CN112686770A - Load prediction method and device based on demand price elastic correction - Google Patents
Load prediction method and device based on demand price elastic correction Download PDFInfo
- Publication number
- CN112686770A CN112686770A CN201910990355.2A CN201910990355A CN112686770A CN 112686770 A CN112686770 A CN 112686770A CN 201910990355 A CN201910990355 A CN 201910990355A CN 112686770 A CN112686770 A CN 112686770A
- Authority
- CN
- China
- Prior art keywords
- load
- demand
- information
- electricity price
- change rate
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The embodiment of the invention provides a load prediction method and a device based on demand price elastic correction, wherein the method comprises the steps of obtaining an electricity price demand response elastic matrix according to historical load demand change rate at each moment of multiple days and historical electricity price change rate at each moment of multiple days; calculating to obtain load demand change estimated value information at any moment in multiple days according to the electricity price demand response elastic matrix and the original electricity consumption-daily electricity price change rate product vector information; constructing a load demand variation quantity reconstruction error minimum function according to load demand variation estimated value information and original power consumption-daily electricity price change rate product vector information; and optimizing the minimum function of the load demand variation reconstruction error through a wolf optimization algorithm, and obtaining an optimized electricity price demand response elastic matrix when a preset condition is met so as to obtain final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix. The load curve before and after the load response is predicted more accurately.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a load prediction method and device based on demand price elastic correction.
Background
With the development of an active power distribution system, a large number of flexible resources such as distributed power sources, electric vehicles and energy storage devices are connected to a power distribution network on a large scale, so that the economical efficiency of power grid operation is influenced, and the safety and the stability of a power system are further influenced. Different from the traditional power distribution network, the load in the active power distribution network can dynamically adjust the power consumption behavior habit along with the power market to improve the power consumption economy and change the original power consumption load curve, obviously, the basic load prediction method can not accurately predict the load participating in demand response,
moreover, only when the change condition of the load response of the user in a period of time in the future is accurately predicted, the measure of the demand response can be provided in a targeted manner, the load curve is improved, and the transaction success rate between a generator and the user is promoted.
Therefore, how to implement load prediction more accurately for an active power distribution system has become an urgent problem to be solved in the industry.
Disclosure of Invention
Embodiments of the present invention provide a load prediction method and apparatus based on demand price flexible correction, so as to solve the technical problems mentioned in the foregoing background technologies, or at least partially solve the technical problems mentioned in the foregoing background technologies.
In a first aspect, an embodiment of the present invention provides a load prediction method based on demand price elastic correction, including:
obtaining an electricity price demand response elastic matrix according to the historical load demand change rate at each moment of multiple days and the historical electricity price change rate at each moment of multiple days;
calculating to obtain load demand change estimated value information at any moment in multiple days according to the electricity price demand response elastic matrix and original electricity consumption-current day electricity price change rate product vector information;
constructing a load demand variation quantity reconstruction error minimum function according to the load demand variation estimated value information and original power consumption-daily electricity price change rate product vector information;
and optimizing the minimum function of the load demand variation reconstruction error through a wolf optimization algorithm, and obtaining an optimized response elastic matrix when a preset condition is met so as to obtain final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix.
More specifically, before the step of obtaining the electricity price demand response elastic matrix according to the historical load demand change rate at each time of multiple days and the historical electricity price change rate at each time of multiple days, the method further includes:
acquiring historical electricity price information at each moment of multiple days and historical load information at each moment of multiple days;
obtaining the historical electricity price change rate of each time of the multiple days according to the historical electricity price information of each time of the multiple days, and obtaining the historical load demand change rate of each time of the multiple days according to the historical load information of each time of the multiple days;
wherein each day includes 24 moments.
More specifically, the step of obtaining the electricity price demand response elastic matrix according to the historical load demand change rate at each time of multiple days and the historical electricity price change rate at each time of multiple days specifically includes:
acquiring the self-response elastic coefficient of the electricity price demand at the same moment;
acquiring cross response elastic coefficients of electricity price requirements at different moments;
and forming a power price demand response elastic matrix from the corresponding elastic coefficient and the power price demand cross response elastic coefficient according to the power price demand.
