CN117811095A - Method and system for generating multi-resource collaborative adjustment strategy of power system - Google Patents
Method and system for generating multi-resource collaborative adjustment strategy of power system Download PDFInfo
- Publication number
- CN117811095A CN117811095A CN202311685397.8A CN202311685397A CN117811095A CN 117811095 A CN117811095 A CN 117811095A CN 202311685397 A CN202311685397 A CN 202311685397A CN 117811095 A CN117811095 A CN 117811095A
- Authority
- CN
- China
- Prior art keywords
- resource
- power system
- scenes
- load fluctuation
- power
- 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 68
- 238000007621 cluster analysis Methods 0.000 claims abstract description 16
- 238000005070 sampling Methods 0.000 claims abstract description 12
- 241000254158 Lampyridae Species 0.000 claims description 30
- 238000004146 energy storage Methods 0.000 claims description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000005457 optimization Methods 0.000 claims description 20
- 241000039077 Copula Species 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 17
- 238000012614 Monte-Carlo sampling Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000007476 Maximum Likelihood Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 description 37
- 238000010248 power generation Methods 0.000 description 12
- 238000009826 distribution Methods 0.000 description 10
- 238000005086 pumping Methods 0.000 description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 10
- 230000009194 climbing Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 8
- 238000005338 heat storage Methods 0.000 description 7
- 229910052799 carbon Inorganic materials 0.000 description 6
- 238000007599 discharging Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000014509 gene expression Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000004378 air conditioning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 241000282326 Felis catus Species 0.000 description 1
- 241000764238 Isis Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000031700 light absorption Effects 0.000 description 1
- 238000004020 luminiscence type Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005405 multipole Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 244000062645 predators Species 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012887 quadratic function Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
-
- 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
- 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
-
- 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
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
- H02J3/144—Demand-response operation of the power transmission or distribution network
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
- H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/40—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation wherein a plurality of decentralised, dispersed or local energy generation technologies are operated simultaneously
-
- 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
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
- H02J2310/56—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads characterised by the condition upon which the selective controlling is based
- H02J2310/58—The condition being electrical
- H02J2310/60—Limiting power consumption in the network or in one section of the network, e.g. load shedding or peak shaving
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Power Engineering (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention belongs to the technical field of power systems, and discloses a method and a system for generating a multi-element resource cooperative regulation strategy of a power system, wherein the method comprises the following steps: analyzing a power system and determining adjustable resources of the power system; analyzing the uncertainty of the power system, and establishing a joint output probability model; analyzing the adjustable resources based on the joint output probability model to obtain a plurality of new energy joint output data and load fluctuation data, and sampling the obtained new energy joint output data and load fluctuation data to obtain a plurality of output scenes and load fluctuation scenes; and performing cluster analysis on the obtained multiple output scenes and load fluctuation scenes to obtain a typical scene, and performing multi-resource collaborative planning solution based on the typical scene to obtain a multi-resource collaborative adjustment strategy. The invention realizes the collaborative planning and comprehensive utilization of resources, improves the overall efficiency of the system, and has stronger applicability of strategies.
Description
Technical Field
The invention relates to the technical field of power systems, in particular to a method and a system for generating a multi-resource cooperative regulation strategy of a power system.
Background
China is one of the countries with the largest energy production and consumption regulations in the world. With the increasing global energy demand, there is an increasing demand for sustainable, clean energy, which has driven the rapid development and widespread use of new energy. In order to slow down climate change and reduce carbon emission, various countries are encouraged to develop and utilize new energy. In recent years, therefore, a large number of new energy generator sets are connected to the power grid, however, due to their extremely high uncertainty and volatility, a great challenge is presented to the stability of the power system. On the other hand, with the rapid development of social economy, the demand of various industries for electric power is continuously increasing, and the load is continuously rising, so that the electric power system is also subjected to greater pressure.
There is a significant lack of flexibility in conventional power systems. The thermal power generating unit in the traditional system cannot rapidly cope with load fluctuation due to the fact that the starting, stopping and climbing speeds are low, and the system is enabled to be placket and elbow when facing the characteristic of high fluctuation of new energy. Meanwhile, units with rapid adjustment capability such as water power, gas power and the like can respond to system requirements rapidly, but the installed capacity of the units is limited, and rapid change of large-scale load cannot be met, so that the flexibility of the whole system is affected. Thus, the grid is faced with two major challenges. On the one hand, the problem of 'promoting the digestion' of the new energy unit is how to efficiently integrate and utilize new energy, ensure that the new energy is stably and continuously injected into the power system, and simultaneously reduce the waste of resources such as wind and light abandoning and the like. Another aspect is the "keep-alive" problem of coping with sudden load increases, i.e. when the load increases rapidly, ensuring that the system is able to steadily supply enough power to meet the user's needs. In order to solve the above challenges, it is required to fully discover flexible resources on the source-grid-load-storage side and use them to cooperatively respond to the new energy output change and the load demand in multiple aspects so as to fully improve the regulation capability of the power system.
At present, an optimization method is mainly adopted for a regulating strategy generation method of the power system. In general, the method relies on historical data firstly, utilizes the historical data to predict the output and load fluctuation of new energy in the future, then inputs the predicted data into a power system, and finally utilizes an optimization algorithm to solve an optimal strategy. However, this approach has some drawbacks: firstly, it cannot adequately characterize the uncertainty of the power system, especially when dealing with emergency situations; and secondly, the complexity of the existing optimization algorithm is high, the solving efficiency is low, the time consumption is long, and timely and effective reference of power system dispatching is difficult to provide.
