CN112862313B - Generator set scheduling method and system based on medium-long term price difference contract electric quantity decomposition - Google Patents

Generator set scheduling method and system based on medium-long term price difference contract electric quantity decomposition Download PDF

Info

Publication number
CN112862313B
CN112862313B CN202110172142.6A CN202110172142A CN112862313B CN 112862313 B CN112862313 B CN 112862313B CN 202110172142 A CN202110172142 A CN 202110172142A CN 112862313 B CN112862313 B CN 112862313B
Authority
CN
China
Prior art keywords
price
market
contract
generator set
day
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110172142.6A
Other languages
Chinese (zh)
Other versions
CN112862313A (en
Inventor
杨明
张长行
高源�
员江洋
朱毅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong University
Economic and Technological Research Institute of State Grid Shandong Electric Power Co Ltd
Original Assignee
Shandong University
Economic and Technological Research Institute of State Grid Shandong Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong University, Economic and Technological Research Institute of State Grid Shandong Electric Power Co Ltd filed Critical Shandong University
Priority to CN202110172142.6A priority Critical patent/CN112862313B/en
Publication of CN112862313A publication Critical patent/CN112862313A/en
Application granted granted Critical
Publication of CN112862313B publication Critical patent/CN112862313B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—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
    • G06Q10/06313—Resource planning in a project environment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0206—Price or cost determination based on market factors
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
    • Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards

Landscapes

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

Abstract

The utility model provides a generator set dispatching method based on medium and long term price difference contract electric quantity decomposition, which obtains the information data of the electric power system and the operation state data of the generator set; obtaining the current market clearing price according to the obtained data; according to the obtained data and the obtained day-ahead market clearing price, the medium-long term price difference contract decomposition optimization result is obtained by taking the maximum generating income of the generator set as a target; according to the obtained decomposition optimization result, carrying out time-interval generator set operation scheduling; the method and the device aim at maximizing the generating income of the generating set, and construct a medium-long term price difference contract decomposition curve of the generating set by combining the change rule of the day-ahead clear price, thereby improving the scheduling precision of the generating set.

