CN116797275A - Market price prediction calculation method based on industrial user supply and demand situation - Google Patents
Market price prediction calculation method based on industrial user supply and demand situation Download PDFInfo
- Publication number
- CN116797275A CN116797275A CN202310964479.XA CN202310964479A CN116797275A CN 116797275 A CN116797275 A CN 116797275A CN 202310964479 A CN202310964479 A CN 202310964479A CN 116797275 A CN116797275 A CN 116797275A
- Authority
- CN
- China
- Prior art keywords
- data
- fluctuation
- load
- coefficient
- matrix
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 28
- 230000005611 electricity Effects 0.000 claims description 184
- 239000011159 matrix material Substances 0.000 claims description 122
- 238000010248 power generation Methods 0.000 claims description 103
- 238000000034 method Methods 0.000 claims description 25
- 230000008859 change Effects 0.000 claims description 13
- 101100134058 Caenorhabditis elegans nth-1 gene Proteins 0.000 claims description 3
- 230000006870 function Effects 0.000 description 11
- 238000003860 storage Methods 0.000 description 7
- 230000009194 climbing Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Optimization (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of power system planning and operation, in particular to a market price prediction calculation method based on industrial user supply and demand situations.
Description
Technical Field
The application relates to the technical field of power system planning and operation, in particular to a market price prediction calculation method based on industrial user supply and demand situations.
Background
In the existing power market, accurate prediction of electricity price has very important significance on power demand and supply and optimal scheduling, the factor of electricity price is influenced by various seasonal factors, but the factor is essentially influenced by the supply-demand relation of load and generated energy, accurate electricity price prediction can provide operation decision support, promote energy market analysis, realize load management and energy efficiency optimization, and provide reliable basis for energy planning and policy formulation, and is especially so for industrial users, the electricity consumers of the power system always are sensitive to fluctuation of electricity price, the industrial users can better optimize energy management by predicting the electricity price, and the industrial users can adjust own production plan and load management strategy aiming at the predicted electricity price trend, so that energy can be efficiently utilized and saved. The later stage can be through measures such as reasonable arrangement electricity consumption time, adjustment production flow, let the industry user reduce the power consumption when the price of electricity is higher, increase the power consumption when the price of electricity is lower, adapt to market change better.
According to the short-term load prediction method based on the real-time electricity price, which is provided by the publication No. CN107491812B, the correlation coefficient of the load and the electricity price is introduced into a neural network model, the relation between the electricity price and the load is reflected by correcting the input weight of an hidden layer of the neural network, but the electricity price is influenced by various factors, besides the influence of the load of electricity consumption, the influence of fluctuation factors of the load and the electricity generation amount also needs to be considered, for example, the climbing problem of the electricity generation unit needs to be considered when the electricity generation amount is improved, and when the electricity generation equipment climbs the electricity generation amount, the cost is higher relative to the condition of stable electricity generation amount, and the predicted electricity price can be increased.
The above method only considers the influence of the load on the electricity price, does not sufficiently consider the relationship between the load and the electricity generation amount, and does not consider the influence of the fluctuation factors of the load and the electricity generation amount on the electricity price, but the fluctuation of the load and the electricity generation amount is an important factor affecting the electricity price, so the above method causes a large error in the predicted electricity price.
Disclosure of Invention
The application aims to provide a market price prediction calculation method based on industrial user supply and demand situations so as to solve the problems in the background technology.
In order to achieve the above purpose, the present application provides the following technical solutions:
a market price prediction calculation method based on industrial user supply and demand situations comprises the following specific steps:
load data, electricity price data and generating capacity data of the electricity utilization end and generating capacity data of the electricity generation end of the past k months are collected, and a load sample data matrix, an electricity price data matrix and a generating capacity sample data matrix are respectively constructed by using the load data, the electricity price data and the generating capacity data;
calculating a monthly load fluctuation coefficient matrix, a power generation fluctuation coefficient matrix and a power price fluctuation matrix according to the load sample data matrix, the power generation sample data matrix and the power price data matrix respectively, and reflecting fluctuation conditions of the monthly load data, the power generation data and the power price;
constructing a fluctuation weight coefficient by using a load fluctuation coefficient matrix, a power generation fluctuation coefficient matrix and a power price fluctuation matrix, and reflecting the influence of the load fluctuation coefficient matrix and the power generation fluctuation coefficient matrix on the power price fluctuation matrix;
load data and generating capacity data of n moments in the month are collected averagely, and average load data and average generating capacity data are calculated according to the load data and the generating capacity data of the n moments respectively;
calculating trend coefficients of the load data and the power generation amount data according to the load data and the power generation amount data at n times respectively, and reflecting the change trends of the load data and the power generation amount data at n times respectively;
combining the current month electricity price, the trend coefficient of load data, the trend coefficient of generating capacity data and the fluctuation weight coefficient, constructing an electricity price prediction model according to the calculated average load data and the calculated average generating capacity data, and gradient predicting the current month electricity price, wherein the constructed electricity price prediction model is as follows:
wherein A is a power generation amount trend weight coefficient, B is a load trend weight coefficient, C is a first gradient weight coefficient, D is a second gradient weight coefficient, A>B>1,C>D>1, t is the current month electricity price, t n For the predicted electricity price, σ is a fluctuation weight coefficient, α is a trend coefficient of load data, and β is a trend coefficient of power generation amount data.