Another problem is that in current power system regulation strategy generation, the development of source-net-load-store side flexible resources is not sufficient, and the potential flexibility of these resources can be scheduled and utilized when needed, but the prior art generally only considers part of the adjustable resources, and cannot better adapt to complex and variable power requirements and new energy fluctuations.
In order to solve the defects existing in the prior art, it is necessary to explore a more accurate and efficient power system multi-element resource collaborative adjustment strategy generation method.
Disclosure of Invention
The embodiment of the invention provides a method and a system for generating a multi-element resource cooperative regulation strategy of an electric power system, which are used for solving the technical problems in the prior art.
The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to a first aspect of an embodiment of the invention, a method for generating a multi-resource collaborative adjustment strategy of an electric power system is provided.
In one embodiment, the method for generating the power system multi-resource collaborative adjustment strategy comprises the following steps:
analyzing a power system and determining adjustable resources of the power system; analyzing the uncertainty of the power system, and establishing a joint output probability model;
analyzing the adjustable resources based on the joint output probability model to obtain a plurality of new energy joint output data and load fluctuation data, and sampling the obtained new energy joint output data and load fluctuation data to obtain a plurality of output scenes and load fluctuation scenes;
And performing cluster analysis on the obtained multiple output scenes and load fluctuation scenes to obtain a typical scene, and performing multi-resource collaborative planning solution based on the typical scene to obtain a multi-resource collaborative adjustment strategy.
In one embodiment, the adjustable resource comprises: power side adjustable resources, load side adjustable resources, and energy storage side adjustable resources.
In one embodiment, the power side adjustable resource comprises: the system comprises an adjustable hydropower station, a gas turbine unit, a thermal power unit and a photo-thermal power station which are subjected to flexibility transformation; the load side adjustable resource includes: temperature control load and electric automobile clusters; the energy storage side adjustable resource comprises: pumped storage power station and energy storage battery.
In one embodiment, analyzing the uncertainty of the electrical power system, establishing the joint output probability model includes: and analyzing the uncertainty of the power system by using a Copula function, and establishing a joint output probability model.
In one embodiment, the equation of the joint output probability model is:
wherein θ is a parameter of a certain parameter space, and estimating according to a maximum likelihood method; ln is the natural logarithm, e is the natural constant; u, v are bivariate of generating function, data used for inputting the combined output; c (u, v) represents a generator of the Copula function.
In one embodiment, sampling the obtained new energy combined output data and the load fluctuation data to obtain a plurality of output scenes and load fluctuation scenes includes: and sampling the obtained new energy combined output data and the load fluctuation data by a Monte Carlo sampling method to obtain a plurality of output scenes and load fluctuation scenes.
In one embodiment, performing cluster analysis on the obtained multiple output scenes and load fluctuation scenes to obtain typical scenes includes: and performing cluster analysis on the obtained multiple output scenes and the load fluctuation scenes by adopting a variation self-encoder clustering method to obtain a typical scene.
In one embodiment, performing the multi-resource collaborative planning solution based on the typical scenario, obtaining the multi-resource collaborative adjustment policy includes: based on the typical scene, a firefly optimization algorithm is adopted to carry out multi-resource collaborative planning and solving, and a multi-resource collaborative adjustment strategy is obtained.
According to a second aspect of the embodiment of the invention, a power system multi-resource collaborative adjustment strategy generation system is provided.
In one embodiment, the power system multi-resource co-regulation policy generation system includes:
The resource analysis module is used for analyzing the power system and determining adjustable resources of the power system; analyzing the uncertainty of the power system, and establishing a joint output probability model;
the scene generation module is used for analyzing the adjustable resources based on the joint output probability model to obtain a plurality of new energy joint output data and load fluctuation data, and sampling the obtained new energy joint output data and load fluctuation data to obtain a plurality of output scenes and load fluctuation scenes;
the scene solving module is used for carrying out cluster analysis on the obtained multiple output scenes and the load fluctuation scenes to obtain a typical scene, and carrying out multi-resource collaborative planning and solving based on the typical scene to obtain a multi-resource collaborative adjustment strategy.
In one embodiment, the adjustable resource comprises: power side adjustable resources, load side adjustable resources, and energy storage side adjustable resources.
In one embodiment, the power side adjustable resource comprises: the system comprises an adjustable hydropower station, a gas turbine unit, a thermal power unit and a photo-thermal power station which are subjected to flexibility transformation; the load side adjustable resource includes: temperature control load and electric automobile clusters; the energy storage side adjustable resource comprises: pumped storage power station and energy storage battery.
In one embodiment, the resource analysis module analyzes the uncertainty of the power system by using a Copula function when analyzing the uncertainty of the power system and building a joint output probability model.
In one embodiment, the equation of the joint output probability model is:
wherein θ is a parameter of a certain parameter space, and estimating according to a maximum likelihood method; ln is the natural logarithm, e is the natural constant; u, v are bivariate of generating function, data used for inputting the combined output; c (u, v) represents a generator of the Copula function.
In one embodiment, the scene generating module samples the obtained new energy combined output data and the load fluctuation data by a Monte Carlo sampling method when sampling the obtained new energy combined output data and the load fluctuation data to obtain a plurality of output scenes and load fluctuation scenes.
In one embodiment, the scene generation module performs cluster analysis on the obtained multiple output scenes and the load fluctuation scenes by adopting a variation self-encoder clustering method when performing cluster analysis on the obtained multiple output scenes and the load fluctuation scenes to obtain a typical scene.
In one embodiment, when the scenario solving module performs multi-resource collaborative planning and solving based on the typical scenario to obtain a multi-resource collaborative adjustment strategy, the scenario solving module performs multi-resource collaborative planning and solving based on the typical scenario by adopting a firefly optimizing algorithm to obtain the multi-resource collaborative adjustment strategy.