Description

Generator set scheduling method and system based on medium-long term price difference contract electric quantity decomposition
Technical Field
The disclosure relates to the technical field of automatic control of electric power systems, in particular to a generator set scheduling method and system based on medium-long term price difference contract electric quantity decomposition.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
A spread contract generally refers to a transaction method in which only the difference between a settlement price and a contract price is used as cash settlement, without involving the exchange of physical commodities or securities. The power spread contracts are mainly aimed at medium-long term financial contracts with determined contract price and contract electric quantity, including both unidirectional spread contracts and bidirectional spread contracts. The introduction of a differential contract in the electric power market reform has great significance to market subjects, especially market subjects in competitive links.
For power generation enterprises, a price difference contract can effectively lock part of transaction electric quantity and price in advance, and provides reliable economic benefits for the power generation enterprises while ensuring long-term stable power requirements of the power generation enterprises. Furthermore, the decomposition mode of the electric quantity of the differential contract is also important for promoting the stable operation of the electric power market reform and ensuring the income of the market main body and avoiding risks. The decomposition of the electric quantity of the differential contract is a key link for the compatibility and the connection of the medium-term contract market and the spot market of the electric power. If the method for decomposing the electricity quantity of the spread contracts is not fair enough, certain power generation companies are possibly given the opportunity of abusing market force; for a user with large power or an electricity selling company, the proportion of the electricity quantity decomposed by the price difference contract is too small at the peak time of load or too large at the valley time of load, so that the electricity purchasing cost of the user is increased, and the operation of the whole power market is also not facilitated.
There have been some studies on the decomposition of contract electricity amount. The document researches a contract electric quantity decomposition algorithm of a single type of generator set; establishing a medium-long term contract electric quantity decomposition model for coordinating new energy source prediction in some documents; other documents incorporate the availability of the generator set into an optimization model, adopt a rolling correction method to process the unit maintenance problem, and distribute the contract electric quantity of the maintenance month to other months and other units. For the aspect of checking and restraining the market power of the generator set, a case that the market power of the generator set is evaluated by using a Lerner index in a contract decomposition algorithm is shown in some documents, and the calculation shows that when the contract decomposition does not consider the market power restraint, the market may fall into an unstable condition with high price and large fluctuation, the scheduling of the generator set is easily disordered, and the optimization of the operation cost of the generator set cannot be realized.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a generator set scheduling method and system based on medium and long term price difference contract electric quantity decomposition, which aims to maximize the generating income of a generator set, combines the change rule of the day-ahead clear price, constructs a medium and long term price difference contract decomposition curve of the generator set and improves the scheduling precision of the generator set.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
the first aspect of the disclosure provides a generator set scheduling method based on medium-long term price difference contract electric quantity decomposition.
A generator set scheduling method based on medium and long term price difference contract electric quantity decomposition comprises the following steps:
acquiring information data of a power system and operation state data of a generator set;
obtaining the current market clearing price according to the obtained data;
according to the obtained data and the obtained day-ahead market clearing price, the medium-long term price difference contract decomposition optimization result is obtained by taking the maximum generating income of the generator set as a target;
and performing time-interval generator set operation scheduling according to the obtained decomposition optimization result.
As some optional implementations, the generating set generation revenue is a sum of the generating revenue the generating set receives from the contract price, the generating revenue the generating set receives from the day-ahead market clearing price, and the generating revenue the generating set receives from the real-time market clearing price.
By way of further limitation, the power generation revenue obtained by the generator set according to the contract price is decomposed into the accumulation of the product of the electric quantity and the contract price in the time period t on the electric power market settlement time period set by the medium-long term price difference contract.
By way of further limitation, the generating income obtained by the generating set according to the day-ahead market clearing price is the accumulation of the product of the difference value of the online electric quantity under the day-ahead market clearing price and the electric quantity within the time period t decomposed by the medium-long term price difference contract and the day-ahead market clearing price on the electric power market clearing time period set.
As a further limitation, the generating revenue obtained by the generator set according to the real-time market clearing price is the accumulation of the product of the difference between the internet surfing electric quantity at the current market clearing price and the internet surfing electric quantity at the market clearing price at the present day and the current market clearing price in the electric power market clearing time period set.
As some optional implementations, the sum of the amounts of power split into the respective periods in a day is equal to the total amount of power specified in the contract.
In some optional implementation manners, the electric quantity decomposed into the time periods is smaller than or equal to the product of the maximum output of the generator set and the preset proportion.
As some optional implementation manners, the electric quantity decomposed to each time interval is greater than or equal to the product of the load demand of the electricity vendor in the time interval and the preset proportion.
The second aspect of the disclosure provides a generator set scheduling system based on medium-long term spread contract electricity quantity decomposition.
A generator set scheduling system based on medium and long term price difference contract electricity decomposition comprises:
a data acquisition module configured to: acquiring information data of a power system and operation state data of a generator set;
a clearing price acquisition module configured to: obtaining the current market clearing price according to the obtained data;
a charge resolving module configured to: according to the obtained data and the obtained day-ahead market clearing price, the medium-long term price difference contract decomposition optimization result is obtained by taking the maximum generating income of the generator set as a target;
an execution scheduling module configured to: and performing the operation scheduling of the generator set in different time intervals according to the obtained decomposition optimization result.
A third aspect of the present disclosure provides a computer-readable storage medium, on which a program is stored, where the program, when executed by a processor, implements the steps in the method for scheduling a generator set based on medium-and-long-term spread contract power decomposition according to the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor, where the processor executes the program to implement the steps in the method for scheduling a generator set based on medium-and-long-term spread contract electricity quantity decomposition according to the first aspect of the present disclosure.
Compared with the prior art, the beneficial effect of this disclosure is:
the scheduling method, the scheduling system, the scheduling medium or the electronic equipment disclosed by the disclosure aim at maximizing the generating income of the generator set, and combine with the change rule of the daily output price of electricity, so that a medium-long-term price difference contract decomposition curve of the generator set is constructed, the scheduling precision of the generator set is improved, the generator set can effectively resist the risk of price fluctuation of the spot market by participating in the power market, and the generating income of the generator set participating in the power market is improved.
Advantages of additional aspects of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
Fig. 1 is a diagram of an artificial neuron model according to embodiment 1 of the present disclosure.
Fig. 2 is a sigmiod function image according to embodiment 1 of the present disclosure.
Fig. 3 is an image of tanh function according to example 1 of the present disclosure.
Fig. 4 is a ReLU function image according to embodiment 1 of the present disclosure.
Fig. 5 is a comparison graph of the predicted future clear price and the actual price of the electric power market in embodiment 1 of the present disclosure.
