CN117175694B - Micro-grid optimal scheduling method and system based on new energy consumption - Google Patents
Micro-grid optimal scheduling method and system based on new energy consumption Download PDFInfo
- Publication number
- CN117175694B CN117175694B CN202311456729.5A CN202311456729A CN117175694B CN 117175694 B CN117175694 B CN 117175694B CN 202311456729 A CN202311456729 A CN 202311456729A CN 117175694 B CN117175694 B CN 117175694B
- Authority
- CN
- China
- Prior art keywords
- data
- micro
- grid
- wind power
- energy
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000005265 energy consumption Methods 0.000 title claims abstract description 24
- 238000005457 optimization Methods 0.000 claims description 51
- 238000012706 support-vector machine Methods 0.000 claims description 33
- 238000004458 analytical method Methods 0.000 claims description 30
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000012544 monitoring process Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 14
- 239000003795 chemical substances by application Substances 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 125000004122 cyclic group Chemical group 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 238000013480 data collection Methods 0.000 claims description 7
- 238000010248 power generation Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 4
- 230000035772 mutation Effects 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 4
- 230000002087 whitening effect Effects 0.000 claims description 4
- 238000007306 functionalization reaction Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 5
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 8
- 241000251468 Actinopterygii Species 0.000 description 5
- 239000002245 particle Substances 0.000 description 5
- 238000012880 independent component analysis Methods 0.000 description 4
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 3
- 229910052799 carbon Inorganic materials 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 238000004146 energy storage Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- -1 electricity Substances 0.000 description 1
- 230000002431 foraging effect Effects 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000011273 social behavior Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a micro-grid optimal scheduling method and a micro-grid optimal scheduling system based on new energy consumption, which relate to the technical field of power systems and comprise the following steps of: extracting wind power data and load data in the energy data; obtaining predicted wind power data of distributed energy and predicted demand data of load side resources; generating a micro-grid power dispatching strategy; implementing the power distribution of the micro-grid; evaluating and optimizing the scheduling strategy; and reapplying the optimized scheduling strategy to the micro-grid until the optimal scheduling strategy is realized. According to the invention, the use efficiency of energy sources can be improved by accurately predicting and optimizing the power demand and the wind power supply, and the green energy source utilization is effectively promoted by optimizing the scheduling strategy of wind power and load resources, so that the environmental pressure is slowed down, the sustainable development of assistance is realized, the intelligent level of a micro-grid is improved, the operation efficiency is further improved, and the management cost is reduced.
Description
Technical Field
The invention relates to the technical field of power systems, in particular to a micro-grid optimal scheduling method and system based on new energy consumption.
Background
At present, a micro-grid is a novel power system network structure and is an effective mode for realizing an active power distribution network. The development and extension of the micro-grid can promote large-scale intervention of distributed power generation and renewable energy sources, and promote transition of a traditional grid to the intelligent grid. The development of the micro-grid is an effective way for solving the problems of distributed generation grid connection and power supply in remote areas or islands, and has very wide application prospect.
Meanwhile, with the development of economic technology, carbon emission problems caused by the combustion of fossil fuels are prominent. In order to solve the problem of carbon emission, the renewable energy power generation scale of each country is continuously enlarged, but the current renewable energy power generation still occupies smaller area. The micro-grid has flexible operation characteristics, and can operate in an island mode or in a grid-connected mode; and the micro-grid is mainly a distributed power supply, and is regulated by utilizing an energy storage and control device, so that energy balance is realized. The micro-grid contains various renewable energy sources, wind power, photovoltaic and geothermal are generally used as main materials, and the complementary effect of the various energy sources improves the overall efficiency and the energy supply reliability of an energy system and increases the flexibility of the renewable energy source. And there are a variety of controllable units. Therefore, the micro-grid can play a vital role in the new energy consumption and scheduling process of the grid.
However, in the existing micro-grid optimal scheduling method based on new energy consumption, new energy in the micro-grid such as wind power and the like cannot be effectively consumed and utilized, the access proportion and the consumption capacity of the new energy cannot be conveniently improved, and wind power and loads cannot be conveniently predicted and optimally scheduled, so that the power demand and the wind power supply of the micro-grid cannot be accurately predicted, and the energy use efficiency is further reduced.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a micro-grid optimal scheduling method and a micro-grid optimal scheduling system based on new energy consumption, which solve the problems that in the prior art, the existing micro-grid optimal scheduling method based on new energy consumption cannot effectively consume and utilize new energy such as wind power and the like in a micro-grid, the access proportion and the consumption capacity of the new energy cannot be conveniently improved, and wind power and loads cannot be conveniently predicted and optimally scheduled, so that the power demand and the wind power supply of the micro-grid cannot be accurately predicted, and the energy use efficiency is further reduced.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
according to one aspect of the invention, there is provided a new energy consumption-based micro-grid optimal scheduling method, which includes the steps of:
s1, constructing an energy monitoring and sensing network, collecting energy data in a micro-grid, preprocessing the energy data, and extracting wind power data and load data in the energy data;
s2, integrating wind power data and load data by using an optimization algorithm, and extracting features of the integrated data to obtain predicted wind power data of the distributed energy and predicted demand data of load side resources;
s3, predicting the predicted wind power data and the predicted demand data of the load side resource by using a prediction algorithm to generate a micro-grid power dispatching strategy;
s4, analyzing the generated micro-grid power dispatching strategy based on an analysis algorithm, and implementing power distribution of the micro-grid;
s5, collecting and detecting operation data of the micro-grid in real time, comparing actual operation data with predicted data, and evaluating and optimizing a scheduling strategy;
s6, reapplying the optimized dispatching strategy to the micro-grid, and carrying out power distribution of the micro-grid of a new round until the optimal dispatching strategy is realized.