The technical scheme provided by the embodiment of the invention can have the following beneficial effects:
the invention considers the diversity of source-network-load-storage side resources in the power system, realizes the collaborative planning and comprehensive utilization of the resources, and improves the overall efficiency of the system, so that the generated strategy has stronger applicability. The method based on data driving improves the solving efficiency, accelerates the generation of strategies, and can provide timely and effective references for the arrangement and scheduling strategies of the power system in the future.
Compared with the method for fitting the data by the parameter estimation method, the method for simulating the power system by using the Copula function has the advantage that the problem of limited application range caused by only adjusting some parameters of probability distribution is solved, and the Copula function can simulate joint distribution of any shape, so that the actual situation can be simulated more accurately. Meanwhile, compared with the traditional clustering method, the deep clustering method based on the variation self-encoder optimizes the feature extraction process by using the deep neural network, and solves the problems of feature extraction and unhooking in the traditional clustering algorithm. The method not only reduces the complexity and improves the clustering efficiency, but also remarkably enhances the clustering effect due to an excellent feature extraction algorithm.
In addition, the firefly optimization algorithm adopted by the invention can find the globally optimal solution or the solution close to the optimal solution in the search space by simulating the mutual attraction behaviors among fireflies, successfully solves the problems that the traditional intelligent optimization algorithm is slow in convergence speed and easy to fall into local optimization, and obtains more excellent optimization effect.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow diagram illustrating a method for generating a coordinated multi-resource adjustment strategy for an electrical power system, according to an exemplary embodiment;
FIG. 2 is a block diagram illustrating a power system multi-resource co-regulation strategy generation system in accordance with an exemplary embodiment;
FIG. 3 is a schematic diagram of a variant self-encoder, according to an example embodiment;
FIG. 4 is a flowchart illustrating extracting a representative scene based on a variance-based self-encoder depth clustering method, according to an example embodiment;
FIG. 5 is a flowchart illustrating a generation strategy solution for a firefly optimization algorithm, according to an example embodiment;
fig. 6 is a schematic diagram of a computer device, according to an example embodiment.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments herein to enable those skilled in the art to practice them. Portions and features of some embodiments may be included in, or substituted for, those of others. The scope of the embodiments herein includes the full scope of the claims, as well as all available equivalents of the claims. The terms "first," "second," and the like herein are used merely to distinguish one element from another element and do not require or imply any actual relationship or order between the elements. Indeed the first element could also be termed a second element and vice versa. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a structure, apparatus, or device that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such structure, apparatus, or device. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a structure, apparatus or device comprising the element. Various embodiments are described herein in a progressive manner, each embodiment focusing on differences from other embodiments, and identical and similar parts between the various embodiments are sufficient to be seen with each other.
The terms "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like herein refer to an orientation or positional relationship based on that shown in the drawings, merely for ease of description herein and to simplify the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operate in a particular orientation, and thus are not to be construed as limiting the invention. In the description herein, unless otherwise specified and limited, the terms "mounted," "connected," and "coupled" are to be construed broadly, and may be, for example, mechanically or electrically coupled, may be in communication with each other within two elements, may be directly coupled, or may be indirectly coupled through an intermediary, as would be apparent to one of ordinary skill in the art.
Herein, unless otherwise indicated, the term "plurality" means two or more.
Herein, the character "/" indicates that the front and rear objects are an or relationship. For example, A/B represents: a or B.
Herein, the term "and/or" is an association relation describing an object, meaning that three relations may exist. For example, a and/or B, represent: a or B, or, A and B.
It should be understood that, although the steps in the flowchart are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or other steps.
The various modules in the apparatus or systems of the present application may be implemented in whole or in part in software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Fig. 1 illustrates one embodiment of a method for generating a coordinated multi-resource adjustment strategy for an electrical power system according to the present invention.
In this alternative embodiment, the method for generating the power system multi-resource collaborative adjustment policy includes:
step S101, analyzing a power system and determining adjustable resources of the power system; analyzing the uncertainty of the power system, and establishing a joint output probability model;
step S103, analyzing the adjustable resources based on the joint output probability model to obtain a plurality of new energy joint output data and load fluctuation data, and sampling the obtained new energy joint output data and load fluctuation data to obtain a plurality of output scenes and load fluctuation scenes;
step S105, performing cluster analysis on the obtained multiple output scenes and load fluctuation scenes to obtain a typical scene, and performing multi-resource collaborative planning solution based on the typical scene to obtain a multi-resource collaborative adjustment strategy.
Fig. 2 illustrates one embodiment of a power system multi-resource co-regulation policy generation system of the present invention.
In this alternative embodiment, the power system multi-resource co-regulation policy generation system includes:
a resource analysis module 201, configured to analyze a power system and determine an adjustable resource of the power system; analyzing the uncertainty of the power system, and establishing a joint output probability model;
the scene generation module 203 is configured to analyze the adjustable resource based on the joint output probability model to obtain multiple new energy joint output data and load fluctuation data, and sample the obtained new energy joint output data and load fluctuation data to obtain multiple output scenes and load fluctuation scenes;
the scenario solving module 205 is configured to perform cluster analysis on the obtained multiple output scenarios and load fluctuation scenarios to obtain a typical scenario, and perform multi-resource collaborative planning and solving based on the typical scenario to obtain a multi-resource collaborative adjustment policy.
In a specific application, the adjustable resources include: power side adjustable resources, load side adjustable resources, and energy storage side adjustable resources.
The power supply side adjustable resource is a generator set with the capacity of quickly adjusting output on the power supply side, and mainly comprises an adjustable hydropower station, a gas turbine set, a thermal power unit and a photo-thermal power station after being flexibly modified.
