CN116128154A - Energy optimal configuration method and device for agricultural park comprehensive energy system - Google Patents
Energy optimal configuration method and device for agricultural park comprehensive energy system Download PDFInfo
- Publication number
- CN116128154A CN116128154A CN202310254512.XA CN202310254512A CN116128154A CN 116128154 A CN116128154 A CN 116128154A CN 202310254512 A CN202310254512 A CN 202310254512A CN 116128154 A CN116128154 A CN 116128154A
- Authority
- CN
- China
- Prior art keywords
- energy
- loads
- agricultural park
- day
- agricultural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 241000283153 Cetacea Species 0.000 claims abstract description 46
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 39
- 238000005457 optimization Methods 0.000 claims abstract description 32
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 18
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 18
- 238000004146 energy storage Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 230000001965 increasing effect Effects 0.000 claims description 5
- 230000005611 electricity Effects 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 2
- RVRCFVVLDHTFFA-UHFFFAOYSA-N heptasodium;tungsten;nonatriacontahydrate Chemical compound O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.[Na+].[Na+].[Na+].[Na+].[Na+].[Na+].[Na+].[W].[W].[W].[W].[W].[W].[W].[W].[W].[W].[W] RVRCFVVLDHTFFA-UHFFFAOYSA-N 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 claims description 2
- 238000010977 unit operation Methods 0.000 claims description 2
- 239000013598 vector Substances 0.000 description 13
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 12
- 238000005265 energy consumption Methods 0.000 description 11
- 238000003860 storage Methods 0.000 description 10
- 239000007789 gas Substances 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000005485 electric heating Methods 0.000 description 5
- 239000003345 natural gas Substances 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 238000005338 heat storage Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 239000002918 waste heat Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000002737 fuel gas Substances 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000009133 cooperative interaction Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000003245 working effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- 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
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Geometry (AREA)
- Water Supply & Treatment (AREA)
- Marine Sciences & Fisheries (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Animal Husbandry (AREA)
- Medical Informatics (AREA)
- Agronomy & Crop Science (AREA)
- Computer Hardware Design (AREA)
- Mining & Mineral Resources (AREA)
- Educational Administration (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
Abstract
The invention discloses an energy optimal configuration method and device for an agricultural park comprehensive energy system, and belongs to the technical field of energy optimal scheduling. The method comprises the following steps: clustering the daily time series data of different types of loads of the agricultural park comprehensive energy system to determine typical representative daily operation scenes corresponding to the loads; based on typical representative daily operation scenes of each load, constructing a multi-objective optimization configuration model of the agricultural park comprehensive energy system; solving the multi-objective optimal configuration model by adopting a whale algorithm to obtain equipment capacity optimal configuration schemes of different types of loads; when the whale algorithm performs position updating iteration, the surrounding method or the spiral bubble method is selected to perform hunting sports based on the position obtained by multiplying the current best position and the self-adaptive weight. The invention can improve the economical efficiency and low carbon property of energy supply of the agricultural park and improve the comprehensive utilization rate of energy.
Description
Technical Field
The invention belongs to the technical field of energy optimization scheduling, and particularly relates to an energy optimization configuration method and device of an agricultural park comprehensive energy system.
Background
In the process of comprehensively propelling clean energy replacement, the rural agricultural planting mode is developed towards the multi-source, intensive and intelligent industrial planting direction of the agricultural park, the comprehensive development of all-purpose energy factors including fuel gas (or biological marsh gas), heat energy, water energy, electric energy and the like is realized, the distributed wind-solar energy storage of novel equipment is also introduced in a large scale, and the traditional agricultural planting mode is advanced towards the modern comprehensive agricultural park. However, the modern development of agricultural parks still has the following disadvantages: on one hand, the current agricultural park has the common characteristics that the production and the energy consumption are still rough, the problems of low energy utilization efficiency, unreasonable energy structure and the like still exist, and the effective peak clipping means are required to be further deeply, reasonably and fully utilized, so that the energy utilization rate in the agricultural park is improved; on the other hand, along with the increasing planting scale of the agricultural park, the energy types are continuously and complexly coupled, the production and the energy consumption in the park are increasingly increased, and the situation that the reasonable and effective planning is not carried out is bound to deviate from the national energy-saving and carbon-reducing aim.