Further, an energy monitoring and sensing network is constructed, energy data in the micro-grid is collected and preprocessed, and the wind power data and load data in the energy data are extracted, wherein the method comprises the following steps of:
s11, distributing distributed monitoring sites by using a geographic information system technology, and establishing an energy monitoring and sensing network;
s12, acquiring original energy data of a distributed monitoring site in a micro-grid;
s13, performing wavelet transformation on the original energy data, converting from a time domain to a frequency domain, and screening out a frequency band containing interference waves;
s14, tracking and acquiring the interference wave direction in the frequency band;
s15, selecting a plurality of road windows with the calculated sample points as centers to perform median filtering, and recovering interference signals at the calculated sample points;
s16, recovering interference signals in each frequency band one by one, and performing wavelet inverse transformation to obtain the whole wave field of the interference wave;
s17, subtracting the interference wave field from the original energy data to obtain an effective signal wave field;
s18, generating denoised original energy data based on the effective signal wave field, checking, extracting effective data and normalizing the original energy data to obtain wind power data and load data in the energy data.
Further, the wind power data and the load data are integrated by using an optimization algorithm, and feature extraction is performed on the integrated data, so that predicted wind power data of the distributed energy and predicted demand data of load side resources are obtained, and the method comprises the following steps:
s21, setting related parameters, integrating wind power data and load data, extracting features, and generating an initial operation decision and a corresponding decision change rate;
s22, calculating the fitness value of each operation decision according to the set fitness function;
s23, calculating the adaptability variance of the operation decision according to preset conditions, and judging whether to perform mutation operation or not;
s24, updating the change rate and the position of the decision according to the calculated adaptability variance and inertia weight formula;
s25, checking whether an end condition is met, if so, ending the optimization, otherwise, turning to the step S22 to continue the optimization;
s26, assigning the optimized parameters to a support vector machine model;
s27, inputting the processed wind power data and load data into a support vector machine model, and training a support vector machine to obtain a trained support vector machine model;
s28, predicting future wind power data and load data by using the trained support vector machine model to obtain predicted wind power data of the distributed energy and predicted demand data of load side resources, and stopping calculation.
Further, the fitness function has the expression:
；
wherein,and->Respectively representing a training output value and an expected value of the support vector machine model;
xrepresented as an input vector;
Ma dimension represented as an input vector;
lrepresenting the number of elements;
f (x) is expressed as a fitness function.
Further, predicting future wind power data and load data by using a trained support vector machine model to obtain predicted wind power data of distributed energy and predicted demand data of load side resources, and stopping calculation comprises the following steps:
s281, predicting future wind power data and load data by using a trained support vector machine model;
s282, presetting a reliability threshold, filtering a low reliability prediction result, and determining class labels of wind power data and load data from probability prediction of a support vector machine model;
s283, taking the determined category labels as the predicted power generation data of the distributed energy and the predicted demand data of the load side resource, and stopping calculation.
Further, the prediction algorithm is utilized to predict the predicted wind power data and the predicted demand data of the load side resource, and the generation of the micro-grid power dispatching strategy comprises the following steps:
s31, inputting initial sample sets of wind power data to be processed and predicted demand data of load side resources;
s32, grading all wind power data of the initial sample set and predicted demand data of load side resources to obtain a plurality of sample subsets containing different wind power data and predicted demand data of the load side resources;
s33, performing cyclic processing on each sample subset to obtain a principal component coefficient matrix;
s34, rearranging the principal component coefficient matrix, and transforming the initial sample set based on the principal component coefficient matrix to generate new wind power data and a predicted demand data sample of the load side resource;
s35, training a prediction model based on new wind power data and a predicted demand data sample of load side resources to obtain a sub-model for predicting power distribution of the micro-grid, returning to the step S32, and circularly presetting for a plurality of times to obtain an integrated prediction model;
s36, predicting a test sample set by using an integrated prediction model, and generating a preliminary power dispatching strategy by using wind power data and predicted demand data of load side resources;
and S37, determining the micro-grid power dispatching strategy through voting according to the prediction results of all the preliminary power dispatching strategies.
Further, performing a cyclic process on each sample subset to obtain a principal component coefficient matrix includes the steps of:
s331, performing cyclic processing on each sample subset to obtain a principal component coefficient matrix;
s332, carrying out principal component analysis on the new wind power data and the predicted demand data sample of the load side resource to obtain principal component coefficient vectors related to micro-grid power dispatching;
s333, repeating the steps S331 to S332 to obtain a plurality of groups of principal component coefficients, and combining the coefficients into a principal component coefficient matrix.
Further, based on the analysis algorithm, analyzing the generated micro-grid power dispatching strategy, and implementing the power distribution of the micro-grid comprises the following steps:
s41, receiving the generated micro-grid power dispatching strategy;
s42, determining an objective function and constraint conditions, and establishing an optimization model;
and S43, applying an analysis algorithm to the optimization model, and searching an optimal solution meeting constraint conditions as a final micro-grid power dispatching strategy.