Fig. 6 is a flowchart illustrating the declaration and settlement process of the power generation enterprise participating in the power market according to embodiment 1 of the present disclosure.
Fig. 7 is a schematic diagram illustrating deviation settlement of power market participation of a power generation enterprise according to embodiment 1 of the present disclosure.
Fig. 8 is a graph of the forecast results of the market clearing price in the future according to embodiment 1 of the present disclosure.
Fig. 9 is a graph illustrating the medium-and long-term contract decomposition after optimization according to embodiment 1 of the present disclosure.
Fig. 10 is a graph of original medium and long term differential contract decomposition as described in example 1 of the present disclosure.
Fig. 11 is a schematic flow chart of a generator set scheduling method based on medium-and-long term spread contract electric quantity decomposition according to embodiment 1 of the present disclosure.
Detailed Description
The present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
Example 1:
the embodiment 1 of the disclosure provides a generator set scheduling method based on medium and long term price difference contract electric quantity decomposition, which includes the following steps:
acquiring information data of a power system and operation state data of a generator set;
obtaining the current market clearing price according to the obtained data;
according to the obtained data and the obtained day-ahead market clearing price, the medium-long term price difference contract decomposition optimization result is obtained by taking the maximum generating income of the generator set as a target;
and performing time-interval generator set operation scheduling according to the obtained decomposition optimization result.
Specifically, the method comprises the following steps:
predicting the clearing price of the market in the day ahead, comprising the following steps:
acquiring various types of information running in the market: the method mainly comprises information such as the price of the fresh and fresh electricity released in the power market and the historical load data of the whole network;
forecasting the clear electricity price in the market at the day ahead: and (4) regular learning is carried out on the historical data by adopting a BP neural network, so that the fresh electricity price of the market before the day is predicted.
A neural network is an operational model made up of a large number of interconnected neurons, i.e. in other words, an artificial neural network that actually appears to be complex is composed of simple elements. A series of nodes and the connection among the nodes form an artificial neural network, and the nodes can be regarded as individual operation units, and the operation units are used for receiving input, processing the input and finally obtaining a result. Each node is followed by a non-linear function called the activation function. The node may process the input simply and easily, some processes may be as simple as calculating the sum of the input, but some processes may be more complicated, for example, the node may be embedded in another network. Nodes and nodes are interconnected and information is then passed between nodes and nodes. The connection between nodes may be unidirectional or bidirectional, in which case the information may be transferred from the a node to the B node or from the B node to the a node. In addition, the connection between two nodes represents a parameter value in the artificial neural network operation, which is called a weight value, and may also be referred to as a weight for short. The artificial neural network is endowed with strong capability of approximating any functional relation only by different weight values, different bias values and different nonlinear activation functions.
The artificial neuron is an operation model which is designed by observing the transmission and the change of electric potential of natural neurons in a static state and an action state and inspiring. It is used as a basic unit to form an artificial neural network. People inspire the process of natural neuron signal transmission and design artificial neurons to simulate the information flow process. Artificial neurons, as their name implies, are individual nodes in an artificial neural network. And the basic elements constituting the neural network system in the biological world are neurons or so-called nerve cells. The structure of a neuron can be roughly divided into three parts: cell bodies, dendrites, and axons. In addition, neurons include myelin sheaths, cell nuclei, and the like. The functions of the cell body mainly include receiving information, processing information, and transmitting information to the outside. The dendrites function to receive and transmit impulses from other nerve axons to the cell body, and the axons function to receive external stimuli and transmit them out of the cell body. When dendrites of neurons are stimulated by an external stimulus, they transmit the stimulus to axons, which in turn are transmitted by surrounding synapses to other neurons, causing a chain reaction of the network. The artificial neuron model is shown in fig. 1. The artificial neuron model is shown in fig. 1.
Artificial neurons have the same characteristics as biological neurons. The neuron model as a whole comprises a plurality of inputs (like synapses) whose values xi are multiplied by different weights wi, respectively, then the multiplied values are summed and added to the corresponding bias values b, and finally used by a mathematical function to computationally decide whether to fire the neuron. Wherein different weight values can be regarded as different magnitudes of received signal strength, etc., and this mathematical function for deciding whether to fire a neuron is called an activation function.
When the inner product of the activation function index is calculated and added with the offset value, the mathematical function is finally used for determining whether to activate the neuron. It is conceivable that without an activation function, the relationship of the input of each layer to the previous layer is linear. In other words, without an activation function, the final output is linear with the input, regardless of the number of layers in the neural network. In this case, the output approximation capability of the artificial neural network becomes very limited, because in this case, the artificial neural network can only fit a certain linear relationship. Just because of introducing the nonlinear function as the activation function, the functional relation that the deep neural network can learn is not only linear but also nonlinear. After the nonlinear function is introduced, the input and the output of the artificial neural network can be single nonlinearity, multiple nonlinearity, and the like.
Commonly used activation functions in building an artificial neural network mainly include a sigmoid function and a tanh function. Since the outputs of these two types of functions are within a certain range, it is advantageous for the input to be the next layer. In addition, the ReLU function and its modified versions (such as Leaky-ReLU, P-ReLU, R-ReLU, etc.) have been popular and widely used in recent years when deep neural networks are built.
sigmoid function
The function is a non-linear mapping between (— infinity, + ∞) input data. More specifically, a relatively large negative number is activated as 0 through the function, and a relatively large positive number is activated as 1,sigmiod function image through the function as shown in fig. 2.
The usage rate of the sigmoid function in the artificial neural network is not high nowadays, so the sigmoid function can be arranged to be placed at the tail part of the artificial neural network as an output layer for two-classification, and is not used at a hidden layer as much as possible.
tan h function
This function maps (— infinity, + ∞) input data between (-1, + 1), and the tanh function image is shown in fig. 3.
Because the tanh function is mapped to (-1, + 1), that is, most of output data after the activation function is basically distributed near 0, the second defect of the sigmoid is solved, so that the use times of the tanh function is a little more than that of the sigmoid function when the artificial neural network is built.
ReLU function
The ReLU function, also called modified linear unit, is itself a piecewise function, each piece of which is a linear function. Such a feature makes it superior to the two activation functions described above because the ReLU function does not have the scenario where the gradient vanishes and the back propagation algorithm fails. The ReLU function image is shown in fig. 4.
A plurality of artificial neuron models are connected according to a certain rule and sequence, and the output of the upper layer is connected with the input of the lower layer, so that the multilayer perceptron is formed. When a neural network is constructed, the nonlinear problems can be solved by carrying out certain permutation and combination on each linear function. Since any non-linear problem can be decomposed into a series of linear problems. Structurally, the biggest difference between the multi-layer feedforward neural network and the network formed by single-layer neurons is the hidden layer. The multilayer feedforward neural network has three parts: input layer, hidden layer, output layer.
The input layer first receives external information and passes the information to the next structure. The information then goes to the hidden layer, which after receiving the signal continues to pass it down to the output layer. The hidden layer may have one layer or multiple layers. The output layer is connected with the outside, and when the output layer receives the information transmitted by the last hidden layer, the information is processed and then transmitted to the outside.
In this embodiment 1, the actual day-ahead clearing price data of a foreign electric power market from No. 10/month 1 in 2020 to No. 1/month 7 in 2021 is used, the neural network is used to predict the day-ahead clearing price of the market, and the absolute error and the average absolute error are used to measure the accuracy of the prediction result.
Figure BDA0002939274170000091
Figure BDA0002939274170000092
The future market-out price prediction based on historical data is shown in fig. 5.
The average absolute error of the forecast result of the daily-released price of the electric power is 4.6%, the absolute error of the forecast result is 1.31$/MWh, and the effectiveness and the accuracy of the method for forecasting the daily-released price of the market by adopting the neural network are proved.
It is assumed that the genset under study plays a "price taker" role in this electricity market, i.e., the market size is large enough relative to a single genset that the quote of the genset and the resolution of medium and long term contracts have negligible impact on the day ahead, real time clearing price of the electricity market.
Before the market is opened in the day-ahead market, a power generation enterprise firstly obtains various transaction information, such as information of day-ahead load prediction and the like issued by a system, and determines the electric quantity and contract price specified by the operation day in a medium-long term contract signed by the power generation enterprise;
in the day-ahead market, power generation enterprises declare the unit of a unit, and specifically include energy prices and energy supply curves of power generation capacity corresponding to the energy prices; in addition, reporting operation parameters such as start-stop cost, start-stop time, climbing rate, unit output upper and lower limit constraints and the like; the method comprises the steps that an electric power market calculates the business clearing of the market in the day ahead by calling a Safety Constraint Unit Combination (SCUC) program, and the dispatching output of each generator set and the marginal electricity price of a day-ahead node are determined; and finally, the market publishes information such as the daily market clearing load, the electricity price and the like to each participant.
In the real-time market, the electric power market calls an economic dispatching model (SCED) considering safety constraints according to the actual load of a user and the daily price of the sealed generator set to clear the real-time market, and determines the information such as the actual power generation plan, the real-time festival, the marginal electricity price of the real-time node and the like of each generator set.
The quotation modes comprise power generation side quotation, user side no quotation, power generation amount quotation and user side quotation; the number of the days of birth and death includes 96 points and 24 points; the declaration rule comprises the number of the capacity sections of the unit, the limit value proportion of the quoted sections, the upper limit and the lower limit of the declaration price, and the trading mode of the generator is shown in fig. 6.
The method mainly comprises the steps of performing resource optimization configuration on the electric power spot market outlook, considering various types of power access systems according to the situations that power generation enterprises declare power generation output and quotation curves, power selling enterprises declare electric quantity and the like, considering constraint conditions such as system balance, power grid safety, unit operation and the like, establishing a safety constraint unit combination and a safety constraint economic dispatching model, and obtaining an optimal solution through a mixed integer planning algorithm.
The unit combination problem is a high-dimension, discrete, non-convex and non-linear optimization problem. On the basis of the existing research results, a new mathematical model of the unit combination problem is established, and the existing solving algorithm is given. The electricity purchasing cost is minimized in the model as an objective function, and system constraints, unit constraints, environmental constraints brought under a new environment of an electric power market, network safety constraints and the like are considered. The system constraints comprise system active power balance constraints, system rotation standby constraints and the like, and the unit constraints comprise generator maximum and minimum output constraints, unit minimum operation and stop time constraints, unit climbing rate constraints and the like.
The objective function of the unit combination problem can be expressed as:
Figure BDA0002939274170000111
the constraint conditions for the unit combination problem are expressed as:
and (4) system constraint:
(1) System active power balance constraints
Figure BDA0002939274170000112
In the formula: t =1,2.., T (same below).
(2) System rotational back-up constraint
Figure BDA0002939274170000113
Unit restraint:
(1) Maximum and minimum output constraints for a generator
P imin (t)≤P i (t)≤P imax (t) (6)
In the formula: i =1,2,., N (same below).
(2) Minimum run and downtime constraints for a unit
[Y i on (t-1)-T i on ]·[U i (t-1)-U i (t)]≥0 (7)
[Y i off (t-1)-T i off ]·[U i (t)-U i (t-1)]≥0 (8)
And (3) restraining the climbing rate of the unit:
P i (t)-P i (t-1)≤RUR i (9)
P i (t-1)-P i (t)≤RDR i (10)
and (3) environmental constraint:
the total amount of exhaust gas (SO 2, NOx and the like) discharged by power generation enterprises should meet the requirement of environmental protection, namely the emission permission cannot be exceeded, and the following steps are provided:
Figure BDA0002939274170000121
network security constraints:
(1) System reactive power balance and generator reactive power upper and lower limit restraint:
Figure BDA0002939274170000122
Q imin (t)≤Q i (t)·U i (t)≤Q imax (t) (13)
and (3) system voltage constraint:
V min ≤V≤V max (14)
for solving the unit combination problem, a Lagrangian Relax (LR) method is an ideal method. The LR method has the basic ideas: for system constraints related to each unit capable of being started and stopped, the system constraints are put into a main problem, and for unit constraints related to only a single unit capable of being started and stopped, the system constraints are put into a sub problem to be considered, and solution is carried out iteratively between the main problem and the sub problem, so that the optimal solution of the main problem can be obtained. The LR method is convenient to process various constraints by introducing a Lagrange multiplier, and the calculated amount of the LR method linearly increases along with the increase of the system scale, so that the method is suitable for solving the actual large-scale mixed integer programming problem. The LR method can effectively solve the problem of large-scale system optimization. After relaxation, the lagrangian relaxation problem is obtained:
Figure BDA0002939274170000131
in the formula: λ (t), μ (t) are the t-period lagrange multipliers, whose vector form is:
λ＝[λ(1)，λ(2)，...，λ(T)] T
μ＝[μ(1)，μ(2)，...，μ(T)] T
the bottom layer problem is used for solving the optimization problem of a single unit:
Figure BDA0002939274170000132
wherein i =1, 2.
The upper layer problem optimizes the lagrange multiplier:
Figure BDA0002939274170000133
wherein μ (T) ≥ 0, T =0, 1.. T;
Figure BDA0002939274170000134
the lagrangian function value is optimized for a given λ, μ for the underlying problem.
The selection of the initial value and the adjustment of the Lagrangian multiplier both have direct influence on the convergence characteristics of the LR method. The selection of a proper initial value can reduce the iteration times and converge as early as possible, thereby reducing the calculation time. Therefore, the average coal consumption of each unit of the system is sequenced, then the load is distributed according to the principle of the equivalent consumption micro-increment rate, and the obtained equivalent consumption micro-increment rate is used as an initial value of a Lagrange multiplier corresponding to the power balance constraint.
The economic dispatching means that under the condition of ensuring the safe operation of the power system and the qualified quality of the electric energy, the energy and the equipment are effectively utilized, so that the operation cost of the power system is minimized. The primary task is to ensure the coordination of electrical safety and economic benefits. The electric energy is transmitted in a power grid according to a certain rule, and meanwhile, the power generation and the power consumption are instantly balanced, so that problems occur in one link, the normal operation of the whole power grid can be caused, and the premise of the introduction of the power market is to accord with the objective rules and ensure the safe and stable operation of the system. Considering the randomness characteristics of uncertainty problems and the influence of the randomness characteristics on system operation, a robust economic dispatching optimization model can be constructed based on a robust optimization theory, randomness factors are introduced into the model through opportunity constraint, the uncertainty factors are taken as targets, the distribution of the uncertainty factors under random disturbance conditions is researched, limiting conditions meeting certain robustness are introduced into the constraint, and corresponding robust solutions are obtained through decision optimization. When the constraint condition is satisfied within the confidence interval, the robust economic dispatching optimization model can realize equivalent expression of the randomness problem in the economic dispatching, and the decision is prevented from being conservative. In a word, based on a decision idea of a robust optimization economic dispatching model based on the robust optimization theory and the optimization under the worst condition, an uncertainty factor set under the system operation environment is expanded, and the power system is ensured to safely and stably operate within a certain disturbance range.