In the aspect of energy station planning of an integrated energy system of an agricultural park, the capacity planning of equipment mostly comprises two aspects, namely coupling cooperation among multiple heterogeneous energy sources and energy storage planning. The energy station equipment capacity optimization model is established by combining the energy storage operation rule and annual operation simulation by a learner considering two aspects of economic factors and environmental factors. In the aspect of economy, the optimal benefit is taken as a target, a micro-energy system optimization planning model is established, related researches are carried out from the two aspects of capacity and power of different equipment, and the solving process is continuously simplified so as to achieve the aim of optimal configuration of the system; in the aspect of environmental protection, the factors such as energy supply and demand balance, heterogeneous energy coupling condition, electric energy substitution condition and the like are considered, the related equipment condition of the energy storage link is analyzed, an energy storage mathematical model is constructed, and optimal configuration solving is carried out.
Although the informatization intelligent degree of the agricultural field in China is higher and higher at present, the energy data in the agricultural park is lack of uniform collection and integration. Meanwhile, the existing research is based on model solving consideration, only partial constraint conditions are often considered, and the actual operation scene of the comprehensive energy system of the agricultural park cannot be accurately represented. In addition, when the objective function is solved by using the traditional whale algorithm, the optimizing capability is poor.
Disclosure of Invention
The invention aims to provide an energy optimization configuration method and device for an agricultural park comprehensive energy system, so as to ensure the representativeness and comprehensiveness of scenes when the agricultural park comprehensive energy system is configured, and optimize the global and local optimizing capability of a configuration model solving algorithm.
In the 1 st aspect, an energy optimization configuration method of an agricultural park comprehensive energy system is disclosed, and the method comprises the following steps:
clustering the daily time series data of different types of loads of the agricultural park comprehensive energy system to determine typical representative daily operation scenes corresponding to the loads;
based on typical representative daily operation scenes of each load, constructing a multi-objective optimization configuration model of the agricultural park comprehensive energy system;
solving the multi-objective optimal configuration model by adopting a whale algorithm to obtain equipment capacity optimal configuration schemes of different types of loads; when the whale algorithm performs position updating iteration, the surrounding method or the spiral bubble method is selected to perform hunting sports based on the position obtained by multiplying the current best position and the self-adaptive weight.
In one embodiment, the convergence factor of the whale algorithm is a nonlinear convergence factor, the convergence factor value is increased in the early stage of iteration, and the convergence factor value is decreased in the later stage of iteration.
In one embodiment, the nonlinear convergence factor
The method comprises the following steps:
wherein ,
as initial value of convergence factor lambda a To control the factor T max Is the maximum number of iterations.
In one embodiment, the adaptive weights δ (t) are:
in one embodiment, the clustering the time-of-day sequence data of different loads of the integrated energy system of the agricultural park to determine a typical representative day operation scene corresponding to each load includes: acquiring historical data of three different loads, namely cold, heat and electricity, and constructing a time-of-day sequence data set corresponding to the three loads; the time of day series data sets are clustered using K-means to obtain a number of classes of representative day comprising different loads and day load output characteristic data for each class of representative day.
In one embodiment, the representative days include spring and autumn holidays, summer and winter holidays, and winter holidays.
In one embodiment, the objective function of the multi-objective optimal configuration model is: f=min { F 1 +f 2 -a }; wherein F is the comprehensive operation cost of the agricultural park; f (f) 1 The production running cost of the agricultural park is; f (f) 2 Cost is reduced for carbon emission treatment.
In one embodiment, the constraints of the multi-objective optimal configuration model include one or a combination of the following constraints: energy balance constraints, installed capacity constraints, equipment output limit constraints, energy storage equipment constraints, new energy supply constraints, and carbon emission constraints.
In the 2 nd aspect, an energy optimizing configuration device of an agricultural park comprehensive energy system is disclosed, the device comprises:
the clustering module is configured to cluster the time-of-day sequence data of different loads of the agricultural park comprehensive energy system so as to determine typical representative day operation scenes corresponding to the loads;
the modeling module is configured to construct a multi-objective optimization configuration model of the agricultural park comprehensive energy system based on typical representative daily operation scenes of each load;
the solving module is configured to solve the multi-objective optimal configuration model by adopting a whale algorithm to obtain equipment capacity optimal configuration schemes of different types of loads; when the whale algorithm performs position updating iteration, the surrounding method or the spiral bubble method is selected to perform hunting sports based on the position obtained by multiplying the current best position and the self-adaptive weight.
Compared with the prior art, the method has the advantages that the application scene of the typical representative day of the comprehensive energy system of the agricultural park is obtained by carrying out cluster analysis on the user load of the agricultural park, a multi-objective model is established by taking the minimum carbon emission of the park and the minimum system running cost as targets, and the multi-objective optimization solution is carried out by using an improved whale algorithm, so that the economy and low carbon of park energy supply can be improved, the energy storage equipment configuration such as electricity storage, cold storage, heat storage and gas storage is enlarged, the comprehensive energy utilization rate is further improved, and the method can be applied to the optimal configuration of the comprehensive energy system of the complex agricultural park.