Further, applying the analysis algorithm to the optimization model, and searching the optimal solution meeting the constraint condition as the final micro-grid power dispatching strategy comprises the following steps:
s431, whitening the observed signal to obtain a whitened observed signal so as to enable the whitened observed signal to meet preset conditions;
s432, initializing parameters of an analysis algorithm, and initializing a micro-grid power dispatching strategy;
s433, calculating the negative entropy corresponding to each optimization agent through objective functionalization, and updating the bulletin board;
s434, each optimizing agent executes optimizing, gathering and tracking actions according to preset conditions, and updates the state;
s435, if the preset iteration times are reached, executing a step S436, otherwise, executing a step S433;
s436, the global optimal position is taken to form a separation matrix, and a final micro-grid power dispatching strategy is obtained.
According to another aspect of the present invention, there is also provided a new energy consumption-based micro grid optimal scheduling system, including:
the data collection and processing module is used for constructing an energy monitoring sensing network, collecting energy data in the micro-grid, preprocessing the energy data, and extracting wind power data and load data in the energy data;
the characteristic extraction module is used for integrating wind power data and load data by utilizing an optimization algorithm, and extracting characteristics of the integrated data to obtain predicted wind power data of the distributed energy and predicted demand data of load side resources;
the prediction and strategy generation module is used for predicting the predicted wind power data and the predicted demand data of the load side resources by using a prediction algorithm to generate a micro-grid power dispatching strategy;
the strategy analysis and implementation module is used for analyzing the generated micro-grid power dispatching strategy based on an analysis algorithm and implementing power distribution of the micro-grid;
the data comparison and optimization module is used for collecting and detecting the operation data of the micro-grid in real time, comparing the actual operation data with the predicted data, and evaluating and optimizing the scheduling strategy;
the strategy implementation and iteration optimization module is used for reapplying the optimized scheduling strategy to the micro-grid and carrying out power distribution of the micro-grid of a new round until the optimal scheduling strategy is realized;
the data collection and processing module is connected with the prediction and strategy generation module through the feature extraction module, and the prediction and strategy generation module is connected with the data comparison and optimization module through the strategy analysis and implementation module and the strategy implementation and iteration optimization module.
The beneficial effects of the invention are as follows:
1. according to the invention, the power demand and the wind power supply are accurately predicted and optimized, so that the energy use efficiency can be obviously improved, the green energy utilization is effectively promoted, the environmental pressure is slowed down, the sustainable development of assistance is realized, the intelligent level of the micro-grid is improved, the operation efficiency is improved, and the management cost is reduced.
2. According to the invention, the wind power data and the load data are integrated and extracted by constructing the energy monitoring and sensing network, so that the electric power demand and the wind power supply of the micro-grid can be predicted more accurately, and the energy utilization efficiency is improved.
3. According to the invention, by utilizing the optimization algorithm, the optimal operation decision can be found by calculating the fitness value of each operation decision, so that the operation of the micro-grid is more efficient and stable, and according to the preset condition, the fitness variance of the operation decision is calculated, and whether the variation operation is carried out or not is judged, so that the scheduling strategy has higher flexibility when coping with the change of wind power data and load data, the power scheduling efficiency and precision of the micro-grid can be effectively improved, the micro-grid is helped to better adapt to the change of energy demands, the energy utilization efficiency is improved, and the operation stability of the micro-grid is enhanced.
4. According to the invention, a preliminary power scheduling strategy is generated by utilizing wind power data and predicted demand data of load side resources, and the power scheduling strategy of the micro-grid is determined through voting, so that the micro-grid can adaptively perform power scheduling according to actual conditions, thereby improving the running stability of the micro-grid, training a prediction model based on new wind power data and predicted demand data samples of the load side resources, obtaining a sub-model for predicting the power distribution of the micro-grid, and more accurately performing power distribution according to actual demands, thereby improving the running efficiency of a power system.
5. According to the invention, through the analysis algorithm, the optimal power scheduling strategy meeting the constraint condition can be found through the setting of the objective function and the constraint condition and the application of the analysis algorithm, so that the power distribution of the micro-grid is optimized, the power utilization efficiency is improved, and the optimizing, gathering and tracking actions are executed according to the preset condition through each optimizing agent, and the state is updated, so that the optimal solution can be quickly found under the condition of meeting the preset iteration times, thereby improving the optimizing efficiency, and further improving the self-adaption capability and the running stability of the micro-grid.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a micro-grid optimized scheduling method based on new energy consumption according to an embodiment of the invention;
fig. 2 is a schematic block diagram of a micro-grid optimal scheduling system based on new energy consumption according to an embodiment of the present invention.
In the figure:
1. a data collection and processing module; 2. a feature extraction module; 3. a prediction and strategy generation module; 4. a policy analysis and enforcement module; 5. the data comparison and optimization module; 6. and a strategy implementation and iteration optimization module.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more. Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
According to the embodiment of the invention, a micro-grid optimal scheduling method and system based on new energy consumption are provided.
The invention will be further described with reference to the accompanying drawings and specific embodiments, as shown in fig. 1, a new energy consumption-based micro-grid optimal scheduling method according to an embodiment of the invention includes the following steps:
s1, constructing an energy monitoring and sensing network, collecting energy data in a micro-grid, preprocessing the energy data, and extracting wind power data and load data in the energy data;
specifically, the monitoring and sensing network is composed of various sensors (water, electricity, gas, heating and the like), an intelligent electricity utilization system, a water supply tail end control system and other controllable systems, and the on-site data sensing and tail end control are completed.