The objective function of the robust economic dispatching optimization model is minimized for the electricity purchasing cost, and the objective function is expressed as follows:
Figure BDA0002939274170000141
wherein, F is the total electricity purchasing cost of the power consumer; p i (t) the output of the unit i in the time period t; f i [P i (t)]The output of the unit is P i (t) the corresponding quote.
And expressing uncertain factors by adopting normal distribution with symmetrical deviation, and performing probabilistic modeling and solving on an objective function or a constraint condition. And adjusting robust parameters in the robust economic dispatching optimization model to control the conservative degree of dispatching decisions, and contracting the value range of uncertainty parameters to realize compromise between the robustness and the economy of a dispatching strategy. The robust economic dispatching optimization model can effectively reflect the situation that how to make dispatching decision when the power system faces complex uncertainty problem so as to ensure the safety and the economy of the system. The model also has important reference value for the renewable energy sources to access the power grid and participate in economic dispatch in market competition environments.
For the power generation enterprises making medium and long term spread contracts, the settlement process participating in the power market is as follows:
firstly, the medium and long term spread contracts are settled: performing gold melting curve decomposition on the medium and long term price difference contracts, and settling accounts according to prices specified in the contracts;
Figure BDA0002939274170000151
wherein, C CFD Represents the generating income, lambda, obtained by the generating set through the medium and long term price difference contract CFD Representing contract price, and Q (t) representing the electric quantity of the medium-long term spread contract decomposed into a time period t; t represents a set of electricity market settlement periods;
then, the market deviation settlement in the day ahead: the deviation amount between a unit power generation plan curve formed in the market before the day and a financial curve formed by decomposing medium and long term price difference contracts is settled according to the price of the clear electricity produced before the day;
Figure BDA0002939274170000152
wherein, C DA Indicates the day-ahead market deviation settlement, lambda of the generator set DA (t) represents the market clearing price of the day ahead, P DA (t) represents the amount of market power output at the day before;
and finally, real-time market deviation settlement: and (3) the deviation amount between the actual generating curve of the unit formed in the real-time market and the generating plan curve of the unit formed in the day-ahead market is settled according to the real-time clear price:
Figure BDA0002939274170000153
wherein, C RT Means generator set passed real-time market deviation settlement, lambda RT (t) real-time market clearing price, P RT And (t) the online electricity quantity at the real-time market clearing price.
The overall settlement diagram of the power generation enterprise in the power market is shown in fig. 7.
Before optimizing the medium-long term price difference contract electric quantity decomposition curve, an assumption is firstly made that a unit participating in the electric power market is a price receiver. Price acceptors refer to prices that must be accepted in the market decision due to complete competition between buyers and sellers in the market. The price faced by each participant in the market is given by the market, i.e., the equilibrium price adjusted by market demand. Based on this assumption, in the power market, the market clearing price is given by the market, and under the condition that the unit price is not changed, the power generation planning curve of the unit before day and the real-time output curve are determined by the market. Therefore, as a price receiver, the decision-making quantity for determining the generating income of the unit is only the electric quantity decomposed into each time interval by the medium-long term price difference contract.
Specifically, for a unit, an objective function with the maximum generating income of the unit as a target is established, as shown in fig. 11:
Figure BDA0002939274170000161
in the process of optimizing the long-term difference contract decomposition curve, the following principles should be followed:
(1) The sum of the electric quantity divided into the time intervals in one day is equal to the total electric quantity specified in the contract:
Figure BDA0002939274170000162
(2) The electric quantity decomposed to each time interval is not greater than a certain proportion of the maximum output of the generator set:
Q(t)≤β·P max (t),t∈T (24)
(3) The electric quantity decomposed to each time interval should not be less than a certain proportion of the load demand of the electricity vendor in the time interval:
Q(t)≥α·D load (t),t∈T (25)
taking the medium-and-long term price difference contract with a decomposition curve signed by a certain province electric power market in China in month 5 as an example, the price of the market clearing price at the day before is predicted by adopting the electricity price prediction method provided by the third part, and the prediction method is used as one of the inputs of an optimization model, and the optimization model is rapidly solved through a cplex optimization tool.
Before and after the decomposition curve is optimized, the generating income of the unit is shown as a table I:
it can be seen from the table that after the differential contract decomposition principle is taken into account, under the premise of the same contract electric quantity and contract price, the optimized decomposition curve can increase the generating revenue of the unit to 21000100 yuan, and the increase amplitude is 16.1%.
The result of the forecast of the day-ahead price of fresh electricity is shown in fig. 8.
The medium-long term contract decomposition electric quantity decomposition curve after optimization is shown in fig. 9.
The raw decomposition curve is shown in fig. 10.
The combination of the forecast results of the prior clear electricity prices shows that the electricity prices are at a very low level between nine am and 3 pm, and in terms of the balance of supply and demand of the whole network, the new energy output greatly rises in the several time intervals, so that the clear electricity prices of the whole network are reduced; the forecast result of the current clear price is combined with the two medium and long term difference price contract decomposition electric quantity and decomposition curves, and the comparison analysis shows that under the original decomposition mode, in the time period of lower current clear price, less electric quantity is distributed to use the difference price contract for settlement, which means that more electric quantity is settled by using lower current clear price; and in the time intervals of nine am to 3 pm, the optimized decomposition curve enables more electric quantity to be settled by contract price, so that the effect of avoiding price risks in spot markets by medium-long term price difference contracts is truly exerted, and the generating income of the unit is effectively improved.
The embodiment is based on the forecast of the coming clear electricity price, the fluctuation trend of the coming market electricity price is accurately grasped, and then the electric quantity of the long-term price difference contract in each time interval is optimized according to the change trend of the electricity price, so that the purpose of improving the income of the generator set is achieved.
Table one: generator set revenue comparison before and after decomposition curve optimization
Figure BDA0002939274170000171
Example 2:
the embodiment 2 of the present disclosure provides a generator set scheduling system based on medium and long term price difference contract electric quantity decomposition, including:
a data acquisition module configured to: acquiring information data of a power system and operation state data of a generator set;
a clearing price obtaining module configured to: obtaining the current market clearing price according to the obtained data;
a charge resolving module configured to: according to the obtained data and the obtained day-ahead market clearing price, the maximum target of the generating income of the generating set is used, and a medium-term and long-term price difference contract decomposition optimization result is obtained;
an operation scheduling module configured to: and performing time-interval generator set operation scheduling according to the obtained decomposition optimization result.
The working method of the system is the same as the generator set scheduling method based on medium-and-long term price difference contract electric quantity decomposition provided in embodiment 1, and details are not repeated here.
Example 3:
the embodiment 3 of the present disclosure provides a computer-readable storage medium, on which a program is stored, where the program, when executed by a processor, implements the steps in the method for scheduling a generator set based on medium-and-long-term spread contract electricity quantity decomposition according to the embodiment 1 of the present disclosure.
Example 4:
the embodiment 4 of the present disclosure provides an electronic device, which includes a memory, a processor, and a program stored on the memory and capable of running on the processor, where the processor executes the program to implement the steps in the generator set scheduling method based on medium-and-long-term spread contract electricity quantity decomposition according to embodiment 1 of the present disclosure.
As will be appreciated by one of skill in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims (7)