Further, the method for constructing the load sample data matrix is to collect load data of the power utilization end in the past k months, collect load data of n moments in each month, and construct a load sample data matrix P:
wherein P is a constructed load sample data matrix lambda i (j) Load data indicating the j-th time in the i-th month;
the constructed k month electricity price data matrix is as follows:
wherein D is a constructed electricity price data matrix, D i Electricity price data of the ith month;
the method for constructing the generated energy sample data matrix is to collect generated energy data of a generating end in the past k months, and collect generated energy data of n moments in each month to form a generated energy sample data matrix V:
wherein V is the constructed generated energy sample data matrix, V i (j) And (3) generating capacity data representing the jth moment in the ith month.
Further, when load data, electricity price data and generating capacity data of the generating end are collected in the k months, the interval time between the collected months is the same.
Further, the method for constructing the load fluctuation coefficient matrix comprises the following steps:
for load data in the same month, calculating load fluctuation coefficients of each month respectively, and forming a 1 Xk matrix of the load fluctuation coefficients of k months according to a time sequence to form a load fluctuation coefficient matrix;
the calculation method of the load fluctuation coefficient of each month is to calculate Euclidean distances between the load data of the next moment and the load data of the previous moment respectively by taking the first moment as a starting point and the n-1 moment as an end point according to the time sequence of acquisition, to carry out superposition summation on the calculated n-1 Euclidean distances, and to divide the summation result by n-1, so as to calculate the average value of the Euclidean distances, namely the load fluctuation coefficient.
Further, the method for constructing the electricity price fluctuation matrix comprises the following steps:
aiming at the electricity price data in the same month, calculating the electricity price fluctuation coefficient of each month respectively, and forming a 1 xk matrix of the electricity price fluctuation coefficient of each month according to the time sequence to form an electricity price fluctuation matrix;
the calculation method of the electricity price fluctuation coefficient of each month is to superimpose the electricity price data of k months, calculate the average electricity price data of k months, and subtract the electricity price data of the current month and the average electricity price data to calculate the absolute value, namely the electricity price fluctuation coefficient.
Further, aiming at the generated energy data in the same month, calculating the generated energy fluctuation coefficient of each month respectively, and forming a 1 xk matrix of the generated energy fluctuation coefficients of k months according to the time sequence to form a generated energy fluctuation coefficient matrix;
the calculation method of the power generation fluctuation coefficient of each month is to calculate Euclidean distances between the power generation data of the next moment and the power generation data of the previous moment respectively by taking the power generation data of n moments as a starting point and the nth-1 moment as an end point according to the collected time sequence, to carry out superposition summation on the calculated n-1 Euclidean distances, and to divide the summation result by n-1, so as to calculate the average number of the Euclidean distances, namely the power generation fluctuation coefficient.
Further, the method for constructing the fluctuation weight coefficient by using the load fluctuation coefficient matrix, the power generation fluctuation coefficient matrix and the electricity price fluctuation matrix comprises the following steps:
respectively extracting a load fluctuation coefficient, a power price fluctuation coefficient and a power generation fluctuation coefficient of each month by using the load fluctuation coefficient matrix, the power generation fluctuation coefficient matrix and the power price fluctuation matrix;
fitting the electricity price fluctuation coefficient and the exponential function aiming at the load fluctuation coefficient, the electricity price fluctuation coefficient and the power generation fluctuation coefficient in each month, and constructing a month fluctuation weight coefficient of a single month, so that the load fluctuation coefficient and the power generation fluctuation coefficient are in positive correlation with the month fluctuation weight coefficient, and a function after fitting the electricity price fluctuation coefficient and the exponential function is in negative correlation with the month fluctuation weight coefficient;
and overlapping the month fluctuation weight coefficients of k months, and calculating an average number, namely the fluctuation weight coefficient.