Specifically, the energy data includes wind power data, solar energy data, load data, battery energy storage state, generator running state, grid frequency, voltage and the like.
Specifically, wind power data mainly refers to data related to wind power generation, such as wind speed, wind direction, rotational speed of a wind power generator, power output of the wind power generator, and the like.
In particular, the load data mainly refers to load conditions in the power system, i.e. demand conditions of power. Including the power requirements of various loads such as household power, industrial power, commercial power, and the like.
S2, integrating wind power data and load data by using an optimization algorithm, and extracting features of the integrated data to obtain predicted wind power data of the distributed energy and predicted demand data of load side resources;
s3, predicting the predicted wind power data and the predicted demand data of the load side resource by using a prediction algorithm to generate a micro-grid power dispatching strategy;
specifically, predicting wind power data refers to predicting wind power output in a period of time according to historical wind power data (including wind speed, wind direction, rotational speed of a wind driven generator, power output of the wind driven generator, etc.) through a prediction model.
Specifically, the predicted demand data of the load side resource refers to the power demand in a period of time predicted by a prediction model according to historical load data (including power demands of various loads such as household power consumption, industrial power consumption, commercial power consumption, etc.).
S4, analyzing the generated micro-grid power dispatching strategy based on an analysis algorithm, and implementing power distribution of the micro-grid;
s5, collecting and detecting operation data of the micro-grid in real time, comparing actual operation data with predicted data, and evaluating and optimizing a scheduling strategy;
specifically, the actual operation data refers to data collected by the micro-grid in the actual operation process, including actual output of various energy sources (such as wind power, solar energy and the like), actual load conditions of the power system, actual operation states of various devices in the micro-grid and the like.
Specifically, the predicted data refers to data predicted by a prediction model for a future period of time, including predicted wind power data and predicted demand data of load side resources.
S6, reapplying the optimized dispatching strategy to the micro-grid, and carrying out power distribution of the micro-grid of a new round until the optimal dispatching strategy is realized.
Specifically, the steps S3 to S5 are circularly executed until the optimal scheduling policy is realized.
Preferably, an energy monitoring and sensing network is constructed, energy data in a micro-grid is collected and preprocessed, and the extraction of wind power data and load data in the energy data comprises the following steps:
s11, distributing distributed monitoring sites by using a geographic information system technology, and establishing an energy monitoring and sensing network;
s12, acquiring original energy data of a distributed monitoring site in a micro-grid;
s13, performing wavelet transformation on the original energy data, converting from a time domain to a frequency domain, and screening out a frequency band containing interference waves;
s14, tracking and acquiring the interference wave direction in the frequency band;
s15, selecting a plurality of road windows with the calculated sample points as centers to perform median filtering, and recovering interference signals at the calculated sample points;
s16, recovering interference signals in each frequency band one by one, and performing wavelet inverse transformation to obtain the whole wave field of the interference wave;
s17, subtracting the interference wave field from the original energy data to obtain an effective signal wave field;
s18, generating denoised original energy data based on the effective signal wave field, checking, extracting effective data and normalizing the original energy data to obtain wind power data and load data in the energy data.
Preferably, the wind power data and the load data are integrated by using an optimization algorithm, and feature extraction is performed on the integrated data, so that predicted wind power data of the distributed energy and predicted demand data of load side resources are obtained, and the method comprises the following steps:
s21, setting related parameters, integrating wind power data and load data, extracting features, and generating an initial operation decision and a corresponding decision change rate;
specifically, related parameters include wind power data related parameters (such as wind speed, wind direction, temperature, humidity, air pressure, etc.), load data related parameters (electric quantity, electricity utilization time, electric equipment type, etc.).
S22, calculating the fitness value of each operation decision according to the set fitness function;
s23, calculating the adaptability variance of the operation decision according to preset conditions, and judging whether to perform mutation operation or not;
specifically, if the mutation occurs, the process goes to step S25, otherwise, the process goes to step S24.
S24, updating the change rate and the position of the decision according to the calculated adaptability variance and inertia weight formula;
s25, checking whether an end condition is met, if so, ending the optimization, otherwise, turning to the step S22 to continue the optimization;
s26, assigning the optimized parameters to a support vector machine model;
s27, inputting the processed wind power data and load data into a support vector machine model, and training a support vector machine to obtain a trained support vector machine model;
s28, predicting future wind power data and load data by using the trained support vector machine model to obtain predicted wind power data of the distributed energy and predicted demand data of load side resources, and stopping calculation.
Specifically, the optimization algorithm is a support vector machine algorithm for optimizing the self-adaptive particle swarm, and is an algorithm combining the particle swarm optimization algorithm and a support vector machine and is used for optimizing parameters of a support vector machine model. The self-adaptive particle swarm optimization support vector machine algorithm is used for searching the optimal support vector machine parameter combination by continuously updating the position and the speed of particles and utilizing the searching capability of the particle swarm algorithm, so that the performance and the generalization capability of the model are improved.
Preferably, the fitness function is expressed as:
；
wherein,and->Respectively representing a training output value and an expected value of the support vector machine model;
xrepresented as an input vector;
Ma dimension represented as an input vector;
lrepresenting the number of elements;
f (x) is expressed as a fitness function.