1. A generator set scheduling method based on medium and long term price difference contract electric quantity decomposition is characterized in that: the method comprises the following steps:
acquiring information data of a power system and operation state data of a generator set;
obtaining the current market clearing price according to the obtained data;
according to the obtained data and the obtained day-ahead market clearing price, the maximum target of the generating income of the generating set is used, and a medium-term and long-term price difference contract decomposition optimization result is obtained;
according to the obtained decomposition optimization result, carrying out generator set operation scheduling in different time periods;
the specific steps of obtaining the day-ahead market clearing price according to the obtained data are as follows:
acquiring various types of information running in the market: the method mainly comprises the information of the day-ahead clear price and the historical load data of the whole network, which are released in the power market;
forecasting the clear electricity price in the market at the day ahead: regular learning is carried out on the historical data by adopting a BP neural network, so that the clearing price of the market before the day is predicted, and the clearing price of the market before the day is obtained;
the generating income of the generating set is the sum of the generating income obtained by the generating set according to the contract price, the generating income obtained by the generating set according to the day-ahead market clearing price and the generating income obtained by the generating set according to the real-time market clearing price;
the generating income obtained by the generator set according to the contract price is the accumulation of the product of the electric quantity and the contract price in the time period t and the electric power market settlement time period set in the medium and long term price difference contract;
the generator set obtains power generation income according to the day-ahead market clearing price, and the power generation income is accumulated on a power market clearing time period set by a product of a difference value of the internet power quantity under the day-ahead market clearing price and the electric quantity in a time period t decomposed by a medium-long term price difference contract and the day-ahead market clearing price;
or,
and the generating income obtained by the generator set according to the real-time market clearing price is the accumulation of the product of the difference value of the internet electricity quantity under the current market clearing price and the current market clearing price on the electric power market clearing time period set.
2. The method for scheduling a generator set based on medium-and-long term spread contract electricity quantity decomposition according to claim 1, wherein:
the sum of the amounts of electricity divided into the respective periods in one day is equal to the total amount of electricity specified in the contract.
3. The medium and long term spread contract electricity decomposition based generator set scheduling method of claim 1, wherein:
the electric quantity decomposed to each time interval is smaller than or equal to the product of the maximum output of the generator set and the preset proportion.
4. The method for scheduling a generator set based on medium-and-long term spread contract electricity quantity decomposition according to claim 1, wherein:
the electric quantity decomposed to each time interval is larger than or equal to the product of the electric power selling business load demand and the preset proportion in the time interval.
5. A generator set dispatching system based on medium and long term price difference contract electric quantity decomposition is characterized in that: the method comprises the following steps:
a data acquisition module configured to: acquiring information data of a power system and operation state data of a generator set;
a clearing price acquisition module configured to: obtaining the current market clearing price according to the obtained data;
a charge resolving module configured to: according to the obtained data and the obtained day-ahead market clearing price, the medium-long term price difference contract decomposition optimization result is obtained by taking the maximum generating income of the generator set as a target;
an operation scheduling module configured to: according to the obtained decomposition optimization result, carrying out time-interval generator set operation scheduling;
the specific steps of obtaining the day-ahead market clearing price according to the obtained data are as follows:
acquiring various types of information running in the market: the method mainly comprises the steps of releasing the daily-released electricity price and the whole network historical load data information in the power market;
forecasting the clear electricity price in the market at the day ahead: regular learning is carried out on historical data by adopting a BP neural network, so that the coming price of the market in the future is predicted, and the coming price of the market in the future is obtained;
the generating income of the generating set is the sum of the generating income obtained by the generating set according to the contract price, the generating income obtained by the generating set according to the day-ahead market clearing price and the generating income obtained by the generating set according to the real-time market clearing price;
the generating income obtained by the generator set according to the contract price is the accumulation of the product of the electric quantity and the contract price in the time period t and the electric power market settlement time period set in the medium and long term price difference contract;
the generator set obtains power generation income according to the day-ahead market clearing price, and the power generation income is the accumulation of the product of the difference value of the internet power under the day-ahead market clearing price and the power within the time period t decomposed by the medium-long term price difference contract and the day-ahead market clearing price on the power market clearing time period set;
or,
and the generating income obtained by the generator set according to the real-time market clearing price is the accumulation of the product of the difference value of the internet electricity quantity under the current market clearing price and the current market clearing price on the electric power market clearing time period set.
6. A computer-readable storage medium, on which a program is stored, wherein the program, when executed by a processor, implements the steps of the method for scheduling a genset based on medium-and-long term spread contract power decomposition according to any one of claims 1-4.
7. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for scheduling a generator set based on medium-and long-term spread contract power split of any one of claims 1-4 when executing the program.
CN202110172142.6A 2021-02-08 2021-02-08 Generator set scheduling method and system based on medium-long term price difference contract electric quantity decomposition Active CN112862313B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110172142.6A CN112862313B (en) 2021-02-08 2021-02-08 Generator set scheduling method and system based on medium-long term price difference contract electric quantity decomposition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110172142.6A CN112862313B (en) 2021-02-08 2021-02-08 Generator set scheduling method and system based on medium-long term price difference contract electric quantity decomposition