Further, the formula according to which the fluctuation weight coefficient is constructed by using the load fluctuation coefficient matrix, the power generation fluctuation coefficient matrix and the electricity price fluctuation matrix is as follows:
wherein PT i For the load fluctuation coefficient of month i, dt i Is the electricity price fluctuation coefficient of the ith month, VT i Is the power generation fluctuation coefficient of the ith month,the lunar fluctuation weight coefficient is obtained.
Further, load data and power generation amount data at n times in the month are averagely collected to be alpha respectively 1 、α 2 、…、α p 、…α n And beta 1 、β 2 、…、β q 、…β n The formulas according to which the average load data and the average power generation amount data are calculated are respectively:
wherein alpha is p Is the load data at the p-th moment in the month, beta q Is the generated energy data at the q-th moment in the month.
Further, formulas according to which the trend coefficient of the load data and the trend coefficient of the power generation amount data are calculated are respectively:
wherein alpha is a trend coefficient of load data, and beta is a trend coefficient of power generation amount data.
Compared with the prior art, the application has the beneficial effects that:
according to the application, load data, electricity price data and electricity generation amount data of an electricity utilization end in historical data are collected, a load fluctuation coefficient matrix, an electricity generation fluctuation coefficient matrix and an electricity price fluctuation matrix are obtained, fluctuation conditions of the load data, the electricity generation amount data and the electricity price per month are reflected, and the electricity price is directly influenced due to fluctuation of the load data and the electricity generation amount data.
According to the application, a fluctuation weight coefficient is constructed by a load fluctuation coefficient matrix, a power generation fluctuation coefficient matrix and a power price fluctuation matrix, the influence of load fluctuation and power generation fluctuation on power price fluctuation is integrally reflected through the fluctuation weight coefficient, the current power price is taken as a prediction basis, the current load data and power generation data are comprehensively combined, a power price prediction model is constructed by introducing the fluctuation weight coefficient, the gradient prediction power price is realized, the fluctuation weight sigma is obtained according to known historical load data, power generation data and power price data, the influence of the load data and the power generation data on the power price is reflected by the system, so that the current load data and the power generation data can be used for predicting the power price through the fluctuation weight sigma.
Drawings
FIG. 1 is a schematic flow chart of the whole method of the application.
Detailed Description
The present application will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present application more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present application belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
Examples:
referring to fig. 1, the present application provides a technical solution:
a market price prediction calculation method based on industrial user supply and demand situations comprises the following specific steps:
load data of the power utilization end and monthly electricity price in the past several months are collected, power utilization monitoring equipment is installed at the current power supply end or power distribution end to collect the load data of the power utilization end, power utilization information comprising load curves and data can be recorded in real time, and the load data of the power utilization end can be obtained or derived through the equipment for analysis.
In this embodiment, load data of the electricity utilization terminal and electricity prices of each month in the past k songs are collected, load data of n moments are collected in each month in average, and a load sample data matrix P is constructed:
wherein lambda is i (j) Load data indicating the j-th time in the i-th month.
In this embodiment, the time of the load data collected each month is the same, for example, the load data is collected between 12 hours and 13 hours of 5, 10, 15, 20 and 25 days each month, and the collected load data forms a load sample data matrix P by month and time.
In this embodiment, monthly electricity prices are collected from power suppliers, which provide historical electricity usage data, including electricity usage and rates to construct a k month electricity price data matrix D:
wherein d i And the electricity price data of the ith month.
In this embodiment, the electricity price data and the load data are in a one-to-one mapping relationship, for example, the electricity price data of the ith month and the load data at all times in the ith month are in a one-to-one correspondence relationship. The load sample data matrix P and the electricity price data matrix D can clearly know the historical data change of the load and the electricity price, so that the periodic or seasonal change of the electricity load and the electricity price is identified, and the future electricity demand and the future electricity price are predicted.
Because the load data and the generating capacity data have a supply-demand relationship, the supply-demand relationship can determine the trend and change of the electricity price, when the load data occupies a large proportion of the generating capacity data, generating mechanisms such as a power plant and the like can produce capacity climbing to meet the demand, and the electricity price can be increased inevitably, so that if the market electricity price is predicted, the direct selling of the generating capacity data is needed inevitably.
