CN111340272A - Heat supply scheduling optimization method based on spider crowd-sourcing algorithm - Google Patents

Heat supply scheduling optimization method based on spider crowd-sourcing algorithm Download PDF

Info

Publication number
CN111340272A
CN111340272A CN202010093799.9A CN202010093799A CN111340272A CN 111340272 A CN111340272 A CN 111340272A CN 202010093799 A CN202010093799 A CN 202010093799A CN 111340272 A CN111340272 A CN 111340272A
Authority
CN
China
Prior art keywords
spider
heat supply
algorithm
individual
optimization
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
Application number
CN202010093799.9A
Other languages
Chinese (zh)
Inventor
王永利
陈振华
孙卫国
王远
谷东先
杨苗
李璇
孙琦月
邹孝旺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Maxtor Instrument Ltd By Share Ltd
Nanjing University of Science and Technology
Original Assignee
Maxtor Instrument Ltd By Share Ltd
Nanjing University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Maxtor Instrument Ltd By Share Ltd, Nanjing University of Science and Technology filed Critical Maxtor Instrument Ltd By Share Ltd
Priority to CN202010093799.9A priority Critical patent/CN111340272A/en
Publication of CN111340272A publication Critical patent/CN111340272A/en
Pending legal-status Critical Current

Links

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
    • 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
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • 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

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Educational Administration (AREA)
  • Water Supply & Treatment (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Primary Health Care (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Public Health (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention discloses a heat supply scheduling optimization method based on a spider crowd-sourcing algorithm, which comprises the following steps of: step 1: performing mathematical description on a multi-constraint heat supply scheduling optimization problem, constructing an optimization objective function of the problem from an entity perspective, and constructing a limiting condition according to constraints; step 2: searching the optimal solution of the current index for each secondary heat supply evaluation index in the limiting condition in the step 1 by using a spider swarm optimization algorithm, and outputting an optimal solution set formed by all indexes; and step 3: and substituting the optimal solution set into the limiting conditions and the objective function, judging whether the optimal solution set meets the optimization objective function, and otherwise, continuing to execute the step 2. The heat supply scheduling optimization method based on the spider crowd-sourcing algorithm provided by the invention designs heuristic optimization rules, guides the formulation of heat supply operation scheduling strategies aiming at different heat supply entities, and improves the rationality and accuracy of heat supply scheduling.

Description

Heat supply scheduling optimization method based on spider crowd-sourcing algorithm
Technical Field
The invention relates to the field of heat supply scheduling, in particular to a heat supply scheduling optimization method.
Background
The heat supply of China starts from a manually operated scattered small boiler room. Along with the technical progress, the heat supply scale is gradually enlarged, the automation level of a heat supply system is gradually improved, various heat sources coexist, part of the heat supply system is informationized, and a heating station is unattended, so that the intelligent heat supply system and the intelligent heat supply operation management are advanced. At present, operation scheduling of some traditional heat supply enterprises still schedules heat sources, heat supply pipe networks, heat stations and heat user systems according to experience of operators, and the supply and demand relationship of heat cannot be accurately grasped, so that energy waste is caused.
Disclosure of Invention
The invention provides a heat supply scheduling optimization method based on a spider crowd-sourcing algorithm, which designs heuristic optimization rules, guides the formulation of heat supply operation scheduling strategies aiming at different heat supply entities and improves the rationality and accuracy of heat supply scheduling.
The technical scheme of the invention for solving the problems comprises the following steps:
a heat supply scheduling optimization method based on a spider crowd-sourcing algorithm comprises the following steps:
step 1: performing mathematical description on a multi-constraint heat supply scheduling optimization problem, constructing an optimization objective function of the problem from an entity perspective, and constructing a limiting condition according to constraints;
Figure BDA0002384587550000011
Figure BDA0002384587550000012
step 2: searching the optimal solution of the current index for each secondary heat supply evaluation index in the limiting condition in the step 1 by using a spider swarm optimization algorithm, and outputting an optimal solution set formed by all indexes;
and step 3: and substituting the optimal solution set into the limiting conditions and the objective function, judging whether the optimal solution set meets the optimization objective function, and otherwise, continuing to execute the step 2.
Further, the spider swarm optimization algorithm of the step 2 comprises the following steps:
step 1: calculating the total amount of female spider swarm individuals and calculating the total amount of male spider swarm individuals;
step 2: initializing a spider female individual population, initializing a spider male individual population, and calculating a mating radius;
and step 3: calculating the weight and fitness of each spider;
weight calculation formula of each spider individual i
Figure BDA0002384587550000013
J(si) Is the fitness value of the i-th individual spider, determined from a fitness function J (-) which is the optimization objective function, worst, set forth in claim 1sAnd bestsFitness values for the best and worst individuals in the spider population, respectively; wherein worstsAnd bestsCan be calculated from the following formula:
bests＝maxJ(sk)k∈{1，2，…，N} (4)
worsts＝minJ(sk)k∈{1，2，…，N} (5)
and 4, step 4: calculating a dynamic learning factor according to a vibration model of the public alternating current network, wherein the dynamic learning factor is used for calculating the communication of the spider individuals in the network;
and 5: female spider location update;
step 6: updating the position of a male spider;
and 7: performing a mating operation;
and 8: judging whether the limiting conditions are met, and if so, stopping the algorithm; otherwise, the algorithm returns to perform step 3.
Further, the step 4 of calculating the dynamic learning factor dynamically adjusts the learning factor based on the dynamic learning strategy, so as to effectively balance the search capability and the exploration capability of the algorithm, and the scheme of dynamic learning is as follows:
Figure BDA0002384587550000021
Figure BDA0002384587550000022
further, the vibration model of the public traffic net in step 4 is used for communication of the individual spider in the net, and the vibration of the individual spider j perceived by the individual spider i can be represented by the following formula:
Figure BDA0002384587550000023
in the formula (d)i，jRepresenting the Euclidean distance between the spider individual i and the spider individual j, and the expression is di，j＝||si-sj||。
Further, the physical view of step 1 includes, but is not limited to, heat source, heat supply network, heat station, and heat user, and the limiting conditions include, but are not limited to, time, temperature, building material, and air quality.
The invention has the beneficial effects that:
the invention provides an intelligent heat supply scheduling method, which can automatically analyze the heat load characteristics of each building according to the meteorological conditions such as temperature, air pollution degree and the like, establish a heat load model of each building, accurately forecast the heat load, and further provide a scheduling scheme of a heat source, a heat supply pipe network, a heat station and a heat user according to a selected proper operation scheduling mode. The method comprises the steps of establishing a regional heating strategy meeting climate conditions, building heat preservation requirements and construction design requirements, forming a mode of reducing the operation energy consumption of a heating system on the premise of ensuring the indoor comfort, realizing energy conservation and emission reduction, and providing auxiliary decision support for operation managers.
Detailed Description
The invention provides a spider Swarm optimization algorithm (Supply Heat based on spinning Swarm optimization, SHSS for short) based on a dynamic learning strategy, which mainly comprises the following three aspects: a dynamic learning strategy is provided, learning factors are dynamically adjusted, and the searching capability and the exploration capability of the algorithm are effectively balanced; a vibration model of a public AC net is provided for communication of the spider individuals in the net; the algorithm is applied to solve the problem of high-dimensional multi-constraint heat supply operation scheduling.
The algorithm simulates a spider cluster motion rule to realize an optimization process, the whole search space is regarded as a spider web to which spider motion is attached, the position of the spider corresponds to a possible solution of an optimization problem, a corresponding weight value corresponds to a fitness value for evaluating the quality of an individual, the SHSS algorithm randomly generates the position of the spider when solving a function optimization problem, and information interaction is carried out through the internal cooperative motion and the matching process of a female spider and a male spider, so that an optimal solution is finally obtained.
A heat supply scheduling optimization method based on a spider crowd-sourcing algorithm comprises the following steps:
the multi-constraint heating scheduling optimization problem is mathematically described, and x is set as a D-dimensional decision vector [ x1, x 2.. xD.. xD.]，xd_min≤xd≤xd_maxD is 1, 2,. D; y is a target vector; n is the total number of optimization targets, M is the total number of secondary optimization indexes,
Figure BDA0002384587550000031
Figure BDA0002384587550000032
the formula (1) represents the maximum evaluation score of the optimization target corresponding to the entity visual angles of heat sources, heat supply pipe networks, heat stations, heat users and the like, namely an objective function of the optimization problem,
formula (2) represents time, temperature, building material, air quality and other limiting conditions, and for any heat supply quality index r, s.t. condition constraint meaning is as follows: 1) the sum of the fractions of the operation scheduling modes of the heat supply entities with different granularities is larger than a reference value; 2) the heat supply quality support weight accumulation sum of each evaluation index is 1, and the number of operation scheduling modes supporting each secondary heat supply quality evaluation index is not more than 10 according to expert experience; 3) x is the number ofl，rRepresenting whether the heat supply operation scheduling mode supports the corresponding evaluation index state or not, when x islWhen the value is equal to 1, the operation scheduling mode l is shown to contribute to the heat supply quality evaluation index; when x islWhen the value is equal to 0, the operation scheduling mode l does not contribute to the heat supply quality evaluation index;
further, the definition specifically related to finding the optimal solution set of the multi-constraint heat supply scheduling optimization problem is as follows:
definitions 1. dominance relationship for arbitrary D ∈ [1, D]Satisfy the requirement of
Figure BDA0002384587550000033
And the presence of D0 ∈ [1, D]Is provided with
Figure BDA0002384587550000034
Then vector
Figure BDA0002384587550000035
Figure BDA0002384587550000036
Dominant vector x ═ x1，x2，...，xD]，f(x*) Governing f (x) the following two conditions must be met:
Figure BDA0002384587550000037
Figure BDA0002384587550000038
the dominant relationship of f (x) is consistent with the dominant relationship of x,
define 2 pareto optimal solution, a solution that is not dominated by any solution in the set of feasible solutions, if x*Is a point in the search space, called x*For non-suboptimal solutions, if and only if x is not present (in the search space feasibility domain) such that fl(x)≤fl(x*) N, 1, 2, · N;
defining 3, giving a multi-objective optimization problem f (x), f (x)*) Is a globally optimal solution and only if for any x, there is f (x) in the search space*)≤f(x)；
And 4, defining an optimal solution set, wherein a set formed by all non-inferior optimal solutions is called an optimal solution set of the multi-objective optimization problem and is also called an acceptable solution set or an effective solution set.
Further, the spider swarm optimization algorithm comprises the following steps:
inputting: the total amount of the spider swarm individuals is the total optimization target number N, the constraint condition C, the heat supply resource fraction set p,
1) for each secondary heating evaluation index i, the following operations are performed:
2) population initialization: according to research, the number of female spider individuals in the spider population accounts for about 65-90% of the total spider population. The method comprises the steps of initializing a spider cluster, namely, initializing the number of male and female individuals of the spider cluster and initializing the position of the individuals. In the SHSS algorithm, N is the number of spider populations, NfAnd NmRespectively representing the number of female spider populations and the number of male spider populations
Calculating the total amount N of female spider group individuals according to the formula (5)fCalculating the total number N of the male spider mite group individuals according to the formula (6)m；
Nf＝floor[(0.9-rand*0.25)*N](5)
rand is a random number between [0, 1], floor (·) is a floor rounding function.
Nm＝N-Nf(6)
The initial positions of female and male spider individuals were as follows:
Figure BDA0002384587550000041
Figure BDA0002384587550000042
in the formula (f)i，jAnd mg，jRespectively representing the positions of female and male spider individuals,
Figure BDA0002384587550000043
and
Figure BDA0002384587550000044
represent the upper and lower bounds of the j-dimension variable, respectively, where i ∈ {1, 2f}，g∈{1，2，...，NmJ ∈ {1, 2.., D }, D being the problem dimension.
3) Weight distribution and fitness value calculation of population individuals
From a biological perspective, the weight of spiders is a criterion to assess the predominance of individual spiders. In the SHSS algorithm, each spider is given a weight wiIt represents the weight of spider individual i. The weight of an individual spider can be calculated from the formula:
Figure BDA0002384587550000045
wherein J(s)i) Is the fitness value of the ith individual spider, worst, obtained according to a fitness function J (-)sAnd bestsFitness values for the best and worst individuals in the spider population, respectively. Wherein worstsAnd bestsCan be calculated from the following formula:
bests＝maxJ(sk)k∈{1，2，…，N} (10)
worsts＝minJ(sk)k∈{1，2，…，N} (11)
4) calculating dynamic learning factor according to vibration model of public traffic network
The communication of the individual spiders in the net is mainly transmitted by the vibration of the individual spiders in the public communication net, and the vibration magnitude sensed by the individual spiders is determined by the distance between the individual spiders and the weight of the individual spiders. The vibration that the individual spider i perceives as the individual spider j can be expressed by the following formula:
Figure BDA0002384587550000046
in the formula (d)i，jRepresenting the Euclidean distance between the spider individual i and the spider individual j, and the expression is di，j＝||si-sjL. Although in reality spiders are able to sense the vibrations of all individual spiders in the public communication network. However, in the SSOR algorithm, it is assumed that each spider can only receive the vibrations emitted by three individual spiders:
vibration information from the nearest heavy spider:
Figure BDA0002384587550000051
vibration information sent by the heaviest spider individual in the public alternating current network:
Figure BDA0002384587550000052
vibration information from female spiders closest to the male spider:
Figure BDA0002384587550000053
dynamic learning factor
The learning factor of the spider swarm optimization algorithm is improved based on a dynamic learning strategy, the learning factor is divided into the random number × vibration perception capability, the learning adjustment is carried out on the learning factor to further balance the searching speed and the convergence precision of the algorithm, and the learning adjustment is carried out on the learning factor, because the relative quality degree of individuals in each generation is dynamically changed, the learning factor is called as the dynamic learning factor, and the specific scheme of the learning factor to other excellent individuals is as follows:
Figure BDA0002384587550000054
Figure BDA0002384587550000055
wherein: d and C are self-adjusting factor and dynamic learning factor, respectively, CminAnd Cmax(DminAnd Dmax) Respectively minimum and maximum learning factors, and a large number of experiments prove that the general value is w0＝0.5，Cmin＝Dmin＝0.2，Dmax＝DmaxWhen the content is 0.6, excellent effect can be obtained; g and G are respectively the current iteration times and the total iteration times; f. ofminAnd fmaxRepresenting the minimum and maximum objective function values (minimization problem), respectively, j being the original individual.
5) Female spider location update
The position updating of the female spider individual is mainly to simulate the attraction or repulsion behavior of the female spider to the same-sex spider, and the mathematical formula is as follows:
Figure BDA0002384587550000056
wherein, α, δ, rmAnd rand represents [0, 1]]K represents the number of iterations, PF is the threshold for controlling the attraction or repulsion behavior of female spiders, scRepresents the spider individual closest to and heavier than the ith spider, sbRepresenting the heaviest spider individuals in the whole spider population, D and C are self-adjusting factors and dynamic learning factors respectively.
6) Male spider location update
Male spiders are divided into two categories: dominant male spiders and nondominant male spiders. Dominant male spiders have the ability to attract nearby female spiders, while the other non-dominant male spiders have the ability to preserve the overall male spider population food, and the male spider individuals renew the individuals according to the rules shown in equation (19).
Figure BDA0002384587550000061
In the formula (II)
Figure BDA0002384587550000062
The male spiders of (1) are called dominant male spiders, and the remaining male spiders which do not satisfy the conditions are nondominant male spiders, sfRepresenting the female spider f closest to the dominant male spider i,
Figure BDA0002384587550000063
is the middle position of the male spider,
Figure BDA0002384587550000064
is the spider weight at the middle of the male spider population.
7) Mating
In the male spider group, the distributed male spiders have the mating right with the female spiders, each distributed male spider has the mating radius of the distributed male spiders, the female spiders in the mating radius can mate with the distributed male spiders, and the mating radius formula is defined as follows:
Figure BDA0002384587550000065
the dominant male spiders produce new offspring spider individuals by mating with female spiders. The weight of spiders in the mating determines the influence of mating individuals on new progeny spider individuals. The heavier the spider weight, the greater the impact on the newly generated offspring spiders, with the probability of each spider impacting PsiDetermined according to the roulette method, represented by the following formula:
Figure BDA0002384587550000066
after the mating process is completed, the weight of newly-produced spider individuals is checked, the newly-produced spider individuals are compared with the spider individuals with the lightest weight in the former population, if the newly-produced spider individuals are heavier, the lightest spider individuals in the population are replaced, otherwise, the newly-produced spider individuals are eliminated, and the whole spider population is kept unchanged.
8) Judging whether r index limiting conditions are met, and stopping the algorithm if the r index limiting conditions are met; otherwise, the algorithm returns to perform operation 3);
9) and (3) outputting: optimal solution set, i.e. x for each lr，l，wr，lWherein x isr，lIndicates whether the l index is selected, wr，lRepresenting the weight corresponding to the first index range;
10) judging whether the algorithm meets an optimization objective function, and if so, stopping the algorithm; otherwise, the algorithm returns to perform operation 2).
The heat supply scheduling optimization method (SHSS) algorithm based on the spider crowd-sourcing algorithm is as follows:
input: the total amount of the individual spider swarm (course total amount) N, the constraint condition C and the heat supply resource score set p
1) For each secondary heating evaluation index i, the following operations are performed:
2) calculating the total amount N of female spider group individuals according to the formula (5)fCalculating the total number N of the male spider mite group individuals according to the formula (6)m；
3) Initializing a spider female individual population F according to formula (7); initializing spider male individual population M according to a formula (8), and calculating a mating radius according to a formula (20);
4) calculating the weight of each course spider according to the formula (11);
5) performing a cooperation pattern between female spider individuals according to equation (18);
6) performing a cooperation pattern between the male spider individuals according to formula (19);
7) performing a mating operation according to equations (20) and (21);
8) judging whether r index limiting condition formula (2) is met, and stopping the algorithm if the r index limiting condition formula (2) is met; otherwise, the algorithm returns to execute 4).
9) Ouput: optimal solution set, i.e. x for each lr,l，wr,l(xr,lIndicates whether the l-th index is selected, wr,lWeight corresponding to the indicator
10) Judging whether the algorithm meets the optimization objective function formula (1) or not, and if so, stopping the algorithm; otherwise, the algorithm returns to execution 2)
The invention provides an intelligent heat supply scheduling method, which can automatically analyze the heat load characteristics of each building according to the meteorological conditions such as temperature, air pollution degree and the like, establish a heat load model of each building, accurately forecast the heat load, and further provide a scheduling scheme of a heat source, a heat supply pipe network, a heat station and a heat user according to a selected proper operation scheduling mode. The method can excavate the characteristics and the trend of the heat supply load in a certain specific area, and determine the heat supply demand in the next scheduling period according to meteorological parameters; according to the configuration condition of the system, an operation adjusting scheme of equipment in the next scheduling period is formulated, the thermal working condition of the system is optimized, and the energy conversion equipment and the power equipment are optimally controlled; and automatically evaluating the operation scheme and the operation effect of the heating system.
The invention provides auxiliary decision support for operation managers by establishing a regional heating strategy meeting climate conditions, building heat preservation requirements and construction design requirements, forms a mode of reducing the operation energy consumption of a heating system on the premise of ensuring the indoor comfort level, realizes energy conservation and emission reduction,
the above description is only exemplary of the invention, and any modification, equivalent replacement, or improvement made without departing from the spirit and principle of the invention should be considered within the scope of the invention.

Claims (5)

1. A heat supply scheduling optimization method based on a spider crowd-sourcing algorithm is characterized by comprising the following steps:
step 1: performing mathematical description on a multi-constraint heat supply scheduling optimization problem, constructing an optimization objective function of the problem from an entity perspective, and constructing a limiting condition according to constraints;
Figure FDA0002384587540000011
Figure FDA0002384587540000012
step 2: searching the optimal solution of the current index for each secondary heat supply evaluation index in the limiting condition in the step 1 by using a spider swarm optimization algorithm, and outputting an optimal solution set formed by all indexes;
and step 3: and substituting the optimal solution set into the limiting conditions and the objective function, judging whether the optimal solution set meets the optimization objective function, and otherwise, continuing to execute the step 2.
2. The heating scheduling optimization method based on the spider crowd sourcing algorithm according to claim 1, wherein the physical perspective of step 1 includes but is not limited to heat source, heating pipe network, heating power station, heat user, and the limiting conditions include but are not limited to time, temperature, building material, air quality.
3. The heating scheduling optimization method based on the spider swarm intelligence algorithm according to claim 1, wherein the spider swarm optimization algorithm in the step 2 comprises the following steps:
step 1: calculating the total amount of female spider swarm individuals and calculating the total amount of male spider swarm individuals;
step 2: initializing a spider female individual population, initializing a spider male individual population, and calculating a mating radius;
and step 3: calculating the weight and fitness of each spider;
weight calculation formula of each spider individual i
Figure FDA0002384587540000013
J(si) Is the fitness value of the i-th individual spider, determined from a fitness function J (-) which is the optimization objective function, worst, set forth in claim 1sAnd bestsFitness values for the best and worst individuals in the spider population, respectively; wherein worstsAnd bestsCan be calculated from the following formula:
bests＝maxJ(sk)k∈{1,2,…,N} (4)
worsts＝minJ(sk)k∈{1,2,…,N} (5)
and 4, step 4: calculating a dynamic learning factor according to a vibration model of the public alternating current network, wherein the dynamic learning factor is used for calculating the communication of the spider individuals in the network;
and 5: female spider location update;
step 6: updating the position of a male spider;
and 7: performing a mating operation;
and 8: judging whether the limiting conditions are met, and if so, stopping the algorithm; otherwise, the algorithm returns to perform step 3.
4. The heat supply scheduling optimization method of the spider crowd sourcing algorithm according to claim 2, wherein the step 4 of calculating the dynamic learning factor is to dynamically adjust the learning factor based on a dynamic learning strategy to effectively balance the search capability and the exploration capability of the algorithm, and the dynamic learning scheme is as follows:
Figure FDA0002384587540000014
Figure FDA0002384587540000021
5. the method for optimizing heat supply scheduling of spider crowd sourcing algorithm according to claim 2, wherein the vibration model of the public traffic network of step 4 is used for communication of the individual spider in the network, and the vibration of the individual spider j perceived by the individual spider i is represented by the following formula:
Figure FDA0002384587540000022
in the formula (d)i,jRepresenting the Euclidean distance between the spider individual i and the spider individual j, and the expression is di,j＝||si-sj||。
CN202010093799.9A 2020-02-14 2020-02-14 Heat supply scheduling optimization method based on spider crowd-sourcing algorithm Pending CN111340272A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010093799.9A CN111340272A (en) 2020-02-14 2020-02-14 Heat supply scheduling optimization method based on spider crowd-sourcing algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010093799.9A CN111340272A (en) 2020-02-14 2020-02-14 Heat supply scheduling optimization method based on spider crowd-sourcing algorithm

Publications (1)

Publication Number Publication Date
CN111340272A true CN111340272A (en) 2020-06-26

Family

ID=71186927

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010093799.9A Pending CN111340272A (en) 2020-02-14 2020-02-14 Heat supply scheduling optimization method based on spider crowd-sourcing algorithm

Country Status (1)

Country Link
CN (1) CN111340272A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113657722A (en) * 2021-07-26 2021-11-16 西安理工大学 Power plant energy-saving scheduling method based on social spider optimization algorithm
CN115169754A (en) * 2022-09-07 2022-10-11 北京邮电大学 Energy scheduling method and device, electronic equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103426032A (en) * 2013-07-25 2013-12-04 广东电网公司电力科学研究院 Method for economically and optimally dispatching cogeneration units
CN109613914A (en) * 2018-09-12 2019-04-12 黎建军 A kind of robot path planning method of the gregarious algorithm of spider
CN109840638A (en) * 2019-02-28 2019-06-04 华南理工大学 A kind of meter and the probabilistic combined heat and power of heat supply network robust economic load dispatching method a few days ago
CN110148971A (en) * 2019-05-24 2019-08-20 安徽理工大学 A kind of distributed generation resource Optimal Configuration Method
CN110347039A (en) * 2019-07-09 2019-10-18 东北大学 Consider that user satisfaction and electric boiler participate in the combined heat and power optimization method of peak regulation
US20190369581A1 (en) * 2017-01-11 2019-12-05 Southeast University Integrated energy system operational optimization method considering thermal inertia of district heating networks and buildings
CN110782366A (en) * 2019-10-12 2020-02-11 大连理工大学 Water supply pipe network multi-objective optimization regulation and control method based on scene uncertainty

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103426032A (en) * 2013-07-25 2013-12-04 广东电网公司电力科学研究院 Method for economically and optimally dispatching cogeneration units
US20190369581A1 (en) * 2017-01-11 2019-12-05 Southeast University Integrated energy system operational optimization method considering thermal inertia of district heating networks and buildings
CN109613914A (en) * 2018-09-12 2019-04-12 黎建军 A kind of robot path planning method of the gregarious algorithm of spider
CN109840638A (en) * 2019-02-28 2019-06-04 华南理工大学 A kind of meter and the probabilistic combined heat and power of heat supply network robust economic load dispatching method a few days ago
CN110148971A (en) * 2019-05-24 2019-08-20 安徽理工大学 A kind of distributed generation resource Optimal Configuration Method
CN110347039A (en) * 2019-07-09 2019-10-18 东北大学 Consider that user satisfaction and electric boiler participate in the combined heat and power optimization method of peak regulation
CN110782366A (en) * 2019-10-12 2020-02-11 大连理工大学 Water supply pipe network multi-objective optimization regulation and control method based on scene uncertainty

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113657722A (en) * 2021-07-26 2021-11-16 西安理工大学 Power plant energy-saving scheduling method based on social spider optimization algorithm
CN113657722B (en) * 2021-07-26 2023-07-21 西安理工大学 Power plant energy-saving scheduling method based on social spider optimization algorithm
CN115169754A (en) * 2022-09-07 2022-10-11 北京邮电大学 Energy scheduling method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN109270842B (en) Bayesian network-based regional heat supply model prediction control system and method
CN112232980B (en) Regulation and control method for heat pump unit of regional energy heat supply system
Alcalá et al. Fuzzy control of HVAC systems optimized by genetic algorithms
Hurtado et al. Smart grid and smart building inter-operation using agent-based particle swarm optimization
WO2023160110A1 (en) System frequency modulation method and system for thermostatically controlled load cluster, and electronic device and storage medium
Alcala et al. A genetic rule weighting and selection process for fuzzy control of heating, ventilating and air conditioning systems
CN110138612A (en) A kind of cloud software service resource allocation methods based on QoS model self-correcting
CN111340272A (en) Heat supply scheduling optimization method based on spider crowd-sourcing algorithm
CN105703355B (en) Diversity load grading self-discipline collaborative demand response method
WO2022127652A1 (en) Air conditioning aggregation control method, system, and regulation apparatus
CN107092991A (en) A kind of adaptive economic load dispatching distribution method of intelligent grid
CN102902772A (en) Web community discovery method based on multi-objective optimization
Chen et al. Multi-population coevolutionary dynamic multi-objective particle swarm optimization algorithm for power control based on improved crowding distance archive management in CRNs
CN109670655B (en) Multi-target particle swarm optimization scheduling method for electric power system
CN106650988B (en) Fuzzy combination optimization method for high-voltage distribution network planning project
CN112012875B (en) Optimization method of PID control parameters of water turbine regulating system
CN116436033A (en) Temperature control load frequency response control method based on user satisfaction and reinforcement learning
CN113110057A (en) Heating power station energy-saving control method based on artificial intelligence and intelligent decision system
CN111478349B (en) Power three-phase balance strategy method based on power utilization equipment intelligent network regulation and control Internet of things
CN109919485A (en) A kind of Multipurpose Optimal Method of the Water Resources Allocation based on NSGA-II
CN115882463A (en) Commercial building air conditioner load schedulable potential evaluation method
CN113110056B (en) Heat supply intelligent decision-making method and intelligent decision-making machine based on artificial intelligence
Yan et al. Self-imitation learning-based inter-cell interference coordination in autonomous HetNets
CN108710748A (en) A kind of drosophila optimization method of locus of planar 4-bar linkage design
CN112787331B (en) Deep reinforcement learning-based automatic power flow convergence adjusting method and system

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