Preferably, the future wind power data and load data are predicted by using a trained support vector machine model to obtain predicted wind power data of distributed energy and predicted demand data of load side resources, and the stopping calculation comprises the following steps:
s281, predicting future wind power data and load data by using a trained support vector machine model;
s282, presetting a reliability threshold, filtering a low reliability prediction result, and determining class labels of wind power data and load data from probability prediction of a support vector machine model;
s283, taking the determined category labels as the predicted power generation data of the distributed energy and the predicted demand data of the load side resource, and stopping calculation.
Preferably, the predicting wind power data and the predicted demand data of the load side resource are predicted by using a prediction algorithm, and the generating of the micro-grid power dispatching strategy comprises the following steps:
s31, inputting initial sample sets of wind power data to be processed and predicted demand data of load side resources;
s32, grading all wind power data of the initial sample set and predicted demand data of load side resources to obtain a plurality of sample subsets containing different wind power data and predicted demand data of the load side resources;
s33, performing cyclic processing on each sample subset to obtain a principal component coefficient matrix;
s34, rearranging the principal component coefficient matrix, and transforming the initial sample set based on the principal component coefficient matrix to generate new wind power data and a predicted demand data sample of the load side resource;
s35, training a prediction model based on new wind power data and a predicted demand data sample of load side resources to obtain a sub-model for predicting power distribution of the micro-grid, returning to the step S32, and circularly presetting for a plurality of times to obtain an integrated prediction model;
s36, predicting a test sample set by using an integrated prediction model, and generating a preliminary power dispatching strategy by using wind power data and predicted demand data of load side resources;
and S37, determining the micro-grid power dispatching strategy through voting according to the prediction results of all the preliminary power dispatching strategies.
Preferably, performing a cyclic process on each sample subset to obtain a principal component coefficient matrix includes the steps of:
s331, performing cyclic processing on each sample subset to obtain a principal component coefficient matrix;
s332, carrying out principal component analysis on the new wind power data and the predicted demand data sample of the load side resource to obtain principal component coefficient vectors related to micro-grid power dispatching;
s333, repeating the steps S331 to S332 to obtain a plurality of groups of principal component coefficients, and combining the coefficients into a principal component coefficient matrix.
Specifically, the prediction algorithm is a heterogeneous multi-classifier integration algorithm, firstly, a rotating forest is adopted to transform and divide an original sample set to obtain a new sample set, then a support vector machine with high classification precision or a kernel matching tracking with high classification speed is selected by a specific proportion to serve as a basic integrated individual classifier, the new sample set is classified to obtain a prediction mark, and finally, the prediction mark under two models is combined.
Preferably, analyzing the generated micro grid power dispatching strategy based on the analysis algorithm, and implementing the power distribution of the micro grid comprises the following steps:
s41, receiving the generated micro-grid power dispatching strategy;
s42, determining an objective function and constraint conditions, and establishing an optimization model;
and S43, applying an analysis algorithm to the optimization model, and searching an optimal solution meeting constraint conditions as a final micro-grid power dispatching strategy.
Preferably, applying the analysis algorithm to the optimization model and finding an optimal solution satisfying the constraint condition as the final micro grid power dispatching strategy includes the following steps:
s431, whitening the observed signal to obtain a whitened observed signal so as to enable the whitened observed signal to meet preset conditions;
specifically, the whitening process is to eliminate correlation between observed signals so as to satisfy conditions such as zero mean and unit variance.
Specifically, the observed signal includes information such as power demand, power supply, and the like.
S432, initializing parameters of an analysis algorithm, and initializing a micro-grid power dispatching strategy;
in particular, the parameters include, but are not limited to, the number of optimization agents, the field of view distance, the maximum movement step size, etc.
Specifically, parameters required for initializing the algorithm, such as the number of groups, the maximum number of iterations, etc. And an initial micro-grid power dispatching strategy is provided as a starting point of the algorithm.
S433, calculating the negative entropy corresponding to each optimization agent through objective functionalization, and updating the bulletin board;
specifically, in the present invention, each optimization agent represents a power scheduling policy.
In particular, negative entropy can be considered as an indicator of the quality of a metric-optimized problem solution. In the present invention, the negative entropy is related to the total energy cost or carbon emissions of the power dispatching strategy, etc.
S434, each optimizing agent executes optimizing, gathering and tracking actions according to preset conditions, and updates the state;
specifically, each optimizing agent performs optimizing, aggregating, tracking and other actions according to certain conditions, and updates the state of the optimizing agent. These behaviors simulate the process of an optimization agent finding the optimal solution.
S435, if the preset iteration times are reached, executing a step S436, otherwise, executing a step S433;
s436, the global optimal position is taken to form a separation matrix, and a final micro-grid power dispatching strategy is obtained.
Specifically, the analysis algorithm is an independent component analysis (Independent Component Analysis, ICA) algorithm based on a shoal of fish algorithm (Artificial Fish Swarm Algorithm, AFSA). The algorithm combines the global search advantage of the fish swarm algorithm with the signal source separation capability of ICA.
The fish swarm algorithm is a group intelligent optimization algorithm for simulating foraging, swarming and rear-end collision behaviors of fishes. The algorithm performs global search in the solution space by simulating social behaviors of fish.