Wherein, the load side adjustable resource refers to controllable load which can participate in demand response, and the controllable load comprises interruptible load and adjustable load. By coordinating and managing these controllable loads, the power system may increase its flexibility and reliability, while increasing energy utilization. The invention mainly models two controllable loads, namely the temperature control load which is most widely used and has the most profound influence and the electric automobile cluster, and specifically comprises the following steps:
for temperature controlled loads, the temperature controlled load meets the power demand by controlling the temperature in the building or equipment. The temperature control load has quick response and is beneficial to balancing the supply and demand of the power system. When the external characteristics of the air conditioner load in the temperature control load are subjected to time domain modeling, a first-order differential equation of an equivalent thermal parameter model of the single air conditioner load is as follows:
wherein T (T) is room temperature at time T, T a (t) is the outdoor temperature at the moment t, R is a room thermal resistance parameter, C is a room heat capacity parameter, s (t) is the on-off state of a single air conditioner load at the moment t, and Q is the refrigerating (heating) quantity; d is a differential operator.
The introduction control cost objective function is as follows:
C ctl (t)＝εT M (t)τ M (t)
wherein C is ctl (T) is a control cost objective function, ε is the user participation, T M (t) is the absolute value of the difference between the air conditioning load and the upper and lower temperature limits, τ M And (t) is the time difference between the air conditioner load switch state and the next natural switching state.
The objective function in two switching states of the air conditioning load from off to on and from on to off can be expressed as follows:
wherein C is ctl,off-on (t) is a control cost objective function for switching the air conditioner load from off to on, C ctl,on-off (T) controlling the cost objective function for switching the air conditioner load from on to off, T max 、T min T (T) is the room temperature at the moment T and is the upper limit and the lower limit of the temperature a And (t) is the outdoor temperature at the moment t, R is a room thermal resistance parameter, C is a room heat capacity parameter, and Q is a refrigerating (heating) quantity.
For the electric automobile cluster, the electric automobile cluster stores and releases electric energy by utilizing the battery, so that the electric automobile cluster has quick and considerable adjusting potential, can relieve the pressure of a power grid, and realizes peak clipping and valley filling. The large-scale electric automobile clusters can be subjected to simplified modeling to evaluate the adjustable capacity of the electric automobile clusters. The method comprises the following steps:
the electric automobile has three states of Charging (CS), idle (IS) and Discharging (DS). The expressions are listed for the power flow provided by the car battery for the three states in the cluster. The state of charge is as follows:
wherein s is CS (t) represents the state of charge SOC of the electric vehicle in the state of charge at time t, its derivative with respect to time Indicating that electric automobile cluster is in charging state at time tThe average change speed of the SOC of the electric automobile, X CS (s, t) represents the number of electric vehicles in the SOC state s at the time t, F CS (s, t) is the flow of the electric vehicle passing through the state s at the moment t; p (P) CS 、η CS Q is the average rated power, charging efficiency and battery capacity of the electric automobile cluster respectively; n (N) ev Representing the number of electric vehicles in the cluster; a, a CS The derivative of the state of charge with respect to time, i.e. the charging speed, when charging the electric vehicle clusters; η (eta) i,CS The charging efficiency of the ith electric automobile; />For partial differentiation operators, e.g.>Is a partial derivative with respect to time.
The expression in idle state is:
since the SOC in the idle state does not change with time t, X IS And (s, t) represents the number of electric vehicles in the electric vehicle cluster, wherein the state of charge of the electric vehicles is s and the electric vehicles are in an idle state.
Similarly, the expression in the discharge state is:
wherein X is DS (s, t) is the number of electric vehicles with the state of charge s and the state of discharge in the electric vehicle cluster at the moment t; p (P) DS 、η DS Respectively is electricAverage rated discharge power and discharge efficiency of the motor car cluster; q is the battery capacity.
The energy storage side adjustable resource is an important means for coping with the randomness of the new energy output and improving the flexibility of the power system. The common energy storage type is a pumped storage power station and an energy storage battery, so that the power generation and the power utilization can be separated in time and space in a certain sense, the flexibility of the system is improved, and the system is particularly as follows:
Pumped-storage power stations are an important facility for energy storage and power generation by using water energy. The pumping model and the conventional power generation model can be respectively shown as follows:
wherein E is m.ps Generating power for the water pump group; e (E) ps Water energy stored for the maximum pumping reservoir capacity; p (P) m.ps Power is consumed for pumping water; dt is the time derivative; t (T) ps For the duration of pumping; η (eta) m The conversion efficiency between electric energy and water energy is achieved; p (P) ps.a The peak regulation capacity of the pumped storage unit; p (P) ps.u Generating power for the pumped storage unit; p (P) ps.s The standby capacity of the pumped storage unit; r is R ps.s Is the standby rate; r is R ps Is water energy-electric energy efficiency; e (E) ps Water energy stored for the maximum pumping reservoir capacity; e (E) ps.a Peak shaving generating capacity of the unit; e (E) ps.s Spare power generation capacity for the unit; the unit determines a limited generating capacity according to the stored water energy; e (E) ps.g A defined power generation amount determined for the unit according to the stored water energy; q ps Is the random outage probability; t (T) ps.f Is the mean time between failures; t (T) ps.r Is the average fault recovery time.
And the operating constraints include: pumping-generating state constraint, start-stop times constraint and maximum state transition times constraint; the formulas are respectively as follows:
N t,g N t,p ＝0
wherein N is t,g E {0,1} is a binary variable of pumping state, 0 represents no pumping, 1 represents pumping; n (N) t,p E {0,1} is a binary variable of the power generation state, 0 means no power generation, and 1 means power generation. n is n t,g ，n t,p The start and stop times of the power generation and pumping states in a period of time respectively;maximum state transition times of the power generation and pumping states respectively in a period of time.