Publications (2)

Publication Number Publication Date
CN112862313A CN112862313A (en) 2021-05-28
CN112862313B true CN112862313B (en) 2023-02-28

Family

ID=75989191

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110172142.6A Active CN112862313B (en) 2021-02-08 2021-02-08 Generator set scheduling method and system based on medium-long term price difference contract electric quantity decomposition

Country Status (1)

Country Link
CN (1) CN112862313B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113689033B (en) * 2021-08-10 2022-09-27 南方电网能源发展研究院有限责任公司 Method and device for checking and determining capacity generation price, computer equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107392432A (en) * 2017-06-27 2017-11-24 东南大学 The frequency modulation electric reserve market implementation method of long-term electricity contract energy decomposition in consideration
CN107895221A (en) * 2017-10-25 2018-04-10 北京微肯佛莱科技有限公司 Long-term scheduling and Maintenance Schedule Optimization method in market environment lower step power station
CN110517164A (en) * 2019-08-19 2019-11-29 国网山西省电力公司 The generation schedulecurve of long-term contract decomposes and settlement method and system in consideration
CN110689286A (en) * 2019-11-13 2020-01-14 国网陕西省电力公司电力科学研究院 Optimal contract electric quantity decision method for wind-fire bundling power plant in medium-and-long-term electric power market
CN110852535A (en) * 2018-07-24 2020-02-28 华北电力大学 Day-ahead market clearing model considering medium-long term trading and wind power uncertainty
CN111126690A (en) * 2019-12-20 2020-05-08 国网福建省电力有限公司 Power difference contract curve decomposition method under plan-centralized market double-track system
CN112288490A (en) * 2020-11-04 2021-01-29 国网湖南省电力有限公司 Method and system for clearing units with different power generation costs in electric power spot market

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109583951B (en) * 2018-11-29 2023-05-02 浙江电力交易中心有限公司 Electric power market difference contract electric quantity decomposition technology and decomposition result comprehensive evaluation method
CN110033319A (en) * 2019-03-29 2019-07-19 清华大学 Clear collusion suppressing method and device are dissolved at random based on main market players's risk aversion
CN110428330A (en) * 2019-07-09 2019-11-08 广东电力交易中心有限责任公司 A kind of three settlement methods processed of spot market environment lower complete period
CN110826763B (en) * 2019-09-19 2022-07-26 国网浙江省电力有限公司台州供电公司 Middle-long term contract electric quantity decomposition method based on guided learning strategy
CN110827062A (en) * 2019-10-16 2020-02-21 广东电力交易中心有限责任公司 Electricity charge settlement system combining medium and long term price difference mode and spot order mode

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107392432A (en) * 2017-06-27 2017-11-24 东南大学 The frequency modulation electric reserve market implementation method of long-term electricity contract energy decomposition in consideration
CN107895221A (en) * 2017-10-25 2018-04-10 北京微肯佛莱科技有限公司 Long-term scheduling and Maintenance Schedule Optimization method in market environment lower step power station
CN110852535A (en) * 2018-07-24 2020-02-28 华北电力大学 Day-ahead market clearing model considering medium-long term trading and wind power uncertainty
CN110517164A (en) * 2019-08-19 2019-11-29 国网山西省电力公司 The generation schedulecurve of long-term contract decomposes and settlement method and system in consideration
CN110689286A (en) * 2019-11-13 2020-01-14 国网陕西省电力公司电力科学研究院 Optimal contract electric quantity decision method for wind-fire bundling power plant in medium-and-long-term electric power market
CN111126690A (en) * 2019-12-20 2020-05-08 国网福建省电力有限公司 Power difference contract curve decomposition method under plan-centralized market double-track system
CN112288490A (en) * 2020-11-04 2021-01-29 国网湖南省电力有限公司 Method and system for clearing units with different power generation costs in electric power spot market

Also Published As

Publication number Publication date
CN112862313A (en) 2021-05-28

Similar Documents

Publication Publication Date Title
Bottieau et al. Very-short-term probabilistic forecasting for a risk-aware participation in the single price imbalance settlement
Simab et al. Multi-objective programming of pumped-hydro-thermal scheduling problem using normal boundary intersection and VIKOR
Glotić et al. Short-term combined economic and emission hydrothermal optimization by surrogate differential evolution
CN109190802B (en) Multi-microgrid game optimization method based on power generation prediction in cloud energy storage environment
Chen et al. Research on day-ahead transactions between multi-microgrid based on cooperative game model
Veit et al. Simulating the dynamics in two-settlement electricity markets via an agent-based approach
Faraji et al. Optimal day-ahead scheduling and operation of the prosumer by considering corrective actions based on very short-term load forecasting
CN110516843B (en) Virtual power plant capacity optimization method, device and system
Yin et al. Hybrid metaheuristic multi-layer reinforcement learning approach for two-level energy management strategy framework of multi-microgrid systems
CN112381263A (en) Block chain distributed data storage based multi-microgrid day-ahead robust electric energy transaction method
Wang et al. Re-scheduling the unit commitment problem in fuzzy environment
Qiu et al. Mean-field multi-agent reinforcement learning for peer-to-peer multi-energy trading
Choudhury et al. Artificial intelligence solution to transmission loss allocation problem
Kumar et al. Dynamic economic dispatch–a review of solution methodologies
Yin et al. Equilibrium stability of asymmetric evolutionary games of multi-agent systems with multiple groups in open electricity market
Huy et al. Real-time energy scheduling for home energy management systems with an energy storage system and electric vehicle based on a supervised-learning-based strategy
Vincent et al. Sustainable microgrid design with multiple demand areas and peer-to-peer energy trading involving seasonal factors and uncertainties
CN112862313B (en) Generator set scheduling method and system based on medium-long term price difference contract electric quantity decomposition
Zheng et al. Data-driven scheme for optimal day-ahead operation of a wind/hydrogen system under multiple uncertainties
Vincent et al. Sustainable microgrid design with peer-to-peer energy trading involving government subsidies and uncertainties
CN115049102A (en) Electricity price prediction method and device, mobile terminal and storage medium
Peng et al. Generation planning for power companies with hybrid production technologies under multiple renewable energy policies
Cai et al. Hierarchical coordinated energy management strategy for electricity-hydrogen integrated charging stations based on IGDT and hybrid game
Kim A new approach to short-term price forecast strategy with an artificial neural network approach: application to the Nord Pool
Tao et al. Portfolio selection of power generation projects considering the synergy of project and uncertainty of decision information

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant