CN117314043A - Scene-driven comprehensive energy complementary capacity planning method and system - Google Patents
Scene-driven comprehensive energy complementary capacity planning method and system Download PDFInfo
- Publication number
- CN117314043A CN117314043A CN202311065675.XA CN202311065675A CN117314043A CN 117314043 A CN117314043 A CN 117314043A CN 202311065675 A CN202311065675 A CN 202311065675A CN 117314043 A CN117314043 A CN 117314043A
- Authority
- CN
- China
- Prior art keywords
- initial
- scene
- layer
- typical
- updating
- 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 39
- 230000000295 complement effect Effects 0.000 title claims abstract description 22
- 238000010248 power generation Methods 0.000 claims abstract description 9
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 17
- 229910052799 carbon Inorganic materials 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 16
- 238000004146 energy storage Methods 0.000 claims description 14
- 238000013135 deep learning Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 abstract description 4
- 239000010410 layer Substances 0.000 description 70
- 238000005457 optimization Methods 0.000 description 6
- 238000005338 heat storage Methods 0.000 description 5
- 239000002355 dual-layer Substances 0.000 description 4
- 239000007789 gas Substances 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 229910052739 hydrogen Inorganic materials 0.000 description 3
- 239000001257 hydrogen Substances 0.000 description 3
- 150000003839 salts Chemical class 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- 229910052720 vanadium Inorganic materials 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005868 electrolysis reaction Methods 0.000 description 2
- 230000008485 antagonism Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
- LEONUFNNVUYDNQ-UHFFFAOYSA-N vanadium atom Chemical compound [V] LEONUFNNVUYDNQ-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
- H02J3/0075—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source according to economic or energy efficiency considerations, e.g. economic dispatch
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)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a scene-driven comprehensive energy complementary capacity planning method and a system, wherein the method comprises the following steps: establishing an initial typical scene set and an initial typical scene set of a region to be configured; constructing an initial multi-target double-layer capacity configuration model; solving an initial multi-target double-layer capacity configuration model to obtain an initial configuration scheme solution set; determining an extreme scene according to the initial configuration scheme solution set; updating the typical scene set; updating the initial multi-target double-layer capacity configuration model according to the updating typical scene set and the probabilities corresponding to all scenes in the updating typical scene set and the probabilities corresponding to the extreme scenes to obtain an updated multi-target double-layer capacity configuration model; according to the method, the solution set of the updated configuration scheme is obtained according to the updated multi-target double-layer capacity configuration model, and the problems that in the prior art, the uncertainty of renewable energy power generation on a source side and the uncertainty of energy consumption requirements on a load side are less considered, and the problem that the reliability is low due to the fact that a small-probability extreme scene is ignored are solved.
Description
Technical Field
The invention relates to the technical field of energy configuration and scheduling, in particular to a scene-driven comprehensive energy complementary capacity planning method and system.
Background
With the increasing demands of energy, unreasonable energy structures, low energy utilization rate and other problems, renewable energy sources such as wind power, photovoltaics and the like are greatly developed. The integrated energy system (Integrated Energy System, IES) facilitates energy conversion and energy structure adjustment due to its multi-energy complementation and cascade utilization of energy. Meanwhile, the operation and control modes of the traditional power system cannot well cope with high-proportion renewable energy access. The distributed renewable energy sources, multiple uncertainties of energy usage, and the mutual coupling of multiple energy flows make the optimal configuration of IES more complex.
To reduce the power supply ripple and to facilitate the digestion of renewable energy sources, renewable energy power stations are often equipped with energy storage systems. The energy storage system has higher cost, and the energy storage configuration with smaller capacity can reduce the system cost, but is not beneficial to the safe and stable operation of the power grid; the larger capacity of the energy storage configuration can ensure the reliability of the power grid, but neglects the economy of the system. Therefore, reasonable capacity allocation of the renewable energy unit and the energy storage device is of great significance to large-scale grid connection of the renewable energy unit.
The existing research on the optimal configuration of the IES is mostly carried out under a single scene, and has certain matching limitation. In the configuration process, less uncertainty is considered in renewable energy power generation on the source side and energy consumption requirement on the load side. Meanwhile, in the random programming method, a large-probability typical scene is generally used for programming configuration, a small-probability extreme scene is often ignored, and certain hidden danger is brought to the reliability of the system. While overcoming IES uncertainty and ensuring reliability is a positive key to capacity configuration requirements.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a scene-driven comprehensive energy complementary capacity planning method and system, and solves the problems that in the prior art, the uncertainty of renewable energy power generation on a source side and the uncertainty of energy consumption requirement on a load side are less considered, and the reliability is low due to neglecting a small-probability extreme scene.