According to another embodiment of the present invention, as shown in fig. 2, there is also provided a micro grid optimal scheduling system based on new energy consumption, including:
the data collection and processing module 1 is used for constructing an energy monitoring sensing network, collecting energy data in the micro-grid, preprocessing the energy data, and extracting wind power data and load data in the energy data;
the characteristic extraction module 2 is used for integrating wind power data and load data by utilizing an optimization algorithm, and extracting characteristics of the integrated data to obtain predicted wind power data of the distributed energy and predicted demand data of load side resources;
the prediction and strategy generation module 3 is used for predicting the predicted wind power data and the predicted demand data of the load side resources by using a prediction model to generate a micro-grid power dispatching strategy;
the strategy analysis and implementation module 4 is used for analyzing the generated micro-grid power dispatching strategy based on an analysis algorithm and implementing power distribution of the micro-grid;
the data comparison and optimization module 5 is used for collecting and detecting the operation data of the micro-grid in real time, comparing the actual operation data with the predicted data, and evaluating and optimizing the scheduling strategy;
the strategy implementation and iteration optimization module 6 is used for reapplying the optimized scheduling strategy to the micro-grid and carrying out power distribution of the micro-grid of a new round until the optimal scheduling strategy is realized;
the data collection and processing module 1 is connected with the prediction and strategy generation module 3 through the feature extraction module 2, the prediction and strategy generation module 3 is connected with the data comparison and optimization module 5 through the strategy analysis and implementation module 4, and the data comparison and optimization module 5 is connected with the strategy implementation and iteration optimization module 6.
In summary, by means of the above technical scheme, the wind power data and the load data are integrated and extracted by constructing the energy monitoring and sensing network, so that the electric power demand and the wind power supply of the micro-grid can be predicted more accurately, and the energy utilization efficiency is improved. According to the invention, by utilizing the optimization algorithm, the optimal operation decision can be found by calculating the fitness value of each operation decision, so that the operation of the micro-grid is more efficient and stable, and according to the preset condition, the fitness variance of the operation decision is calculated, and whether the variation operation is carried out or not is judged, so that the scheduling strategy has higher flexibility when coping with the change of wind power data and load data, the power scheduling efficiency and precision of the micro-grid can be effectively improved, the micro-grid is helped to better adapt to the change of energy demands, the energy utilization efficiency is improved, and the operation stability of the micro-grid is enhanced. According to the invention, a preliminary power scheduling strategy is generated by utilizing wind power data and predicted demand data of load side resources, and the power scheduling strategy of the micro-grid is determined through voting, so that the micro-grid can adaptively perform power scheduling according to actual conditions, thereby improving the running stability of the micro-grid, training a prediction model based on new wind power data and predicted demand data samples of the load side resources, obtaining a sub-model for predicting the power distribution of the micro-grid, and more accurately performing power distribution according to actual demands, thereby improving the running efficiency of a power system. According to the invention, through the analysis algorithm, the optimal power scheduling strategy meeting the constraint condition can be found through the setting of the objective function and the constraint condition and the application of the analysis algorithm, so that the power distribution of the micro-grid is optimized, the power utilization efficiency is improved, and the optimizing, gathering and tracking actions are executed according to the preset condition through each optimizing agent, and the state is updated, so that the optimal solution can be quickly found under the condition of meeting the preset iteration times, thereby improving the optimizing efficiency, and further improving the self-adaption capability and the running stability of the micro-grid
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. The micro-grid optimal scheduling method based on new energy consumption is characterized by comprising the following steps of:
s1, constructing an energy monitoring and sensing network, collecting energy data in a micro-grid, preprocessing the energy data, and extracting wind power data and load data in the energy data;
s2, integrating wind power data and load data by using an optimization algorithm, and extracting features of the integrated data to obtain predicted wind power data of the distributed energy and predicted demand data of load side resources;
s3, predicting the predicted wind power data and the predicted demand data of the load side resource by using a prediction algorithm to generate a micro-grid power dispatching strategy;
s4, analyzing the generated micro-grid power dispatching strategy based on an analysis algorithm, and implementing power distribution of the micro-grid;
s5, collecting and detecting operation data of the micro-grid in real time, comparing actual operation data with predicted data, and evaluating and optimizing a scheduling strategy;
s6, reapplying the optimized dispatching strategy to the micro-grid, and carrying out power distribution of the micro-grid of a new round until the optimal dispatching strategy is realized;
the method for constructing the energy monitoring and sensing network, collecting energy data in the micro-grid, preprocessing the energy data, and extracting wind power data and load data in the energy data comprises the following steps:
s11, distributing distributed monitoring sites by using a geographic information system technology, and establishing an energy monitoring and sensing network;
s12, acquiring original energy data of a distributed monitoring site in a micro-grid;
s13, performing wavelet transformation on the original energy data, converting from a time domain to a frequency domain, and screening out a frequency band containing interference waves;
s14, tracking and acquiring the interference wave direction in the frequency band;
s15, selecting a plurality of road windows with the calculated sample points as centers to perform median filtering, and recovering interference signals at the calculated sample points;
s16, recovering interference signals in each frequency band one by one, and performing wavelet inverse transformation to obtain the whole wave field of the interference wave;