More specifically, before the step of obtaining the load demand change estimated value information at any time of multiple days by calculating the electricity price demand response elastic matrix and the original electricity consumption-current day electricity price change rate product vector information, the method further includes:
acquiring initial power consumption information of a first moment according to historical load information of each moment of the multiple days;
acquiring the electricity price variable quantity information of 24 moments of the day at which the first moment is located according to the historical electricity price information of each moment of the multiple days;
and obtaining the original power consumption-daily electricity price change rate product vector information according to the initial power consumption information at the first moment and the electricity price variable information at 24 moments of the day where the first moment is.
More specifically, the step of obtaining the final predicted daily load information according to the optimized electricity price demand response elastic matrix specifically includes:
obtaining the information of the predicted daily electricity price and the information of the predicted daily load to obtain the information of the change rate of the predicted daily electricity price;
obtaining predicted daily response load information according to the predicted daily electricity price change rate information and the optimized electricity price demand response elastic matrix;
and superposing the basic load information of the forecast day and the response load information of the forecast day to obtain the final load forecast information of the forecast day.
More specifically, before the step of superimposing the predicted daily base load information and the predicted daily response load information, the method further includes:
constructing prediction day characteristic matrix information;
performing principal component analysis on the feature matrix information, and selecting similar day information;
and obtaining the basic load of the forecast day by a CS-SVM short-term load forecasting method according to the similar day information.
In a second aspect, an embodiment of the present invention provides a load prediction apparatus based on demand price elastic correction, including:
the first calculation module is used for obtaining an electricity price demand response elastic matrix according to the historical load demand change rate at each moment of multiple days and the historical electricity price change rate at each moment of multiple days;
the second calculation module is used for calculating and obtaining load demand change estimated value information at any moment in multiple days according to the electricity price demand response elastic matrix and the original electricity consumption-daily electricity price change rate product vector information;
the reconstruction error module is used for constructing a minimum function of the reconstruction error of the load demand variation according to the load demand variation estimated value information and the original power consumption-daily electricity price variation rate product vector information;
and the prediction module is used for optimizing the minimum function of the load demand variation reconstruction error through a wolf optimization algorithm, obtaining an optimized response elastic matrix when a preset condition is met, and obtaining final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the demand price elastic correction-based load prediction method according to the first aspect when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the demand price elastic correction-based load prediction method according to the first aspect.
According to the load prediction method and device based on demand price elastic correction, the load is divided into the basic load and the demand response load to be predicted respectively, the electricity price demand response elastic coefficient is constructed from the self-response elasticity and cross-response elasticity angles, the minimum error function is reconstructed by constructing the load demand variation, the optimized response elastic matrix is obtained by applying the gray wolf optimization algorithm, the demand response load is predicted, the overall load combination prediction method in the demand response environment is established on the basis of the basic load prediction obtained by the basic load prediction method based on the similar day, the load curves before and after the load response are predicted accurately, the basis is provided for the safe scheduling of the power system and the ordered performance of the power market, and the method and device have important significance for the better implementation of the demand response strategy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flowchart illustrating a method for load forecasting based on demand price elastic correction according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for predicting base load according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a load forecasting apparatus based on price demand flexible correction according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart illustrating a method for load forecasting based on demand price elastic correction according to an embodiment of the present invention, as shown in fig. 1, including:
step S1, obtaining an electricity price demand response elastic matrix according to the historical load demand change rate at each moment of multiple days and the historical electricity price change rate at each moment of multiple days;
step S2, calculating to obtain the load demand change estimated value information at any time in multiple days according to the electricity price demand response elastic matrix and the original electricity consumption-the-day electricity price change rate product vector information;
step S3, constructing a load demand variation reconstruction error minimum function according to the load demand variation estimated value information and the original power consumption-daily electricity price variation rate product vector information;
and step S4, optimizing the minimum function of the load demand variation reconstruction error through a wolf optimization algorithm, and obtaining an optimized electricity price demand response elastic matrix when a preset condition is met so as to obtain final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix.