In order to make the generated energy data correspond to the load data and the electricity price, in this embodiment, the generated energy data of the generating end in the past k months is collected, and the generated energy data of n times are collected in each month to form a generated energy sample data matrix V:
wherein V is i (j) And (3) generating capacity data representing the jth moment in the ith month.
In this embodiment, the power generation amount data and the load data are collected at the j-th time in the i-th month in a one-to-one mapping relationship i (j) Collecting generating capacity data V still at the j moment in the i month i (j) The power generation amount sample data matrix V is constituted.
In this embodiment, the generating capacity data may obtain generating capacity data from the generating equipment and the system, the power plant may install the monitoring equipment and the data recording system to monitor the generating capacity and the running state in real time, the power plant operator may monitor and record the generating capacity information in the power supply system, including the generating capacity of each power plant and the total generating capacity transmitted to the network, and may also collect the historical generating capacity data according to the power grid operator.
In this embodiment, when load data, electricity price data, and electricity generation amount data of the electricity generation end are collected for k months, the interval time between the collected months is the same, that is, the interval time between the (i+1) th month and the (i) th month is the same.
The fluctuation of load data and generating capacity data can directly influence electricity price, when the load data is increased, a power supply system can face the situation of shortage of supply, so that electricity price rises, when the generating capacity data is increased, the capacity of a power plant is in a climbing stage at the moment, the cost demand is high in a short time, so that the electricity price rises.
In this embodiment, the method for constructing the load fluctuation coefficient matrix includes:
for load data in the same month, calculating load fluctuation coefficients of each month respectively, and forming a 1 Xk matrix of the load fluctuation coefficients of k months according to a time sequence to form a load fluctuation coefficient matrix;
the calculation method of the load fluctuation coefficient of each month is to calculate Euclidean distances between the load data of the next moment and the load data of the previous moment respectively by taking the first moment as a starting point and the n-1 moment as an end point according to the time sequence of acquisition, to carry out superposition summation on the calculated n-1 Euclidean distances, and to divide the summation result by n-1, so as to calculate the average value of the Euclidean distances, namely the load fluctuation coefficient.
Specifically, a monthly load fluctuation coefficient matrix PT is calculated according to the load sample data matrix P:
wherein PT i Load fluctuation coefficient of the ith month, PT i The formula is as follows:
from the above formula, it can be seen that, in the ith month, the larger the phase difference of the load data collected at a plurality of moments, i.e. the larger the fluctuation, the load fluctuation coefficient PT corresponding to the ith month i The larger.
In the embodiment, aiming at the generated energy data in the same month, the generated energy fluctuation coefficient of each month is calculated respectively, and the generated energy fluctuation coefficients of k months form a 1 xk matrix according to the time sequence to form a generated energy fluctuation coefficient matrix;
the calculation method of the power generation fluctuation coefficient of each month is to calculate Euclidean distances between the power generation data of the next moment and the power generation data of the previous moment respectively by taking the power generation data of n moments as a starting point and the nth-1 moment as an end point according to the collected time sequence, to carry out superposition summation on the calculated n-1 Euclidean distances, and to divide the summation result by n-1, so as to calculate the average number of the Euclidean distances, namely the power generation fluctuation coefficient.
Specifically, a monthly power generation fluctuation coefficient matrix VT is calculated according to the power generation amount sample data matrix V:
wherein VT is i Is the power generation fluctuation coefficient of the ith month, VT i The formula is as follows:
from the above formula, it can be seen that, in the ith month, the larger the fluctuation of the power generation amount data acquired at a plurality of times is, the power generation fluctuation coefficient VT corresponding to the ith month is i The larger.
In this embodiment, the method for constructing the electricity price fluctuation matrix includes:
aiming at the electricity price data in the same month, calculating the electricity price fluctuation coefficient of each month respectively, and forming a 1 xk matrix of the electricity price fluctuation coefficient of each month according to the time sequence to form an electricity price fluctuation matrix;
the calculation method of the electricity price fluctuation coefficient of each month is to superimpose the electricity price data of k months, calculate the average electricity price data of k months, and subtract the electricity price data of the current month and the average electricity price data to calculate the absolute value, namely the electricity price fluctuation coefficient.