Drawings
FIG. 1 is a schematic diagram of a typical agricultural park integrated energy flow;
FIG. 2 is a schematic flow chart of an energy optimization configuration method of an agricultural park comprehensive energy system according to an embodiment of the invention;
FIG. 3 is a schematic diagram of an energy optimizing configuration device of an agricultural park comprehensive energy system according to an embodiment of the invention;
fig. 4 (a) is a working day electric load output characteristic curve obtained by clustering, and fig. 4 (b) is a holiday electric load output characteristic curve obtained by clustering;
fig. 5 (a) is a working day cold load output characteristic curve obtained by clustering, and fig. 4 (b) is a holiday cold load output characteristic curve obtained by clustering;
fig. 6 (a) is a working day heat load output characteristic curve obtained by clustering, and fig. 4 (b) is a holiday heat load output characteristic curve obtained by clustering;
FIG. 7 is a graph showing the comparison of the convergence curves of example 1 using the genetic algorithm, the conventional WOA algorithm, and the modified WOA algorithm.
Detailed Description
Embodiments of the present invention are described in detail below with reference to the accompanying drawings.
FIG. 1 is a schematic diagram of a typical agricultural park integrated energy flow. As shown in fig. 1, the integrated energy system is composed of a plurality of parts, mainly including: the energy storage system, the virtual power plant, the demand management side system, the electric heating water-gas system and the like, and meanwhile, the different parts can also generate cooperative interaction of different energy sources, and the comprehensive energy source system can generate mutual conversion among various energy sources, so that the efficient utilization of energy sources is promoted. The comprehensive energy system can coordinate and optimize a plurality of distributed power supplies so as to facilitate reasonable utilization and optimal configuration of resources.
By analyzing the energy flow relation of the park energy system, the typical requirement of the park comprehensive energy is analyzed from the energy supply side, the energy conversion link and the load requirement side, and the typical characteristics and the main energy supply units of different types of parks are compared.
Data metering layer: is a basic data layer of the whole system and comprises various energy data such as cold, hot, electric water and the like in a park. The bottom layer equipment of the comprehensive energy management system comprises a deployment acquisition gateway, an electric heat metering device, a communication cable between the metering device and the acquisition gateway, and finally various meter data are accessed to the comprehensive energy management center. The equipment layer is the basis of the whole system, is various intelligent metering devices installed in the park, and is used for collecting and integrating various energy consumption data in the park.
Data transmission layer: the intelligent gateway transmits various collected data to a first level through Ethernet and the like. The data acquisition layer is an on-site acquisition system, the energy management system is used for completing data acquisition of various metering devices of cold and hot electric water in an agricultural park, the metering devices are connected into the data acquisition gateway through an RS485 MODBUS protocol, energy data acquisition and processing are realized, and various energy consumption data are provided for supervision of the system.
System storage layer: and carrying out energy consumption analysis and storage on the acquired data, and classifying and storing the energy consumption data by using a main stream structured database so as to improve the processing performance of the whole system. The energy consumption data information of the field instrument is automatically acquired through the communication module and the network, so that the real-time acquisition and display of the energy consumption are realized.
System processing layer: the system is used for tracking and evaluating the energy consumption condition of the system by establishing a related model, carrying out background analysis on the energy consumption condition by utilizing big data analysis, intelligent calculation and the like, and intuitively displaying the energy consumption condition by a control interface, providing a monitoring operation interface by the system, adopting a menu to carry out interface switching, and displaying real-time energy data of multiple areas of each level, flow directions and consumption conversion conditions of various energy sources, working states and configuration information of the intelligent metering instrument and the like by the interface.
By constructing system functions and equipment components comprising a metering layer, a transmission layer, a storage layer and a processing layer, a unified data base is provided for the follow-up specific comprehensive energy planning.
Fig. 2 is a schematic flow chart of an energy optimization configuration method 200 of an agricultural park comprehensive energy system according to an embodiment of the invention. As shown in fig. 2, the method 200 includes the steps of:
step 201, clustering time-of-day sequence data of different loads of an agricultural park comprehensive energy system to determine typical representative day operation scenes corresponding to the loads;
the accuracy of the load model is directly related to the rationality of the optimization configuration of the park comprehensive energy system. There are many types of farm loads, and there are uncertainty and timing characteristics. The invention uses K-means to perform cluster analysis on the agricultural park load, taking an agricultural park comprehensive energy system containing cold, heat and electric loads as an example, and specifically comprises the following steps:
step S1, acquiring historical data of three different loads of cold, heat and electricity, and constructing a time-of-day sequence data set D= { D corresponding to the three loads i I e {1,2,3 }; wherein D is i ＝{x i1 ,x i2 ,L,x im And } represents a load time series.
In one embodiment, the present invention sets six types of typical days according to the work day and load distribution characteristics: spring and autumn holidays, spring and autumn weekdays, summer holidays, summer weekdays, winter holidays, and winter weekdays, expressed as c= { C 1 ,C 2 ,L,C k ,L,C 6 }。
Step S2, the time-of-day sequence data set D= { D i I e {1,2,3} } characterizing to form a training dataset;
specifically, data x i Performing dimensionless treatment by using a formula (1):
step S3, randomly selecting a sample time sequence corresponding to six typical days from the training data set, and sequentially taking the sample time sequence as a centroid vector of the cold-hot electric load;
randomly selecting 6×3 sample time series from six corresponding spring and autumn holidays, spring and autumn working days, summer holidays, summer working days, winter holidays and winter working days in the training data set, and sequentially using the time series as k centroid vectors of cold and hot electric loads (sequentially expressed by 1,2 and 3), wherein the k centroid vectors are expressed as U= { { mu } 1 ,μ 2 ,Lμ 6 I=1, 2,3}, where μ 1 ,μ 2 ,Lμ 6 A time series corresponding to the spring and autumn holidays, summer holidays, winter holidays, and winter holidays in sequence.
S4, calculating Pearson coefficients of two time sequences of the training data set and each centroid vector, and classifying according to the maximum Pearson coefficient;
calculating training data set and each centroid vector U i Pearson coefficients of two time sequences of (j=1, 2, lk), according to the sum U i The largest Pearson coefficient is categorized.
Let two time sequences x= { X 1 ,x 2 ,L,x t L x n }，Y＝{y 1 ,y 2 ,L,y t L y n -then:
s5, recalculating the mass center of the data points in the classification result;
the new centroid is recalculated for all sample points divided into Ui, i.e.:
repeating the steps S3 to S5 until the centroid sequence is not changed or the maximum iteration number is reached, and outputting a clustering result, wherein the clustering result comprises six types of typical representative day numbers of different loads and daily load output characteristic data of each type of typical representative day.
Aiming at the shortages and time sequence characteristics of multiple energy sources such as electric heating and cooling in an agricultural park, the invention adopts a typical user load classification method based on K-means, combines seasonality and working property to be divided into six types of loads including representative spring and autumn holidays, spring and autumn working days, summer holidays, summer working days, winter holidays and winter working days, thereby ensuring the representativeness and comprehensiveness of scenes when an energy system is configured, reducing the calculated amount compared with daily optimization in the whole year, and improving the calculation efficiency.
Step 202, constructing an agricultural park comprehensive energy system multi-objective optimization configuration model based on typical representative daily operation scenes of each load;
the method is used for constructing a multi-objective optimal configuration model by taking the minimum running cost of the agricultural park comprehensive energy system and the minimum park carbon emission calculation cost as targets. Considering the calculation efficiency of the annual operation condition, the invention adopts the typical daily operation condition to replace the annual operation condition, namely, the objective function of the multi-objective optimal configuration model is as follows:
F＝min{f 1 +f 2 } (4)
wherein F is the comprehensive operation cost of the agricultural park; f (f) 1 The production running cost of the agricultural park is; f (f) 2 Cost is reduced for carbon emission treatment.
Wherein N represents the total number of days of the typical scene adopted; d, d n Representing the total number of days of the nth scene; s is S n,i,t Representing the unit operation maintenance cost of the device i at the time t on the nth typical day; l (L) n,i,t A power output value of the device i at the time t on the nth typical day is represented; lambda (lambda) i Representing annual equity investment conversion coefficients of equipment in the system;
representing the investment cost of the m-th class of equipment i in each unit capacity; />
Representing the capacity of class m device i.
in the formula ,ξi Representing the carbon emission coefficient of the device i; omega c Cost per ton of carbon emissions treatment; q (Q) i1 And (t) represents the input energy of the conversion device i at the time t.
in the formula ,
the annual discount rate of the equipment in the system; and l is the service life of the equipment in the system.
Meanwhile, the invention sets the following constraint conditions for the multi-objective optimal configuration model: energy balance constraints, installed capacity constraints, equipment output limit constraints, energy storage equipment constraints, new energy supply constraints, and carbon emission constraints.
(1) Energy balance constraint:
in the formula ,Pt c 、P t pv The power generation power of the CCHP unit and the photovoltaic generator unit at the time t is P t pp The power purchased at time t; p (P) t l Power lost at time t;
the heat of the CCHP unit, the gas boiler and the purchase at the time t are respectively; />
The heat/cold power loss at time t; />
Natural gas energy purchased to the outside for the comprehensive energy system; />
The natural gas energy of the combustion of the CCHP unit is represented; />
Natural gas energy consumed by the gas boiler is represented; />
Is the loss of natural gas; p (P) t E1 、
The electrical load demand, the heat/cold load demand and the natural gas demand of the user at time t, respectively.
(2) Installed capacity constraints
Z i,min ≤Z i ≤Z i,max (9)
in the formula ,Zi,min and Zi,max The upper and lower limits of installation capacity are allowed for the in-energy center device i.
(3) Force limiting constraint for a device
in the formula ,ηi,min 、η i,max The maximum load rate and the minimum load rate of the ith equipment in the comprehensive energy system are respectively.
(4) Restraint of energy storage devices
in the formula ,
represents the lower energy storage limit of the alpha-th device, < ->
Representing an upper energy storage limit; />
Indicating the upper limit of the charging efficiency of the alpha-th device,/->
An upper energy release limit; s is S α Is the storage capacity of the energy storage device.
(5) New energy supply constraint
0≤∑S PV ≤S PVmax (14)
in the formula ,SPV Representing the footprint of the photovoltaic in the agricultural park; s is S PVmax Representing the maximum planable floor area of photovoltaic power generation in the agricultural park.
(6) Carbon emission constraints
in the formula ,
representing co generated by device i at runtime 2 ，T i Representing the runtime of device i, Q it Representation devicei input energy at time t, +.>
Representing all devices co 2 Maximum discharge.
The multi-objective optimization configuration model of the agricultural park comprehensive energy system constructed by the invention not only considers the production and operation costs of the park, but also considers the carbon emission costs of the comprehensive energy system, and the optimization objective takes both economy and environmental protection into consideration. On the other hand, the constraint conditions consider the practical production and operation constraint conditions of equipment such as energy balance constraint, equipment installed capacity and operation rated power constraint, energy storage equipment constraint, carbon emission constraint and the like, and the optimal configuration model is ensured to be more suitable for practical production.
And 203, solving the multi-objective optimal configuration model by adopting a whale algorithm to obtain the equipment capacity optimal configuration schemes of different types of loads.
Traditional WOA mainly involves several stages of searching, hunting, predation, and resuming searching for hunting. The whale can take the position of the whale as a feasible solution in the predation moving process, and the global optimal solution is obtained along with the continuous position updating process of the whale in the hunting searching process, and the traditional WOA steps are as follows:
(1) Hunting object
When whale carries out hunting, the whale needs to surround the hunting object first, and meanwhile, the position information of whale is updated, and the formula is updated as shown in formula (16).
D(t+1)＝D * (t)-α×d (16)
d＝|β×D * (t)-d(t)| (17)
Wherein alpha and beta are vector coefficients, t is the current iteration number, D * (t) represents the best position so far and D (t) represents the position vector in which whale is currently located. Alpha and beta can be obtained from the following formula:
α＝(2λ 1 -1)×ω (18)
β＝2λ 2 (19)
in the formula ,λ1 and λ2 Is any number of (0, 1), T max For the maximum number of iterations to be performed,
is a convergence factor.
(2) Bubble-net predation
When whale is in spiral feeding, the position updating mode of whale is expressed by the formula (21):
D(t+1)＝D * (t)+d p e kl cos(2πl) (21)
d l ＝|D * (t)-D(t)| (22)
in the formula ,dl Indicating the distance from whale to target, D * (t) represents the best current position vector, k is a spiral-shaped parameter, l is a uniformly distributed random number, and the value range is [ -1,1]。
When whale is contracted and surrounded by a game in a spiral form, WOA is determined according to probability P i To select the shrink wrap mechanism, select 1-P i The position of whale is updated, and the updated position is expressed as formula (23).
Wherein, p is the probability of predation mechanism, and the value range is the random number of [0,1 ].
(3) Searching for prey
In order to comprehensively search and catch the target, the WOA continuously updates the position of the target, and the distance between whales is mainly used as the basis for updating judgment. Therefore, when the absolute value A is more than or equal to 1, the caught individuals can be continuously approaching to the random whales.
D(t+1)＝D r -α×d 1 (25)
in the formula ,Dr Representing a position vector of a random whale, d 1 Represents the distance of the random whale from the current whale.
Due to the convergence factor of conventional WOA
The optimization is performed in a linear control mode, and in a multi-target optimization configuration scene of the comprehensive energy system in the agricultural park, the optimization effect cannot reflect the actual optimization searching process. Therefore, the invention improves the traditional whale algorithm, and adds self-adaptive weight and nonlinear convergence factor to enhance the optimizing capability of the algorithm.