s17, subtracting the interference wave field from the original energy data to obtain an effective signal wave field;
s18, generating denoised original energy data based on an effective signal wave field, checking the original energy data, extracting effective data and normalizing the effective data to obtain wind power data and load data in the energy data;
the method for obtaining the predicted wind power data of the distributed energy and the predicted demand data of the load side resource by utilizing the optimization algorithm to integrate the wind power data and the load data and extracting the characteristics of the integrated data comprises the following steps:
s21, setting related parameters, integrating wind power data and load data, extracting features, and generating an initial operation decision and a corresponding decision change rate;
s22, calculating the fitness value of each operation decision according to the set fitness function;
s23, calculating the adaptability variance of the operation decision according to preset conditions, and judging whether to perform mutation operation or not;
s24, updating the change rate and the position of the decision according to the calculated adaptability variance and inertia weight formula;
s25, checking whether an end condition is met, if so, ending the optimization, otherwise, turning to the step S22 to continue the optimization;
s26, assigning the optimized parameters to a support vector machine model;
s27, inputting the processed wind power data and load data into a support vector machine model, and training a support vector machine to obtain a trained support vector machine model;
s28, predicting future wind power data and load data by using the trained support vector machine model to obtain predicted wind power data of the distributed energy and predicted demand data of load side resources, and stopping calculation;
the method for generating the micro-grid power scheduling strategy comprises the following steps of:
s31, inputting initial sample sets of wind power data to be processed and predicted demand data of load side resources;
s32, grading all wind power data of the initial sample set and predicted demand data of load side resources to obtain a plurality of sample subsets containing different wind power data and predicted demand data of the load side resources;
s33, performing cyclic processing on each sample subset to obtain a principal component coefficient matrix;
s34, rearranging the principal component coefficient matrix, and transforming the initial sample set based on the principal component coefficient matrix to generate new wind power data and a predicted demand data sample of the load side resource;
s35, training a prediction model based on new wind power data and a predicted demand data sample of load side resources to obtain a sub-model for predicting power distribution of the micro-grid, returning to the step S32, and circularly presetting for a plurality of times to obtain an integrated prediction model;
s36, predicting a test sample set by using an integrated prediction model, and generating a preliminary power dispatching strategy by using wind power data and predicted demand data of load side resources;
and S37, determining the micro-grid power dispatching strategy through voting according to the prediction results of all the preliminary power dispatching strategies.
2. The micro-grid optimal scheduling method based on new energy consumption according to claim 1, wherein the expression of the fitness function is:
；
wherein,and->Respectively representing a training output value and an expected value of the support vector machine model;
xrepresented as an input vector;
Ma dimension represented as an input vector;
lrepresenting the number of elements;
f (x) is expressed as a fitness function.
3. The micro-grid optimal scheduling method based on new energy consumption according to claim 1, wherein the predicting future wind power data and load data by using a trained support vector machine model to obtain predicted wind power data of distributed energy and predicted demand data of load side resources, and stopping calculation comprises the following steps:
s281, predicting future wind power data and load data by using a trained support vector machine model;
s282, presetting a reliability threshold, filtering a low reliability prediction result, and determining class labels of wind power data and load data from probability prediction of a support vector machine model;
s283, taking the determined category labels as the predicted power generation data of the distributed energy and the predicted demand data of the load side resource, and stopping calculation.
4. The micro-grid optimal scheduling method based on new energy consumption according to claim 1, wherein the performing the cyclic processing on each sample subset to obtain the principal component coefficient matrix comprises the following steps:
s331, performing cyclic processing on each sample subset to obtain a principal component coefficient matrix;
s332, carrying out principal component analysis on the new wind power data and the predicted demand data sample of the load side resource to obtain principal component coefficient vectors related to micro-grid power dispatching;
s333, repeating the steps S331 to S332 to obtain a plurality of groups of principal component coefficients, and combining the coefficients into a principal component coefficient matrix.
5. The micro-grid optimal scheduling method based on new energy consumption according to claim 1, wherein the analyzing algorithm-based analysis of the generated micro-grid power scheduling strategy and the implementation of the micro-grid power distribution comprises the following steps:
s41, receiving the generated micro-grid power dispatching strategy;
s42, determining an objective function and constraint conditions, and establishing an optimization model;
and S43, applying an analysis algorithm to the optimization model, and searching an optimal solution meeting constraint conditions as a final micro-grid power dispatching strategy.
6. The micro-grid optimal scheduling method based on new energy consumption according to claim 5, wherein the steps of applying an analysis algorithm to an optimization model and searching an optimal solution meeting constraint conditions as a final micro-grid power scheduling strategy comprise the following steps:
s431, whitening the observed signal to obtain a whitened observed signal so as to enable the whitened observed signal to meet preset conditions;
s432, initializing parameters of an analysis algorithm, and initializing a micro-grid power dispatching strategy;
s433, calculating the negative entropy corresponding to each optimization agent through objective functionalization, and updating the bulletin board;
s434, each optimizing agent executes optimizing, gathering and tracking actions according to preset conditions, and updates the state;
s435, if the preset iteration times are reached, executing a step S436, otherwise, executing a step S433;
s436, the global optimal position is taken to form a separation matrix, and a final micro-grid power dispatching strategy is obtained.