For an energy storage battery, the energy storage system can be modeled as a positive and negative adjustable generator that charges and discharges according to the system state, the energy storage SOC, and the energy storage power capacity limit. Its state of charge SOC can be expressed as:
wherein E is N Rated power of the energy storage battery; SOC (State of Charge) t The state of charge of the battery at the moment t; Δt is the time step increment;the output power of the energy storage battery at the corresponding moment; dt is the time derivative.
The operating constraints include: the upper limit and the lower limit of the SOC are constrained, the charge and discharge power is constrained, and the charge times are constrained, wherein the formulas are respectively as follows:
in SOC max ，SOC min Respectively the upper limit and the lower limit of the charge state of the energy storage battery;respectively the upper limit and the lower limit of the energy storage battery when participating in primary frequency modulation of the power grid; n is n t,be The charge and discharge times in one period; />Is the maximum charge and discharge times in one period.
In addition, in the specific application, when the uncertainty of the electric power system is analyzed and the joint output probability model is established, the uncertainty of the electric power system can be analyzed by utilizing a Copula function, and the joint output probability model is established. And when the obtained new energy combined output data and load fluctuation data are sampled to obtain a plurality of output scenes and load fluctuation scenes, the obtained new energy combined output data and load fluctuation data can be sampled by a Monte Carlo sampling method to obtain a plurality of output scenes and load fluctuation scenes. The method comprises the following steps:
The main idea of the Copula function is to map multidimensional random variables onto unit hypercubes (units hypercubes) and then describe the correlation between them with a function. According to the invention, a Gumbel Copula function, a Clayton Copula function and a Frank Copula function in the Archimedes Copula function are used for respectively representing the combined output probability model of wind power, photovoltaic power and photo-heat in the new energy unit. The following three formulas represent their function generator and expression, respectively.
The three formulas are respectively the generator and the expression of Gumbel Copula function, clayton Copula function and Frank Copula function in the Copula function. Wherein θ is a parameter of a certain parameter space, which can be estimated according to a maximum likelihood method in the invention; ln is the natural logarithm, e is the natural constant; u, v are bivariate generating functions for inputting the data of the combined output.
Then, a joint output probability model generated based on a Copula function, namely a possible value of a new energy unit and load fluctuation is approximately represented by a limited number of output samples, and then the probability model is sampled by adopting a Monte Carlo sampling method to generate a large number of scenes.
When the obtained multiple output scenes and load fluctuation scenes are subjected to cluster analysis to obtain a typical scene, the obtained multiple output scenes and load fluctuation scenes can be subjected to cluster analysis by adopting a variation self-encoder clustering method to obtain the typical scene. The method comprises the following steps:
The invention adopts a depth clustering method based on a variation self-encoder (variable AutoEncoder, VAE) to cluster generated scenes, and can simultaneously perform unsupervised learning and cluster analysis. The structure of the variable self-encoder is shown in fig. 3, and the main steps of the algorithm implementation thereof can be shown in fig. 4, and the specific details are as follows:
data preprocessing: for the Monte Carlo sampling method adopted in scene generation, the expectation and variance of random variable groups generated by sampling can be used for checking the validity of data, so that non-conforming random variable groups are removed.
Wherein E is MC Represents a sample expected value obtained by a Monte Carlo sampling method, h (x) represents data in scene generation, n is the total number of samples, and D MC Representing the sample variance obtained by the monte carlo sampling method.
After abnormal data are removed, data standardization is carried out, so that the similar scale of each feature is ensured, and the dominant influence of a few features on model training is avoided.
Building a VAE model: VAEs are a powerful generative learning framework that requires intermediate features to follow a given gaussian distribution. And the VAE model is composed of three parts, namely cluster class c, intermediate feature (i.e. hidden layer) z of the cluster and sample x. The generation process can be expressed as:
p(x,z,c)＝p(x|z)p(z|c)p(c)
Where p () represents the probability of an event occurring, p (|·) represents the conditional probability, e.g., p (c) represents the probability of cluster class c, p (z|c) represents the probability of an intermediate feature z existing again under the condition of cluster class c, p (x|z) represents the probability of a sample x occurring under the condition of intermediate feature z, and p (x, z, c) represents the probability generation process of the model.
And the generation process of the sample x can be expressed as:
wherein cat (·) represents the discrete distribution of categories; k is the number of cluster clusters defined in advance; mu (mu) c ，σ c C is the mean and variance corresponding to c; n represents a normal distribution.
After the model is generated with the VAE, the main objective is to approximate the true distribution p (x) of the sample x in order to achieve a clustering effect.
Designing an objective function: the optimization objective of the VAE is to maximize the lower bound of evidence as much as possible, while the main objective of this process is to approximate the intermediate features of the sample as closely as possible to a given a priori distribution. It can be expressed specifically by the following formula:
wherein: l (θ, φ, X) is the objective function of the VAE; q φ (z|x i ) Representing the empirical posterior probability, the approximation representing the true posterior probability of the unknown, also the encoder,representing the expected value of the encoder; p (z) represents the occupied probability of the intermediate feature (i.e. hidden layer); d (D) KL KL divergence representing posterior probability distribution and prior distribution; p is p θ (x i Z) represents a decoder. The encoder may be implemented with a depth network, while the hidden layer z itself obeys a gaussian distribution.