Specifically, the electricity price fluctuation matrix DT is calculated according to the electricity price data matrix D:
wherein dt is i Is the electricity price fluctuation coefficient of the ith month, dt i The formula is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,the calculated result is the average electricity price in k months, and the electricity price fluctuation coefficient dt of the ith month i The value of (2) represents the magnitude of fluctuation of electricity prices.
Since load fluctuation and power generation quantity fluctuation directly influence power price fluctuation, the power price fluctuation plays a vital role in predicting the power price, and therefore the power price fluctuation matrix DT and the load fluctuation coefficient matrix PT are combined, fluctuation weights are calculated according to the known power price fluctuation matrix DT, and the influence of the power price fluctuation matrix DT and the load fluctuation coefficient matrix PT on the power price fluctuation matrix DT is reflected through the fluctuation weights.
In this embodiment, the method for constructing the fluctuation weight coefficient by using the load fluctuation coefficient matrix, the power generation fluctuation coefficient matrix and the electricity price fluctuation matrix includes:
respectively extracting a load fluctuation coefficient, a power price fluctuation coefficient and a power generation fluctuation coefficient of each month by using the load fluctuation coefficient matrix, the power generation fluctuation coefficient matrix and the power price fluctuation matrix;
fitting the electricity price fluctuation coefficient and the exponential function aiming at the load fluctuation coefficient, the electricity price fluctuation coefficient and the power generation fluctuation coefficient in each month, and constructing a month fluctuation weight coefficient of a single month, so that the load fluctuation coefficient and the power generation fluctuation coefficient are in positive correlation with the month fluctuation weight coefficient, and a function after fitting the electricity price fluctuation coefficient and the exponential function is in negative correlation with the month fluctuation weight coefficient;
overlapping the month fluctuation weight coefficients of k months, and calculating an average number, namely the fluctuation weight coefficient
Specifically, the electricity price fluctuation matrix DT, the load fluctuation coefficient matrix PT and the power generation fluctuation coefficient matrix VT are associated, and fluctuation weight sigma is calculated:
wherein, the liquid crystal display device comprises a liquid crystal display device,the lunar fluctuation weight coefficient is obtained.
In the actual power supply scenario, the electricity price has hysteresis with respect to the change of the load and the power generation amount, and the change of the electricity price always changes with the change of the load and the power generation amount, that is, the change of the electricity price can be reflected only after the supply-demand relationship of the load and the power generation amount changes, so that the law is also reflected on the fluctuation weight sigma.
From the above, it can be seen that the power generation fluctuation coefficient VT i And a load fluctuation coefficient PT i Larger electricity price fluctuation coefficient dt i When the load fluctuation and the power generation amount fluctuation are smaller, the power price is not influenced, but the influence on the power price is gradually increased, the corresponding fluctuation weight sigma is larger, the fluctuation of the load data and the power generation amount data can have larger direct influence on the supply and demand balance, the power supply system can face the problem of supply shortage or the power supply system can be excessive, and the influence on the power price is larger.
Coefficient of fluctuation VT of power generation i And a load fluctuation coefficient PT i Larger electricity price fluctuation coefficient dt i When larger, it is stated that load fluctuation, power generation amount fluctuation have affected electricity prices at this time, similar to the power generation of a power plant, the power generation amount has been in a stage of climbing, but the influence on electricity prices will gradually decrease thereafter.
Based on electricity price fluctuation coefficient dt i An exponential function model is constructed, and the power generation fluctuation coefficient VT is constructed i And a load fluctuation coefficient PT i Less electricity price fluctuation coefficient dt i The larger the supply and demand relationship is in the state of balance, the smaller the influence on the electricity price is, but in the actual supply and demand relationship, the electricity price cannot rise infinitely, when the electricity price reaches a certain degree, the fluctuation coefficient dt of the electricity price i The smaller the influence on the electricity price is, the better the electricity price fluctuation coefficient dt can be fitted by adopting an exponential function model i For the influence of electricity price, when
The fluctuation weight sigma is obtained according to known historical load data, generated energy data and electricity price data, the influence of the load data and the generated energy data on the electricity price is reflected by the system, and the current load data and the generated energy data can be used for predicting the electricity price.
In this embodiment, the specific steps for predicting electricity price data include:
average acquisition of load data alpha at n moments in the month 1 、α 2 、…、α p 、…α n And calculate average load dataSaid average load data->The formula on which the calculation is based is:
wherein alpha is p Is the load data at the p-th moment in the month.
Average collecting generating capacity data beta of n moments in the same month 1 、β 2 、…、β q 、…β n And calculate average power generation amount dataMean power generation data->The formula on which the calculation is based is:
wherein beta is q Is the generated energy data at the q-th moment in the month.
In the present embodiment, the electricity price t under prediction n The specific method of (a) is as follows:
calculating a trend coefficient alpha of the load data, wherein a formula according to which the trend coefficient alpha of the load data is calculated is as follows:
the trend coefficient alpha of the load data can systematically reflect the trend change of the load in the current month if
Less than 0, a gradual decrease in load is indicated, ifIf the load is smaller than 0, the load is gradually reduced, and if the load is larger than 0, the load is gradually increased.
Calculating a trend coefficient beta of the generated energy data, wherein a formula on which the trend coefficient beta of the generated energy data is calculated is as follows:
the trend coefficient beta of the power generation amount data can systematically reflect the trend change of the power generation amount in the current month ifIf the power generation amount is less than 0, the power generation amount is gradually reduced, if +.>When the power generation amount is larger than 1, the power generation amount is gradually increased, whether the power generation amount in the current month is gradually increased or decreased can be comprehensively judged through summation, if the power generation amount is smaller than 0, the power generation amount in the current month is gradually decreased, and if the power generation amount is larger than 0, the power generation amount in the current month is gradually increased.
Constructing an electricity price prediction model to predict the electricity price t of the next month n The formula on which the prediction is based is:
wherein A is a power generation amount trend weight coefficient, B is a load trend weight coefficient, C is a first gradient weight coefficient, D is a second gradient weight coefficient, A>B>1,C>D>1, t is the current month electricity price, t n For predicted electricity prices, σ is the fluctuation weight coefficient.
As can be seen from the above, whenIt is clear that in this case the amount of generated electricity is large relative to the load, indicating that there may be an excessive problem with the power supply system, and therefore the predicted electricity price is the lowest, along with +.>Relative to->The power generation amount occupied by the load gradually increases gradually, and the predicted electricity price gradually increases at the same time.
The fluctuation weight sigma is larger than 0, which indicates the influence on electricity price, when the load is gradually reduced, the electricity generation amount is gradually reduced, the electricity price is gradually reduced no matter the load is gradually increased or the electricity generation amount is gradually increased, the difference between the supply and the demand is larger, and the electricity charge is gradually increased.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is merely a channel underwater topography change analysis system and method logic function division, and other divisions may be implemented in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the application is not intended to limit the application, but to enable any modification, equivalent or improvement to be made without departing from the spirit and principles of the application.
Claims (10)
1. A market price prediction calculation method based on industrial user supply and demand situations is characterized by comprising the following specific steps:
load data, electricity price data and generating capacity data of the electricity utilization end and generating capacity data of the electricity generation end of the past k months are collected, and a load sample data matrix, an electricity price data matrix and a generating capacity sample data matrix are respectively constructed by using the load data, the electricity price data and the generating capacity data;
calculating a monthly load fluctuation coefficient matrix, a power generation fluctuation coefficient matrix and a power price fluctuation matrix according to the load sample data matrix, the power generation sample data matrix and the power price data matrix respectively, and reflecting fluctuation conditions of the monthly load data, the power generation data and the power price;
constructing a fluctuation weight coefficient by using a load fluctuation coefficient matrix, a power generation fluctuation coefficient matrix and a power price fluctuation matrix, and reflecting the influence of the load fluctuation coefficient matrix and the power generation fluctuation coefficient matrix on the power price fluctuation matrix;
load data and generating capacity data of n moments in the month are collected averagely, and average load data and average generating capacity data are calculated according to the load data and the generating capacity data of the n moments respectively;
calculating trend coefficients of the load data and the power generation amount data according to the load data and the power generation amount data at n times respectively, and reflecting the change trends of the load data and the power generation amount data at n times respectively;
combining the current month electricity price, the trend coefficient of load data, the trend coefficient of generating capacity data and the fluctuation weight coefficient, constructing an electricity price prediction model according to the calculated average load data and the calculated average generating capacity data, and gradient predicting the current month electricity price, wherein the constructed electricity price prediction model is as follows:
wherein A is a power generation amount trend weight coefficient, B is a load trend weight coefficient, C is a first gradient weight coefficient, D is a second gradient weight coefficient, A>B>1,C>D>1, t is the current month electricity price, t n For the predicted electricity price, σ is a fluctuation weight coefficient, α is a trend coefficient of load data, and β is a trend coefficient of power generation amount data.
2. The market price prediction calculation method based on the industrial user supply and demand situation according to claim 1, wherein: the method for constructing the load sample data matrix is to collect load data of the electricity utilization end of the past k months, collect load data of n moments in each month in average, and construct the load sample data matrix P:
wherein P is a constructed load sample data matrix lambda i (j) Load data indicating the j-th time in the i-th month;
the constructed k month electricity price data matrix is as follows:
wherein D is a constructed electricity price data matrix, D i Electricity price data of the ith month;
the method for constructing the generated energy sample data matrix is to collect generated energy data of a generating end in the past k months, and collect generated energy data of n moments in each month to form a generated energy sample data matrix V:
wherein V is the constructed generated energy sample data matrix, V i (j) Indicating the j-th time in the i-th monthIs a power generation amount data of (a).
3. The market price prediction calculation method based on the industrial user supply and demand situation according to claim 2, wherein: and when the load data, the electricity price data and the generating capacity data of the generating end are collected, the interval time among the collected months is the same.
4. The market price prediction calculation method based on the industrial user supply and demand situation according to claim 2, wherein: the method for constructing the load fluctuation coefficient matrix comprises the following steps:
for load data in the same month, calculating load fluctuation coefficients of each month respectively, and forming a 1 Xk matrix of the load fluctuation coefficients of k months according to a time sequence to form a load fluctuation coefficient matrix;
the calculation method of the load fluctuation coefficient of each month is to calculate Euclidean distances between the load data of the next moment and the load data of the previous moment respectively by taking the first moment as a starting point and the n-1 moment as an end point according to the time sequence of acquisition, to carry out superposition summation on the calculated n-1 Euclidean distances, and to divide the summation result by n-1, so as to calculate the average value of the Euclidean distances, namely the load fluctuation coefficient.
5. The market price prediction calculation method based on the industrial user supply and demand situation according to claim 4, wherein: the method for constructing the electricity price fluctuation matrix comprises the following steps:
aiming at the electricity price data in the same month, calculating the electricity price fluctuation coefficient of each month respectively, and forming a 1 xk matrix of the electricity price fluctuation coefficient of each month according to the time sequence to form an electricity price fluctuation matrix;
the calculation method of the electricity price fluctuation coefficient of each month is to superimpose the electricity price data of k months, calculate the average electricity price data of k months, and subtract the electricity price data of the current month and the average electricity price data to calculate the absolute value, namely the electricity price fluctuation coefficient.
6. The market price prediction calculation method based on the industrial user supply and demand situation according to claim 5, wherein: aiming at the generating capacity data in the same month, calculating the generating fluctuation coefficient of each month respectively, and forming a 1 Xk matrix of the generating fluctuation coefficients of k months according to the time sequence to form a generating fluctuation coefficient matrix;
the calculation method of the power generation fluctuation coefficient of each month is to calculate Euclidean distances between the power generation data of the next moment and the power generation data of the previous moment respectively by taking the power generation data of n moments as a starting point and the nth-1 moment as an end point according to the collected time sequence, to carry out superposition summation on the calculated n-1 Euclidean distances, and to divide the summation result by n-1, so as to calculate the average number of the Euclidean distances, namely the power generation fluctuation coefficient.
7. The market price prediction calculation method based on the industrial user supply and demand scenario of claim 6, wherein: the method for constructing the fluctuation weight coefficient by using the load fluctuation coefficient matrix, the power generation fluctuation coefficient matrix and the electricity price fluctuation matrix comprises the following steps:
respectively extracting a load fluctuation coefficient, a power price fluctuation coefficient and a power generation fluctuation coefficient of each month by using the load fluctuation coefficient matrix, the power generation fluctuation coefficient matrix and the power price fluctuation matrix;
fitting the electricity price fluctuation coefficient and the exponential function aiming at the load fluctuation coefficient, the electricity price fluctuation coefficient and the power generation fluctuation coefficient in each month, and constructing a month fluctuation weight coefficient of a single month, so that the load fluctuation coefficient and the power generation fluctuation coefficient are in positive correlation with the month fluctuation weight coefficient, and a function after fitting the electricity price fluctuation coefficient and the exponential function is in negative correlation with the month fluctuation weight coefficient;
and overlapping the month fluctuation weight coefficients of k months, and calculating an average number, namely the fluctuation weight coefficient.