Specifically, the historical load demand change rate at each time of multiple days and the historical electricity price change rate at each time of multiple days described in the embodiment of the present invention are obtained by responding to the historical electricity price information and the historical load information in the previous and subsequent power grid historical data, and each time of multiple days in the embodiment of the present invention refers to unspecified multiple days in the historical data, and 24 times exist each day, that is, each time may refer to one hour.
The electricity price demand response elastic matrix described in the embodiment of the present invention is an electricity price demand response elastic matrix composed of an electricity price demand self-response elastic coefficient at the same time and an electricity price demand cross-response elastic coefficient at different times.
The load demand variation described in the embodiment of the present invention refers to a difference between the corresponding load and the demand load.
The electricity price demand response elastic matrix is specifically as follows:
wherein E (i, j) is an element of the ith row and the jth column of the electricity price demand response elastic matrix E and represents the influence of the electricity price change at the time j on the load change at the time i.
The vector information of the product of the original power consumption and the daily electricity price change rate described in the embodiment of the invention specifically refers to the initial power consumption in the ith time period of the mth day and the achievement vector of the electricity price change rate in 24 time periods of the day, and the vector information is 1 × 24 dimension.
The method for calculating the load demand change estimated value information at any moment in multiple days specifically means that the demand change rate delta q in the ith period of M days is calculated through electricity price demand response elasticityi mIs estimated value of
Namely, it is
Wherein e (i, j) is the price demand response elastic matrix vector, qi mThe method is the vector information of the product of the original electricity consumption and the change rate of the electricity price on the day.
The construction of the minimum function of the reconstruction error of the load demand variation described in the embodiment of the present invention refers to an objective function with the minimum reconstruction error function of the demand variation in the i time period, that is:
wherein q isi mThe vector information of the product of the original electricity consumption and the change rate of the electricity price on the day,
estimate information is predicted for load demand change.
The optimization process through the gray wolf optimization algorithm described in the embodiment of the invention means that an optimal solution is output to the minimum function of the load demand variation reconstruction error through the gray wolf optimization algorithm each time, then i +1 is repeatedly optimized through the gray wolf algorithm until i is more than or equal to 24, a plurality of optimal solutions are obtained, and therefore the optimized electricity price demand response elastic matrix is obtained.
Specifically, the scale of the wolf colony is set to be D, and the maximum iteration number is set to be tmaxDirection correction probability PVA 1 is mixing Ei(1×24)The 24 elements of (2) are set as the initial coordinate space of the wolf pack.
Updating the positions of the wolfs according to rules of surrounding, hunting, updating and the like when the gray wolf is hunted, generating a new generation of individuals, and combining the parent wolf and the offspring wolf into a new wolf group D by adopting a elite maintenance strategy.
Judging whether population iteration reaches the maximum value ymaxIf yes, carrying out the next step; otherwise, the head wolf is replaced, the wolf group position is updated by adopting rapid non-inferior solution sequencing, and the iteration time t is t + 1.
Judging whether i is more than or equal to 24, if so, carrying out the next step; otherwise, i is i +1, and the optimization of the response coefficient at the next moment is continued until i is 24, and the response elastic matrix is obtained.
Obtaining the information of the change rate of the predicted daily electricity price according to the electricity price information and the predicted daily load information of the predicted day, then obtaining the information of the predicted daily response load by combining the optimized electricity price demand response elastic matrix, obtaining the basic load prediction by a similar daily basic load prediction method, and finally superposing the predicted daily basic load and the predicted daily response load information to obtain the final load prediction information of the predicted day.
The method of the embodiment of the invention also comprises the following steps:
and aiming at the demand response load curve, introducing four clustering indexes, namely a maximum load reduction proportion, a minimum load increase proportion, a load reduction peak-valley difference proportion and a maximum peak-valley load difference proportion index, clustering the demand response load curve to respectively obtain a clustered maximum load reduction electricity price demand elastic matrix, a clustered minimum load increase electricity price demand elastic matrix, a load reduction peak-valley difference electricity price demand elastic matrix and a clustered maximum peak-valley load difference electricity price demand elastic matrix.