In order to achieve the above object, the present invention provides the following solutions:
a scene-driven comprehensive energy complementary capacity planning method comprises the following steps:
establishing an initial typical scene set of a region to be configured and probabilities corresponding to all scenes in the initial typical scene set;
constructing an initial multi-target double-layer capacity configuration model based on the initial typical scene set of the region to be configured;
solving the initial multi-target double-layer capacity configuration model to obtain an initial configuration scheme solution set;
determining an extreme scene and a probability corresponding to the extreme scene according to the initial configuration scheme solution set;
according to the extreme scenes and the probabilities corresponding to the extreme scenes, reducing and updating the initial typical scene set to obtain an updated typical scene set and probabilities corresponding to each scene in the updated typical scene set;
updating the initial multi-target double-layer capacity configuration model according to the updating typical scene set, the probability corresponding to each scene in the updating typical scene set and the probability corresponding to the extreme scene to obtain an updated multi-target double-layer capacity configuration model;
and obtaining an updated configuration scheme solution set according to the updated multi-target double-layer capacity configuration model.
Preferably, the establishing the probability corresponding to each scene in the initial typical scene set and the initial typical scene set of the to-be-configured area includes:
acquiring source side historical data and load side historical data of an area to be configured, wherein the source side historical data comprise wind speed and illumination, and the load side historical data comprise electric load, thermal load and cold load;
generating joint data according to the source side historical data and the load side historical data to obtain an initial scene set;
and obtaining the probability corresponding to each scene in the initial typical scene set according to the initial scene set.
Preferably, the generating the joint data according to the source side historical data and the load side historical data to obtain an initial scene set includes:
training the deep learning network to obtain a trained deep learning network;
and obtaining an initial scene set by using the source side historical data and the load side historical data through the trained deep learning network.
Preferably, the constructing an initial multi-objective dual-layer capacity configuration model includes:
utilizing the capacity of the device to be configured as a decision variable to establish an initial upper-layer multi-target planning model and constraint conditions thereof;
using the daily operation output of the device to be configured as a decision variable, and establishing an initial lower-layer optimized scheduling model and constraint conditions thereof;
and constructing an initial multi-target double-layer capacity configuration model according to the initial upper-layer multi-target planning model and the constraint conditions thereof and the initial lower-layer optimized scheduling model and the constraint conditions thereof.
Preferably, the objective function of the initial upper-layer multi-objective planning model is:
minF upper ＝{f1,f2,f3}
the constraint conditions corresponding to the initial upper multi-target planning model are as follows:
wherein C is inv The investment costs for the configuration of the device,for the minimum expected value of the sunrise cost of the lower layer, W i,CE For the carbon emission of unit i, Ω c For a set which can generate carbon emission in the power generation process, P (t) is the energy supply of the energy storage device removal system at the moment t, and P ave (t) providing an average value of the energy supply to the whole system, V j ，/> The minimum and maximum values of the capacity of the device j to be configured and its configurable capacity, respectively.
Preferably, the objective function of the initial underlying multi-objective planning model is:
wherein pi s For the probability corresponding to a typical scene s, T is the scheduling period, Ω is the set of devices to be configured,for the operating cost of device k at time t.
Preferably, the solving the initial multi-objective dual-layer capacity configuration model to obtain an initial configuration scheme solution set includes:
generating a population based on an intelligent optimizing algorithm, taking the random capacity of a device to be configured as an initial value, taking characteristic parameters, typical scene data, configuration cost coefficients and carbon emission coefficients of the device to be configured as known conditions, and carrying out iterative solution on the initial upper-layer multi-target planning model to obtain an initial upper-layer target solution set;
acquiring a typical daily optimal scheduling scheme, and calculating the system investment cost, the system operation carbon emission and the load mean square deviation fluctuation;
obtaining an initial next target solution set according to the system investment cost, the system operation carbon emission and the load mean square deviation fluctuation;
obtaining a pareto solution set according to the initial upper layer target solution set and the initial lower layer target solution set;
based on a comprehensive evaluation method, an initial configuration scheme solution set is obtained according to the pareto solution set.
Preferably, the lower layer objective function of the updated multi-objective dual-layer capacity configuration model is:
wherein pi s Probability pi corresponding to "typical scene s newly divided s 'probability corresponding to extreme scene s', x s’,t For the value of the load loss at time t in the extreme scene s', κ is the penalty cost for the unit load loss.
A scene driven integrated energy complementary capacity planning system comprising:
the initial scene construction module is used for establishing an initial typical scene set of the region to be configured and probabilities corresponding to all scenes in the initial typical scene set;
the initial model building module is used for building an initial multi-target double-layer capacity configuration model based on the initial typical scene set of the area to be configured;
the initial scheme acquisition module is used for solving the initial multi-target double-layer capacity configuration model to obtain an initial configuration scheme solution set;
the extreme scene determining module is used for determining the extreme scene and the probability corresponding to the extreme scene according to the initial configuration scheme solution set;
the scene updating module is used for carrying out reduction updating on the initial typical scene set according to the extreme scene and the probability corresponding to the extreme scene to obtain an updated typical scene set and the probability corresponding to each scene in the updated typical scene set;
the model updating module is used for updating the initial multi-target double-layer capacity configuration model according to the updating typical scene set, the probability corresponding to each scene in the updating typical scene set and the probability corresponding to the extreme scene to obtain an updated multi-target double-layer capacity configuration model;
and the updating scheme acquisition module is used for acquiring an updating scheme solution set according to the updating multi-target double-layer capacity configuration model.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a scene-driven comprehensive energy complementary capacity planning method and a system, wherein the method comprises the following steps: establishing an initial typical scene set of a region to be configured and probabilities corresponding to all scenes in the initial typical scene set; constructing an initial multi-target double-layer capacity configuration model based on the initial typical scene set of the region to be configured; solving the initial multi-target double-layer capacity configuration model to obtain an initial configuration scheme solution set; determining an extreme scene and a probability corresponding to the extreme scene according to the initial configuration scheme solution set; according to the extreme scenes and the probabilities corresponding to the extreme scenes, reducing and updating the initial typical scene set to obtain an updated typical scene set and probabilities corresponding to each scene in the updated typical scene set; updating the initial multi-target double-layer capacity configuration model according to the updating typical scene set, the probability corresponding to each scene in the updating typical scene set and the probability corresponding to the extreme scene to obtain an updated multi-target double-layer capacity configuration model; and obtaining an updated configuration scheme solution set according to the updated multi-target double-layer capacity configuration model. The invention considers typical and extreme scenes at the same time, and effectively improves the energy supply reliability of the configured system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for planning the complementary capacity of a scene driven comprehensive energy source provided by an embodiment of the invention;
FIG. 2 is a diagram of a system to be configured according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a scene-driven comprehensive energy complementary capacity planning system according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The terms "first," "second," "third," and "fourth" and the like in the description and in the claims of this application and in the drawings, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, inclusion of a list of steps, processes, methods, etc. is not limited to the listed steps but may alternatively include steps not listed or may alternatively include other steps inherent to such processes, methods, products, or apparatus.
The invention aims to provide a scene-driven comprehensive energy complementary capacity planning method and system, and solves the problems that in the prior art, the uncertainty of renewable energy power generation at a source side and the uncertainty of energy consumption requirement at a load side are considered less, and the reliability is low due to the fact that a small-probability extreme scene is ignored.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
As shown in fig. 1, the present invention provides a scenario-driven comprehensive energy complementary capacity planning method, which includes:
step 100: establishing an initial typical scene set of a region to be configured and probabilities corresponding to all scenes in the initial typical scene set;
step 200: constructing an initial multi-target double-layer capacity configuration model based on the initial typical scene set of the region to be configured;
step 300: solving the initial multi-target double-layer capacity configuration model to obtain an initial configuration scheme solution set;
step 400: determining an extreme scene and a probability corresponding to the extreme scene according to the initial configuration scheme solution set;
step 500: according to the extreme scenes and the probabilities corresponding to the extreme scenes, reducing and updating the initial typical scene set to obtain an updated typical scene set and probabilities corresponding to each scene in the updated typical scene set;
step 600: updating the initial multi-target double-layer capacity configuration model according to the updating typical scene set, the probability corresponding to each scene in the updating typical scene set and the probability corresponding to the extreme scene to obtain an updated multi-target double-layer capacity configuration model;
step 700: and obtaining an updated configuration scheme solution set according to the updated multi-target double-layer capacity configuration model.
Further, the establishing the probability corresponding to each scene in the initial typical scene set and the initial typical scene set of the to-be-configured area includes:
acquiring source side historical data and load side historical data of an area to be configured, wherein the source side historical data comprise wind speed and illumination, and the load side historical data comprise electric load, thermal load and cold load;
generating joint data according to the source side historical data and the load side historical data to obtain an initial scene set;
and obtaining the probability corresponding to each scene in the initial typical scene set according to the initial scene set.
Further, the generating the joint data according to the source side historical data and the load side historical data to obtain an initial scene set includes:
training the deep learning network to obtain a trained deep learning network;
and obtaining an initial scene set by using the source side historical data and the load side historical data through the trained deep learning network.
Training a deep learning network through source-load side historical data of an area to be configured, generating source-load side joint data through the trained deep learning network, reducing a large number of generated scenes (initial scene sets), and extracting typical scenes (initial typical scene sets) and probability thereof;
further, the constructing an initial multi-objective dual-layer capacity configuration model includes:
utilizing the capacity of the device to be configured as a decision variable to establish an initial upper-layer multi-target planning model and constraint conditions thereof;
using the daily operation output of the device to be configured as a decision variable, and establishing an initial lower-layer optimized scheduling model and constraint conditions thereof;
and constructing an initial multi-target double-layer capacity configuration model according to the initial upper-layer multi-target planning model and the constraint conditions thereof and the initial lower-layer optimized scheduling model and the constraint conditions thereof.
The steps 300-600 specifically include: when solving the multi-target double-layer capacity configuration model, the upper layer takes the capacity of the random device as an initial value, and updates decision variables through a non-dominant genetic algorithm according to the sunrise state of the lower layer; the lower layer and the upper layer decision variable values are the capacity constraint of the decision variables and are solved based on a CPLEX solver. Repeatedly executing iteration until the iteration stopping condition is met; screening and generating scenes which cannot meet the matching of source charges under the current capacity configuration condition in the scenes by combining the initial capacity configuration result, defining the scenes as extreme scenes, and distributing probability for the extreme scenes; removing extreme scenes in the original generated scenes, and carrying out scene reduction again to obtain new typical scenes and probability thereof; and updating the upper and lower objective functions of the double-layer optimization model by combining the typical scene and the extreme scene, and carrying out capacity reconfiguration optimization solution.
Further, capturing power characteristics of a source load side of the region to be configured through a deep learning network; generating a large number of scenes through the trained network, and performing scene reduction to obtain a typical scene; respectively establishing an upper multi-objective planning model and a lower optimal scheduling model; updating particles based on an NSGA-III algorithm by taking a random unit capacity value as an initial value, and solving the optimal expected daily output based on a CPLEX solver by taking the capacity value of the upper layer of the lower layer as a constraint; iterative calculation is carried out until a preset condition is met; screening out extreme scenes which cannot meet the matching of the source load in the original generated scenes according to the first configuration result, and reducing the rest scenes again; and updating the lower objective function, and comprehensively considering the typical scene and the extreme scene in the configuration process.
Specifically, in the embodiment of the present example, the countermeasure network is generated by convolution as the depth network for training, and the input vector L of the network is composed of the wind speed and illumination intensity data of the source side and the electric load and thermal load data of the load side.
L＝[v w ,v s ,u P ,u H ]；
Wherein v is w 、v s Wind speed and illumination intensity data of the source side, u P 、u H And the data are respectively power consumption and heat consumption load data of the load side.
The loss function of the countermeasure network generator is generated as follows:
L G ＝-E Z [D(G(Z))]；
the loss function of the countermeasure network discriminator is generated as follows:
L D ＝-E L [D(L)]+E Z [D(G(Z))]；
the convolution generation antagonism network overall loss function can be expressed as:
minmaxV(G,D)＝E L [D(L)]-E Z [D(G(Z))]；
wherein L is an input vector, Z is noise, D is a discriminator, and G is a generator.
Specifically, after the convolution generation countermeasure network training is finished, noise is input, and then the source load side data scene can be output. The network is used for generating a large number of scenes which can represent the natural resource condition of the area to be configured and the corresponding electricity and heat load condition.
Further, a synchronous substitution method is adopted to cut the scene, and a typical scene is obtained. The synchronous substitution method comprises the following calculation steps:
1) An initial probability is assigned to each scene in the set of scenes. Assuming that there are N scenes in total, the probability of each scene is 1/N.
2) Calculating any two different scenes S in a scene set i 、S j Euclidean distance D between si,sj ：
D si,sj ＝||S i -S j || 2
3) Find distance scene S i Probability distance P Ds Minimum scene S m ：
4) Calculating probability distance P between any two different scenes in scene set Ds Sorting according to the probability distance, and sorting the minimum P D The scene to which it belongs is deleted:
P D ＝min{P Ds|1≤S≤N }
5) Updating the scene probability after pruning, and repeatedly executing the steps 1) -4) until the number of the scenes in the scene set is the same as the set number of the cut scenes.
In the embodiment of the present example, the structure of the system to be configured is as shown in fig. 2, and is composed of wind power (WT), photovoltaic Power (PV), conventional thermal power unit (TP), cogeneration unit (CHP), electric grid (PG), molten Salt Boiler (MSB), vanadium redox flow battery (VRB), fuel Cell (FC), electrolytic hydrogen device (ELE), heat Storage Tank (HST), gas Storage Tank (GST).
Further, taking the capacity of the device to be configured as a decision variable, establishing an upper multi-objective optimization model which aims at minimizing the economic cost, the carbon emission and the mean square error of load fluctuation of the system, wherein the objective function of the initial upper multi-objective planning model is as follows:
minF upper ＝{f1,f2,f3}
the constraint conditions corresponding to the initial upper multi-target planning model are as follows:
wherein C is inv The investment costs for the configuration of the device,for the minimum expected value of the sunrise cost of the lower layer, W i,CE For the carbon emission of unit i, Ω c For a set which can generate carbon emission in the power generation process, P (t) is the energy supply of the energy storage device removal system at the moment t, and P ave (t) providing an average value of the energy supply to the whole system, V j ，/> The minimum and maximum values of the capacity of the device j to be configured and its configurable capacity, respectively.
The capacity configuration solving algorithm adopts a double-layer optimization structure. The upper layer is a configuration layer, the annual economic cost, the carbon emission and the load mean square error of the system are taken as the multi-objective function of the upper layer, and the NSGA-III optimization algorithm is adopted for capacity configuration; the lower layer is an operation layer, and is used for scheduling the system operation cost day before day in each typical scene, and a CPLEX solver is called by adopting yalminip to obtain an optimal operation strategy.
Further, the objective function of the initial underlying multi-objective planning model is:
wherein pi s For the probability corresponding to a typical scene s, T is the scheduling period, Ω is the set of devices to be configured,for the operating cost of device k at time t.
In this embodiment, the lower model performs day-ahead optimal scheduling of the system, determines the optimal output of each device, and forms an optimal day-ahead scheduling scheme.
The lower model takes the minimum expected running cost of each typical date of the system as an objective function, and the lower model is expressed by the following formula:
in the embodiment of the present example, the constraint conditions of the lower-layer optimization scheduling model include an energy balance constraint condition, an output condition of each unit operation state, an output constraint condition of each unit, an operation constraint condition of the energy storage device, a capacity constraint condition of the energy storage device, a power transmission constraint condition of the power grid, and the like. Wherein:
the energy balance constraint is:
electric power balance:
P PV +P WT +P grid +P CHP +P TP +P VRB +P FC -P ELE -P MSB ＝P L ；
wherein P is PV ,P WT ,P grid ,P CHP ,P TP The output of the photovoltaic power generation, the wind power generation, the power grid, the CHP unit and the conventional thermal power unit respectivelyPower, P VRB ,P FC ,P ELE Output power of all-vanadium redox flow energy storage battery, fuel cell and hydrogen electrolysis device, P MSB P is the power consumption of the fused salt boiler L Is the load demand on the load side of the system.
Thermal power balance:
H CHP +H MSB +H HST ＝P H ；
wherein H is CHP ,H MSB The heat power output of the CHP unit and the molten salt boiler are respectively H HST For heat power output of heat storage tank, P H Is the load side thermal load requirement of the system.
Unit output constraint: p (P) i min ≤P i ≤P i max ；
Wherein,the minimum output and the maximum output of each unit are respectively.
Energy storage device capacity constraints:
wherein,minimum gas storage capacity, maximum gas storage capacity of gas storage device connected with fuel cell and hydrogen electrolysis device respectively, < ->Minimum storage capacity and maximum storage capacity of energy storage of all-vanadium redox flow energy storage battery respectively, < + >>The minimum heat storage capacity and the maximum heat storage capacity of the heat storage tank are respectively.
Grid power transfer constraints:
wherein,is the maximum transmission power interacting with the grid.
Further, the solving the initial multi-target double-layer capacity configuration model to obtain an initial configuration scheme solution set includes:
generating a population based on an intelligent optimizing algorithm, taking the random capacity of a device to be configured as an initial value, taking characteristic parameters, typical scene data, configuration cost coefficients and carbon emission coefficients of the device to be configured as known conditions, and carrying out iterative solution on the initial upper-layer multi-target planning model to obtain an initial upper-layer target solution set;
acquiring a typical daily optimal scheduling scheme, and calculating the system investment cost, the system operation carbon emission and the load mean square deviation fluctuation;
obtaining an initial next target solution set according to the system investment cost, the system operation carbon emission and the load mean square deviation fluctuation;
obtaining a pareto solution set according to the initial upper layer target solution set and the initial lower layer target solution set;
based on a comprehensive evaluation method, an initial configuration scheme solution set is obtained according to the pareto solution set.
Specifically, when solving the multi-target double-layer capacity configuration model, the upper layer takes the capacity of the random device as an initial value, and updates decision variables through an NSGA-III algorithm according to the sunrise force state of the lower layer; the lower layer and the upper layer decision variable values are the capacity constraint of the decision variables and are solved based on a CPLEX solver. Repeatedly executing iteration until the iteration stopping condition is met;
stopping iteration when the upper multi-objective planning model meets the set iteration number;
ending the program operation to obtain a pareto solution set of capacity configuration;
screening and generating scenes which cannot meet the matching of source charges under the current capacity configuration condition in the scenes by combining the initial capacity configuration result, defining the scenes as extreme scenes, and distributing probability for the extreme scenes; and eliminating the extreme scenes in the original generated scenes, and carrying out scene reduction again to obtain a new typical scene and probability thereof.
Specifically, a solution with highest score is selected from the pareto solution set using an approximate ideal solution ordering method (Technique for Order Preference by Similarity to Ideal Solution, TOPSIS) as the final configuration solution. The TOPSIS algorithm solving steps are as follows:
1) The original matrix x ij Forward conversion to obtain forward conversion matrix y ij ：
y ij ＝max{x 1j ,x 2j ,…,x nj }-x ij
2) The matrix y is orthogonalized ij Normalizing to obtain a normalized matrix z ij ：
3) Calculating the positive ideal solution z + Negative ideal solution z - Distance of each sample to the ideal
Distance of negative ideal solution
4) Calculating the approach degree of each evaluation object and the optimal scheme, score i The range of the values is as follows
[0,1],Score i The larger the number, the better the solution:
under the configuration of the selected solution, the scene which cannot meet the matching of the source load is the extreme scene s'. And eliminating extreme scenes from a large number of originally generated scenes, carrying out scene reduction based on a synchronous back substitution method on the rest scenes again to obtain a new typical scene s', and reallocating the probability.
Updating the upper and lower objective functions, and comprehensively considering a typical scene and an extreme scene:
minF upper ＝{f1,f2,f3}
newly adding constraint conditions:
0≤x s′,t ≤P s′,t
and using an upper NSGA-III algorithm, and performing secondary solving by using a lower CPLEX solver. The final configuration result is selected from the pareto solution set using the TOPSIS algorithm.
Wherein pi s "typical scene for New partitions' probability, pi s 'probability corresponding to extreme scene s', x s’,t For the value of the load loss at time t in the extreme scene s', κ is the penalty cost for the unit load loss.
As shown in fig. 3, this embodiment further specifically discloses a scenario-driven comprehensive energy complementary capacity planning system, including:
the initial scene construction module is used for establishing an initial typical scene set of the region to be configured and probabilities corresponding to all scenes in the initial typical scene set;
the initial model building module is used for building an initial multi-target double-layer capacity configuration model based on the initial typical scene set of the area to be configured;
the initial scheme acquisition module is used for solving the initial multi-target double-layer capacity configuration model to obtain an initial configuration scheme solution set;
the extreme scene determining module is used for determining the extreme scene and the probability corresponding to the extreme scene according to the initial configuration scheme solution set;
the scene updating module is used for carrying out reduction updating on the initial typical scene set according to the extreme scene and the probability corresponding to the extreme scene to obtain an updated typical scene set and the probability corresponding to each scene in the updated typical scene set;
the model updating module is used for updating the initial multi-target double-layer capacity configuration model according to the updating typical scene set, the probability corresponding to each scene in the updating typical scene set and the probability corresponding to the extreme scene to obtain an updated multi-target double-layer capacity configuration model;
and the updating scheme acquisition module is used for acquiring an updating scheme solution set according to the updating multi-target double-layer capacity configuration model.
The beneficial effects of the invention are as follows:
and generating a large number of scenes by extracting the historical data information of the regional source load side, and reducing to obtain typical scenes. The influence of uncertainty of wind power and photovoltaic on system source load matching is reduced through random planning under multiple scenes; the configuration and scheduling operation are combined and optimized through the upper layer and the lower layer, so that the configuration feasibility is improved; the extreme scenes in the original generated scenes are screened through the primary configuration result, and the capacity reconfiguration is carried out based on the typical scenes and the extreme scenes, so that the running risk problem caused by neglecting the configuration of the small probability scenes is solved, and the reliability of the system is improved.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (9)
1. The scene-driven comprehensive energy complementary capacity planning method is characterized by comprising the following steps of:
establishing an initial typical scene set of a region to be configured and probabilities corresponding to all scenes in the initial typical scene set;
constructing an initial multi-target double-layer capacity configuration model based on the initial typical scene set of the region to be configured;
solving the initial multi-target double-layer capacity configuration model to obtain an initial configuration scheme solution set;
determining an extreme scene and a probability corresponding to the extreme scene according to the initial configuration scheme solution set;
according to the extreme scenes and the probabilities corresponding to the extreme scenes, reducing and updating the initial typical scene set to obtain an updated typical scene set and probabilities corresponding to each scene in the updated typical scene set;
updating the initial multi-target double-layer capacity configuration model according to the updating typical scene set, the probability corresponding to each scene in the updating typical scene set and the probability corresponding to the extreme scene to obtain an updated multi-target double-layer capacity configuration model;
and obtaining an updated configuration scheme solution set according to the updated multi-target double-layer capacity configuration model.
2. The method for planning the complementary capacity of a comprehensive energy source driven by a scene according to claim 1, wherein the establishing the probability corresponding to each scene in the initial typical scene set and the initial typical scene set of the area to be configured comprises:
acquiring source side historical data and load side historical data of an area to be configured, wherein the source side historical data comprise wind speed and illumination, and the load side historical data comprise electric load, thermal load and cold load;
generating joint data according to the source side historical data and the load side historical data to obtain an initial scene set;
and obtaining the probability corresponding to each scene in the initial typical scene set according to the initial scene set.
3. The method for planning a scene-driven comprehensive energy complementary capacity according to claim 2, wherein the generating the joint data according to the source-side historical data and the load-side historical data to obtain an initial scene set comprises:
training the deep learning network to obtain a trained deep learning network;
and obtaining an initial scene set by using the source side historical data and the load side historical data through the trained deep learning network.
4. The scene driven comprehensive energy complementary capacity planning method according to claim 1, wherein the constructing an initial multi-objective double-layer capacity configuration model comprises:
utilizing the capacity of the device to be configured as a decision variable to establish an initial upper-layer multi-target planning model and constraint conditions thereof;
using the daily operation output of the device to be configured as a decision variable, and establishing an initial lower-layer optimized scheduling model and constraint conditions thereof;
and constructing an initial multi-target double-layer capacity configuration model according to the initial upper-layer multi-target planning model and the constraint conditions thereof and the initial lower-layer optimized scheduling model and the constraint conditions thereof.
5. The scene driven integrated energy complementary capacity planning method according to claim 4, wherein the objective function of the initial upper layer multi-objective planning model is:
minF upper ＝{f1,f2,f3}
the constraint conditions corresponding to the initial upper multi-target planning model are as follows:
wherein C is inv The investment costs for the configuration of the device,for the minimum expected value of the sunrise cost of the lower layer, W i,CE For the carbon emission of unit i, Ω c For a set which can generate carbon emission in the power generation process, P (t) is the energy supply of the energy storage device removal system at the moment t, and P ave (t) providing an average value of the energy supply to the whole system, V j ，/> Respectively are devices to be configuredThe capacity of j and its configurable minimum and maximum capacities.
6. The scene driven integrated energy complementary capacity planning method according to claim 4, wherein the objective function of the initial underlying multi-objective planning model is:
wherein pi s For the probability corresponding to a typical scene s, T is the scheduling period, Ω is the set of devices to be configured,for the operating cost of device k at time t.
7. The scene driven comprehensive energy complementary capacity planning method according to claim 6, wherein the solving the initial multi-objective double-layer capacity configuration model to obtain an initial configuration scheme solution set comprises:
generating a population based on an intelligent optimizing algorithm, taking the random capacity of a device to be configured as an initial value, taking characteristic parameters, typical scene data, configuration cost coefficients and carbon emission coefficients of the device to be configured as known conditions, and carrying out iterative solution on the initial upper-layer multi-target planning model to obtain an initial upper-layer target solution set;
acquiring a typical daily optimal scheduling scheme, and calculating the system investment cost, the system operation carbon emission and the load mean square deviation fluctuation;
obtaining an initial next target solution set according to the system investment cost, the system operation carbon emission and the load mean square deviation fluctuation;
obtaining a pareto solution set according to the initial upper layer target solution set and the initial lower layer target solution set;
based on a comprehensive evaluation method, an initial configuration scheme solution set is obtained according to the pareto solution set.
8. The scene driven comprehensive energy complementary capacity planning method according to claim 7, wherein the lower objective function of the updated multi-objective double-layer capacity configuration model is:
wherein pi s” Probability pi corresponding to the newly divided typical scene s', pi s’ For the probability of the extreme scene s', x s’,t For the value of the load loss at time t in the extreme scene s', κ is the penalty cost for the unit load loss.
9. A scene driven integrated energy complementary capacity planning system, comprising:
the initial scene construction module is used for establishing an initial typical scene set of the region to be configured and probabilities corresponding to all scenes in the initial typical scene set;
the initial model building module is used for building an initial multi-target double-layer capacity configuration model based on the initial typical scene set of the area to be configured;
the initial scheme acquisition module is used for solving the initial multi-target double-layer capacity configuration model to obtain an initial configuration scheme solution set;
the extreme scene determining module is used for determining the extreme scene and the probability corresponding to the extreme scene according to the initial configuration scheme solution set;
the scene updating module is used for carrying out reduction updating on the initial typical scene set according to the extreme scene and the probability corresponding to the extreme scene to obtain an updated typical scene set and the probability corresponding to each scene in the updated typical scene set;
the model updating module is used for updating the initial multi-target double-layer capacity configuration model according to the updating typical scene set, the probability corresponding to each scene in the updating typical scene set and the probability corresponding to the extreme scene to obtain an updated multi-target double-layer capacity configuration model;
and the updating scheme acquisition module is used for acquiring an updating scheme solution set according to the updating multi-target double-layer capacity configuration model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311065675.XA CN117314043A (en) | 2023-08-23 | 2023-08-23 | Scene-driven comprehensive energy complementary capacity planning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311065675.XA CN117314043A (en) | 2023-08-23 | 2023-08-23 | Scene-driven comprehensive energy complementary capacity planning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117314043A true CN117314043A (en) | 2023-12-29 |
Family
ID=89259276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311065675.XA Pending CN117314043A (en) | 2023-08-23 | 2023-08-23 | Scene-driven comprehensive energy complementary capacity planning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117314043A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639870A (en) * | 2020-06-04 | 2020-09-08 | 国网山东省电力公司潍坊供电公司 | Power transmission network multi-target flexible planning method and system considering source load uncertainty |
| CN114492985A (en) * | 2022-01-24 | 2022-05-13 | 天津大学 | Hybrid energy storage double-layer optimal configuration method for industrial park comprehensive energy system |
| CN115115277A (en) * | 2022-08-23 | 2022-09-27 | 华北电力大学 | Garden comprehensive energy scheduling method and device, computer equipment and storage medium |
| CN115207972A (en) * | 2022-07-12 | 2022-10-18 | 华北电力大学 | Power supply planning method with coordinated capacity electricity price and wind, light and fire ratio |
| CN115833255A (en) * | 2022-10-09 | 2023-03-21 | 国网福建省电力有限公司经济技术研究院 | Source-load cooperative optimization scheduling method with balanced flexibility supply and demand and terminal |
| WO2023134254A1 (en) * | 2022-01-11 | 2023-07-20 | 云南电网有限责任公司电力科学研究院 | Equipment model selection method for energy interconnection system |
-
2023
- 2023-08-23 CN CN202311065675.XA patent/CN117314043A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639870A (en) * | 2020-06-04 | 2020-09-08 | 国网山东省电力公司潍坊供电公司 | Power transmission network multi-target flexible planning method and system considering source load uncertainty |
| WO2023134254A1 (en) * | 2022-01-11 | 2023-07-20 | 云南电网有限责任公司电力科学研究院 | Equipment model selection method for energy interconnection system |
| CN114492985A (en) * | 2022-01-24 | 2022-05-13 | 天津大学 | Hybrid energy storage double-layer optimal configuration method for industrial park comprehensive energy system |
| CN115207972A (en) * | 2022-07-12 | 2022-10-18 | 华北电力大学 | Power supply planning method with coordinated capacity electricity price and wind, light and fire ratio |
| CN115115277A (en) * | 2022-08-23 | 2022-09-27 | 华北电力大学 | Garden comprehensive energy scheduling method and device, computer equipment and storage medium |
| CN115833255A (en) * | 2022-10-09 | 2023-03-21 | 国网福建省电力有限公司经济技术研究院 | Source-load cooperative optimization scheduling method with balanced flexibility supply and demand and terminal |
Non-Patent Citations (1)
| Title |
|---|
| 胡阳，赵玥莉，胡宇阳，杨泽: ""计及源-荷互动的区域电-热联合系统日前优化调度"", 《热力发电》, vol. 52, no. 3, 31 March 2023 (2023-03-31), pages 102 - 111 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107634518B (en) | Source-network-load coordinated active power distribution network economic dispatching method | |
| CN103151797B (en) | Multi-objective dispatching model-based microgrid energy control method under grid-connected operation mode | |
| Li et al. | A novel bi-level robust game model to optimize a regionally integrated energy system with large-scale centralized renewable-energy sources in Western China | |
| WO2020140743A1 (en) | Power distribution area source-load cooperative access method, terminal, and storage medium | |
| CN109599856A (en) | Electric car management of charging and discharging optimization method and device in a kind of more building of microgrid | |
| CN109636056A (en) | A kind of multiple-energy-source microgrid decentralization Optimization Scheduling based on multi-agent Technology | |
| CN110676849B (en) | Method for constructing islanding micro-grid group energy scheduling model | |
| CN105305423A (en) | Determination method for optimal error boundary with uncertainty of intermittent energy resource being considered | |
| CN113850474A (en) | Thermoelectric hydrogen multi-energy flow comprehensive energy system and optimal scheduling method thereof | |
| WO2023179118A1 (en) | Method and system for optimizing direct-current power transmission curve of multi-energy complementary integrated external transmission base | |
| CN115759610A (en) | Multi-target planning method for source-grid and storage cooperation of power system and application thereof | |
| CN114069687A (en) | Distributed photovoltaic planning method considering reactive power regulation effect of inverter | |
| CN113705892B (en) | Demand side resource and intelligent soft switch distribution robust joint planning method | |
| CN112883630B (en) | Multi-microgrid system day-ahead optimization economic dispatching method for wind power consumption | |
| CN113723793A (en) | Method, device, equipment and medium for realizing park comprehensive energy system | |
| CN113708418A (en) | Micro-grid optimization scheduling method | |
| CN110867902B (en) | Micro-grid distributed power supply decentration optimization operation method based on power generation prediction | |
| CN112803491A (en) | Wind, light and water multi-energy complementary short-term optimization scheduling method coupled with electricity abandoning risk | |
| CN117134409A (en) | Micro-grid system considering electro-hydro-thermal complementation and multi-objective optimal configuration method thereof | |
| CN116776538A (en) | Uncertainty-considered low-carbon planning method for electric power-natural gas-hydrogen coupling network | |
| CN116805192A (en) | Comprehensive energy system double-layer planning optimization method considering optimal energy rejection rate and application thereof | |
| CN110098623A (en) | A kind of Prosumer unit control method based on intelligent load | |
| CN117314043A (en) | Scene-driven comprehensive energy complementary capacity planning method and system | |
| Heo et al. | Energy resource capacity optimization for zero-energy housing complex | |
| Sun et al. | Optimal operation strategy of wind-hydrogen integrated energy system based on NSGA-II algorithm |
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 |