(1) Nonlinear convergence factor
Whether the vector alpha changes is controlled by
But for multi-objective optimization of integrated energy systems there is a large computational effort and a large number of iterations, linear convergence factor ∈ ->
The WOA cannot be made to enter local search faster, so that the optimizing effect of the WOA cannot be better reflected.
Thus, the present invention is directed to a convergence factor
Is improved by increasing +.>
Value, thereby enhancing the seeking ability, promoting the omnibearing searching thereof, and reducing +.>
The value is used for improving the local search optimizing effect of WOA. Improved nonlinear Convergence factor->
Specific formulas of (c) are as (26):
in the formula ：
as initial value of convergence factor lambda a Is a control factor for adjusting the convergence speed.
(2) Adaptive weights
In order to prevent the optimal solution from falling into the local optimal condition, the invention adds self-adaptive weight in WOA to adjust the searching capability of the algorithm. When the self-adaptive weight is large, the WOA can perform global searching with a large range; when the adaptive weight is small, the WOA will perform a local search around the optimal solution. The expression of the adaptive weights is:
by combining the adaptive weights with a nonlinear convergence factor, the weights can be dynamically adjusted during the contraction process.
After adding the adaptive weights, the update of the location can be expressed by:
that is, the improved whale algorithm multiplies the current best position by the adaptive weight delta (t) when performing the position update, and selects the surrounding method or the spiral bubble method for hunting based on the multiplied position.
On this basis, the specific solving process for solving the objective function based on the aforementioned constraint condition is similar to that of the conventional WOA algorithm, and will not be described in detail here. For example, N target functions satisfying constraint conditions are randomly generated firstSolution vectors for variables in the number; taking the number N of solution vectors as the number of whales; taking the variable number M in the objective function as the dimension of a whale search space; taking the ith solution vector as the position X of the ith whale in M-dimensional space i The method comprises the steps of carrying out a first treatment on the surface of the The objective function value is taken as the fitness function value. Algorithm iterations are then performed, during which position updates are performed based on formulas (26), (27), (28). And when the final algorithm is finished, the obtained updated whale optimal position Xp is the optimal solution of the objective function.
The improved whale algorithm is adopted to carry out optimal configuration solving, the convergence factor is improved to evolve in a linear control mode on the basis of the traditional whale algorithm, the nonlinear control condition of the predation process cannot be described, the self-adaptive weight and nonlinear convergence factor algorithm is provided, the algorithm efficiency is improved, and meanwhile, the global and local optimizing capability of the algorithm is optimized.
Fig. 3 is a schematic diagram of an energy optimizing configuration device 300 of an agricultural park comprehensive energy system according to an embodiment of the invention. As shown in fig. 3, the apparatus 300 includes:
the clustering module 301 is configured to cluster time-of-day sequence data of different loads of the agricultural park comprehensive energy system so as to determine typical representative day operation scenes corresponding to the loads;
the modeling module 302 is configured to construct an agricultural park comprehensive energy system multi-objective optimization configuration model based on typical representative daily operation scenes of each load;
and the solving module 303 is configured to solve the multi-objective optimal configuration model by adopting a whale algorithm to obtain the equipment capacity optimal configuration schemes of different types of loads.
Example 1:
an integrated agricultural park is taken as a research object. The comprehensive agricultural park is provided with a photovoltaic power generation power supply, the installation capacity of the photovoltaic power generation power supply is 20% of the total load, the park comprises a plurality of loads such as agriculture, business and the like, and fuel gas is used as a standby source.
Firstly, clustering different data to obtain characteristic curves of various loads in one year. Specifically, the typical daily operation condition obtained by K-means clustering is adopted to replace the operation condition of each season, and the days of spring and autumn working days, spring and autumn holidays, summer working days, summer holidays, winter working days and winter holidays 75 days, 43 days, 75 days, 29 days, 99 days and 44 days in sequence can be obtained. The time sequence characteristic curves of the cold, heat and electric loads in the middle of the year are obtained through clustering and are shown in figures 4-6.
The equipment to be optimally configured comprises: the thermoelectric efficiency of the gas turbine is 0.35, the heat supply efficiency of the waste heat boiler is 0.88, the heat supply efficiency of the gas boiler is 0.92, the heat conversion efficiency of the electric heating boiler is 0.98, the electric-cold conversion efficiency of the cold supply heat pump is 0.4, the cold conversion efficiency of the absorption refrigerator is 0.8, the thermoelectric conversion efficiency of the extraction condensing turbine is 0.28, and the electric storage and heat storage efficiency is 0.95. The service life of the electric power storage device is 5 years, the service lives of the electric heating boiler, the gas boiler and the waste heat boiler are 15 years, and the service lives of other devices are 20 years. The energy storage configuration is to cut peaks and fill valleys (only consider electric load), and the optimal configuration is calculated according to 20 years, and the annual discount rate is 6%. The economic and technical parameters of the different optimally configured devices are shown in the following table.
The optimization variables are various equipment capacities (kVA or kW) of the agricultural park comprehensive energy system, the optimization model is a multi-objective optimization configuration model, the improved whale algorithm is adopted for solving, and then optimization is carried out on various scenes respectively, so that the comprehensive operation cost with the lowest accumulated value in the various scenes is obtained, and the corresponding scheme is the optimal configuration scheme.
Comparing the improved whale algorithm adopted by the invention with the traditional whale algorithm and genetic algorithm, the convergence curve of the optimized result is shown in figure 7. As can be seen from fig. 7, the conventional whale algorithm and genetic algorithm need to be further improved in terms of solving the optimal value, the improved whale algorithm has the advantages of high convergence rate, wider optimizing range and higher solving precision, and can be applied to the specific solution of the complex agricultural park optimal configuration.
The final comprehensive operation cost is 2842 ten thousand yuan, and the corresponding park equipment optimizing configuration scheme is shown in the following table:
| device category | Electric heating boiler | Heat pump | Electric refrigerator | Gas turbine | Internal combustion engine | Gas boiler |
| Capacity of the device | 415 | 426 | 1684 | 1114 | 900 | 1543 |
| Device category | Waste heat boiler | Absorption refrigerator | Storage battery | Heat storage tank | Cold accumulation tank | |
| Capacity of the |
0 | 1810 | 852 | 2120 | 2430 |
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same. Although the invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some or all of the technical features thereof, without departing from the spirit of the technical solutions of the embodiments of the invention.
Claims (10)
1. The energy optimization configuration method of the agricultural park comprehensive energy system is characterized by comprising the following steps of:
clustering the daily time series data of different types of loads of the agricultural park comprehensive energy system to determine typical representative daily operation scenes corresponding to the loads;
based on typical representative daily operation scenes of each load, constructing a multi-objective optimization configuration model of the agricultural park comprehensive energy system;
solving the multi-objective optimal configuration model by adopting a whale algorithm to obtain equipment capacity optimal configuration schemes of different types of loads; when the whale algorithm performs position updating iteration, the surrounding method or the spiral bubble method is selected to perform hunting sports based on the position obtained by multiplying the current best position and the self-adaptive weight.
2. The energy optimizing configuration method according to claim 1, wherein the convergence factor of the whale algorithm is a nonlinear convergence factor, the convergence factor value is increased in the early iteration stage, and the convergence factor value is decreased in the later iteration stage.
3. The energy optimizing configuration method according to claim 2, wherein the nonlinear convergence factor
The method comprises the following steps:
wherein ,
as initial value of convergence factor lambda a To control the factor T max Is the maximum number of iterations.
4. The energy optimizing configuration method according to claim 3, wherein the adaptive weight δ (t) is:
5. the energy optimizing configuration method according to claim 1, wherein the clustering the time-of-day sequence data of different loads of the integrated energy system of the agricultural park to determine a typical representative day operation scene corresponding to each load comprises: acquiring historical data of three different loads, namely cold, heat and electricity, and constructing a time-of-day sequence data set corresponding to the three loads; the time of day series data sets are clustered using K-means to obtain a number of classes of representative day comprising different loads and day load output characteristic data for each class of representative day.
6. The energy optimizing configuration method according to claim 5, wherein the representative days include spring-autumn holidays, summer holidays, winter holidays, and winter holidays.
7. The energy optimization configuration method according to claim 1, wherein the objective function of the multi-objective optimization configuration model is: f=min { F 1 +f 2 -a }; wherein F is the comprehensive operation cost of the agricultural park; f (f) 1 The production running cost of the agricultural park is; f (f) 2 Cost is reduced for carbon emission treatment.
8. The energy optimal configuration method according to claim 7, wherein the production running cost f of the agricultural park 1 Cost f for converting carbon emission treatment 2 The method comprises the following steps of:
wherein N represents the typical total days of day employed; d, d n Total days representing the nth representative day; s is S n,i,t Representing the unit operation maintenance cost of the device i at the time t on the nth representative day; l (L) n,i,t The output value of the device i at the time t is represented at the nth representative day; lambda (lambda) i A annual equity investment conversion coefficient representing the equipment i;
representing the investment cost of the m-th class of equipment i in each unit capacity; />
Representing the capacity of class m device i; zeta type toy i Representing the carbon emission coefficient of the device i; omega c Cost per ton of carbon emissions treatment; q (Q) i1 (t) represents the input energy of the conversion device i at the time tAmount of the components.
9. The energy optimal configuration method according to claim 7, wherein the constraint conditions of the multi-objective optimal configuration model include one or a combination of the following constraints: energy balance constraints, installed capacity constraints, equipment output limit constraints, energy storage equipment constraints, new energy supply constraints, and carbon emission constraints.
10. An energy optimizing configuration device of an agricultural park comprehensive energy system is characterized in that the device comprises:
the clustering module is configured to cluster the time-of-day sequence data of different loads of the agricultural park comprehensive energy system so as to determine typical representative day operation scenes corresponding to the loads;
the modeling module is configured to construct a multi-objective optimization configuration model of the agricultural park comprehensive energy system based on typical representative daily operation scenes of each load;
the solving module is configured to solve the multi-objective optimal configuration model by adopting a whale algorithm to obtain equipment capacity optimal configuration schemes of different types of loads; when the whale algorithm performs position updating iteration, the surrounding method or the spiral bubble method is selected to perform hunting sports based on the position obtained by multiplying the current best position and the self-adaptive weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310254512.XA CN116128154A (en) | 2023-03-16 | 2023-03-16 | Energy optimal configuration method and device for agricultural park comprehensive energy system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310254512.XA CN116128154A (en) | 2023-03-16 | 2023-03-16 | Energy optimal configuration method and device for agricultural park comprehensive energy system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116128154A true CN116128154A (en) | 2023-05-16 |
Family
ID=86295750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310254512.XA Pending CN116128154A (en) | 2023-03-16 | 2023-03-16 | Energy optimal configuration method and device for agricultural park comprehensive energy system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116128154A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116485042A (en) * | 2023-06-16 | 2023-07-25 | 国网上海能源互联网研究院有限公司 | Method and device for optimizing park energy system operation based on load clustering |
-
2023
- 2023-03-16 CN CN202310254512.XA patent/CN116128154A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116485042A (en) * | 2023-06-16 | 2023-07-25 | 国网上海能源互联网研究院有限公司 | Method and device for optimizing park energy system operation based on load clustering |
| CN116485042B (en) * | 2023-06-16 | 2023-09-01 | 国网上海能源互联网研究院有限公司 | Method and device for optimizing park energy system operation based on load clustering |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | Stochastic multi-scenario optimization for a hybrid combined cooling, heating and power system considering multi-criteria | |
| Song et al. | Hourly heat load prediction model based on temporal convolutional neural network | |
| CN106385025B (en) | A kind of distributed generation resource and interconnection multistage collaborative planning method | |
| CN113822496B (en) | Multi-unit thermal power plant heat supply mode and parameter online optimizing method | |
| CN111681130B (en) | Comprehensive energy system optimal scheduling method considering conditional risk value | |
| CN112952807B (en) | Multi-objective optimization scheduling method considering wind power uncertainty and demand response | |
| CN115065078B (en) | Energy storage capacity configuration method and system in micro-grid environment | |
| CN104376373A (en) | Distributed power supply planning method based on time sequence characteristic and environmental benefit | |
| CN111724064B (en) | Energy-storage-containing power distribution network planning method based on improved immune algorithm | |
| CN114418174A (en) | Electric vehicle charging load prediction method | |
| CN111639819A (en) | Multi-stage optimization control method for comprehensive energy park | |
| CN114154744A (en) | Capacity expansion planning method and device of comprehensive energy system and electronic equipment | |
| CN116128154A (en) | Energy optimal configuration method and device for agricultural park comprehensive energy system | |
| CN113887141A (en) | Micro-grid group operation strategy evolution method based on federal learning | |
| CN105514986A (en) | DER user bidding grid-connection method based on virtual power plant technology | |
| CN113488990B (en) | Micro-grid optimal scheduling method based on improved bat algorithm | |
| CN114117925A (en) | Comprehensive energy system planning method considering high-proportion distributed photovoltaic consumption | |
| CN117748444A (en) | Operation simulation method of power distribution system | |
| CN105552941B (en) | A kind of distributed generation resource peak capacity optimization method | |
| CN114139830B (en) | Optimal scheduling method and device for intelligent energy station and electronic equipment | |
| CN114186640B (en) | Regional hydropower overall power generation capacity prediction method | |
| CN115293502A (en) | Data-driven random-distribution robust low-carbon scheduling method for park integrated energy system | |
| CN114444955A (en) | Key parameter data mining and long-term configuration prediction method and system for comprehensive energy | |
| CN114240203A (en) | Power distribution network and distributed wind power collaborative planning method and device containing heat pump | |
| CN115660187B (en) | Low-carbon town ground source heat pump capacity optimization configuration method |
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 |