Evaluation of clustering results: three common indexes are adopted to evaluate the effectiveness of the clustering result so as to extract a typical scene. Respectively, unsupervised clustering accuracy (Unsupervised Clustering Accuracy, ACC), homogeneity (Homegeneity) and normalized mutual information (Normalized Mutual Information, NMI). The calculation is described by the following formula:
where n is the number of samples, H (Y, C) represents the entropy of information between the variables Y, C, f (x) represents the homogeneity function, Y i Representing the sample genuine label c i Namely, the predictive label, m represents the mapping relation between the predictive label and the real label, H represents the information entropy, I (Y, C) represents the mutual information between the variables Y, C, and H (Y), H (C) are dividedThe information entropy of the variable Y, C is indicated.
Through the clustering and the evaluation and verification of the effectiveness, the probability of different typical scenes (new energy output and load fluctuation) can be finally obtained, and the probability is combined to perform the strategy generation corresponding to various typical scenes in the next step.
When the multi-resource collaborative planning solution is carried out based on the typical scene to obtain the multi-resource collaborative adjustment strategy, the multi-resource collaborative planning solution can be carried out by adopting a firefly optimization algorithm based on the typical scene to obtain the multi-resource collaborative adjustment strategy. The method comprises the following steps:
The objective function of the firefly optimization algorithm is to minimize economic cost, minimum cut load and minimum new energy waste, reasonable weights are assigned to the objective function of the multi-objective optimization, and the formula is as follows:
minw 1 C+w 2 ΔL+w 3 ΔP
wherein w is 1 ,w 2 ,w 3 Weights for different targets; c refers to economic cost, in the invention, the main considered cost is coal consumption cost and start-stop cost of the thermal power unit, wherein the coal consumption cost isIs the output P of the thermal power generating unit i,t Can be fitted by a quadratic function and the start-stop cost is expressed as +.>And->ΔL refers to the cut load of the system, < +.>Referring to the load shedding value of the ith bus at the moment t, the whole target should take the minimum load shedding as the primary target to ensure the safe and reliable operation of the power system, so that w 2 Maximum; total power loss of Δp value system, +.>The electric quantity of the wind power generation, photovoltaic and photo-thermal units is respectively represented; Δt represents the time step increment; n represents the number of thermal power generating units; n (N) b Representing the number of bus bars; n (N) w 、N pv 、N csp The number of the wind turbine generators, the photovoltaic power stations and the photo-thermal power stations is respectively.
Constraints of the firefly optimization algorithm include: system balance constraint, unit technology constraint and direct current power flow constraint. The method comprises the following steps:
1. the system balancing constraints include: the power balance constraint of the system (namely, the output of all units is equal to the electric quantity required by the load of all nodes) and the hot standby constraint of the system are respectively expressed in the following formulas:
Wherein P is i,t Is the output active power of the ith thermal power unit at the moment t, N is the number of the thermal power units, N L The number of load nodes;the active power of the ith new energy unit at the moment t; l (L) j,t Is the electric quantity required by the j node load at the moment t; />Is systematic inActive standby capacity; nm is the number of new energy units; u (U) i,t E {0,1} refers to the start-stop state of the ith unit at the moment t; p (P) i,max Is the maximum power which can be output by the ith thermal power generating unit; ρ refers to the rotational stand-by coefficient of the system.
2. The unit technical constraint comprises: the method comprises the steps of outputting and climbing constraint of a unit, starting and stopping time constraint of a thermal power unit, upper and lower limits of wind and light output in a new energy unit, upper and lower limits of charge and discharge power and capacity of an energy storage system of a photo-thermal power station, climbing constraint of output power of the photo-thermal power station, charge and discharge electric quantity balance of a novel energy storage battery, power limit, SOC capacity constraint and limit of charge and discharge times in a period; the formulas are respectively as follows:
-V d Δt≤P t+1，csp -P t，csp ≤V u Δt
in U i,t E {0,1} is the start-stop state of the ith unit at time t, and when t=k, the start-stop state is expressed as U i,k ；P i,min The lower limit of the output power of the ith thermal power unit; v (V) d The downward climbing speed of the thermal power generating unit is set; v (V) u The upward climbing speed of the thermal power unit is the upward climbing speed, and the output and climbing constraint of the unit are described; p (P) t,w/pv Is the power of wind power or photovoltaic power generation,for its upper limit, it means that its power is limited by natural conditions; t (T) stop The minimum shutdown time of the thermal power generating unit; t (T) start The minimum starting time of the thermal power generating unit; />Charging and discharging power of the thermal power station heat storage system respectively;the upper and lower limits thereof, respectively; /> The heat storage levels of the heat storage systems should meet the upper and lower limits of the capacity of the heat storage device, respectively; />The heat storage level for the heat storage system should meet the heat storage device capacity; p (P) t，csp The output power of the photo-thermal power station at the time t; />Is the maximum output power of the photo-thermal power station; Δt is the time step increment; v (V) d The downward climbing speed of the output power of the photo-thermal power station is increased; v (V) u The downward climbing speed of the output power of the photo-thermal power station is increased; p (P) be,c Represents the charging power of the energy storage battery, the maximum value of which is +.>P be,d Represents the discharge power of the energy storage cell, the maximum value of which is +.>Representing charge and discharge efficiency of the battery; />Respectively representing the charge and discharge power of the battery at the time t; delta T is the time step increment; />Maximum and minimum values of battery state of charge, respectively limited by technical reasons; n is n be The number of cyclic discharges in one cycle, respectively.
3. The direct current power flow constraint comprises: the phase angle difference constraint at two ends of the line, the power constraint flowing on the line and the relation constraint of the power flowing on the line and the phase angles at two ends of the line are respectively shown in the following formulas:
Wherein B is ij For susceptance of the line between node i and node j,for the capacity of line l, q l The state of line l; θ l,i -θ l,j Representing the phase angle difference between node i and node j; p (P) l Is the load power.
The solving process comprises the following steps: the firefly algorithm used in the invention is a heuristic optimization algorithm, the inspiration of which is derived from the fact that fireflies in nature mutually send signals through flashing light rays to attract partners and warn potential predators. The greatest advantage is that a good initial solution is not required to start the optimization process, i.e. it will get the same optimal solution whatever the initial solution is. Compared with other intelligent algorithms, the firefly optimization algorithm has two advantages: active division of sub-populations and processing of multipole to be optimized functions. In the algorithm, attractive force is inversely proportional to distance, and firefly groups are automatically promoted to be divided into a plurality of subgroups and distributed in each local extremum region of the function search space to be optimized. The active grouping characteristic not only enables the algorithm to automatically acquire the global optimal value of the function to be optimized, but also enables all individuals to search the global optimal solution together under the condition that the population size is far larger than the peak value of the function to be optimized. The algorithm flow is shown in fig. 5.
There are four notable factors for solving the continuous optimization problem with this algorithm:
wherein x is i Representing the position of the ith firefly, the first formula represents I i I.e. the luminescence intensity of firefly, f (x i ) Is an objective function value; the second formula r ij Is the distance between two firefly fires, x i,k Is the kth component of the ith firefly space coordinate, d is the dimension of the problem; the third formula beta (r) is the attractive force of a firefly, beta 0 Is the maximum attractive force, and gamma is the light absorption coefficient; the last formula shows the update of the firefly position, if the luminous intensity of the jth firefly is larger than that of the ith firefly, the ith firefly is attracted, the spatial position changes, wherein alpha is a random term coefficient, and rand refers to the fact that the two fireflies are uniformly distributed in [0,1 ]]Random numbers of (a); e is a natural constant, r ij Representing the distance between the ith firefly and the jth firefly; xi and xj are different only in subscript, and both represent firefly positions; xj, k is the same as xi, k except for the difference between the ith firefly and the jth firefly.
Solving the model according to the firefly algorithm to obtain the strategy of multi-element resource cooperative regulation in a typical scene.
FIG. 6 illustrates one embodiment of a computer device of the present invention. The computer device may be a server including a processor, memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used for communicating with an external terminal through a network connection. Which computer program, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
The invention further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the steps in the embodiment of the method.
In addition, the invention also provides a computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the steps of the above-mentioned method embodiments.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The present invention is not limited to the structure that has been described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (16)
1. The method for generating the cooperative regulation strategy of the multiple resources of the power system is characterized by comprising the following steps of:
analyzing a power system and determining adjustable resources of the power system; analyzing the uncertainty of the power system, and establishing a joint output probability model;
analyzing the adjustable resources based on the joint output probability model to obtain a plurality of new energy joint output data and load fluctuation data, and sampling the obtained new energy joint output data and load fluctuation data to obtain a plurality of output scenes and load fluctuation scenes;
and performing cluster analysis on the obtained multiple output scenes and load fluctuation scenes to obtain a typical scene, and performing multi-resource collaborative planning solution based on the typical scene to obtain a multi-resource collaborative adjustment strategy.
2. The method of generating a coordinated multi-resource adjustment policy for a power system of claim 1, wherein the adjustable resource comprises: power side adjustable resources, load side adjustable resources, and energy storage side adjustable resources.
3. The power system multi-resource co-regulation policy generation method according to claim 2, wherein the power source side adjustable resource includes: the system comprises an adjustable hydropower station, a gas turbine unit, a thermal power unit and a photo-thermal power station which are subjected to flexibility transformation; the load side adjustable resource includes: temperature control load and electric automobile clusters; the energy storage side adjustable resource comprises: pumped storage power station and energy storage battery.
4. The method for generating the multi-resource collaborative adjustment policy for the power system according to claim 1, wherein analyzing the uncertainty of the power system and establishing the joint output probability model includes:
and analyzing the uncertainty of the power system by using a Copula function, and establishing a joint output probability model.
5. The method for generating a coordinated multi-resource adjustment strategy for an electric power system according to claim 4, wherein the equation of the joint output probability model is:
wherein θ is a parameter of the parameter space, and estimating according to a maximum likelihood method; ln is the natural logarithm, e is the natural constant; u, v are bivariate of generating function, data used for inputting the combined output; c (u, v) represents a generator of the Copula function.
6. The method for generating the multi-resource collaborative adjustment policy for the power system according to claim 1, wherein sampling the obtained new energy combined output data and the load fluctuation data to obtain a plurality of output scenes and load fluctuation scenes comprises:
and sampling the obtained new energy combined output data and the load fluctuation data by a Monte Carlo sampling method to obtain a plurality of output scenes and load fluctuation scenes.
7. The method for generating the cooperative adjustment strategy for the multiple resources of the power system according to claim 1, wherein the clustering analysis is performed on the obtained multiple output scenes and the load fluctuation scenes, and the obtaining of the typical scene comprises the following steps:
and performing cluster analysis on the obtained multiple output scenes and the load fluctuation scenes by adopting a variation self-encoder clustering method to obtain a typical scene.
8. The method for generating the multi-resource collaborative adjustment policy for the electric power system according to claim 1, wherein the step of performing multi-resource collaborative planning solution based on the typical scenario to obtain the multi-resource collaborative adjustment policy comprises:
based on the typical scene, a firefly optimization algorithm is adopted to carry out multi-resource collaborative planning and solving, and a multi-resource collaborative adjustment strategy is obtained.
9. A power system multi-resource collaborative adjustment policy generation system, comprising:
the resource analysis module is used for analyzing the power system and determining adjustable resources of the power system; analyzing the uncertainty of the power system, and establishing a joint output probability model;
the scene generation module is used for analyzing the adjustable resources based on the joint output probability model to obtain a plurality of new energy joint output data and load fluctuation data, and sampling the obtained new energy joint output data and load fluctuation data to obtain a plurality of output scenes and load fluctuation scenes;
the scene solving module is used for carrying out cluster analysis on the obtained multiple output scenes and the load fluctuation scenes to obtain a typical scene, and carrying out multi-resource collaborative planning and solving based on the typical scene to obtain a multi-resource collaborative adjustment strategy.
10. The power system multi-resource co-regulation policy generation system of claim 9, wherein the adjustable resources comprise: power side adjustable resources, load side adjustable resources, and energy storage side adjustable resources.
11. The power system multi-resource co-regulation policy generation system of claim 10, wherein the power source side adjustable resources comprise: the system comprises an adjustable hydropower station, a gas turbine unit, a thermal power unit and a photo-thermal power station which are subjected to flexibility transformation; the load side adjustable resource includes: temperature control load and electric automobile clusters; the energy storage side adjustable resource comprises: pumped storage power station and energy storage battery.
12. The system of claim 9, wherein the resource analysis module, when analyzing the uncertainty of the power system to create a joint output probability model, analyzes the uncertainty of the power system by using a Copula function to create a joint output probability model.
13. The power system multi-resource co-regulation strategy generation system of claim 12, wherein the equation of the joint output probability model is:
wherein θ is a parameter of the parameter space, and estimating according to a maximum likelihood method; ln is the natural logarithm, e is the natural constant; u, v are bivariate of generating function, data used for inputting the combined output; c (u, v) represents a generator of the Copula function.
14. The system of claim 9, wherein the scenario generation module samples the obtained new energy combined output data and the load fluctuation data to obtain a plurality of output scenarios and load fluctuation scenarios, and samples the obtained new energy combined output data and the load fluctuation data by a monte carlo sampling method to obtain a plurality of output scenarios and load fluctuation scenarios.
15. The system of claim 9, wherein the scene generation module performs cluster analysis on the obtained plurality of output scenes and the load fluctuation scenes to obtain a typical scene by using a variation self-encoder clustering method.
16. The system of claim 9, wherein the scenario solution module performs multi-resource collaborative planning solution based on the typical scenario, and when obtaining the multi-resource collaborative adjustment policy, performs multi-resource collaborative planning solution based on the typical scenario by using a firefly optimization algorithm, so as to obtain the multi-resource collaborative adjustment policy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311685397.8A CN117811095A (en) | 2023-12-08 | 2023-12-08 | Method and system for generating multi-resource collaborative adjustment strategy of power system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311685397.8A CN117811095A (en) | 2023-12-08 | 2023-12-08 | Method and system for generating multi-resource collaborative adjustment strategy of power system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117811095A true CN117811095A (en) | 2024-04-02 |
Family
ID=90420810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311685397.8A Pending CN117811095A (en) | 2023-12-08 | 2023-12-08 | Method and system for generating multi-resource collaborative adjustment strategy of power system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117811095A (en) |
-
2023
- 2023-12-08 CN CN202311685397.8A patent/CN117811095A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yousefi et al. | A comparison study on stochastic modeling methods for home energy management systems | |
| Maleki et al. | Optimal sizing of autonomous hybrid photovoltaic/wind/battery power system with LPSP technology by using evolutionary algorithms | |
| CN106532688B (en) | It is a kind of for assessing the method and system of micro-capacitance sensor operational reliability | |
| Mosadeghy et al. | A time-dependent approach to evaluate capacity value of wind and solar PV generation | |
| CN111340274A (en) | Virtual power plant participation-based comprehensive energy system optimization method and system | |
| CN111754037B (en) | Long-term load hybrid prediction method for regional terminal integrated energy supply system | |
| CN111626527A (en) | Intelligent power grid deep learning scheduling method considering fast/slow charging/discharging form of schedulable electric vehicle | |
| CN114519449A (en) | Operation optimization method for park energy system | |
| CN107977741B (en) | Energy scheduling optimization method of combined cooling heating and power micro-grid system | |
| CN116681171A (en) | Multi-scene comprehensive energy system distribution robust optimization scheduling method and system | |
| CN117172499A (en) | Smart community energy optimal scheduling method, system and storage medium based on reinforcement learning | |
| CN117592010A (en) | Temperature prediction method, temperature prediction device, electronic equipment and computer readable storage medium | |
| CN108767855A (en) | A kind of electric system random production analog method that sequential persistently mixes | |
| CN114662922B (en) | Resident demand response potential evaluation method and system considering photovoltaic uncertainty | |
| CN117811095A (en) | Method and system for generating multi-resource collaborative adjustment strategy of power system | |
| CN116151553A (en) | Hydrogen production system scheduling method, position and nonvolatile storage medium | |
| CN114239922A (en) | City multi-energy coordination optimization scheduling method | |
| Fang et al. | Energy scheduling and decision learning of combined cooling, heating and power microgrid based on deep deterministic policy gradient | |
| Zandi et al. | An automatic learning framework for smart residential communities | |
| CN114336597A (en) | Light storage inverter energy scheduling based on self-adaptive penalty function particle swarm algorithm | |
| Ge et al. | EV Charging Behavior Simulation and Analysis Using Real-World Charging Load Data | |
| CN113222216A (en) | Method, device and system for predicting cooling, heating and power loads | |
| Chinnadurrai et al. | Energy Management of a Microgrid based on LSTM Deep Learning Prediction Model | |
| CN106056317B (en) | A kind of multiple flexible resource multimode Risk Calculation method | |
| Liu et al. | Flexibility Evaluation of Flexible Resource Based on TOPSIS of CRITIC |
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 |