps of:
s41: respectively constructing a mapping of new energy output and background load requirements, a mapping of heat accumulating type electric heating regulation and control capacity and a mapping curve of heat accumulating type electric heating state data, converting the curve into pictures, and dividing the pictures into a training set and a verification set according to a preset proportion;
s42: and training the convolutional neural network by using the training set, optimizing the convolutional neural network based on a genetic algorithm, predicting the heat accumulating type electric heating operation strategy of each clustering cluster in each period in the future, and verifying an output result on the verification set according to the additional consumption of new energy and the electric charge saved by a user as indexes.
6. A heat accumulating type electric heating power utilization control decision system based on Pso-CNN is characterized by comprising the following modules:
the load clustering module is used for collecting all heat accumulating type electric heating load data in an area, determining the clustering characteristics of the heat accumulating type electric heating loads, and clustering the heat accumulating type electric heating loads according to the clustering characteristics based on a K-means algorithm to obtain a clustering result;
the dynamic model establishing module is used for establishing a heat accumulating type electric heating temperature dynamic model and a dynamic mathematical model of a heat accumulating type electric heating energy storage device, and determining a model parameter of each cluster according to the cluster result;
the method comprises the steps that an operation strategy module is obtained and used for constructing a target function to enable the target function to meet a dynamic model of the heat accumulating type electric heating temperature and a dynamic mathematical model of a heat accumulating type electric heating energy storage device and constraint conditions of the dynamic model and the dynamic mathematical model; initializing each cluster operation strategy, calculating a target function value based on a particle swarm optimization algorithm, and iteratively optimizing the heat accumulating type electric heating operation strategy of each cluster;
and the prediction future operation strategy module is used for respectively constructing a mapping of new energy output and background load requirements, a mapping of heat accumulating type electric heating regulation and control capacity and a mapping curve of heat accumulating type electric heating state data, converting the mapping curves into corresponding images, inputting the images into a convolutional neural network, and predicting the heat accumulating type electric heating operation strategy of each cluster in each period in the future.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210380057.3A CN114742410A (en) | 2022-04-12 | 2022-04-12 | Pso-CNN-based regenerative electric heating power utilization control decision method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210380057.3A CN114742410A (en) | 2022-04-12 | 2022-04-12 | Pso-CNN-based regenerative electric heating power utilization control decision method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114742410A true CN114742410A (en) | 2022-07-12 |
Family
ID=82282198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210380057.3A Pending CN114742410A (en) | 2022-04-12 | 2022-04-12 | Pso-CNN-based regenerative electric heating power utilization control decision method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114742410A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117154740A (en) * | 2023-10-31 | 2023-12-01 | 国网浙江省电力有限公司宁波供电公司 | Load regulation and control method and device for heat accumulating type electric heating participating power distribution network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107665384A (en) * | 2017-10-27 | 2018-02-06 | 天津大学 | A kind of electric power heating power integrated energy system dispatching method of the energy source station containing multizone |
| CN112671831A (en) * | 2020-12-02 | 2021-04-16 | 华电电力科学研究院有限公司 | Multistage application system for digital intelligent heat supply platform of large group company |
| WO2021108680A1 (en) * | 2019-11-25 | 2021-06-03 | Strong Force Iot Portfolio 2016, Llc | Intelligent vibration digital twin systems and methods for industrial environments |
| CN113864854A (en) * | 2021-10-12 | 2021-12-31 | 华北电力大学 | Multi-objective optimization method and system for heat accumulating type electric heating to participate in wind power consumption |
| CN114169236A (en) * | 2021-12-03 | 2022-03-11 | 国网新疆电力有限公司昌吉供电公司 | Phase-change heat storage type electric heating negative control system control method based on LSTM algorithm |
-
2022
- 2022-04-12 CN CN202210380057.3A patent/CN114742410A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107665384A (en) * | 2017-10-27 | 2018-02-06 | 天津大学 | A kind of electric power heating power integrated energy system dispatching method of the energy source station containing multizone |
| WO2021108680A1 (en) * | 2019-11-25 | 2021-06-03 | Strong Force Iot Portfolio 2016, Llc | Intelligent vibration digital twin systems and methods for industrial environments |
| CN112671831A (en) * | 2020-12-02 | 2021-04-16 | 华电电力科学研究院有限公司 | Multistage application system for digital intelligent heat supply platform of large group company |
| CN113864854A (en) * | 2021-10-12 | 2021-12-31 | 华北电力大学 | Multi-objective optimization method and system for heat accumulating type electric heating to participate in wind power consumption |
| CN114169236A (en) * | 2021-12-03 | 2022-03-11 | 国网新疆电力有限公司昌吉供电公司 | Phase-change heat storage type electric heating negative control system control method based on LSTM algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 杨桂兴 等: "面向广域分布的家庭蓄热式电采暖集群控制方法", 《电力自动化设备》, vol. 43, no. 8, 23 March 2023 (2023-03-23), pages 56 - 62 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117154740A (en) * | 2023-10-31 | 2023-12-01 | 国网浙江省电力有限公司宁波供电公司 | Load regulation and control method and device for heat accumulating type electric heating participating power distribution network |
| CN117154740B (en) * | 2023-10-31 | 2024-01-26 | 国网浙江省电力有限公司宁波供电公司 | Load regulation and control method and device for heat accumulating type electric heating participating power distribution network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113394817A (en) | Multi-energy capacity optimal configuration method of wind, light, water and fire storage system | |
| CN107451686B (en) | Micro-grid energy optimization method of genetic algorithm considering random prediction error | |
| CN111525601A (en) | Charging and discharging control method and device for user side energy storage equipment and storage medium | |
| Welch et al. | Energy dispatch fuzzy controller for a grid-independent photovoltaic system | |
| CN117498400B (en) | Distributed photovoltaic and energy storage data processing method and system | |
| CN113794199B (en) | Maximum benefit optimization method of wind power energy storage system considering electric power market fluctuation | |
| CN110707711B (en) | User side comprehensive energy system hierarchical regulation and control method and system | |
| CN116628972A (en) | Heat supply system control method for industrial waste heat integrated heat supply network based on predictive model | |
| CN114742410A (en) | Pso-CNN-based regenerative electric heating power utilization control decision method and system | |
| CN116826710A (en) | Peak clipping strategy recommendation method and device based on load prediction and storage medium | |
| CN113469412A (en) | Real-time operation strategy optimization method and system for comprehensive energy system | |
| CN116191508A (en) | Energy storage-containing active power distribution network economic operation optimization method considering wind and light output | |
| CN113991640B (en) | Thermal power-based multi-energy complementary energy base energy configuration planning method | |
| CN111951123B (en) | Method and device for controlling electrical load, computer equipment and storage medium | |
| CN117424204B (en) | Source-network-load-storage collaborative planning method considering source-load uncertainty | |
| Welch et al. | Comparison of two optimal control strategies for a grid independent photovoltaic system | |
| CN113393085B (en) | Cluster dividing method considering flexibility supply and demand balance and response speed | |
| CN114977166A (en) | Optimization method for day-ahead-day two-stage power reporting of wind-storage station | |
| CN114398748A (en) | Electric heat storage device planning method and system based on hydraulic calculation and double-layer optimization | |
| CN109950920B (en) | Photovoltaic station side electrochemical energy storage charging and discharging plan making method based on dynamic programming algorithm | |
| CN118232369B (en) | User side energy storage control method and system based on multi-objective solution | |
| CN114742449B (en) | Electric automobile grouping scheduling method based on priority weight coefficient | |
| CN117541384B (en) | Construction method and device of electric energy transaction model, computer equipment and storage medium | |
| CN114430177B (en) | Heterogeneous electric automobile aggregation management and control method and system | |
| CN118589523A (en) | Method, device, computer equipment and storage medium for optimizing private variable multiple load |
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 |