8. The market price prediction calculation method based on the industrial user supply and demand scenario of claim 7, wherein: the formula according to which the fluctuation weight coefficient is constructed by utilizing the load fluctuation coefficient matrix, the power generation fluctuation coefficient matrix and the electricity price fluctuation matrix is as follows:
wherein PT i For the load fluctuation coefficient of month i, dt i Is the electricity price fluctuation coefficient of the ith month, VT i Is the power generation fluctuation coefficient of the ith month,the lunar fluctuation weight coefficient is obtained.
9. The market price prediction calculation method based on the industrial user supply and demand situation according to claim 1, wherein: the average collection of load data and power generation data at n moments in the same month is alpha respectively 1 、α 2 、…、α p 、…α n And beta 1 、β 2 、…、β q 、…β n The formulas according to which the average load data and the average power generation amount data are calculated are respectively:
wherein alpha is p Is the load data at the p-th moment in the month, beta q Is the generated energy data at the q-th moment in the month.
10. The market price prediction calculation method based on the industrial user supply and demand scenario of claim 8, wherein: the formulas according to which the trend coefficients of the load data and the trend coefficients of the generated energy data are calculated are respectively as follows:
wherein alpha is a trend coefficient of load data, and beta is a trend coefficient of power generation amount data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310964479.XA CN116797275A (en) | 2023-08-02 | 2023-08-02 | Market price prediction calculation method based on industrial user supply and demand situation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310964479.XA CN116797275A (en) | 2023-08-02 | 2023-08-02 | Market price prediction calculation method based on industrial user supply and demand situation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116797275A true CN116797275A (en) | 2023-09-22 |
Family
ID=88034661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310964479.XA Pending CN116797275A (en) | 2023-08-02 | 2023-08-02 | Market price prediction calculation method based on industrial user supply and demand situation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116797275A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688520A (en) * | 2024-02-04 | 2024-03-12 | 国网安徽省电力有限公司经济技术研究院 | Electric-carbon price conduction data analysis method based on electric-carbon market association |
-
2023
- 2023-08-02 CN CN202310964479.XA patent/CN116797275A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688520A (en) * | 2024-02-04 | 2024-03-12 | 国网安徽省电力有限公司经济技术研究院 | Electric-carbon price conduction data analysis method based on electric-carbon market association |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11398000B2 (en) | Methods and systems for machine-learning for prediction of grid carbon emissions | |
| Burger et al. | The efficiency and distributional effects of alternative residential electricity rate designs | |
| CN116646933B (en) | Big data-based power load scheduling method and system | |
| US10873209B2 (en) | System and method for dynamic energy storage system control | |
| Cheng et al. | PowerLSTM: power demand forecasting using long short-term memory neural network | |
| US7089125B2 (en) | Distributed asset optimization (DAO) system and method | |
| Holttinen et al. | Using standard deviation as a measure of increased operational reserve requirement for wind power | |
| Hossan et al. | Integrated CVR and demand response framework for advanced distribution management systems | |
| US11824360B2 (en) | Apparatus and method for optimizing carbon emissions in a power grid | |
| CN116797275A (en) | Market price prediction calculation method based on industrial user supply and demand situation | |
| CN116579590A (en) | Demand response evaluation method and system in virtual power plant | |
| Oprea et al. | Big data processing for commercial buildings and assessing flexibility in the context of citizen energy communities | |
| Kim et al. | Economical energy storage systems scheduling based on load forecasting using deep learning | |
| CN112288130A (en) | New energy consumption calculation method based on two-stage multi-objective optimization | |
| CN116883064A (en) | Energy storage transaction operation management method and system based on subsection price prediction | |
| CN110826931A (en) | User-side distributed energy storage economy evaluation system | |
| Martinek et al. | Efficient prediction of concentrating solar power plant productivity using data clustering | |
| Tang et al. | A grid view on the dynamics of processes participating in demand response programs | |
| CN111368257A (en) | Method and device for analyzing and predicting coal-to-electricity load characteristics | |
| CN105203838B (en) | A kind of coulomb collection system | |
| Zhang et al. | Analytics and Optimization for Renewable Energy Integration | |
| Dannecker et al. | Efficient forecasting for hierarchical time series | |
| CN112086977B (en) | User energy storage capacity configuration method based on energy storage profit space maximization | |
| CN117291756B (en) | Energy storage device configuration adjustment method and device and storage medium | |
| CN117993560A (en) | Sparrow search algorithm-based battery charging method and sparrow search algorithm-based battery charging system for battery replacement station |
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 |