And respectively reconstructing a minimum error function by constructing a load demand variation quantity reconstruction function and obtaining an optimized response elastic matrix by using a wolf optimization algorithm according to the clustered maximum load reduction electricity price demand elastic matrix, minimum load increase electricity price demand elastic matrix, load reduction peak-valley difference electricity price demand elastic matrix and maximum peak-valley load difference electricity price demand elastic matrix, thereby realizing the prediction of the demand response load. By the method of clustering prior to analysis, the algorithm operation amount can be effectively reduced, the algorithm convergence is accelerated, and the prediction accuracy is ensured.
The embodiment of the invention carries out prediction respectively by decomposing the load into the basic load and the demand response load, constructs the electricity price demand response elastic coefficient from the self-response elasticity and cross-response elasticity angles, reconstructs the error minimum function by constructing the load demand variation, and obtains the optimized response elastic matrix by applying the wolf optimization algorithm, thereby realizing the prediction of the demand response load.
On the basis of the above embodiment, before the step of obtaining the electricity price demand response elastic matrix according to the historical load demand change rate at each time of multiple days and the historical electricity price change rate at each time of multiple days, the method further includes:
acquiring historical electricity price information at each moment of multiple days and historical load information at each moment of multiple days;
obtaining the historical electricity price change rate of each time of the multiple days according to the historical electricity price information of each time of the multiple days, and obtaining the historical load demand change rate of each time of the multiple days according to the historical load information of each time of the multiple days;
wherein each day includes 24 moments.
The step of obtaining the electricity price demand response elastic matrix according to the historical load demand change rate at each moment of the multiple days and the historical electricity price change rate at each moment of the multiple days specifically includes:
acquiring the self-response elastic coefficient of the electricity price demand at the same moment;
acquiring cross response elastic coefficients of electricity price requirements at different moments;
and forming a power price demand response elastic matrix from the corresponding elastic coefficient and the power price demand cross response elastic coefficient according to the power price demand.
Specifically, the response relationship between the electricity price and the electricity demand of the user can be expressed by an elastic coefficient. Rate of change of power demand Δ q at the same timeiAnd rate of change of electricity price Δ piThe ratio is the self-response elastic coefficient of the electricity price demand, and the calculation formula is as follows:
wherein q isi0And q isiThe demand before and after the user response at the moment i respectively; p is a radical ofi0And piThe original electricity price and the response electricity price at the moment i are respectively.
Rate of change of demand Δ q at a certain timeiRate of change of electricity price Δ p at another timejThe ratio is the cross response elastic coefficient of the electricity price demand, and the calculation formula is as follows:
wherein p isj0And pjThe original electricity price and the response electricity price at the moment j are respectively.
The response elastic matrix composed of self-response elastic coefficient and cross-response elastic coefficient is
Wherein E (i, j) is an element of the ith row and the jth column of the electricity price demand response elastic matrix E and represents the influence of the electricity price change at the time j on the load change at the time i.
According to the embodiment of the invention, the electricity price demand response elastic matrix is effectively constructed through the electricity price demand self-response elastic coefficient at the same moment and the electricity price demand cross-response elastic coefficient at different moments, so that the subsequent steps can be favorably carried out.
On the basis of the above embodiment, before the step of obtaining the load demand change estimated value information at any time of multiple days by calculating the electricity price demand response elastic matrix and the original electricity consumption-daily electricity price change rate product vector information, the method further includes:
acquiring initial power consumption information of a first moment according to historical load information of each moment of the multiple days;
acquiring the electricity price variable quantity information of 24 moments of the day at which the first moment is located according to the historical electricity price information of each moment of the multiple days;
and obtaining the original power consumption-daily electricity price change rate product vector information according to the initial power consumption information at the first moment and the electricity price variable information at 24 moments of the day where the first moment is.
Specifically, the first time described in the embodiment of the present invention refers to any time among the multiple days of the historical data.
Load demand variation Δ q at M days ii(m) and the rate of change of electricity price at each time Δ pi(m)：
Wherein i is 1,2, …,24, M is 1,2, …, M, Δ qi m＝qi m-qi0 mThe rate of change of power demand is Δ qi。
The vector q of the product of the initial electricity consumption of the ith period of M days and the electricity price change rate of 24 periods of the dayi(M×24)：
Wherein the content of the first and second substances,
Pj0 minitial price of electricity, P, for the j-th time period on the m-th dayj mThe electricity price of the j time period of the mth day; original power consumption-daily electricity price change rate product vector information
The vector of the product of the original electricity consumption in the ith period of the mth day and the electricity price change rate in 24 periods of the day is 1 multiplied by 24 dimensions.
According to the embodiment of the invention, the initial power consumption information at the first moment and the electricity price variable information at 24 moments of the day at the first moment are calculated, so that the subsequent prediction of the demand variable quantity is facilitated, and the realization of load prediction is facilitated.
On the basis of the above embodiment, the step of obtaining the final predicted daily load prediction information according to the optimized electricity price demand response elastic matrix specifically includes:
obtaining the information of the predicted daily electricity price and the information of the predicted daily load to obtain the information of the change rate of the predicted daily electricity price;
obtaining predicted daily response load information according to the predicted daily electricity price change rate information and the optimized electricity price demand response elastic matrix;
and superposing the basic load information of the forecast day and the response load information of the forecast day to obtain the final load forecast information of the forecast day.
Specifically, the information of the predicted daily electricity prices and the information of the predicted daily loads described in the embodiments of the present invention may be searched through a prior database, for example, a network of the u.s.pjm power market may search specific data.
The embodiment of the present invention describes that obtaining the predicted daily response load information according to the predicted daily electricity price change rate information and the optimized electricity price demand response elastic matrix specifically includes:
where E (i, j) is an element in the ith row and jth column of the response elastic matrix E, and represents the influence of the electricity price change at the time j on the load change at the time i.
The superposition of the basic load information and the response load information of the prediction day described in the embodiment of the invention may specifically mean that the basic load information and the response load information of the prediction day are added, so as to obtain the final load prediction information of the prediction day.
The load is divided into the basic load and the demand response load to be respectively predicted, and the basic load and the demand response load are superposed, so that the load curves before and after the load response are accurately predicted, a basis is provided for the safe dispatching and the ordered electricity market of the power system, and the method and the device have important significance for better implementation of the demand response strategy.
On the basis of the above embodiment, before the step of superimposing the predicted daily base load and the predicted daily response load information, the method further includes:
constructing prediction day characteristic matrix information;
performing principal component analysis on the feature matrix information, and selecting similar day information;
and obtaining the basic load of the forecast day by a CS-SVM short-term load forecasting method according to the similar day information.
Specifically, fig. 2 is a flowchart of a basic load prediction method described in an embodiment of the present invention, and as shown in fig. 2, the method includes constructing a feature matrix according to load data and meteorological factors, holiday types, maximum air temperature, and other factors, then analyzing the feature matrix by using a principal component analysis method, performing dimensionality reduction optimization on the feature matrix to obtain a dimensionality reduction optimized feature matrix, calculating distances of the feature matrices after dimensionality reduction optimization, selecting the feature matrices as similar days if the distances are smaller than a preset value, and obtaining a predicted daily basic load by using a CS-SVM short-term load prediction method.
The embodiment of the invention obtains the basic load prediction through the traditional method, so that the basic load and the demand response load can be conveniently superposed to obtain more accurate prediction.
Fig. 3 is a schematic structural diagram of a load prediction apparatus based on price demand elastic correction according to an embodiment of the present invention, as shown in fig. 3, including: a first calculation module 310, a second calculation module 320, a reconstruction error module 330, and a prediction module 340; the first calculating module 310 is configured to obtain an electricity price demand response elastic matrix according to the historical load demand change rate at each moment of multiple days and the historical electricity price change rate at each moment of multiple days; the second calculating module 320 is configured to calculate, through the electricity price demand response elastic matrix and the original electricity consumption-daily electricity price change rate product vector information, to obtain load demand change pre-evaluation value information at any time of multiple days; the reconstruction error module 330 is configured to construct a minimum function of a load demand variation reconstruction error according to the load demand variation estimated value information and the original power consumption-daily electricity price change rate product vector information; the prediction module 340 is configured to optimize the minimum function of the load demand variation reconstruction error through a grey wolf optimization algorithm, and when a preset condition is met, obtain an optimized response elastic matrix, so as to obtain final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix.
The apparatus provided in the embodiment of the present invention is used for executing the above method embodiments, and for details of the process and the details, reference is made to the above embodiments, which are not described herein again.
The load is divided into the basic load and the demand response load to be respectively predicted, the electricity price demand response elastic coefficient is constructed from the self-response elasticity and cross-response elasticity angles, the load demand variation quantity reconstruction error minimum function is constructed, the optimized response elastic matrix is obtained by applying the wolf optimization algorithm, the demand response load is predicted, the total load combination prediction method in the demand response environment is established on the basis of obtaining the basic load prediction based on the similar day basic load prediction method, the load curves before and after the load response are accurately predicted, the basis is provided for the safety scheduling of the power system and the ordered performance of the power market, and the method has important significance for better implementation of the demand response strategy.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 4, the electronic device may include: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may call logic instructions in the memory 430 to perform the following method: obtaining an electricity price demand response elastic matrix according to the historical load demand change rate at each moment of multiple days and the historical electricity price change rate at each moment of multiple days; calculating to obtain load demand change estimated value information at any moment in multiple days according to the electricity price demand response elastic matrix and original electricity consumption-current day electricity price change rate product vector information; constructing a load demand variation quantity reconstruction error minimum function according to the load demand variation estimated value information and original power consumption-daily electricity price change rate product vector information; and optimizing the minimum function of the load demand variation reconstruction error through a wolf optimization algorithm, and obtaining an optimized electricity price demand response elastic matrix when a preset condition is met so as to obtain final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
An embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer can execute the methods provided by the above method embodiments, for example, the method includes: obtaining an electricity price demand response elastic matrix according to the historical load demand change rate at each moment of multiple days and the historical electricity price change rate at each moment of multiple days; calculating to obtain load demand change estimated value information at any moment in multiple days according to the electricity price demand response elastic matrix and original electricity consumption-current day electricity price change rate product vector information; constructing a load demand variation quantity reconstruction error minimum function according to the load demand variation estimated value information and original power consumption-daily electricity price change rate product vector information; and optimizing the minimum function of the load demand variation reconstruction error through a wolf optimization algorithm, and obtaining an optimized electricity price demand response elastic matrix when a preset condition is met so as to obtain final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix.
Embodiments of the present invention provide a non-transitory computer-readable storage medium storing server instructions, where the server instructions cause a computer to execute the method provided in the foregoing embodiments, for example, the method includes: obtaining an electricity price demand response elastic matrix according to the historical load demand change rate at each moment of multiple days and the historical electricity price change rate at each moment of multiple days; calculating to obtain load demand change estimated value information at any moment in multiple days according to the electricity price demand response elastic matrix and original electricity consumption-current day electricity price change rate product vector information; constructing a load demand variation quantity reconstruction error minimum function according to the load demand variation estimated value information and original power consumption-daily electricity price change rate product vector information; and optimizing the minimum function of the load demand variation reconstruction error through a wolf optimization algorithm, and obtaining an optimized electricity price demand response elastic matrix when a preset condition is met so as to obtain final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A load prediction method based on demand price elastic correction is characterized by comprising the following steps:
obtaining an electricity price demand response elastic matrix according to the historical load demand change rate at each moment of multiple days and the historical electricity price change rate at each moment of multiple days;
calculating to obtain load demand change estimated value information at any moment in multiple days according to the electricity price demand response elastic matrix and original electricity consumption-current day electricity price change rate product vector information;
constructing a load demand variation quantity reconstruction error minimum function according to the load demand variation estimated value information and original power consumption-daily electricity price change rate product vector information;
and optimizing the minimum function of the load demand variation reconstruction error through a wolf optimization algorithm, and obtaining an optimized electricity price demand response elastic matrix when a preset condition is met so as to obtain final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix.
2. The demand price elasticity correction-based load prediction method according to claim 1, wherein before the step of obtaining the electricity price demand response elasticity matrix according to the historical load demand change rate at each time of the multiple days and the historical electricity price change rate at each time of the multiple days, the method further comprises:
acquiring historical electricity price information at each moment of multiple days and historical load information at each moment of multiple days;
obtaining the historical electricity price change rate of each time of the multiple days according to the historical electricity price information of each time of the multiple days, and obtaining the historical load demand change rate of each time of the multiple days according to the historical load information of each time of the multiple days;
wherein each day includes 24 moments.
3. The demand price elastic correction-based load prediction method according to claim 1, wherein the step of obtaining the electricity price demand response elastic matrix according to the historical load demand change rate at each time of multiple days and the historical electricity price change rate at each time of multiple days specifically comprises:
acquiring the self-response elastic coefficient of the electricity price demand at the same moment;
acquiring cross response elastic coefficients of electricity price requirements at different moments;
and forming a power price demand response elastic matrix from the corresponding elastic coefficient and the power price demand cross response elastic coefficient according to the power price demand.
4. The demand price elastic correction-based load forecasting method according to claim 2, wherein before the step of calculating the load demand change forecast information at any one of a plurality of days through the electricity demand response elasticity matrix and the original electricity consumption-daily electricity demand change rate product vector information, the method further comprises:
acquiring initial power consumption information of a first moment according to historical load information of each moment of the multiple days;
acquiring the electricity price variable quantity information of 24 moments of the day at which the first moment is located according to the historical electricity price information of each moment of the multiple days;
and obtaining the original power consumption-daily electricity price change rate product vector information according to the initial power consumption information at the first moment and the electricity price variable information at 24 moments of the day where the first moment is.
5. The demand price elastic correction-based load prediction method according to claim 1, wherein the step of obtaining the final predicted daily load prediction information according to the optimized electricity price demand response elastic matrix specifically comprises:
obtaining the information of the predicted daily electricity price and the information of the predicted daily load to obtain the information of the change rate of the predicted daily electricity price;
obtaining predicted daily response load information according to the predicted daily electricity price change rate information and the optimized electricity price demand response elastic matrix;
and superposing the basic load information of the forecast day and the response load information of the forecast day to obtain the final load forecast information of the forecast day.
6. The demand price elastic correction-based load prediction method according to claim 5, wherein before the step of superimposing the predicted daily base load and the predicted daily response load information, the method further comprises:
constructing prediction day characteristic matrix information;
performing principal component analysis on the feature matrix information, and selecting similar day information;
and obtaining the basic load of the forecast day by a CS-SVM short-term load forecasting method according to the similar day information.
7. A demand price elastic correction-based load prediction apparatus, comprising:
the first calculation module is used for obtaining an electricity price demand response elastic matrix according to the historical load demand change rate at each moment of multiple days and the historical electricity price change rate at each moment of multiple days;
the second calculation module is used for calculating and obtaining load demand change estimated value information at any moment in multiple days according to the electricity price demand response elastic matrix and the original electricity consumption-daily electricity price change rate product vector information;
the reconstruction error module is used for constructing a minimum function of the reconstruction error of the load demand variation according to the load demand variation estimated value information and the original power consumption-daily electricity price variation rate product vector information;
and the prediction module is used for optimizing the minimum function of the load demand variation reconstruction error through a wolf optimization algorithm, obtaining an optimized response elastic matrix when a preset condition is met, and obtaining final load prediction information of a prediction day according to the optimized electricity price demand response elastic matrix.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the demand price elasticity correction based load prediction method according to any one of claims 1 to 6.
9. A non-transitory computer readable storage medium, having a computer program stored thereon, wherein the computer program, when being executed by a processor, implements the steps of the demand price elasticity correction based load prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910990355.2A CN112686770A (en) | 2019-10-17 | 2019-10-17 | Load prediction method and device based on demand price elastic correction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910990355.2A CN112686770A (en) | 2019-10-17 | 2019-10-17 | Load prediction method and device based on demand price elastic correction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112686770A true CN112686770A (en) | 2021-04-20 |
Family
ID=75444666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910990355.2A Pending CN112686770A (en) | 2019-10-17 | 2019-10-17 | Load prediction method and device based on demand price elastic correction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686770A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116885704A (en) * | 2023-07-07 | 2023-10-13 | 国网北京市电力公司 | User baseline load estimation method and system for multiple composite interaction demand response |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636010A (en) * | 2018-11-23 | 2019-04-16 | 国网湖北省电力有限公司 | Provincial power network short-term load forecasting method and system based on correlative factor matrix |
| CN109672184A (en) * | 2018-12-12 | 2019-04-23 | 国网江西省电力有限公司电力科学研究院 | One kind distribution network voltage control method of photovoltaic containing high proportion and system |
-
2019
- 2019-10-17 CN CN201910990355.2A patent/CN112686770A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636010A (en) * | 2018-11-23 | 2019-04-16 | 国网湖北省电力有限公司 | Provincial power network short-term load forecasting method and system based on correlative factor matrix |
| CN109672184A (en) * | 2018-12-12 | 2019-04-23 | 国网江西省电力有限公司电力科学研究院 | One kind distribution network voltage control method of photovoltaic containing high proportion and system |
Non-Patent Citations (4)
| Title |
|---|
| 刘孝杰: "计及需求响应和电力市场作用的主动配电系统负荷预测研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 3, pages 15 - 83 * |
| 刘孝杰等: "面向主动响应和售电市场的主动配电系统负荷预测", 《电力系统及其自动化学报》, vol. 29, no. 2, pages 121 - 128 * |
| 徐达宇等: "改进GWO优化SVM的云计算资源负载短期预测研究", 《计算机工程与应用》, vol. 53, no. 7, pages 68 - 73 * |
| 李文博等: "考虑不确定性的区域能源互联网源-荷-储协调优化", 《现代电力》, vol. 36, no. 3, pages 11 - 18 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116885704A (en) * | 2023-07-07 | 2023-10-13 | 国网北京市电力公司 | User baseline load estimation method and system for multiple composite interaction demand response |
| CN116885704B (en) * | 2023-07-07 | 2024-05-24 | 国网北京市电力公司 | User baseline load estimation method and system for multiple composite interaction demand response |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kabir et al. | Neural network-based uncertainty quantification: A survey of methodologies and applications | |
| CN113099729B (en) | Deep reinforcement learning of production schedule | |
| Cheng et al. | Probabilistic residential load forecasting based on micrometeorological data and customer consumption pattern | |
| JP5248372B2 (en) | Power generation plan creation method, device, program, and storage device | |
| CN110019420B (en) | Data sequence prediction method and computing device | |
| CN106779177A (en) | Multiresolution wavelet neutral net electricity demand forecasting method based on particle group optimizing | |
| CN109815541B (en) | Method and device for dividing rail transit vehicle product parts and modules and electronic equipment | |
| CN113656691A (en) | Data prediction method, device and storage medium | |
| Yeze et al. | Stock price prediction based on information entropy and artificial neural network | |
| CN112132356A (en) | Stock price prediction method based on space-time diagram attention mechanism | |
| CN112686770A (en) | Load prediction method and device based on demand price elastic correction | |
| CN114202174A (en) | Electricity price risk grade early warning method and device and storage medium | |
| CN112686693A (en) | Method, system, equipment and storage medium for predicting marginal electricity price of electric power spot market | |
| CN110705738B (en) | Intelligent electricity utilization stimulation demand response method and system based on artificial intelligence | |
| CN109784748B (en) | User electricity consumption behavior identification method and device under market competition mechanism | |
| CN112836885B (en) | Combined load prediction method, combined load prediction device, electronic equipment and storage medium | |
| CN112101612A (en) | Prediction method of town gas usage, storage medium and terminal equipment | |
| CN116316617A (en) | Multi-station intelligent fusion new energy generation power region prediction method and system | |
| CN112039111A (en) | Method and system for participating in peak regulation capacity of power grid by new energy microgrid | |
| CN115049458A (en) | Commodity pushing method and device based on user crowd modeling, medium and equipment | |
| CN114169923A (en) | Photovoltaic power station power prediction method, system, terminal and storage medium | |
| CN112950033B (en) | Reservoir dispatching decision method and system based on reservoir dispatching rule synthesis | |
| CN113962747A (en) | Order prediction method and device, electronic equipment and storage medium | |
| CN112330017A (en) | Power load prediction method, power load prediction device, electronic device, and storage medium | |
| CN114240052A (en) | Combined sales strategy optimization method and system based on genetic algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |