CN114580298A - RBF-ISBO-based microgrid optimization scheduling method and system - Google Patents

RBF-ISBO-based microgrid optimization scheduling method and system Download PDF

Info

Publication number
CN114580298A
CN114580298A CN202210240896.5A CN202210240896A CN114580298A CN 114580298 A CN114580298 A CN 114580298A CN 202210240896 A CN202210240896 A CN 202210240896A CN 114580298 A CN114580298 A CN 114580298A
Authority
CN
China
Prior art keywords
microgrid
equipment
power generation
grid
micro
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.)
Withdrawn
Application number
CN202210240896.5A
Other languages
Chinese (zh)
Inventor
于军琪
薛志璐
赵安军
虎群
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian University of Architecture and Technology
Original Assignee
Xian University of Architecture and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian University of Architecture and Technology filed Critical Xian University of Architecture and Technology
Priority to CN202210240896.5A priority Critical patent/CN114580298A/en
Publication of CN114580298A publication Critical patent/CN114580298A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
    • H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected networks
    • 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
    • H02J3/28—Arrangements for balancing of the load in a network by storage of energy
    • H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/04—Power grid distribution networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
    • 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]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/10—The dispersed energy generation being of fossil origin, e.g. diesel generators
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/22—The renewable source being solar energy
    • H02J2300/24—The renewable source being solar energy of photovoltaic origin
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/28—The renewable source being wind energy
    • 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)
  • Power Engineering (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention discloses a RBF-ISBO-based microgrid optimization scheduling method and system, which are used for constructing a microgrid system by taking the economic benefit and carbon reduction of the microgrid as targets; the method comprises the steps that an RBF neural network is adopted to carry out equipment modeling on renewable energy in a micro-grid system to obtain an equipment model; the method comprises the steps that with the minimum power generation cost of the micro-grid as an optimization target, on the premise that the constraint conditions of rated output power of wind-solar power generation, a diesel generator and energy storage equipment of the micro-grid are met, an equipment model established by the RBF neural network is optimized by using an improved SBO algorithm to obtain a power supply combination of micro-grid equipment; according to the power supply combination of the micro-grid equipment, the corresponding power generation cost of the micro-grid is calculated, sequencing is carried out according to the power generation cost, the optimal power supply combination is found out, so that the power generation cost of the micro-grid equipment is the minimum, and optimal scheduling of the micro-grid is realized. After ISBO optimized scheduling is adopted, the power generation cost of the micro-grid is reduced by 16.7% -21.2%, and the micro-grid has better convergence and robustness.

Description

RBF-ISBO-based microgrid optimization scheduling method and system
Technical Field
The invention belongs to the technical field of microgrid scheduling, and particularly relates to a microgrid optimization scheduling method and a microgrid optimization scheduling system based on RBF-ISBO.
Background
In recent years, with the increasing demand for electric power, the rising cost of conventional power generation, and the decreasing cost of power generation by renewable energy, renewable energy has received more and more extensive attention, especially to a new power grid represented by a microgrid. Besides the consideration of the power generation cost, the environmental friendliness of renewable energy power generation and the rapid development of the concept of the microgrid make the problem of optimizing and scheduling the energy of the microgrid a very valuable research topic.
At present, the basis of energy optimization scheduling of a microgrid is to establish an optimization model of each device. Common renewable resource device models have a physics model, a parameter identification model, and a machine learning model. However, the mechanism model has the defects of strong dependence and complexity on the intrinsic physical laws of equipment variables, so that the actual operation state of the equipment cannot be well reflected. The renewable energy power generation is greatly influenced by weather parameters, the characteristics of obvious uncertainty and intermittence exist, and the fixed parameter model established through parameter identification has obvious inadaptability. In contrast, machine learning models with few model parameters, high generalization capability, and ease of use are often used to model renewable energy power generation. Meanwhile, due to uncertainty of the scheduling essence of the microgrid and uncertainty of dynamic market quotation and demand curves, how to optimize the scheduling of the microgrid equipment is the key to realize the optimal economy of the microgrid. The intelligent algorithm adopted in the prior art does not combine the characteristics of the microgrid equipment model, the calculation process is complex and time-consuming, and the overall optimization of the microgrid is difficult to realize.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a micro-grid optimized scheduling method and system based on RBF-ISBO aiming at the defects in the prior art, so as to solve the problems that the uncertainty in the operation of a micro-grid system is obviously increased and an equipment model is difficult to dynamically adjust along with the load demand and meteorological change, and simultaneously solve the technical problems of poor robustness and poor optimization effect in the prior art.
The invention adopts the following technical scheme:
a micro-grid optimization scheduling method based on RBF-ISBO comprises the following steps:
s1, aiming at economic benefit and carbon reduction of the microgrid, selecting a wind turbine and a photovoltaic panel as power supply equipment, and forming the microgrid system by adopting the photovoltaic panel, the wind turbine, a diesel generator, a power distribution network and energy storage equipment;
s2, taking temperature, humidity, solar radiation degree, last-moment generating power and wind speed as input variables of the photovoltaic panel of the microgrid, taking temperature, humidity, air pressure, last-moment generating power and wind speed as input variables of a wind turbine, and carrying out equipment modeling on renewable energy in the microgrid system constructed in the step S1 by adopting an RBF neural network to obtain an equipment model;
s3, with the minimum power generation cost of the micro-grid as an optimization target, optimizing the power generation power output by the equipment model established by the RBF neural network in the step S2 by using an improved SBO algorithm on the premise of meeting the constraint conditions of the rated output power of the micro-grid wind-solar power generation, the diesel generator and the energy storage equipment to obtain the power supply combination of the micro-grid equipment;
and S4, calculating the corresponding power generation cost of the micro-grid according to the power supply combination of the micro-grid equipment obtained in the step S3, sequencing according to the power generation cost, finding out the optimal power supply combination to enable the power generation cost of the micro-grid equipment to be the minimum, and realizing optimized scheduling of the micro-grid.
Specifically, in step S2, the modeling of the renewable energy device in the microgrid system by using the RBF neural network specifically includes:
s201, performing standardization processing on historical data of renewable energy equipment;
s202, taking a factor x with high equipment power generation correlation as the input of the RBF neural network, and taking equipment power generation power Y as the output of the RBF neural network;
s203, introducing a Gaussian function as an activation function into a hidden layer of the RBF neural network, converting a nonlinear function into a high-dimensional linear separable space, and obtaining the number n of neurons of the hidden layer by a grid search method;
and S204, calculating by using the activation function obtained in the step S203 to obtain the output of the linear combination hidden node, and outputting the generated power Y of each power supply device when the network parameters tend to be stable and the output error is minimum.
Further, in step S203, the activation function Φ (x, ρ) is:
Figure BDA0003541569190000031
wherein x is a factor vector with high equipment power generation correlation; rho is the center of the RBF neuron;
Figure BDA0003541569190000032
a transfer function for the RBF neuron; σ is the smoothness of the transfer function.
Further, in step S204, the output Y of the linear combination hidden node is calculated as follows:
Figure BDA0003541569190000033
wherein n is the number of hidden layers of the RBF neural network; w is a0Bias parameters in the output layer that allow adjustment of neuron sensitivity; w is aiThe connection weight of the hidden layer and the output layer is x, and the factor vector with high equipment power generation correlation is x; ρ is the center of the RBF neuron.
Specifically, in step S3, the optimization of the device model established by the RBF neural network in step S2 based on the improved SBO algorithm is specifically:
s301, initializing output values of all devices of the micro-grid by introducing a chaotic sequence mode;
s302, after initializing in the step S301, aiming at the multivariable nonlinear problem in the micro-grid scheduling optimization, introducing a speed concept into a satin blue gardener algorithm to update and calculate the power supply combination of the micro-grid equipment;
s303, updating the introduced speed by adopting an inertial weight nonlinear decrement updating strategy, and updating the speed to continuously update the positions of the nests to find an optimal value to finish optimization.
Further, in step S301, the chaos mechanism adopts cubic mapping as follows:
Figure BDA0003541569190000034
wherein, beta is a chaotic factor,
Figure BDA0003541569190000035
for the kth dimension component of the ith coupling kiosk for the t +1 th generation,
Figure BDA0003541569190000036
is the kth dimension component of the ith coupling kiosk for the tth generation.
Further, the kth-dimension component velocity of the ith coupling pavilion in the t +1 th iteration
Figure BDA0003541569190000037
Comprises the following steps:
Figure BDA0003541569190000038
wherein the content of the first and second substances,
Figure BDA0003541569190000039
the kth component velocity of the ith decoupling pavilion for the t iteration, omega is the inertia weight, c1Is a learning factor, r1Is [0, 1]]The number of the internal random numbers is the same as the random number,
Figure BDA0003541569190000041
for the kth component, λ, of the ith generation of the ith coupling pavilionkIs a step size factor, XjkSearch for the ith spouse pavilion to the ith generation time historical optimum position, Xelite,kThe global optimum value of the k-dimension component in the coupling booth is obtained.
Further, in step S303, the update introducing speed is specifically:
w(t)＝(wmin+wmax)/2+(wmax-wmin)cos(tπ/T)
wherein, wmaxIs the initial inertial weight; w is aminIs the inertial weight at the end of the iteration; and T is the maximum iteration number.
Specifically, step S4 specifically includes:
s401, setting algorithm parameters, initializing the position of the individual puppet pavilion of the gardener, and generating an NxK matrix;
s402, calculating the power generation cost of the corresponding microgrid according to the initialized position of the puppet pavilion and the position of the puppet pavilion after iterative updating;
s403, sequencing the power generation costs of the micro-grid obtained in the step S402 according to the height, selecting the puppet pavilion position with the lowest power generation cost as the optimal puppet pavilion position, and calculating the probability Prob of each puppet pavilion position being selectedi；
S404, correspondingly updating the position of each gardener puppet pavilion according to the speed v and the nonlinear inertia weight w;
s405, calculating the power generation cost corresponding to the position where each spouse pavilion is located after the updating of the step S404, and updating the optimal spouse pavilion position;
s406, if the random number rand is larger than the constant p, performing variation on the even pavilion;
and S407, repeating the iteration process from the step S403 to the step S406, if the set precision requirement or the specified maximum iteration number is reached, terminating, and outputting the minimum power generation cost of the microgrid equipment corresponding to the optimal power supply combination.
The other technical scheme of the invention is that a micro-grid optimization scheduling system based on RBF-ISBO comprises:
the system module is used for selecting a wind turbine and a photovoltaic panel as power supply equipment and forming a microgrid system by adopting the photovoltaic panel, the wind turbine, a diesel generator, a power distribution network and energy storage equipment by taking the economic benefit and carbon reduction of the microgrid as targets;
the modeling module is used for performing equipment modeling on renewable energy sources in the microgrid system constructed by the system module by adopting an RBF neural network to obtain an equipment model by taking temperature, humidity, solar radiation degree, last-moment generating power and wind speed as input variables of the photovoltaic panel of the microgrid and taking temperature, humidity, air pressure, last-moment generating power and wind speed as input variables of a wind turbine;
the optimizing module is used for optimizing an equipment model established by the RBF neural network in the modeling module by using an improved SBO algorithm on the premise of meeting the constraint conditions of rated output power of the wind-solar power generation, the diesel generator and the energy storage equipment of the microgrid by taking the minimum power generation cost of the microgrid as an optimization target to obtain a power supply combination of the microgrid equipment;
and the scheduling module is used for calculating the corresponding power generation cost of the microgrid according to the power supply combination of the microgrid equipment obtained by the optimizing module, sequencing according to the power generation cost, finding out the optimal power supply combination to ensure that the power generation cost of the microgrid equipment is the minimum, and realizing optimized scheduling of the microgrid.
Compared with the prior art, the invention has at least the following beneficial effects:
the invention relates to a RBF-ISBO-based microgrid optimization scheduling method. Due to the fluctuation of the RESs output, the energy storage device is used for reducing the negative influence of the unpredictability of the RESs output on the microgrid. The distribution grid and diesel generators meet the demand for non-reducible loads in the microgrid system to ensure a continuous and reliable energy supply in the microgrid. Due to the unpredictable meteorological parameters and the influence of the uninterrupted operation of the system, the actual operation state and the rated characteristics of the renewable energy device have differences, and therefore factors with larger influence are selected as input variables of the main power supply device. The method is influenced by randomness and fluctuation of renewable energy power generation, and has the characteristics of large and redundant data set, complex mechanism modeling and insufficient adaptability. The RBF neural network has the advantages of strong operability, high convergence speed, good generalization capability, capability of controlling input noise and the like, and can well build a nonlinear model by instant and online learning, so that the RBF neural network is utilized to model the renewable energy equipment. And then under the constraint condition of the rated characteristics of the micro-grid equipment, aiming at minimizing the power generation cost of the micro-grid, providing an improved SBO algorithm to optimize the micro-grid energy scheduling.
Further, due to the influence of randomness and fluctuation of renewable energy power generation and the characteristics of large and redundant data sets, mechanism modeling is complex and has the problem of insufficient adaptability. The RBF neural network is a feedforward network based on the biological neuron local response principle, has the advantages of strong operability, high convergence speed, good generalization capability, capability of controlling input noise and the like, and can well build a nonlinear model by instant and online learning, so that the RBF neural network is utilized to model renewable energy equipment.
Furthermore, the micro-grid scheduling optimization problem relates to the nonlinear problem of multivariable, so that the nonlinear function can be converted into a high-dimensional linear separable space by introducing a Gaussian function as an activation function into the hidden layer of the RBF neural network, and the RBF neural network has strong nonlinear approximation capability.
Further, the problem of multivariable nonlinearity is involved in the microgrid scheduling optimization problem. The meta-heuristic algorithm relies on high-quality feasible solution space and effective searching capability, and has obvious advantages in solving the problems. However, the traditional SBO algorithm has obvious disadvantages in solving the optimization problem, which mainly manifests the problems of complexity and time consumption in optimization and easy falling into local optimization. Meanwhile, the traditional algorithm usually adopts a relatively simple random mode to initiate population, and the requirement of generating a high-quality solution cannot be well met. Therefore, by improving the traditional SBO algorithm in the aspects of the strategies of initialization mode, population updating and inertia weight updating, the improved algorithm can well overcome the defects of the traditional SBO algorithm, reasonably improve the utilization rate of renewable energy sources, reduce the environmental cost and improve the economy of a micro-grid system to the maximum extent.
Further, the chaos sequence mode means that on the premise of meeting the output power constraint conditions of the micro-grid wind-solar power generation, the diesel generator and the energy storage device, initial individuals are randomly generated, then population individuals are uniformly distributed in a feasible solution space by using a chaos mechanism, and the whole space can be fully searched in an iterative optimization process, so that an optimal value is found.
Furthermore, when solving the non-linear problem, the particle swarm optimization is favorable for enhancing the information exchange among the populations due to the speed attribute, and the convergence performance of the optimization is effectively improved. In order to more effectively realize the information exchange of the doll pavilion, the position of the doll pavilion is updated by introducing a speed concept on the basis that the conventional method is used for realizing the population updating of the male bird according to the historical best nest. And solving the power supply combination and power generation cost of the corresponding micro-grid equipment according to the position of the coupling pavilion until the position of the optimal coupling pavilion is found, namely the optimal solution.
Further, in order to solve the problems of low system energy utilization rate and high cost caused by multiple energy forms in the micro-grid and avoid the limitation problems of low convergence rate and the like of the traditional SBO algorithm, the ISBO algorithm is adopted to optimize the equipment model established by the RBF neural network, so that the scheduling optimization of the micro-grid is realized. Through tests, the result shows that the optimization strategy obtained by the improved SBO algorithm has good economical efficiency and better convergence effect in micro-grid dispatching. Compared with the method before optimization, after optimized scheduling is carried out by utilizing the improved satin blue gardener algorithm, the power generation cost of the micro-grid is reduced by 16.7% -21.2%, and the micro-grid running after optimized satin blue gardener algorithm has better economic potential. Compared with the improved front satin blue gardener algorithm and the particle swarm algorithm, the algorithm has better convergence and robustness, so that the algorithm has good adaptability in the aspect of solving the problem of optimal scheduling of the micro-grid system.
In conclusion, aiming at the problems of low system energy utilization rate and high cost caused by multiple energy forms in the microgrid, the invention introduces an improved satin blue gardener algorithm to solve the optimal output combination of wind-solar power generation, diesel generators, a power distribution network and energy storage equipment in the microgrid, and adopts an RBF neural network to establish an equipment model because the mechanism model of renewable equipment in the microgrid is difficult to solve the problem of random volatility. Secondly, initializing the output of each device by using a chaotic sequence mechanism with the minimum power generation cost of the micro-grid as an optimization target, and improving the search performance of the algorithm by adopting improved nonlinear inertial weight; compared with other algorithms, the power generation cost of the micro-grid is reduced by 16.7% -21.2% after ISBO optimized scheduling, and the method has better convergence and robustness.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a diagram of a RBF neural network architecture;
FIG. 2 is a flow chart of the ISBO algorithm;
FIG. 3 is a graph comparing photovoltaic RBF modeling results;
FIG. 4 is a graph comparing wind turbine RBF modeling results;
FIG. 5 is a diagram of microgrid device model performance indicators;
fig. 6 is a diagram of results of scheduling optimization of the microgrid, where (a) is an ISBO scheduling optimization result, (b) is an SBO scheduling optimization result, and (c) is a PSO scheduling optimization result;
FIG. 7 is a comparison graph of the microgrid scheduling optimization results;
FIG. 8 is a diagram of three optimization algorithm iterations;
fig. 9 is a box plot of the three algorithm robustness contrasts.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be understood that the terms "comprises" and/or "comprising" indicate the presence of the stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and including such combinations, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that although the terms first, second, third, etc. may be used to describe preset ranges, etc. in embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from one another. For example, the first preset range may also be referred to as a second preset range, and similarly, the second preset range may also be referred to as the first preset range, without departing from the scope of the embodiments of the present invention.
The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
Various structural schematics according to the disclosed embodiments of the invention are shown in the drawings. The figures are not drawn to scale, wherein certain details are exaggerated and possibly omitted for clarity of presentation. The shapes of various regions, layers and their relative sizes and positional relationships shown in the drawings are merely exemplary, and deviations may occur in practice due to manufacturing tolerances or technical limitations, and a person skilled in the art may additionally design regions/layers having different shapes, sizes, relative positions, according to actual needs.
The invention provides a radio base function-ISBO (radial basis function-ISBO) based microgrid optimization scheduling method, which solves the problem that an equipment model is difficult to dynamically adjust along with load requirements and meteorological changes based on the equipment model of a radial basis function neural network, introduces an improved satin blue gardener algorithm to solve the problems of low system energy utilization rate and high cost caused by multiple energy forms in a microgrid, and achieves the optimization target of minimum power generation cost of the microgrid.
The invention relates to a micro-grid optimization scheduling method based on RBF-ISBO, which comprises the following steps:
s1, aiming at economic benefit and carbon reduction of the microgrid, selecting a wind turbine and a photovoltaic panel as power supply equipment, and forming the microgrid system by adopting the photovoltaic panel, the wind turbine, a diesel generator, a power distribution network and energy storage equipment;
s2, aiming at constantly changing load requirements, taking temperature, humidity, solar radiation degree, last moment generated power and wind speed as input variables of the photovoltaic equipment board of the microgrid, taking temperature, humidity, air pressure, last moment generated power and wind speed as input variables of a wind turbine, carrying out equipment modeling on renewable energy in the microgrid system constructed in the step S1 by adopting an RBF neural network to obtain an equipment model, and outputting generated power at the current moment for verifying the effectiveness of the equipment model;
the root mean square error and the average absolute percentage error are used as performance indexes for evaluation.
The RBF neural network is a feedforward network based on the biological neuron local response principle, has the advantages of strong operability, high convergence speed, good generalization capability, capability of controlling input noise and the like, and can well build a nonlinear model by means of instant and online learning.
Referring to fig. 1, a structure diagram of an RBF neural network is shown, and a process of modeling a renewable energy device by using the RBF neural network specifically includes the following steps:
s201, performing standardization processing on historical data of the renewable energy device, wherein a data standardization formula is as follows:
Figure BDA0003541569190000101
wherein z is normalized data of the original renewable energy device data set, zmean is the mean value of the original renewable energy device data set, and zstd is the standard deviation of the original renewable energy device data set.
S202, taking a factor x (x1, x2, x 3.. xn) with high equipment power generation correlation as an input of the RBF neural network, and taking equipment power generation Y as an output;
s203, introducing a Gaussian function into the hidden layer to serve as an activation function, and converting the nonlinear function into a high-dimensional linear separable space. And obtaining the number n of the neurons of the hidden layer by a grid search method, wherein the formula is as follows:
Figure BDA0003541569190000102
wherein x is a factor vector with high equipment power generation correlation; rho is the center of the RBF neuron;
Figure BDA0003541569190000103
a transfer function for the RBF neuron; σ is the smoothness of the transfer function.
And S204, calculating to obtain the output of the linear combination hidden node, and outputting the generated power Y of equipment when the network parameters tend to be stable and the output error is minimum.
The output Y of the linear combination hidden node is calculated as follows:
Figure BDA0003541569190000104
wherein n is the number of hidden layers of the RBF neural network; ω 0 is a bias parameter in the output layer that allows adjustment of neuron sensitivity; ω i is the connection weight of the hidden layer and the output layer.
S3, with the minimum power generation cost of the micro-grid as an optimization target, on the premise of meeting the output power constraint conditions of the micro-grid wind-solar power generation, the diesel generator and the energy storage equipment, providing an improved SBO algorithm to optimize the equipment model established by the RBF neural network in the step S2 to obtain the power supply combination of the micro-grid equipment;
s301, initializing output values of all devices of the micro-grid by introducing a chaotic sequence mode;
the chaos sequence mode is that initial individuals are randomly generated on the premise of meeting the output power constraint conditions of micro-grid wind-solar power generation, a diesel generator and energy storage equipment, and then population individuals are uniformly distributed in a feasible solution space by utilizing a chaos mechanism. The chaos mechanism uses cubic mapping as follows:
Figure BDA0003541569190000111
wherein, beta is a chaos factor, namely a random number of [ -1,1 ].
S302, after initialization, aiming at the problem of multivariable nonlinearity in the scheduling optimization of the microgrid, a speed concept is introduced into a traditional satin blue gardener algorithm to update and calculate the power supply combination of the microgrid equipment.
When solving the non-linear problem, the particle swarm algorithm has the speed attribute which is favorable for strengthening the information exchange among the populations, and effectively improves the convergence performance of the algorithm. On the basis that the conventional mode is that the male bird realizes population updating according to the historical best nest, the concept of 'speed' is introduced to update the position of the nest:
Figure BDA0003541569190000112
Figure BDA0003541569190000113
wherein the content of the first and second substances,
Figure BDA0003541569190000114
the kth-dimensional component velocity for the ith coupling pavilion for the t +1 th iteration;
Figure BDA0003541569190000115
component velocity of k-dimension for ith coupling pavilion of the t iteration: omega is an inertia weight and determines the influence of the speed at the previous moment on the next movement; c. C1For the learning factor, 2 is usually taken; r is1Is [0, 1]]And the internal random number represents a disturbance factor.
And S303, updating the introduced speed by adopting an inertia weight nonlinear decrement updating strategy.
The traditional inertia weight is changed linearly according to different stages of population updating, and the searching capability of the algorithm in different iteration stages is enhanced. However, the strategy is difficult to find a balance point between the global search capability and the local search capability of the algorithm, and the optimization performance of the algorithm is reduced. The inertial weight is decreased in a nonlinear way along with the iteration of the population, the decreasing speed of the inertial weight is reduced to different degrees in the early stage and the later stage of the search, the global and local search capabilities of the algorithm are balanced, and the search potential of the algorithm is well mined:
w(t)＝(wmin+wmax)/2+(wmax-wmin)cos(tπ/T)
wherein, wmaxIs the initial inertial weight; w is aminIs the inertial weight at the end of the iteration; and T is the maximum iteration number.
And S4, calculating the corresponding power generation cost of the micro-grid according to the power supply combination of the micro-grid equipment obtained in the step S3, sequencing according to the power generation cost, finding out the optimal power supply combination to enable the power generation cost of the micro-grid equipment to be the minimum, and realizing optimized scheduling of the micro-grid.
Referring to fig. 2, the overall optimization process of the ISBO algorithm is as follows:
s401, setting algorithm parameters, and initializing the position of the individual puppet pavilion of the gardener;
and initializing the output value of the microgrid equipment by using the chaotic sequence according to the upper and lower limits of the rated power of the microgrid equipment to generate an NxK matrix.
S402, calculating a micro-grid equipment power supply combination corresponding to the position of the coupling kiosk;
s403, calculating the power generation cost (fitness value) y of the micro-grid corresponding to the positions of the N bird puppet pavilions according to the following formulai；
min yi＝CSW+Cdg+CP-CIN
S404, determining an optimal solution of the puppet pavilion;
sequencing the power generation costs (fitness values) obtained in the step S403 according to the height, selecting the puppet pavilion position with the lowest power generation cost as the optimal puppet pavilion position, and calculating the probability Probi of the selected puppet pavilion position according to the following formula;
Figure BDA0003541569190000121
s405, updating the position of the puppet pavilion;
and correspondingly updating the position of each gardener puppet pavilion according to the introduced velocity v and a nonlinear inertia weight w formula.
S406, calculating power generation cost (fitness value);
and calculating the power generation cost corresponding to the position of each coupling pavilion after updating, and updating the position of the optimal coupling pavilion.
S407, if rand is less than p, mutating the coupling pavilion by adopting the following two formulas;
Figure BDA0003541569190000122
τ＝η*(varmax-varmin)
wherein p is a constant; τ is the standard deviation; eta is a scaling factor; varmaxAnd varminUpper and lower limits for the variables, respectively.
And S408, repeating the iteration process from the step S404 to the step S407, and if the set precision requirement or the specified maximum iteration number is reached, terminating the algorithm and outputting the minimum power generation cost of the microgrid equipment corresponding to the optimal power supply combination.
In another embodiment of the present invention, an RBF-ISBO based microgrid optimization scheduling system is provided, which can be used for implementing the RBF-ISBO based microgrid optimization scheduling method, and specifically, the RBF-ISBO based microgrid optimization scheduling system includes a system module, a modeling module, an optimization module, and a scheduling module.
The system module is used for selecting a wind turbine and a photovoltaic panel as power supply equipment and forming a microgrid system by adopting the photovoltaic panel, the wind turbine, a diesel generator, a power distribution network and energy storage equipment by taking the economic benefit and carbon reduction of the microgrid as targets;
the modeling module is used for modeling equipment on renewable energy sources in the microgrid system constructed by the system modules by using an RBF neural network to obtain an equipment model, wherein the temperature, the humidity, the solar radiation degree, the last-moment generating power and the wind speed are used as input variables of the photovoltaic panel of the microgrid, and the temperature, the humidity, the air pressure, the last-moment generating power and the wind speed are used as input variables of a wind turbine;
the optimizing module is used for optimizing an equipment model established by the RBF neural network in the modeling module by using an improved SBO algorithm on the premise of meeting the constraint conditions of rated output power of the wind-solar power generation, the diesel generator and the energy storage equipment of the microgrid by taking the minimum power generation cost of the microgrid as an optimization target to obtain a power supply combination of the microgrid equipment;
and the scheduling module is used for calculating the corresponding power generation cost of the microgrid according to the power supply combination of the microgrid equipment obtained by the optimizing module, sequencing according to the power generation cost, finding out the optimal power supply combination to ensure that the power generation cost of the microgrid equipment is the minimum, and realizing optimized scheduling of the microgrid.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Matlab algorithm simulation is carried out by taking a microgrid of a certain park as a research object, and main equipment of the Matlab algorithm simulation comprises 3 diesel generators, 1 photovoltaic power generation device, 1 wind power generation device and energy storage equipment.
Referring to fig. 3, 4 and 5, by collecting data of temperature, humidity, solar irradiance, power generation power at the previous moment, wind speed of the photovoltaic panel, temperature, humidity, air pressure of the wind turbine, power generation power at the previous moment, wind speed and the like as input variables, the model 1 adopts the RBF neural network to establish a renewable energy device model, and the model 2 is a mechanism model established by the renewable energy device. Meanwhile, in order to verify the effectiveness of the model, the root mean square error and the average absolute percentage error are used as performance indexes for evaluation. 3-4, the RBF equipment model has higher fitting degree with the actual generated power, and the similarity of the variation trends of the predicted power value and the actual power value is higher; as can be seen from FIG. 5, the comprehensive prediction effect of the model 1 of the RBF equipment is obviously better than that of the model 2, and the prediction error is smaller. The RMSE of the RBF model of the whole wind power and photovoltaic equipment is close to 0.925, and the MAPE fluctuates in the range of about 1.56, so that the effectiveness of the RBF model is demonstrated, and the uncertainty problem of photovoltaic power generation and wind power generation can be well solved.
Referring to fig. 6, scheduling results of three algorithms are given; by selecting the actual working conditions of the microgrid system in the 8-month 6-day operation period of 2020, and respectively optimizing by adopting ISBO, SBO and PSO algorithms, the valley period can be seen, the load requirements are mainly met by wind power generation, the electricity price is lowest, the electric energy of the microgrid is dynamically scheduled, and the storage battery is in a charging state at the moment; in the flat time period, the load demand gradually rises, the photovoltaic output continuously rises along with the rise of the temperature and the illumination intensity, and the difference value between the photovoltaic output and the load demand is output by a power grid; during peak time, the wind and light output is large, the unit power generation cost of the power grid is considered to be high, and the diesel generator and the storage battery are preferentially selected to make up the difference between renewable energy and load requirements. The dynamic change of the unit power generation cost of the power grid is comprehensively considered, the operation cost can be effectively reduced, meanwhile, the storage battery is charged during the valley and the peak time and preferentially supplies power during the peak time, and the economic effect of the storage battery on the peak power utilization is fully exerted.
Referring to fig. 7, in order to better analyze the optimization effect of the ISBO algorithm, it can be seen by comparing the economic evaluation indexes after optimization scheduling of different algorithms, that the renewable energy utilization rate of the microgrid after scheduling optimization of ISBO is obviously improved, and the utilization rates are respectively improved by 8.8% and 13.5%. Meanwhile, although the emission of the same amount of CO2 is increased, the power generation cost of the system is reduced by 16.7% and 21.2% respectively by adopting the optimal operation condition after ISBO optimization. Compared with other algorithms, the method has the advantages that the utilization rate of renewable energy sources is improved, the environmental cost is reduced, and the economy of the micro-grid system can be improved to the maximum extent.
In order to comprehensively reflect the effect of the ISBO algorithm in application, the system is optimized and scheduled under the actual working condition of 24 hours, the optimization performance of the ISBO is evaluated from two aspects of convergence and robustness of the actual optimization result, and the evaluation is compared with SBO and PSO. The iteration case of the three algorithms is shown in fig. 8. The result shows that the adaptability value of the ISBO algorithm optimized scheduling model, namely the power generation cost, is in a steady descending trend overall. Iterations through around 17 generations lead to a system that is optimized and the cost of power generation is minimized. Therefore, the ISBO algorithm has better convergence in practical applications.
According to the actual working conditions of the microgrid system within the operation time period of 9 months and 30 days in 2020, the maximum value, the minimum value and the average value of the power generation cost are shown in fig. 9, wherein the three algorithms of ISBO, SBO and PSO are respectively used for 30 independent experiments. The results show that ISBO yields power generation costs that are better than SBO and PSO in terms of maximum, minimum, and average values. Meanwhile, the difference value between the maximum value and the minimum value obtained by the ISBO algorithm is the minimum of the three, so that the ISBO algorithm has good robustness.
In summary, the RBF-ISBO based microgrid optimization scheduling method and system provided by the invention have the following advantages:
firstly, aiming at the influence of randomness and fluctuation of renewable energy power generation and the characteristics of large and redundant data set, the mechanism modeling is complex and has the problem of insufficient adaptability. A feedforward network based on a biological neuron local response principle, namely an RBF neural network, is provided, and the RBF neural network has the advantages of strong operability, high convergence speed, good generalization capability, capability of controlling input noise and the like, and can well build a nonlinear model by means of instant and online learning. The problem of uncertainty of photovoltaic power generation and wind power generation can be well solved.
Secondly, firstly, initializing individuals in the population by adopting a chaos sequence mode, so that the uniformity of feasible solutions can be improved, and the population is evolved to a higher level. Secondly, the 'speed' in the particle swarm algorithm is introduced to update the positions of the nests so as to improve the search efficiency and the convergence performance of the algorithm. And finally, updating the population by adopting an inertia weight nonlinear decrement updating strategy, namely the inertia weight is nonlinearly decremented along with the iteration of the population, and the velocity of inertia weight decrement is reduced to different degrees in the early stage and the later stage of the search, so that the global and local search capacities of the algorithm are balanced, the search potential of the algorithm is well mined, and meanwhile, the defects of the traditional inertia weight are overcome.
Thirdly, the improved satin blue gardener optimization algorithm can minimize the overall power generation cost after optimization, solves the problems that the problem that the traditional SBO algorithm is applied to microgrid scheduling optimization is easy to fall into local optimization and the optimization process is complex and time-consuming, and has obvious advantages in solving the multivariable nonlinear problem related to the microgrid scheduling optimization problem by depending on high-quality feasible solution space and effective searching capability. The method has good convergence and robustness, and can improve the economy of the micro-grid system to the maximum extent. .
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.

Claims (10)

1. A micro-grid optimization scheduling method based on RBF-ISBO is characterized by comprising the following steps:
s1, aiming at economic benefits and carbon reduction of the microgrid, selecting a wind turbine and a photovoltaic panel as power supply equipment, and forming the microgrid system by adopting the photovoltaic panel, the wind turbine, a diesel generator, a power distribution network and energy storage equipment;
s2, taking temperature, humidity, solar radiation degree, last-moment generating power and wind speed as input variables of the photovoltaic panel of the microgrid, taking temperature, humidity, air pressure, last-moment generating power and wind speed as input variables of a wind turbine, and carrying out equipment modeling on renewable energy in the microgrid system constructed in the step S1 by adopting an RBF neural network to obtain an equipment model;
s3, with the minimum power generation cost of the micro-grid as an optimization target, optimizing the power generation power output by the equipment model established by the RBF neural network in the step S2 by using an improved SBO algorithm on the premise of meeting the constraint conditions of the rated output power of the micro-grid wind-solar power generation, the diesel generator and the energy storage equipment to obtain the power supply combination of the micro-grid equipment;
and S4, calculating the corresponding power generation cost of the micro-grid according to the power supply combination of the micro-grid equipment obtained in the step S3, sequencing according to the power generation cost, finding out the optimal power supply combination to enable the power generation cost of the micro-grid equipment to be the minimum, and realizing optimized scheduling of the micro-grid.
2. The RBF-ISBO-based microgrid optimization scheduling method of claim 1, wherein in the step S2, the modeling of the renewable energy devices in the microgrid system by using the RBF neural network is specifically as follows:
s201, performing standardization processing on historical data of renewable energy equipment;
s202, taking a factor x with high equipment power generation correlation as the input of an RBF neural network, and taking equipment power generation power Y as the output of the RBF neural network;
s203, introducing a Gaussian function as an activation function into a hidden layer of the RBF neural network, converting a nonlinear function into a high-dimensional linear separable space, and obtaining the number n of neurons of the hidden layer by a grid search method;
and S204, calculating by using the activation function obtained in the step S203 to obtain the output of the linear combination hidden node, and outputting the generated power Y of each power supply device when the network parameters tend to be stable and the output error is minimum.
3. The RBF-ISBO-based microgrid optimized scheduling method of claim 2, wherein in the step S203, the activation function Φ (x, ρ) is:
Figure FDA0003541569180000021
wherein x is a factor vector with high equipment power generation correlation; rho is the center of the RBF neuron;
Figure FDA0003541569180000022
a transfer function for the RBF neuron; σ is the smoothness of the transfer function.
4. The RBF-ISBO based microgrid optimized scheduling method of claim 2, wherein in step S204, the output Y of the linear combination hidden node is calculated as follows:
Figure FDA0003541569180000023
wherein n is the number of hidden layers of the RBF neural network; w is a0Bias parameters in the output layer that allow adjustment of neuron sensitivity; w is aiThe connection weight of the hidden layer and the output layer is defined, and x is a factor vector with high equipment power generation correlation; ρ is the center of the RBF neuron.
5. The RBF-ISBO-based microgrid optimization scheduling method of claim 1, wherein in the step S3, the optimization of the equipment model established by the RBF neural network in the step S2 based on the improved SBO algorithm is specifically:
s301, initializing output values of all devices of the micro-grid by introducing a chaotic sequence mode;
s302, after initializing in the step S301, aiming at the multivariable nonlinear problem in the micro-grid scheduling optimization, introducing a speed concept into a satin blue gardener algorithm to update and calculate the power supply combination of the micro-grid equipment;
s303, updating the introduced speed by adopting an inertial weight nonlinear decrement updating strategy, and updating the speed to continuously update the positions of the nests to find an optimal value to finish optimization.
6. The RBF-ISBO-based microgrid optimized scheduling method of claim 5, wherein in the step S301, the chaos mechanism adopts cubic mapping as follows:
Figure FDA0003541569180000024
wherein, beta is a chaotic factor,
Figure FDA0003541569180000025
for the kth dimension component of the ith coupling kiosk for the t +1 th generation,
Figure FDA0003541569180000026
is the kth dimension component of the ith coupling kiosk for the tth generation.
7. The RBF-ISBO based microgrid optimized scheduling method of claim 6, characterized in that component velocity of k dimension of ith coupling pavilion is iterated for t +1 times
Figure FDA0003541569180000031
Comprises the following steps:
Figure FDA0003541569180000032
wherein the content of the first and second substances,
Figure FDA0003541569180000033
the kth component velocity of the ith decoupling pavilion for the t iteration, omega is the inertia weight, c1Is a learning factor, r1Is [0, 1]]The number of the internal random numbers is the same as the random number,
Figure FDA0003541569180000034
for the kth component, λ, of the ith generation of the ith coupling pavilionkIs a step size factor, XjkSearch for the ith spouse pavilion to the ith generation time historical optimum position, Xelite,kThe global optimum value of the k-dimension component in the coupling booth is obtained.
8. The RBF-ISBO-based microgrid optimized dispatching method of claim 5, wherein in the step S303, the speed of update introduction is specifically as follows:
w(t)＝(wmin+wmax)/2+(wmax-wmin)cos(tπ/T)
wherein, wmaxIs the initial inertial weight; w is aminIs the inertial weight at the end of the iteration; and T is the maximum iteration number.
9. The RBF-ISBO-based microgrid optimized dispatching method of claim 1, wherein the step S4 is specifically as follows:
s401, setting algorithm parameters, initializing the position of the individual puppet pavilion of the gardener, and generating an NxK matrix;
s402, calculating the power generation cost of the corresponding microgrid according to the initialized position of the puppet pavilion and the position of the puppet pavilion after iterative updating;
s403, sequencing the power generation costs of the micro-grid obtained in the step S402 according to the height, selecting the puppet pavilion position with the lowest power generation cost as the optimal puppet pavilion position, and calculating the probability Prob of each puppet pavilion position being selectedi；
S404, correspondingly updating the position of each gardener puppet pavilion according to the speed v and the nonlinear inertia weight w;
s405, calculating the power generation cost corresponding to the position where each spouse pavilion is located after the updating of the step S404, and updating the optimal spouse pavilion position;
s406, if the random number rand is larger than the constant p, the even pavilion is mutated;
and S407, repeating the iteration process from the step S403 to the step S406, and if the set precision requirement or the specified maximum iteration number is reached, terminating and outputting the minimum power generation cost of the microgrid equipment corresponding to the optimal power supply combination.
10. A micro-grid optimization scheduling system based on RBF-ISBO is characterized by comprising:
the system module is used for selecting a wind turbine and a photovoltaic panel as power supply equipment and forming a microgrid system by adopting the photovoltaic panel, the wind turbine, a diesel generator, a power distribution network and energy storage equipment, aiming at economic benefits and carbon reduction of the microgrid;
the modeling module is used for performing equipment modeling on renewable energy sources in the microgrid system constructed by the system module by adopting an RBF neural network to obtain an equipment model by taking temperature, humidity, solar radiation degree, last-moment generating power and wind speed as input variables of the photovoltaic panel of the microgrid and taking temperature, humidity, air pressure, last-moment generating power and wind speed as input variables of a wind turbine;
the optimizing module is used for optimizing the power generation power output by the equipment model established by the RBF neural network in the modeling module by using an improved SBO algorithm on the premise of meeting the constraint conditions of the rated output power of the wind-solar power generation, the diesel generator and the energy storage equipment of the microgrid by taking the minimum power generation cost of the microgrid as an optimization target to obtain the power supply combination of the microgrid equipment;
and the scheduling module is used for calculating the corresponding power generation cost of the microgrid according to the power supply combination of the microgrid equipment obtained by the optimizing module, sequencing according to the power generation cost, finding out the optimal power supply combination to ensure that the power generation cost of the microgrid equipment is the minimum, and realizing optimized scheduling of the microgrid.
CN202210240896.5A 2022-03-10 2022-03-10 RBF-ISBO-based microgrid optimization scheduling method and system Withdrawn CN114580298A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210240896.5A CN114580298A (en) 2022-03-10 2022-03-10 RBF-ISBO-based microgrid optimization scheduling method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210240896.5A CN114580298A (en) 2022-03-10 2022-03-10 RBF-ISBO-based microgrid optimization scheduling method and system

Publications (1)

Publication Number Publication Date
CN114580298A true CN114580298A (en) 2022-06-03

Family

ID=81780957

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210240896.5A Withdrawn CN114580298A (en) 2022-03-10 2022-03-10 RBF-ISBO-based microgrid optimization scheduling method and system

Country Status (1)

Country Link
CN (1) CN114580298A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116544983A (en) * 2023-07-06 2023-08-04 广州市虎头电池集团股份有限公司 Wind-solar power generation energy storage system and optimal configuration method thereof

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116544983A (en) * 2023-07-06 2023-08-04 广州市虎头电池集团股份有限公司 Wind-solar power generation energy storage system and optimal configuration method thereof
CN116544983B (en) * 2023-07-06 2024-02-27 广州市虎头电池集团股份有限公司 Wind-solar power generation energy storage system and optimal configuration method thereof

Similar Documents

Publication Publication Date Title
CN111709672B (en) Virtual power plant economic dispatching method based on scene and deep reinforcement learning
Tan et al. Multi-objective energy management of multiple microgrids under random electric vehicle charging
Moghaddam et al. Multi-objective operation management of a renewable MG (micro-grid) with back-up micro-turbine/fuel cell/battery hybrid power source
CN109886473B (en) Watershed wind-solar water system multi-objective optimization scheduling method considering downstream ecology
CN107732960A (en) Micro-grid energy storage system capacity configuration optimizing method
CN111934360B (en) Virtual power plant-energy storage system energy collaborative optimization regulation and control method based on model predictive control
Wang et al. Short-term photovoltaic power generation forecasting based on environmental factors and GA-SVM
Squartini et al. Optimization algorithms for home energy resource scheduling in presence of data uncertainty
CN111144641B (en) Improved particle swarm algorithm-based microgrid optimization scheduling method
CN113783224A (en) Power distribution network double-layer optimization planning method considering operation of various distributed energy sources
Li et al. Energy hub-based optimal planning for integrated energy systems considering part-load characteristics and synergistic effect of equipment
Teferra et al. Fuzzy-based prediction of solar PV and wind power generation for microgrid modeling using particle swarm optimization
Chatziagorakis et al. Enhancement of hybrid renewable energy systems control with neural networks applied to weather forecasting: the case of Olvio
Haddad et al. Mixed integer linear programming approach to optimize the hybrid renewable energy system management for supplying a stand-alone data center
CN114580298A (en) RBF-ISBO-based microgrid optimization scheduling method and system
Souabi et al. Data-driven prediction models of photovoltaic energy for smart grid applications
Fu et al. A spatial forecasting method for photovoltaic power generation combined of improved similar historical days and dynamic weights allocation
CN115021269A (en) Two-stage optimal power flow solving method based on data driving
Long et al. Short-term solar power interval prediction with interval width initilization approach
Chakraborty et al. Fuzzy quantum computation based thermal unit commitment strategy with solar-battery system injection
CN115995840A (en) New energy system peak regulation optimization method and device based on coordination of wind, light and energy storage
Wang et al. Self-organizing maps for scenario reduction in long-term hydropower scheduling
CN113222216A (en) Method, device and system for predicting cooling, heating and power loads
CN111859780A (en) Micro-grid operation optimization method and system
Berdonosov et al. Analysis and development potential of predictive models for energy flows of autonomous hybrid energy systems

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20220603

WW01 Invention patent application withdrawn after publication