7. A new energy consumption-based micro-grid optimal scheduling system for implementing the new energy consumption-based micro-grid optimal scheduling method as set forth in any one of claims 1 to 6, wherein the new energy consumption-based micro-grid optimal scheduling system comprises:
the data collection and processing module is used for constructing an energy monitoring sensing network, collecting energy data in the micro-grid, preprocessing the energy data, and extracting wind power data and load data in the energy data;
the characteristic extraction module is used for integrating wind power data and load data by utilizing an optimization algorithm, and extracting characteristics of the integrated data to obtain predicted wind power data of the distributed energy and predicted demand data of load side resources;
the prediction and strategy generation module is used for predicting the predicted wind power data and the predicted demand data of the load side resources by using a prediction algorithm to generate a micro-grid power dispatching strategy;
the strategy analysis and implementation module is used for analyzing the generated micro-grid power dispatching strategy based on an analysis algorithm and implementing power distribution of the micro-grid;
the data comparison and optimization module is used for collecting and detecting the operation data of the micro-grid in real time, comparing the actual operation data with the predicted data, and evaluating and optimizing the scheduling strategy;
the strategy implementation and iteration optimization module is used for reapplying the optimized scheduling strategy to the micro-grid and carrying out power distribution of the micro-grid of a new round until the optimal scheduling strategy is realized;
the data collection and processing module is connected with the prediction and strategy generation module through the feature extraction module, and the prediction and strategy generation module is connected with the data comparison and optimization module through the strategy analysis and implementation module and the strategy implementation and iteration optimization module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311456729.5A CN117175694B (en) | 2023-11-03 | 2023-11-03 | Micro-grid optimal scheduling method and system based on new energy consumption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311456729.5A CN117175694B (en) | 2023-11-03 | 2023-11-03 | Micro-grid optimal scheduling method and system based on new energy consumption |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117175694A CN117175694A (en) | 2023-12-05 |
| CN117175694B true CN117175694B (en) | 2024-01-23 |
Family
ID=88939843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311456729.5A Active CN117175694B (en) | 2023-11-03 | 2023-11-03 | Micro-grid optimal scheduling method and system based on new energy consumption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117175694B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117791613A (en) * | 2024-02-27 | 2024-03-29 | 浙电(宁波北仑)智慧能源有限公司 | Decision method and system based on resource cluster regulation and control |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112003279A (en) * | 2020-08-21 | 2020-11-27 | 国网黑龙江省电力有限公司 | Method for evaluating new energy consumption capability of hierarchical micro-grid |
| CN116029498A (en) * | 2022-12-07 | 2023-04-28 | 南昌大学 | Micro-grid economic dispatching optimization method based on improved multi-objective artificial buzzer algorithm |
| CN116979611A (en) * | 2023-04-06 | 2023-10-31 | 国网湖北省电力有限公司随州供电公司 | Hierarchical optimization scheduling method for source network load storage |
-
2023
- 2023-11-03 CN CN202311456729.5A patent/CN117175694B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112003279A (en) * | 2020-08-21 | 2020-11-27 | 国网黑龙江省电力有限公司 | Method for evaluating new energy consumption capability of hierarchical micro-grid |
| CN116029498A (en) * | 2022-12-07 | 2023-04-28 | 南昌大学 | Micro-grid economic dispatching optimization method based on improved multi-objective artificial buzzer algorithm |
| CN116979611A (en) * | 2023-04-06 | 2023-10-31 | 国网湖北省电力有限公司随州供电公司 | Hierarchical optimization scheduling method for source network load storage |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117175694A (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | Multi-objective optimization of stand-alone hybrid PV-wind-diesel-battery system using improved fruit fly optimization algorithm | |
| Zhang et al. | Wind power prediction based on LS-SVM model with error correction | |
| CN117175694B (en) | Micro-grid optimal scheduling method and system based on new energy consumption | |
| CN111414717A (en) | XGboost-L ightGBM-based unit power prediction method | |
| CN109711609A (en) | Photovoltaic plant output power predicting method based on wavelet transformation and extreme learning machine | |
| CN115796393B (en) | Energy management optimization method, system and storage medium based on multi-energy interaction | |
| CN114021390A (en) | Random robust optimization method for urban comprehensive energy system and application thereof | |
| CN109002926A (en) | The photovoltaic power generation quantity prediction model and its construction method of a kind of high accuracy and application | |
| Noman et al. | Comprehensive review of wind energy in Malaysia: Past, present, and future research trends | |
| CN115065078B (en) | Energy storage capacity configuration method and system in micro-grid environment | |
| Gao et al. | Optimal parameter selection for support vector machine based on artificial bee colony algorithm: a case study of grid-connected pv system power prediction | |
| CN116014715A (en) | Digital twinning-based comprehensive energy control method and system | |
| CN116581750A (en) | Intelligent line load charging method based on power grid load level | |
| Quaiyum et al. | Application of artificial neural network in forecasting solar irradiance and sizing of photovoltaic cell for standalone systems in Bangladesh | |
| CN108846529A (en) | A kind of generated energy forecasting system | |
| CN110472770A (en) | A kind of photovoltaic power generation power prediction method | |
| CN105844350A (en) | Short period wind power prediction system based on covariance preferable combination model | |
| CN116167508B (en) | Short-term photovoltaic output rapid prediction method and system based on meteorological factor decomposition | |
| CN102156408B (en) | System and method for tracking and controlling maximum power point in dynamically self-adaptive evolvement process | |
| CN116720751A (en) | Collaborative planning method of comprehensive energy system considering garbage power generation carbon circulation | |
| CN116826726A (en) | Micro-grid power generation amount prediction method, device and storage medium | |
| CN116914719A (en) | Photovoltaic power station power prediction method based on space-time diagram network | |
| CN116128154A (en) | Energy optimal configuration method and device for agricultural park comprehensive energy system | |
| CN113488990B (en) | Micro-grid optimal scheduling method based on improved bat algorithm | |
| Ghazanfari-Rad et al. | A Survey of Renewable Energy Approaches in Cloud Data Centers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |