CN115600825B - Power load scheduling method and device, storage medium and electronic equipment - Google Patents
Power load scheduling method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN115600825B CN115600825B CN202211576013.4A CN202211576013A CN115600825B CN 115600825 B CN115600825 B CN 115600825B CN 202211576013 A CN202211576013 A CN 202211576013A CN 115600825 B CN115600825 B CN 115600825B
- Authority
- CN
- China
- Prior art keywords
- response
- load
- load end
- value
- end set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000004044 response Effects 0.000 claims abstract description 405
- 238000001914 filtration Methods 0.000 claims abstract description 23
- 230000000694 effects Effects 0.000 claims description 42
- 238000002360 preparation method Methods 0.000 claims description 35
- 230000033228 biological regulation Effects 0.000 claims description 23
- 230000005611 electricity Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000011084 recovery Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 230000001105 regulatory effect Effects 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 12
- 230000008901 benefit Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005485 electric heating Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses a power load scheduling method and device, a storage medium and electronic equipment, wherein the method comprises the following steps: collecting response index data of each load end in a first load end set in a response area in multiple dimensions; respectively calculating response recommended values of each load end in the first load end set in multiple dimensions according to the response index data, wherein each dimension corresponds to one response recommended value; constructing response admittance conditions by adopting response index data, and filtering the first load end set based on the response admittance conditions to obtain a second load end set; and calculating the total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value. The invention solves the technical problem of low power load dispatching efficiency in the related technology, and can accurately realize load coordination and reduce the pressure on peak load of a power grid.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a power load scheduling method and device, a storage medium and electronic equipment.
Background
In the related art, the requirements of various aspects of society on electric power are rapidly increased along with the rapid development of national economy, the upgrading and adjustment of industrial structures and the continuous improvement of the living standard of people.
During the summer period of windward, the electricity utilization coincidence characteristic is represented by the maximum load which continuously and rapidly grows, the peak-valley difference which continuously expands, the load rate which continuously decreases and the annual maximum load utilization hours, the regional and seasonal electricity deficiency happens, and the safe, stable and economic operation of the electric power system is difficult to ensure. When the power grid distributes load, the power is strictly distributed according to the pre-divided areas, so that the power of partial areas is excessive, the partial areas are not available, the power resource is wasted, and the power is scheduled through the experience of network distribution personnel, so that the efficiency is low and the error rate is high.
In view of the above problems in the related art, no effective solution has been found yet.
Disclosure of Invention
The embodiment of the invention provides a power load scheduling method and device, a storage medium and electronic equipment.
According to an aspect of the embodiments of the present application, there is provided a scheduling method of an electrical load, including: collecting response index data of each load end in a first load end set in a response area in multiple dimensions; respectively calculating response recommended values of each load end in the first load end set in multiple dimensions according to the response index data, wherein each dimension corresponds to one response recommended value; constructing a response admittance condition by adopting the response index data, and filtering the first load end set based on the response admittance condition to obtain a second load end set; and calculating the total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value.
Further, collecting response index data of each load end in the first load end set in the response area in multiple dimensions includes: collecting response quantity index data of each load end in a first load end set in a response area, wherein the response quantity index data comprises: security load, highest electricity load, electricity reference value; collecting response rate index data of each load end in a first load end set in a response area, wherein the response rate index data comprises: adjusting the preparation time and the response time; collecting response economic cost index data of each load end in a first load end set in a response area; and acquiring response reliability index data of each load end in the first load end set in the response area.
Further, the response recommended value includes a first response recommended value of a response volume dimension, and calculating the response recommended value of each load end in the first load end set in a plurality of dimensions according to the response index data includes: for each load end in the first load end set, reading a real-time power consumption load reference value, a security load and a load to be adjusted from the response index data; calculating a difference between the electricity load reference value and the security load; positioning a first gradient range in which the difference value is located in a first preset gradient space, wherein the maximum value of the first preset gradient space is a disaster recovery coefficient of the load to be adjusted, the minimum value is the load to be adjusted, and the disaster recovery coefficient is larger than 1; searching a first index value matched with the first gradient range, and configuring the first index value as the first response recommended value, wherein the first index value is in negative correlation with the first gradient range.
Further, the response recommended value includes a second response recommended value of a response rate dimension, and calculating the response recommended value of each load end in the first load end set in a plurality of dimensions according to the response index data includes: for each load end in the first load end set, reading an adjustment preparation time and an adjustment response time from the response index data; calculating the sum of the adjustment preparation time and the adjustment response time; positioning a second gradient range in which the sum value is located in a second preset gradient space; and searching a second index value matched with the second gradient range, and configuring the second index value as the second response recommended value, wherein the second index value is in negative correlation with the second gradient range.
Further, the response recommended value includes a third response recommended value of a response economic cost dimension, and calculating the response recommended value of each load end in the first load end set in a plurality of dimensions according to the response index data includes: for each load end in the first load end set, reading a load cost value from the response index data; inputting the load cost value into a pre-trained time sequence prediction model, and outputting a load effect value of the load cost value, wherein the time sequence prediction model is a pre-trained neural network model and is used for outputting a corresponding load effect value based on the load cost value; and configuring the load effect value as the third response recommended value.
Further, the time series prediction model is a Prophet model, and before inputting the load cost value into the pre-trained time series prediction model, the method further comprises: collecting training data of a historical time sequence; determining a time unit of the historical time sequence, and dividing the training data into a plurality of sub-data according to the time unit; predicting a load effect value of each time period by adopting an initial regression coefficient; gradient descent fitting is performed by adopting the following formula until a preset stopping condition is met:
wherein ,
for the regression coefficient of the current time period, +.>
And for the regression coefficient of the previous period of the current time period, alpha is a dynamic adjustment step length, and the preset stopping condition comprises: the difference between the predicted load effect value of the current time period and the actual load effect value of the current time period is smaller than a preset threshold value; />
For the predicted load effect value of the current time period,/->
The actual load effect value of the current time period is represented by i, which is a period sequence number; and configuring the current regression coefficient after stopping fitting as the regression coefficient of the Prophet model to obtain the time sequence prediction model.
Further, the response recommended value includes a fourth response recommended value of a response reliability dimension, and calculating the response recommended value of each load end in the first load end set in a plurality of dimensions according to the response index data includes: for each load end in the first load end set, reading a historical peak shaving contribution amount and a historical peak shaving task amount from the response index data, wherein the historical peak shaving contribution amount is used for representing the actual total power of the corresponding load end in the historical time for participating in the power grid peak shaving consumption, and the historical peak shaving task amount is used for representing the total power distributed by the corresponding load end in the historical time; calculating the deviation amount of the historical peak shaving contribution amount relative to the historical peak shaving task amount; the inverse of the deviation amount is configured as the fourth response recommendation value.
Further, constructing a response admittance condition by adopting the response index data, and filtering the first load end set based on the response admittance condition, wherein the obtaining a second load end set comprises: for each load end in the first load end set, reading actual adjustment duration from the response index data, referring to the adjustment duration, adjusting preparation time, adjusting response time, historical peak shaving contribution and historical peak shaving task quantity; judging whether the actual adjustment duration is greater than or equal to a reference adjustment duration, judging whether the adjustment preparation time and the adjustment response time are less than or equal to preset disaster recovery time, calculating the deviation amount of the historical peak regulation contribution amount relative to the historical peak regulation task amount, and judging whether the deviation amount is less than or equal to preset deviation; and if the actual adjustment duration is greater than or equal to the reference adjustment duration, the adjustment preparation time and the adjustment response time are less than or equal to a preset disaster recovery time, and if the deviation is less than or equal to a preset deviation, filtering the corresponding load ends from the first load end set, and adding the load ends to the second load end set.
Further, calculating a total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value includes: for each load end in the second load end set, acquiring a weight coefficient combination of the load end in the multiple dimensions, wherein the weight coefficient combination comprises multiple weight coefficients, each weight coefficient corresponds to a response recommended value of one dimension, and the sum of all weight coefficients is 1; the weight coefficient combination and the weight coefficient combination of the plurality of dimensions are adopted for weighted summation, so that the total recommended value of the corresponding load end is obtained; sorting the load ends in the second load end set in a descending order according to the total recommended value; acquiring the load to be adjusted of each load end in the second load end set from the response index data; calculating the total load of the power grid to be peak regulated in the current peak regulation period; and sequentially and stepwise selecting a plurality of load ends in the second load end set until the sum of loads to be adjusted of the currently selected load ends reaches the total power of the power grid, and determining the currently selected load ends as target load ends for load response to be executed.
According to another aspect of the embodiments of the present application, there is also provided a scheduling apparatus of an electrical load, including: the acquisition module is used for acquiring response index data of each load end in the first load end set in the response area in multiple dimensions; the calculation module is used for calculating response recommended values of each load end in the first load end set in multiple dimensions according to the response index data, wherein each dimension corresponds to one response recommended value; the filtering module is used for constructing response admittance conditions by adopting the response index data, and filtering the first load end set based on the response admittance conditions to obtain a second load end set; the selecting module is used for calculating the total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value.
Further, the acquisition module includes: the first acquisition unit is used for acquiring response quantity index data of each load end in the first load end set in the response area, wherein the response quantity index data comprises: security load, highest electricity load, electricity reference value; the second acquisition unit is used for acquiring response rate index data of each load end in the first load end set in the response area, wherein the response rate index data comprises: adjusting the preparation time and the response time; the third acquisition unit is used for acquiring response economic cost index data of each load end in the first load end set in the response area; and acquiring response reliability index data of each load end in the first load end set in the response area.
Further, the response recommendation value includes a first response recommendation value for a response volume dimension, and the computing module includes: the first reading unit is used for reading the real-time power consumption load reference value, the security load and the load to be adjusted from the response index data for each load end in the first load end set; a first calculation unit for calculating a difference between the electricity load reference value and the security load; the first positioning unit is used for positioning a first gradient range in which the difference value is located in a first preset gradient space, wherein the maximum value of the first preset gradient space is the load to be adjusted, the disaster tolerance coefficient is the load to be adjusted, the minimum value is the load to be adjusted, and the disaster tolerance coefficient is larger than 1; and the first configuration unit is used for searching a first index value matched with the first gradient range and configuring the first index value as the first response recommended value, wherein the first index value is in negative correlation with the first gradient range.
Further, the response recommendation value includes a second response recommendation value for a response rate dimension, and the computing module includes: a second reading unit, configured to read, for each load end in the first load end set, an adjustment preparation time and an adjustment response time from the response index data; a second calculation unit for calculating a sum of the adjustment preparation time and the adjustment response time; the second positioning unit is used for positioning a second gradient range in which the sum value is located in a second preset gradient space; and the second configuration unit is used for searching a second index value matched with the second gradient range and configuring the second index value into the second response recommended value, wherein the second index value is in negative correlation with the second gradient range.
Further, the response recommendation value includes a third response recommendation value for a response economic cost dimension, and the computing module includes: a third reading unit, configured to read, for each load end in the first load end set, a load cost value from the response index data; the prediction unit is used for inputting the load cost value into a pre-trained time sequence prediction model and outputting a load effect value of the load cost value, wherein the time sequence prediction model is a pre-trained neural network model and is used for outputting a corresponding load effect value based on the load cost value; and a third configuration unit configured to configure the load effect value as the third response recommendation value.
Further, the timing prediction model is a propset model, and the apparatus further includes: the sample module is used for collecting training data of a historical time sequence before the calculation module inputs the load cost value into a pre-trained time sequence prediction model; the segmentation module is used for determining a time unit of the historical time sequence and segmenting the training data into a plurality of sub-data according to the time unit; the prediction module is used for predicting the load effect value of each time period by adopting the initial regression coefficient; the fitting module is used for performing gradient descent fitting by adopting the following formula until the preset stopping condition is met:
wherein ,
for the regression coefficient of the current time period, +.>
And for the regression coefficient of the previous period of the current time period, alpha is a dynamic adjustment step length, and the preset stopping condition comprises: the difference between the predicted load effect value of the current time period and the actual load effect value of the current time period is smaller than a preset threshold value; />
For the predicted load effect value of the current time period,/->
The actual load effect value of the current time period is represented by i, which is a period sequence number; a generation module for configuring the fitted current regression coefficient as the regression coefficient of the Prophet model to obtain the time sequence prediction model。
Further, the response recommendation value includes a fourth response recommendation value for a response reliability dimension, the computing module includes: a fourth reading unit, configured to read, for each load end in the first load end set, a historical peak shaving contribution and a historical peak shaving task amount from the response index data, where the historical peak shaving contribution is used to represent an actual total power of the corresponding load end participating in power grid peak shaving consumption in a historical time, and the historical peak shaving task amount is used to represent a total power of the corresponding load end distributed in the historical time; a third calculation unit, configured to calculate a deviation amount of the historical peak shaver contribution amount relative to the historical peak shaver task amount; and a fourth configuration unit configured to configure an inverse of the deviation amount as the fourth response recommendation value.
Further, the filtration module includes: the reading unit is used for reading the actual adjustment duration from the response index data for each load end in the first load end set, referring to the adjustment duration, adjusting the preparation time, adjusting the response time, historical peak shaving contribution and historical peak shaving task quantity; the judging unit is used for judging whether the actual adjustment duration is greater than or equal to the reference adjustment duration, judging whether the adjustment preparation time and the adjustment response time are smaller than or equal to a preset disaster tolerance time, calculating the deviation amount of the historical peak regulation contribution amount relative to the historical peak regulation task amount, and judging whether the deviation amount is smaller than or equal to a preset deviation; and the filtering unit is used for filtering the corresponding load ends from the first load end set and adding the load ends to the second load end set if the actual adjustment duration is greater than or equal to the reference adjustment duration, the adjustment preparation time and the adjustment response time are less than or equal to the preset disaster tolerance time, and the deviation amount is less than or equal to the preset deviation.
Further, the selection module includes: the first computing unit is used for acquiring a weight coefficient combination of the load end in the multiple dimensions aiming at each load end in the second load end set, wherein the weight coefficient combination comprises multiple weight coefficients, each weight coefficient corresponds to a response recommended value of one dimension, and the sum of all weight coefficients is 1; the weight coefficient combination and the weight coefficient combination of the plurality of dimensions are adopted for weighted summation, so that the total recommended value of the corresponding load end is obtained; the sorting unit is used for sorting the load ends in the second load end set in a descending order according to the total recommended value; the obtaining unit is used for obtaining the load to be adjusted of each load end in the second load end set from the response index data; the second calculation unit is used for calculating the total load of the power grid to be peak-regulated in the current peak-regulation period; the selecting unit is used for sequentially and step-by-step selecting a plurality of load ends in the second load end set until the sum of loads to be adjusted of the currently selected load ends reaches the total power of the power grid, and determining the currently selected load ends as target load ends for load response to be executed.
According to another aspect of the embodiments of the present application, there is also provided a storage medium including a stored program that performs the steps described above when running.
According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus; wherein: a memory for storing a computer program; and a processor for executing the steps of the method by running a program stored on the memory.
Embodiments of the present application also provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform the steps of the above method.
According to the invention, the response index data of each load end in multiple dimensions are collected, the response recommended value of each load end in the multiple dimensions is calculated, the admission condition is constructed, finally the total recommended value of each load end in the second load end set is calculated according to the response recommended values in the multiple dimensions, the target load end for load response to be executed is selected, various index data in the multiple dimensions are quantized into the response recommended values, a scheme for screening the response load by combining the priorities in the multiple dimensions is realized, the technical problem of low power load dispatching efficiency in the related art is solved, the load coordination can be accurately realized, the peak load pressure on a power grid is reduced, the power supply cost and the power consumption cost are reduced, and the double effects of power supply and demand balance and economic benefit are realized.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a block diagram of the hardware architecture of a computer according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of scheduling electrical loads according to an embodiment of the invention;
FIG. 3 is a flow chart of a method for providing a load-characteristic-based step response demand side in accordance with the present invention;
FIG. 4 is a block diagram of a power load scheduler according to an embodiment of the present invention;
fig. 5 is a block diagram of an electronic device embodying an embodiment of the present invention.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
The method embodiment provided in the first embodiment of the present application may be executed in a server, a computer, a mobile phone, or a similar computing device. Taking a computer as an example, fig. 1 is a block diagram of a hardware structure of a computer according to an embodiment of the present invention. As shown in fig. 1, the computer may include one or more processors 102 (only one is shown in fig. 1) (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, and optionally, a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those of ordinary skill in the art that the configuration shown in FIG. 1 is merely illustrative and is not intended to limit the architecture of the computer described above. For example, the computer may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a power load scheduling method in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, implement the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory located remotely from processor 102, which may be connected to the computer via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communications provider of a computer. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.
In this embodiment, a power load scheduling method is provided, fig. 2 is a flowchart of a power load scheduling method according to an embodiment of the present invention, and as shown in fig. 2, the flowchart includes the following steps:
s202, acquiring response index data of each load end in a first load end set in a response area in multiple dimensions;
the first load end set in this embodiment includes a plurality of load ends (may be simply referred to as loads), where the load ends may be according to load types, network-changing power stations, areas, electric devices, and the like, such as electric automobile charging piles, intelligent home devices, heat accumulating electric heating devices, electric storage devices, and adjustable industry and commerce.
The response index data in this embodiment refers to index data that affects response amount, response rate, response economic cost, response reliability, and the like, and the response index data in multiple dimensions includes: and responding to the volume index data, the rate index data, the economic cost index data and the reliability index data. The index data of the present embodiment may be a minimum value, a maximum value, a reference value, a rated value, a reference value, or the like.
S204, respectively calculating response recommended values of each load end in the first load end set in multiple dimensions according to the response index data, wherein each dimension corresponds to one response recommended value;
The response recommendation value in this embodiment is used to characterize the priority in the corresponding dimension, and is the quantification of the priority, and the higher the response recommendation value, the higher the priority of the dimension.
S206, constructing response admittance conditions by adopting response index data, and filtering the first load end set based on the response admittance conditions to obtain a second load end set;
the response admittance condition of the embodiment is the lowest condition of the load end which needs to respond to the load, and abnormal load or low-quality load which obviously does not meet the condition can be screened.
S208, calculating the total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value.
After selecting the target load side, the grid dispatching center dispatches power usage (KMW) to the target load side.
Through the steps, the response index data of each load end in multiple dimensions are collected, the response recommended value of each load end in the multiple dimensions is calculated, the admission condition is constructed, finally the total recommended value of each load end in the second load end set is calculated according to the response recommended values in the multiple dimensions, the target load end for load response to be executed is selected, various index data in the multiple dimensions are quantized into the response recommended values, a scheme for screening the response load by combining the priorities in the multiple dimensions is realized, the technical problem of low power load scheduling efficiency in the related art is solved, the load coordination can be accurately realized, the peak load pressure of a power grid is reduced, the power supply cost and the power consumption cost are reduced, and the double effects of power supply and demand balance and economic benefit are realized.
In one implementation manner of this embodiment, collecting response index data of each load end in the first load end set in the response area in multiple dimensions includes: collecting response quantity index data of each load end in a first load end set in a response area, wherein the response quantity index data comprises: security load, highest electricity load, electricity reference value; the method comprises the steps of collecting response rate index data of each load end in a first load end set in a response area, wherein the response rate index data comprise: adjusting the preparation time and the response time; collecting response economic cost index data of each load end in a first load end set in a response area; and acquiring response reliability index data of each load end in the first load end set in the response area.
By adopting the embodiment, the real-time highest electricity load, security load, reference load and the like of different types of loads are collected; all loads are prepared in real time, response economic cost index, deviation percentage of actual execution output of the historical execution output of the peak shaving of the participating power grid and the plan of peak shaving of the participating power grid, historical adjustment duration time, current load capacity to be adjusted and the like.
In one embodiment, the response recommendation value includes a first response recommendation value of a response volume dimension, and calculating the response recommendation value of each load end in the first load end set in multiple dimensions according to the response index data includes: for each load end in the first load end set, reading a real-time power consumption load reference value, a security load and a load to be adjusted from response index data; calculating a difference between the electricity load reference value and the security load; positioning a first gradient range in which a difference value is positioned in a first preset gradient space, wherein the maximum value of the first preset gradient space is a disaster tolerance coefficient of a load to be adjusted, and the minimum value is the load to be adjusted, and the disaster tolerance coefficient is larger than 1; searching a first index value matched with the first gradient range, and configuring the first index value as a first response recommended value, wherein the first index value is in negative correlation with the first gradient range.
In one example, the disaster recovery factor is 2 and the first response recommendation value is
The various load peak shaver response ratings model is as follows: when->
Or->
，/>
The method comprises the steps of carrying out a first treatment on the surface of the When (when)
When (I)>
The method comprises the steps of carrying out a first treatment on the surface of the When->
When (I)>
The method comprises the steps of carrying out a first treatment on the surface of the When->
When (I)>
. wherein ,/>
Recommending a value for the first response;
a real-time electricity load reference value of the load at the moment i; / >
The lowest electricity load which is the load in a certain time period depends on the security load; />
The load to be adjusted is the current load; according to various load regulation calculation models, when +.>
When the adjustable load of various loads is smaller than that to be adjustedThe load is difficult to independently meet the load regulation requirement; when->
When the load adjustable capacity is far larger than the load to be adjusted, the load adjustable capacity is not an intelligent choice, and in the two cases, the load loses response opportunities as the upper boundary and the lower boundary of the gradient interval. When->
The load meets the ideal regulation capacity requirement, and the highest rating score of the load peak regulation response is obtained, namely 3 scores. When (when)
The load meets the requirement of ideal regulation capacity, and the rating score of the obtained load peak regulation response is 2. When->
The load meets the requirement of basic capacity regulation, and the rating score of the obtained load peak regulation response is 1.
In another embodiment, the response recommendation value includes a second response recommendation value of a response rate dimension, and calculating, according to the response index data, the response recommendation value of each load end in the first load end set in multiple dimensions includes: for each load end in the first load end set, reading an adjustment preparation time and an adjustment response time from the response index data; calculating a sum of the adjustment preparation time and the adjustment response time; positioning a second gradient range in which the sum value is located in a second preset gradient space; and searching a second index value matched with the second gradient range, and configuring the second index value as a second response recommended value, wherein the second index value is inversely related to the second gradient range.
By adopting the implementation mode, the capacity of various load response rates is measured and calculated by constructing various load response rate rating models.
Recommending a value for the second response; />
The preparation time is adjusted in real time for various loads; />
The response time is adjusted in real time for various loads; to->
For response rate ranking criteria, ranking scores +.>
The shorter the time sum, the higher the rating score.
In another embodiment, the response recommendation value includes a third response recommendation value of a response economic cost dimension, and calculating the response recommendation value of each load end in the first load end set in multiple dimensions according to the response index data includes: for each load end in the first load end set, reading a load cost value from the response index data; inputting the load cost value into a pre-trained time sequence prediction model, and outputting a load effect value of the load cost value, wherein the time sequence prediction model is a pre-trained neural network model and is used for outputting the corresponding load effect value based on the load cost value; the load achievement value is configured as a third response recommendation value.
By adopting the implementation mode, various load response economic benefits are measured and calculated by constructing various load response economic cost rating models (time sequence prediction models). 
For the third response recommendation value, making a rating ranking score +.>
The higher the economic benefit, the higher the rating score.
Optionally, the time series prediction model is a Prophet model, and before inputting the load cost value into the pre-trained time series prediction model, the method further comprises: collecting training data of a historical time sequence; determining a time unit of a historical time sequence, and dividing training data into a plurality of sub-data according to the time unit; predicting a load effect value of each time period by adopting an initial regression coefficient; gradient descent fitting is performed by adopting the following formula until a preset stopping condition is met:
wherein ,
for the regression coefficient of the current time period, +.>
For the regression coefficient of the previous period of the current time period, alpha is the dynamic adjustment step length, and the preset stopping condition comprises: the difference between the predicted load effect value of the current time period and the actual load effect value of the current time period is smaller than a preset threshold value; />
For the predicted load effect value of the current time period,/->
The actual load effect value of the current time period is represented by i, which is a period sequence number; and configuring the current regression coefficient after stopping fitting as the regression coefficient of the Prophet model to obtain a time sequence prediction model.
The Prophet model of the embodiment is an open-source time sequence prediction model, and is realized based on fitting of time and variable values combined with time sequence decomposition and machine learning. And taking the single-sequence data of the historical time sequence as input data, inputting a future time sequence to be predicted into the Prophet model, and outputting data trend corresponding to the future time to be predicted, wherein the data trend comprises a fitting curve, a predicted upper limit value, a predicted lower limit value and the like. The present example uses historical single sequence data to calculate the first regression coefficient of the propset model in the historical time sequence, where each regression coefficient corresponds to a cycle time, e.g., when the cycle time is months, the regression coefficient appears as an addition or multiplication factor for each month.
According to the embodiment of the invention, a machine is used for replacing a manual power load scheduling work, and the technical problem of high labor cost of parameter scheduling of the Prophet model is solved.
In yet another embodiment, the response recommendation value includes a fourth response recommendation value of a response reliability dimension, and calculating the response recommendation value of each load end in the first load end set in multiple dimensions according to the response index data includes: for each load end in the first load end set, reading a historical peak shaving contribution amount and a historical peak shaving task amount from response index data, wherein the historical peak shaving contribution amount is used for representing the actual total power of the corresponding load end participating in power grid peak shaving consumption in the historical time, and the historical peak shaving task amount is used for representing the total power distributed by the corresponding load end in the historical time; calculating the deviation amount of the historical peak shaving contribution amount relative to the historical peak shaving task amount; the inverse of the deviation amount is configured as a fourth response recommendation value.
And constructing various load response reliability rating models, and measuring and calculating various load response reliability capacities.
For the fourth response recommended value, the actual execution output and the planning deviation of the adjustable load participating in the peak shaving of the power grid are +.>
Ranking score for each type of load response rate capability as reference index>
The smaller the bias, the higher the rating score.
In one implementation manner of the embodiment, constructing a response admission condition by using response index data, and filtering the first load end set based on the response admission condition, so as to obtain a second load end set includes: for each load end in the first load end set, reading actual adjustment duration from the response index data, and referring to the adjustment duration, adjusting preparation time, response time, historical peak shaving contribution and historical peak shaving task quantity; judging whether the actual adjustment duration is greater than or equal to the reference adjustment duration, judging whether the adjustment preparation time and the adjustment response time are less than or equal to the preset disaster recovery time, calculating the deviation amount of the historical peak regulation contribution amount relative to the historical peak regulation task amount, and judging whether the deviation amount is less than or equal to the preset deviation; if the actual adjustment duration is greater than or equal to the reference adjustment duration, the adjustment preparation time and the adjustment response time are less than or equal to the preset disaster recovery time, and if the deviation amount is less than or equal to the preset deviation, the corresponding load ends are filtered from the first load end set and added to the second load end set.
In this embodiment, the admission conditions are reconstructed, load screening is performed, and the admission conditions are as follows:
wherein 0 and 1 represent disallowed entry and admitted entry respectively,
average adjustment duration for each type of load over a period of time; />
The adjustment duration required for the load to be adjusted. It can be seen that when->
When the response sustainable time length of the load is longer than or equal to the time length required by the load to be regulated, the admission condition is met; when->
When the response sustainable market of the load is smaller than the time required by the load to be regulated, the admission condition is not satisfied.
In this embodiment, calculating a total recommended value of each load end in the second load end set according to response recommended values of multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value includes: for each load end in the second load end set, acquiring a weight coefficient combination of the load end in multiple dimensions, wherein the weight coefficient combination comprises multiple weight coefficients, each weight coefficient corresponds to a response recommended value of one dimension, and the sum of all weight coefficients is 1; weighting and summing the weight coefficient combination and the weight coefficient combination of a plurality of dimensions to obtain a total recommended value of a corresponding load end; sorting the load ends in the second load end set in a descending order according to the total recommended value; acquiring the load to be adjusted of each load end in the second load end set from the response index data; calculating the total load of the power grid to be peak regulated in the current peak regulation period; and sequentially and stepwise selecting a plurality of load ends in the second load end set until the sum of the loads to be adjusted of the currently selected load ends reaches the total power of the power grid, and determining the currently selected load ends as target load ends for load response to be executed.
The step selection in this embodiment refers to accumulation selection with a step size of 1, sequentially selecting load ends from the second load end set, and calculating the sum of loads to be adjusted of the currently selected load ends.
In one example, the weight coefficient combination is [0.5,0.2,0.2,0.1 ]]And constructing a final sorting model of the response capability of various load steps, and measuring the response capability of various loads. According to the formula:
and determining a final sorting score K (total recommended value) of various loads, thereby determining the loads participating in the response of the demand side, carrying out final scheduling, and dynamically adjusting a load end list according to real-time data.
The invention provides a method for a cascade response demand side based on load characteristics, which fully considers response capacity, response speed, response economy and the like and determines a method for representing the cascade response demand side according to the load characteristics. Fig. 3 is a flow chart of a method for providing a step response demand side based on load characteristics according to the present invention, including the following steps:
s31, acquiring response quantity, response speed, response economic cost and response reliability index data in real time. According to load classification, acquiring response quantity indexes such as various loads, security loads, highest electricity loads, reference values and the like, and setting a demand adjustment threshold according to the load to be adjusted; acquiring load preparation time, response time and other adjustment rate indexes, and actual execution output and issuing plan deviation and other reliability indexes;
S32, calculating a response rating score
Response rate rating score->
Responsive economic cost rating score->
Response reliability rating score +.>
. Calculating response capacity, response speed and corresponding reliability sequences of various loads, and finally obtaining comprehensive capacity sequences of various loads;
s33, judging admission conditions, and carrying out load screening;
s34, calculating a final sorting score K of the load response capability;
s35, dynamically adjusting the list to participate in real-time response. And dynamically adjusting the comprehensive capacity sequencing of various loads according to the load index and the load to be regulated, and preferentially arranging the ranking to respond to the front load according to the sequencing.
By adopting the scheme of the embodiment, load coordination is accurately realized, the pressure of peak load on a power grid is reduced, the power supply cost and the electricity consumption cost are reduced, and the double effects of power supply and demand balance and economic benefit are realized through load step response demand sides. The step response is carried out on the demand side response according to a more standard, so that multiple targets such as economy, reliability and continuity can be realized while peak clipping and valley filling can be realized.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
Example 2
The present embodiment also provides a power load scheduling device, which is used to implement the foregoing embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Fig. 4 is a block diagram of a power load scheduling apparatus according to an embodiment of the present invention, as shown in fig. 4, including: an acquisition module 40, a calculation module 42, a filtering module 44, a selection module 46, wherein,
the acquisition module 40 is configured to acquire response index data of each load end in the first load end set in the response area in multiple dimensions;
the calculating module 42 is configured to calculate, according to the response index data, response recommended values of each load end in the first load end set in multiple dimensions, where each dimension corresponds to one response recommended value;
the filtering module 44 is configured to construct a response admission condition by using the response index data, and filter the first load end set based on the response admission condition to obtain a second load end set;
The selecting module 46 is configured to calculate a total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and select a target load end for executing load response in the second load end set according to the total recommended value.
Optionally, the acquisition module includes: the first acquisition unit is used for acquiring response quantity index data of each load end in the first load end set in the response area, wherein the response quantity index data comprises: security load, highest electricity load, electricity reference value; the second acquisition unit is used for acquiring response rate index data of each load end in the first load end set in the response area, wherein the response rate index data comprises: adjusting the preparation time and the response time; the third acquisition unit is used for acquiring response economic cost index data of each load end in the first load end set in the response area; and acquiring response reliability index data of each load end in the first load end set in the response area.
Optionally, the response recommendation value includes a first response recommendation value of a response volume dimension, and the calculation module includes: the first reading unit is used for reading the real-time power consumption load reference value, the security load and the load to be adjusted from the response index data for each load end in the first load end set; a first calculation unit for calculating a difference between the electricity load reference value and the security load; the first positioning unit is used for positioning a first gradient range in which the difference value is located in a first preset gradient space, wherein the maximum value of the first preset gradient space is the load to be adjusted, the disaster tolerance coefficient is the load to be adjusted, the minimum value is the load to be adjusted, and the disaster tolerance coefficient is larger than 1; and the first configuration unit is used for searching a first index value matched with the first gradient range and configuring the first index value as the first response recommended value, wherein the first index value is in negative correlation with the first gradient range.
Optionally, the response recommendation value includes a second response recommendation value of a response rate dimension, and the calculation module includes: a second reading unit, configured to read, for each load end in the first load end set, an adjustment preparation time and an adjustment response time from the response index data; a second calculation unit for calculating a sum of the adjustment preparation time and the adjustment response time; the second positioning unit is used for positioning a second gradient range in which the sum value is located in a second preset gradient space; and the second configuration unit is used for searching a second index value matched with the second gradient range and configuring the second index value into the second response recommended value, wherein the second index value is in negative correlation with the second gradient range.
Optionally, the response recommendation value includes a third response recommendation value of a response economic cost dimension, and the computing module includes: a third reading unit, configured to read, for each load end in the first load end set, a load cost value from the response index data; the prediction unit is used for inputting the load cost value into a pre-trained time sequence prediction model and outputting a load effect value of the load cost value, wherein the time sequence prediction model is a pre-trained neural network model and is used for outputting a corresponding load effect value based on the load cost value; and a third configuration unit configured to configure the load effect value as the third response recommendation value.
Optionally, the timing prediction model is a propset model, and the apparatus further includes: the sample module is used for collecting training data of a historical time sequence before the calculation module inputs the load cost value into a pre-trained time sequence prediction model; the segmentation module is used for determining a time unit of the historical time sequence and segmenting the training data into a plurality of sub-data according to the time unit; the prediction module is used for predicting the load effect value of each time period by adopting the initial regression coefficient; the fitting module is used for performing gradient descent fitting by adopting the following formula until the preset stopping condition is met:
wherein ,
for the regression coefficient of the current time period, +.>
And for the regression coefficient of the previous period of the current time period, alpha is a dynamic adjustment step length, and the preset stopping condition comprises: the difference between the predicted load effect value of the current time period and the actual load effect value of the current time period is smaller than a preset threshold value; />
For the predicted load effect value of the current time period,/->
The actual load effect value of the current time period is represented by i, which is a period sequence number; and the generation module is used for configuring the current regression coefficient after the fitting is stopped as the regression coefficient of the Prophet model to obtain the time sequence prediction model.
Optionally, the response recommendation value includes a fourth response recommendation value of a response reliability dimension, and the calculating module includes: a fourth reading unit, configured to read, for each load end in the first load end set, a historical peak shaving contribution and a historical peak shaving task amount from the response index data, where the historical peak shaving contribution is used to represent an actual total power of the corresponding load end participating in power grid peak shaving consumption in a historical time, and the historical peak shaving task amount is used to represent a total power of the corresponding load end distributed in the historical time; a third calculation unit, configured to calculate a deviation amount of the historical peak shaver contribution amount relative to the historical peak shaver task amount; and a fourth configuration unit configured to configure an inverse of the deviation amount as the fourth response recommendation value.
Optionally, the filtering module includes: the reading unit is used for reading the actual adjustment duration from the response index data for each load end in the first load end set, referring to the adjustment duration, adjusting the preparation time, adjusting the response time, historical peak shaving contribution and historical peak shaving task quantity; the judging unit is used for judging whether the actual adjustment duration is greater than or equal to the reference adjustment duration, judging whether the adjustment preparation time and the adjustment response time are smaller than or equal to a preset disaster tolerance time, calculating the deviation amount of the historical peak regulation contribution amount relative to the historical peak regulation task amount, and judging whether the deviation amount is smaller than or equal to a preset deviation; and the filtering unit is used for filtering the corresponding load ends from the first load end set and adding the load ends to the second load end set if the actual adjustment duration is greater than or equal to the reference adjustment duration, the adjustment preparation time and the adjustment response time are less than or equal to the preset disaster tolerance time, and the deviation amount is less than or equal to the preset deviation.
Optionally, the selecting module includes: the first computing unit is used for acquiring a weight coefficient combination of the load end in the multiple dimensions aiming at each load end in the second load end set, wherein the weight coefficient combination comprises multiple weight coefficients, each weight coefficient corresponds to a response recommended value of one dimension, and the sum of all weight coefficients is 1; the weight coefficient combination and the weight coefficient combination of the plurality of dimensions are adopted for weighted summation, so that the total recommended value of the corresponding load end is obtained; the sorting unit is used for sorting the load ends in the second load end set in a descending order according to the total recommended value; the obtaining unit is used for obtaining the load to be adjusted of each load end in the second load end set from the response index data; the second calculation unit is used for calculating the total load of the power grid to be peak-regulated in the current peak-regulation period; the selecting unit is used for sequentially and step-by-step selecting a plurality of load ends in the second load end set until the sum of loads to be adjusted of the currently selected load ends reaches the total power of the power grid, and determining the currently selected load ends as target load ends for load response to be executed.
It should be noted that each of the above modules may be implemented by software or hardware, and for the latter, it may be implemented by, but not limited to: the modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.
Example 3
An embodiment of the invention also provides a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
Alternatively, in the present embodiment, the above-described storage medium may be configured to store a computer program for performing the steps of:
s1, acquiring response index data of each load end in a first load end set in a response area in multiple dimensions;
s2, respectively calculating response recommended values of each load end in the first load end set in multiple dimensions according to the response index data, wherein each dimension corresponds to one response recommended value;
s3, constructing response admittance conditions by adopting the response index data, and filtering the first load end set based on the response admittance conditions to obtain a second load end set;
S4, calculating the total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value.
Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.
An embodiment of the invention also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
Optionally, the electronic device may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:
S1, acquiring response index data of each load end in a first load end set in a response area in multiple dimensions;
s2, respectively calculating response recommended values of each load end in the first load end set in multiple dimensions according to the response index data, wherein each dimension corresponds to one response recommended value;
s3, constructing response admittance conditions by adopting the response index data, and filtering the first load end set based on the response admittance conditions to obtain a second load end set;
s4, calculating the total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments and optional implementations, and this embodiment is not described herein.
FIG. 5 is a block diagram of an electronic device according to an embodiment of the present invention, as shown in FIG. 5, including a processor 102, a communication interface 62, a memory 104, and a communication bus 64, where the processor 102, the communication interface 62, and the memory 104 communicate with each other via the communication bus 64, and the memory 104 is used to store a computer program; a processor 102 for executing programs stored on a memory 104.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, such as the division of the units, is merely a logical function division, and may be implemented in another manner, for example, multiple units or components may be combined or may be 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 through some interfaces, units or modules, or may be in electrical or other forms.
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 on 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 each embodiment 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 integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.
Claims (12)
1. A method of scheduling electrical loads, comprising:
collecting response index data of each load end in a first load end set in a response area in multiple dimensions;
respectively calculating response recommended values of each load end in the first load end set in multiple dimensions according to the response index data, wherein each dimension corresponds to one response recommended value;
constructing a response admittance condition by adopting the response index data, and filtering the first load end set based on the response admittance condition to obtain a second load end set;
and calculating the total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value.
2. The scheduling method of claim 1, wherein collecting response index data for each load end in the first set of load ends in the response area in multiple dimensions comprises:
Collecting response quantity index data of each load end in a first load end set in a response area, wherein the response quantity index data comprises: security load, highest electricity load, electricity reference value;
collecting response rate index data of each load end in a first load end set in a response area, wherein the response rate index data comprises: adjusting the preparation time and the response time;
collecting response economic cost index data of each load end in a first load end set in a response area;
and acquiring response reliability index data of each load end in the first load end set in the response area.
3. The scheduling method according to claim 1, wherein the response recommendation value includes a first response recommendation value of a response volume dimension, and calculating the response recommendation value of each load end in the first load end set in a plurality of dimensions according to the response index data includes:
for each load end in the first load end set, reading a real-time power consumption load reference value, a security load and a load to be adjusted from the response index data;
calculating a difference between the electricity load reference value and the security load;
Positioning a first gradient range in which the difference value is located in a first preset gradient space, wherein the maximum value of the first preset gradient space is a disaster recovery coefficient of the load to be adjusted, the minimum value is the load to be adjusted, and the disaster recovery coefficient is larger than 1;
searching a first index value matched with the first gradient range, and configuring the first index value as the first response recommended value, wherein the first index value is in negative correlation with the first gradient range.
4. The scheduling method according to claim 1, wherein the response recommendation value includes a second response recommendation value of a response rate dimension, and calculating the response recommendation value of each load end in the first load end set in a plurality of dimensions according to the response index data includes:
for each load end in the first load end set, reading an adjustment preparation time and an adjustment response time from the response index data;
calculating the sum of the adjustment preparation time and the adjustment response time;
positioning a second gradient range in which the sum value is located in a second preset gradient space;
and searching a second index value matched with the second gradient range, and configuring the second index value as the second response recommended value, wherein the second index value is in negative correlation with the second gradient range.
5. The scheduling method according to claim 1, wherein the response recommendation values include a third response recommendation value of a response economic cost dimension, and calculating the response recommendation value of each load end in the first load end set in a plurality of dimensions according to the response index data includes:
for each load end in the first load end set, reading a load cost value from the response index data;
inputting the load cost value into a pre-trained time sequence prediction model, and outputting a load effect value of the load cost value, wherein the time sequence prediction model is a pre-trained neural network model and is used for outputting a corresponding load effect value based on the load cost value;
and configuring the load effect value as the third response recommended value.
6. The scheduling method of claim 5, wherein the timing prediction model is a propset model, and wherein prior to inputting the load cost value into the pre-trained timing prediction model, the method further comprises:
collecting training data of a historical time sequence;
determining a time unit of the historical time sequence, and dividing the training data into a plurality of sub-data according to the time unit;
Predicting a load effect value of each time period by adopting an initial regression coefficient;
gradient descent fitting is performed by adopting the following formula until a preset stopping condition is met:
wherein ,
for the regression coefficient of the current time period, +.>
And for the regression coefficient of the previous period of the current time period, alpha is a dynamic adjustment step length, and the preset stopping condition comprises: the difference between the predicted load effect value of the current time period and the actual load effect value of the current time period is smaller than a preset threshold value; />
For the predicted load effect value of the current time period,/->
The actual load effect value of the current time period is represented by i, which is a period sequence number;
and configuring the current regression coefficient after stopping fitting as the regression coefficient of the Prophet model to obtain the time sequence prediction model.
7. The scheduling method according to claim 1, wherein the response recommendation values include a fourth response recommendation value of a response reliability dimension, and calculating the response recommendation value of each load end in the first load end set in a plurality of dimensions according to the response index data includes:
for each load end in the first load end set, reading a historical peak shaving contribution amount and a historical peak shaving task amount from the response index data, wherein the historical peak shaving contribution amount is used for representing the actual total power of the corresponding load end in the historical time for participating in the power grid peak shaving consumption, and the historical peak shaving task amount is used for representing the total power distributed by the corresponding load end in the historical time;
Calculating the deviation amount of the historical peak shaving contribution amount relative to the historical peak shaving task amount;
the inverse of the deviation amount is configured as the fourth response recommendation value.
8. The scheduling method of claim 7, wherein constructing a response admission condition using the response indicator data and filtering the first set of load terminals based on the response admission condition to obtain a second set of load terminals comprises:
for each load end in the first load end set, reading actual adjustment duration from the response index data, referring to the adjustment duration, adjusting preparation time, adjusting response time, historical peak shaving contribution and historical peak shaving task quantity;
judging whether the actual adjustment duration is greater than or equal to a reference adjustment duration, judging whether the adjustment preparation time and the adjustment response time are less than or equal to preset disaster recovery time, calculating the deviation amount of the historical peak regulation contribution amount relative to the historical peak regulation task amount, and judging whether the deviation amount is less than or equal to preset deviation;
and if the actual adjustment duration is greater than or equal to the reference adjustment duration, the adjustment preparation time and the adjustment response time are less than or equal to a preset disaster recovery time, and if the deviation is less than or equal to a preset deviation, filtering the corresponding load ends from the first load end set, and adding the load ends to the second load end set.
9. The scheduling method of claim 1, wherein calculating a total recommended value for each load end in the second set of load ends from the response recommended values for the plurality of dimensions, and selecting a target load end in the second set of load ends from the total recommended value comprises:
for each load end in the second load end set, acquiring a weight coefficient combination of the load end in multiple dimensions, wherein the weight coefficient combination comprises multiple weight coefficients, each weight coefficient corresponds to a response recommended value of one dimension, and the sum of all weight coefficients is 1; the weight coefficient combination and the corresponding recommended value are adopted for weighted summation, and the total recommended value of the corresponding load end is obtained;
sorting the load ends in the second load end set in a descending order according to the total recommended value;
acquiring the load to be adjusted of each load end in the second load end set from the response index data;
calculating the total load of the power grid to be peak regulated in the current peak regulation period;
and sequentially and stepwise selecting a plurality of load ends in the second load end set until the sum of loads to be adjusted of the currently selected load ends reaches the total power of the power grid, and determining the currently selected load ends as target load ends for load response to be executed.
10. A power load scheduling apparatus comprising:
the acquisition module is used for acquiring response index data of each load end in the first load end set in the response area in multiple dimensions;
the calculation module is used for calculating response recommended values of each load end in the first load end set in multiple dimensions according to the response index data, wherein each dimension corresponds to one response recommended value;
the filtering module is used for constructing response admittance conditions by adopting the response index data, and filtering the first load end set based on the response admittance conditions to obtain a second load end set;
the selecting module is used for calculating the total recommended value of each load end in the second load end set according to the response recommended values of the multiple dimensions, and selecting a target load end for executing load response in the second load end set according to the total recommended value.
11. A storage medium having a computer program stored therein, wherein the computer program is arranged to perform the scheduling method of any one of claims 1 to 9 when run.
12. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the scheduling method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211576013.4A CN115600825B (en) | 2022-12-09 | 2022-12-09 | Power load scheduling method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211576013.4A CN115600825B (en) | 2022-12-09 | 2022-12-09 | Power load scheduling method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115600825A CN115600825A (en) | 2023-01-13 |
| CN115600825B true CN115600825B (en) | 2023-05-02 |
Family
ID=84852884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211576013.4A Active CN115600825B (en) | 2022-12-09 | 2022-12-09 | Power load scheduling method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115600825B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829786B (en) * | 2023-02-16 | 2023-04-28 | 国网浙江省电力有限公司金华供电公司 | Power grid response adjusting method based on air conditioner load |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222877B (en) * | 2019-05-17 | 2021-08-03 | 华中科技大学 | Load prediction system and load prediction method based on user-defined neural network |
| CN111275240B (en) * | 2019-12-27 | 2023-06-09 | 华北电力大学 | Load prediction method based on multi-energy coupling scene |
| CN111145045B (en) * | 2020-01-20 | 2023-01-03 | 云南电网有限责任公司 | VaR-considered power large-user flexible load assessment method and system |
| CN112330077B (en) * | 2021-01-04 | 2021-09-24 | 南方电网数字电网研究院有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN113379564A (en) * | 2021-04-08 | 2021-09-10 | 国网河北省电力有限公司营销服务中心 | Power grid load prediction method and device and terminal equipment |
-
2022
- 2022-12-09 CN CN202211576013.4A patent/CN115600825B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 袁小凯 ; 李果 ; 许爱东 ; 张乾坤 ; 张福铮 ; .基于改进增强型神经网络的短期电力负荷预测.计算机与数字工程.2020,(第02期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115600825A (en) | 2023-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bu et al. | A game-theoretical decision-making scheme for electricity retailers in the smart grid with demand-side management | |
| CN115600825B (en) | Power load scheduling method and device, storage medium and electronic equipment | |
| Berlink et al. | Batch reinforcement learning for smart home energy management | |
| CN110111214B (en) | User energy management method and system based on priority | |
| CN112070301A (en) | Method, system and equipment for adjusting power consumption of user | |
| CN112016817A (en) | Demand response method based on companion effect in smart power grid | |
| CN105471107B (en) | A kind of timesharing task acquisition method of electric power over power network metering system | |
| US11861702B2 (en) | Method and apparatus for renewable energy allocation based on reinforcement learning | |
| CN113902181A (en) | Short-term prediction method and equipment for common variable heavy overload | |
| Sharifinia et al. | Extended Kalman filter-based approach for nodal pricing in active distribution networks | |
| CN113935856A (en) | Method and device for controlling electric energy, processor and computer readable storage medium | |
| CN113722882A (en) | Park power grid energy storage optimization configuration method and system considering multiple profit modes | |
| CN116542490A (en) | Virtual power plant day-ahead dispatching encapsulation model and dispatching ex-definition model construction method | |
| CN111952978A (en) | Demand response excitation method and system considering user response characteristics | |
| CN112614010A (en) | Load prediction method and device, storage medium and electronic device | |
| CN115630858A (en) | Virtual power plant peak regulation performance evaluation method and device, storage medium and power grid equipment | |
| CN114074569A (en) | Charging control method and system | |
| CN104834968B (en) | A kind of real-time grid economical operation assessment sub- optimization algorithm of thermoelectricity | |
| CN114580919A (en) | Multi-scene two-stage demand response resource optimal scheduling method, device and equipment | |
| CN108539799A (en) | The dispatching method and device of wind-powered electricity generation in a kind of power grid | |
| CN115545588A (en) | Fixed energy storage system site selection determining method and device, electronic equipment and storage medium | |
| CN111445154A (en) | Power market resource self-scheduling optimization method, system and equipment | |
| CN115149554A (en) | Method and system for evaluating interactive response capability of electric vehicle participating in power grid | |
| CN113095669A (en) | Comprehensive energy scheduling method and system based on energy consumption coupling coordination | |
| CN112465196A (en) | System load prediction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230713 Address after: 321000 No. 420, Shuang Xi Road, Wucheng District, Jinhua, Zhejiang. Patentee after: JINHUA POWER SUPPLY COMPANY OF STATE GRID ZHEJIANG ELECTRIC POWER Co.,Ltd. Patentee after: Beijing Huadian energy Internet Research Institute Co.,Ltd. Patentee after: NORTH CHINA ELECTRIC POWER University Address before: 321000 No. 420, Shuang Xi Road, Wucheng District, Jinhua, Zhejiang. Patentee before: JINHUA POWER SUPPLY COMPANY OF STATE GRID ZHEJIANG ELECTRIC POWER Co.,Ltd. Patentee before: Beijing Huadian energy Internet Research Institute Co.,Ltd. |