CN113222270A - Power consumption load prediction method, power consumption load prediction device, electronic device, and storage medium - Google Patents
Power consumption load prediction method, power consumption load prediction device, electronic device, and storage medium Download PDFInfo
- Publication number
- CN113222270A CN113222270A CN202110569405.7A CN202110569405A CN113222270A CN 113222270 A CN113222270 A CN 113222270A CN 202110569405 A CN202110569405 A CN 202110569405A CN 113222270 A CN113222270 A CN 113222270A
- Authority
- CN
- China
- Prior art keywords
- date
- power consumption
- factor
- similarity
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 6
- 230000005611 electricity Effects 0.000 description 6
- 230000006872 improvement Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000926 separation method Methods 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a power consumption load prediction method, which comprises the following steps: obtaining N historical date dataiN similarity factors s with the target date destiWherein the similarity factor siFor characterising historical dateiThe similarity degree with the target date dest, N and i are natural numbers, i is more than or equal to 1 and less than or equal to N; from N similarity factors s based on a preset algorithmiSelecting a plurality of proximity similarity factors; and generating the power consumption load data of the target date based on the power consumption load data of a plurality of historical dates corresponding to the plurality of proximity similarity factors one by one. The prediction method can accurately predict the power consumption load of the target date.
Description
Technical Field
The present invention relates to the field of power scheduling technologies, and in particular, to a method and an apparatus for predicting a power consumption load, an electronic device, and a storage medium.
Background
With the development of smart grids, the free trade and power industry separation mechanism of the power market is continuously perfected, and smart electric meters, smart household appliances and energy management systems are gradually popularized and applied. Under the environment of the intelligent power grid, demand response is decided and controlled by means of the intelligent terminal, and management and regulation of the electricity consumption behaviors of residents can be better achieved; meanwhile, the electricity consumption behavior of residents is optimized by means of an information interaction technology, and the efficiency of the electric power market is improved. Because the electricity consumption of residents is an important component of the demand side, the intelligent demand response needs to use behaviors and situations thereof as bases, and reasonable price signals or incentive mechanisms are formulated to guide the electricity consumption behaviors of the resident groups, so as to respond to the dispatching of the power system.
Therefore, how to predict the household power consumption load becomes an urgent problem to be solved.
Disclosure of Invention
The invention aims to provide a power consumption load prediction method, a power consumption load prediction device, an electronic device and a storage medium.
In order to achieve one of the above objects, an embodiment of the present invention provides a method for predicting a power consumption load, including: obtaining N historical date dataiN similarity factors s with the target date destiWherein the similarity factor siFor characterising historical dateiThe similarity degree with the target date dest, N and i are natural numbers, i is more than or equal to 1 and less than or equal to N; from N similarity factors s based on a preset algorithmiSelecting a plurality of proximity similarity factors; and generating the power consumption load data of the target date based on the power consumption load data of a plurality of historical dates corresponding to the plurality of proximity similarity factors one by one.
As a further improvement of one embodiment of the invention, the similarity factor s is selected from N based on a preset algorithmiThe selection of the plurality of proximity similarity factors specifically includes: when similarity factor si>When the threshold value is preset, the similarity factor siIs a near similarity factor; or from N similarity factors siH with the largest value is selected as a proximity similarity factor, wherein H is a natural number.
As a further improvement of an embodiment of the present invention, the "generating power consumption load data on the target date based on power consumption load data on a plurality of history dates corresponding to the plurality of proximity similarity factors in one-to-one correspondence" specifically includes: acquiring power consumption load data of a plurality of historical dates corresponding to a plurality of proximity similarity factors one by one, wherein the number of the plurality of historical periods is H, and the resident load data of the H-th historical date comprises the following steps: a plurality of switch states P corresponding to K electrical appliances in J continuous time periodsh,j,kWherein H, H, J, K, J, K are natural numbers, H is more than or equal to 1 and less than or equal to H, J is more than or equal to 1 and less than or equal to J, K is more than or equal to 1 and less than or equal to K, and when P is Ph,j,k1, representing that the kth electric appliance is in an open state in the h historical date and the jth time period; when P is presenth,j,kThe characteristic is that the kth electric appliance is in a closed state in the h historical date and the jth time period; in the target date, the probability that the kth electric appliance is in an open state in the jth time periodIn the target date, the power consumption power in the jth time period isPowerkThe consumed power of the kth electric appliance.
As a further improvement of one embodiment of the present invention, the step of "obtaining N historical date dataiN similarity factors s with the target date destiThe method specifically comprises the following steps: obtaining N historical date dataiCharacteristic data of (human comfort factor alpha)iDate, dateDifference factor deltaiWeek type factor lambdaiAnd a significant event factor thetai]Characteristic data [ human comfort factor alpha, date difference factor delta, week type factor lambda and significant event factor theta ] of the target date dest](ii) a For characteristic data [ human comfort factor alphaiDate difference factor deltaiWeek type factor lambdaiAnd a significant event factor thetai]Carrying out normalization processing to obtain characteristic data of human body comfort factor alpha'iDate difference factor delta'iDay type factor lambda'iAnd significant event factor θ'i]Wherein, is alpha'i=αi/max(α1,α2,...,αN),δ′i=δi/max(δ1,δ2,...,δN),λ′i=λi/max(λ1,λ2,...,λN),θ′i=θi/max(θ1,θ2,...,θN) (ii) a Similarity factorWherein, w1、w2、w3And w4Are weights. As a further improvement of an embodiment of the present invention, wherein, in the formula, TaFor historical dateiCorresponding to the ambient temperature, HrFor historical dateiCorresponding relative humidity of air, u being historical dateiCorresponding to the average wind speed m/s.
As a further improvement of an embodiment of the present invention,wherein d is history dateiDays between dest and the target date, beta1And beta2For the attenuation coefficient, i () is the rounding function, and N340.
As a further improvement of an embodiment of the present invention, λi=1-|f(Ci)-f(C)|,Wherein, CiAnd C are history date, respectivelyiA day type corresponding to the target date dest, w-1 indicates monday, w-2 indicates tuesday, w-3 indicates wednesday, w-4 indicates thursday, w-5 indicates friday, w-6 indicates saturday, and w-7 indicates sunday;
when historical dateiFalse time of the same section as the target date dest, thetai1, otherwise, θi=0。
The embodiment of the invention also provides a device for predicting the power consumption load, which comprises the following modules:
a data acquisition module for acquiring N historical date dataiN similarity factors s with the target date destiWherein the similarity factor siFor characterising historical dateiThe similarity degree with the target date dest, N and i are natural numbers, i is more than or equal to 1 and less than or equal to N;
a data screening module for selecting N similarity factors s based on a preset algorithmiSelecting a plurality of proximity similarity factors;
and the data processing module is used for generating the power consumption load data of the target date based on the power consumption load data of the plurality of historical dates corresponding to the plurality of proximity similarity factors one by one.
An embodiment of the present invention further provides an electronic device, including: a memory for storing executable instructions; and a processor for implementing the above-described power consumption load prediction method when executing the executable instructions stored in the memory.
The embodiment of the invention also provides a storage medium, which stores executable instructions and is used for causing a processor to execute, so that the power consumption load prediction method is realized.
Compared with the prior art, the invention has the technical effects that: the embodiment of the invention provides a method for predicting power consumption load, which comprises the following steps: obtaining N historical date dataiN similarity factors s with the target date destiWherein the similarity factor siFor characterising historical dateiThe similarity degree with the target date dest, N and i are natural numbers, i is more than or equal to 1 and less than or equal to N; from N similarity factors s based on a preset algorithmiSelecting a plurality of proximity similarity factors; and generating the power consumption load data of the target date based on the power consumption load data of a plurality of historical dates corresponding to the plurality of proximity similarity factors one by one. The prediction method can accurately predict the power consumption load of the target date.
Drawings
Fig. 1 is a flowchart illustrating a method for predicting a power consumption load according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to embodiments shown in the drawings. These embodiments are not intended to limit the present invention, and structural, methodological, or functional changes made by those skilled in the art according to these embodiments are included in the scope of the present invention.
Terms such as "upper," "above," "lower," "below," and the like, used herein to denote relative spatial positions, are used for ease of description to describe one element or feature's relationship to another element or feature as illustrated in the figures. The spatially relative positional terms may be intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "below" or "beneath" other elements or features would then be oriented "above" the other elements or features. Thus, the exemplary term "below" can encompass both an orientation of above and below. The device may be otherwise oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
An embodiment of the present invention provides a method for predicting a power consumption load, as shown in fig. 1, including the following steps:
step 101: obtaining N historical date dataiN similarity factors s with the target date destiWherein the similarity factor siFor characterising historical dateiThe similarity degree with the target date dest, N and i are natural numbers, i is more than or equal to 1 and less than or equal to N; here, for the history dateiWith respect to the target date dest, they can be described by a number of features, such as body comfort, date gap, week type, milestone, PM2.5 and day peak air temperature, and historical dateiComparing the characteristics corresponding to each target date dest to obtain the difference between the characteristics, wherein the greater the difference is, the greater the similarity factor siThe smaller, otherwise the similarity factor siThe larger.
Step 102: from N similarity factors s based on a preset algorithmiSelecting a plurality of proximity similarity factors;
step 103: and generating the power consumption load data of the target date based on the power consumption load data of a plurality of historical dates corresponding to the plurality of proximity similarity factors one by one.
The basic process of the power consumption load prediction method is as follows: first, the power consumption load data of a plurality of historical dates are obtained, and then the similarity factor between the target date and each historical date is obtained, it can be understood that if the similarity factor between some historical dates and the target date best meets the requirement (for example, the similarity factor is larger than a certain threshold value, or the similarity factors are arranged from large to small, H maximum similarity factors are selected, and the like), the power consumption loads between the target date and the historical dates should be similar, and then the power consumption load data of the historical dates can be used for predicting the power consumption load data of the target date. Here, the power consumption load can be understood as: the power consumption amount and/or power consumption amount of each time zone may be understood as a power consumption load by dividing one day into several consecutive time zones (for example, the length of the time zone is one minute, etc.), and furthermore, the change in the power consumption amount and/or power consumption amount of the residents in the time zone may be considered to be small, and thus, the power consumption amount and/or power consumption amount of the residents in the time zone may be considered to be a constant value.
In this embodiment, the similarity factor s is derived from N numbers based on a preset algorithmiThe selection of the plurality of proximity similarity factors specifically includes:
when similarity factor si>When the threshold value is preset, the similarity factor siIs a near similarity factor; here, a preset threshold may be preset, and then, when the value of a certain similarity factor is greater than the preset threshold, the similarity factor is a close similarity factor.
Or from N similarity factors siH with the largest value is selected as a proximity similarity factor, wherein H is a natural number. Here, N similarity factors s may be usediThe data are arranged into a column according to the sequence from big to small, then H are selected as the proximity similarity factors according to the direction from the head of the queue to the tail of the queue, and H is less than or equal to N.
In this embodiment, the "generating power consumption load data on the target date based on power consumption load data on a plurality of historical dates corresponding to the plurality of approximate similarity factors one to one" specifically includes:
acquiring power consumption load data of a plurality of historical dates corresponding to a plurality of proximity similarity factors one by one, wherein the number of the plurality of historical periods is H, and the resident load data of the H-th historical date comprises the following steps: a plurality of switch states P corresponding to K electrical appliances in J continuous time periodsh,j,kWherein H, H, J, K, J, K are natural numbers, H is more than or equal to 1 and less than or equal to H, J is more than or equal to 1 and less than or equal to J, K is more than or equal to 1 and less than or equal to K, and when P is Ph,j,k1, representing that the kth electric appliance is in an open state in the h historical date and the jth time period; when P is presenth,j,kThe characteristic is that the kth electric appliance is in a closed state in the h historical date and the jth time period;
in the target date, the probability that the kth electric appliance is in an open state in the jth time period
In the target date, the power consumption power in the jth time period isPowerkThe consumed power of the kth electric appliance.
Here, a day is divided into J consecutive time periods, for example: each time period is of equal length, which may be one minute, and thus, one day is divided into 1440 time periods. Here, in order to obtain the on-off state of each electrical appliance in each time period, each electrical appliance may be electrically connected to a smart socket, which is capable of obtaining the power consumption of the electrical appliance, for example, when the power consumption > standby power, it may be determined that the electrical appliance is in an on state; when the power consumption is less than or equal to the standby power, the electric appliance can be judged to be in the off state.
For a certain electrical appliance, the on-off states corresponding to the H historical dates in a certain specific time period are obtained, the average value of the on-off states is taken, the probability that the electrical appliance is opened in the specific time period in the target date can be judged, and the possible total power consumption of all the electrical appliances is further calculated.
In this embodiment, the step of "obtaining N historical date dataiN similarity factors s with the target date destiThe method specifically comprises the following steps:
obtaining N historical date dataiCharacteristic data of (human comfort factor alpha)iDate difference factor deltaiWeek type factor lambdaiAnd a significant event factor thetai]Characteristic data [ human comfort factor alpha, date difference factor delta, week type factor lambda and significant event factor theta ] of the target date dest];
For characteristic data [ human comfort factor alphaiDate difference factor deltaiType of weekFactor lambdaiAnd a significant event factor thetai]Carrying out normalization processing to obtain characteristic data of human body comfort factor alpha'iDate difference factor delta'iDay type factor lambda'iAnd significant event factor θ'i]Wherein, is alpha'i=αi/max(α1,α2,...,αN),δ′i=δi/max(δ1,δ2,...,δN),λ′i=λi/max(λ1,λ2,...,λN),θ′i=θi/max(θ1,θ2,...,θN);
Here, in the long-term work of the inventor, it was found that human comfort, date difference, week type, major event PM2.5, daily maximum temperature, and the like all affect the power consumption load. The Pearson correlation coefficient is an important index for measuring the linear correlation degree between 2 random variables, the Pearson correlation coefficients corresponding to the factors and the load are respectively 0.696, -0.530, 0.430, 0.406, 0.124 and 0.113, the characteristic factors with the correlation absolute value larger than 0.400 are selected by utilizing the Pearson correlation coefficient, the human comfort factor, the date difference factor, the week type factor and the major event factor are incorporated into the characteristic vector of the similar day of a single household, and the similarity characteristic vector is adopted for representing the similarity between the historical day and the forecast day.
Compared with independent indexes such as wind-cold index and hot index, the human body comfort factor can reflect the association between meteorological conditions and loads more comprehensively. Therefore, the human comfort factor is adopted to measure the similarity degree of the target date and the historical date on the weather.
With the development of economy, the load of residents rises periodically. Therefore, the closer the selected similar day is to the target date, the more valuable the power consumption load data is. A date gap factor is used to represent the similarity of the target date and the historical date over a long time span, and the similarity decreases as the absolute time difference between the target date and the historical date increases.
In short term, the load of residents also shows a certain regularity in each day of the week. Therefore, the similarity degree of the predicted day and the historical day on the week type is measured by using a week type factor, and the value of the factor is larger when the similarity degree of the week type is larger.
Because of the influence of some major events, the electricity utilization behavior of residents fluctuates in a short time, and in the embodiment, the influence of holidays of major festivals such as spring festival on the electricity utilization behavior of residents is mainly considered. Therefore, significant event factors must be considered.
In, TaFor historical dateiCorresponding to the ambient temperature, HrFor historical dateiCorresponding relative humidity of air, u being historical dateiCorresponding to the average wind speed m/s.
In the present embodiment, the first and second electrodes are,wherein d is history dateiDays between dest and the target date, beta1And beta2For the attenuation coefficient, i () is the rounding function, and N340. Wherein, beta1And beta2The value ranges of (1) are all 0.90-0.98.
In this embodiment, λi=1-|f(Ci)-f(C)|,Wherein, CiAnd C are history date, respectivelyiThe day type corresponding to the target date dest, w-1 indicates monday, w-2 indicates tuesday, w-3 indicates wednesday, w-4 indicates thursday, and w-5 indicates starPeriod five, w-6 for saturday and w-7 for sunday;
when historical dateiFalse time of the same section as the target date dest, thetai1, otherwise, θi=0。
The second embodiment of the present invention provides a power consumption load prediction apparatus, including the following modules:
a data acquisition module for acquiring N historical date dataiN similarity factors s with the target date destiWherein the similarity factor siFor characterising historical dateiThe similarity degree with the target date dest, N and i are natural numbers, i is more than or equal to 1 and less than or equal to N;
a data screening module for selecting N similarity factors s based on a preset algorithmiSelecting a plurality of proximity similarity factors;
and the data processing module is used for generating the power consumption load data of the target date based on the power consumption load data of the plurality of historical dates corresponding to the plurality of proximity similarity factors one by one.
An embodiment of the present invention provides an electronic device, including: a memory for storing executable instructions;
and the processor is used for realizing the power consumption load prediction method in the first embodiment when the processor executes the executable instructions stored in the memory.
A fourth embodiment of the present invention provides a storage medium, which stores executable instructions for causing a processor to execute the method for predicting a power consumption load according to the first embodiment.
It should be understood that although the present description refers to embodiments, not every embodiment contains only a single technical solution, and such description is for clarity only, and those skilled in the art should make the description as a whole, and the technical solutions in the embodiments can also be combined appropriately to form other embodiments understood by those skilled in the art.
The above-listed detailed description is only a specific description of a possible embodiment of the present invention, and they are not intended to limit the scope of the present invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for predicting a power consumption load, comprising the steps of:
obtaining N historical date dataiN similarity factors s with the target date destiWherein the similarity factor siFor characterising historical dateiThe similarity degree with the target date dest, N and i are natural numbers, i is more than or equal to 1 and less than or equal to N;
from N similarity factors s based on a preset algorithmiSelecting a plurality of proximity similarity factors;
and generating the power consumption load data of the target date based on the power consumption load data of a plurality of historical dates corresponding to the plurality of proximity similarity factors one by one.
2. The prediction method according to claim 1, wherein said "is based on a preset algorithm, from N similarity factors siThe selection of the plurality of proximity similarity factors specifically includes:
when similarity factor si>When a threshold value is preset, the similarity factor si is a close similarity factor;
or from N similarity factors siH with the largest value is selected as a proximity similarity factor, wherein H is a natural number.
3. The prediction method according to claim 1, wherein the "generating the power consumption load data on the target date based on the power consumption load data on the plurality of history dates corresponding to the plurality of proximity similarity factors in one-to-one correspondence" specifically includes:
acquiring power consumption load data of a plurality of historical dates corresponding to a plurality of similarity factors one by one, wherein the number of the plurality of historical periods is H, and the residential load of the H-th historical dateThe data includes: a plurality of switch states P corresponding to K electrical appliances in J continuous time periodsh,j,kWherein H, H, J, K, J, K are natural numbers, H is more than or equal to 1 and less than or equal to H, J is more than or equal to 1 and less than or equal to J, K is more than or equal to 1 and less than or equal to K, and when P is Ph,j,k1, representing that the kth electric appliance is in an open state in the h historical date and the jth time period; when P is presenth,j,kThe characteristic is that the kth electric appliance is in a closed state in the h historical date and the jth time period;
in the target date, the probability that the kth electric appliance is in an open state in the jth time period
4. The power consumption load prediction method according to claim 1, wherein the "obtaining N history date dataiN similarity factors s with the target date destiThe method specifically comprises the following steps:
obtaining N historical date dataiCharacteristic data of (human comfort factor alpha)iDate difference factor deltaiWeek type factor lambdaiAnd a significant event factor thetai]Characteristic data [ human comfort factor alpha, date difference factor delta, week type factor lambda and significant event factor theta ] of the target date dest];
For characteristic data [ human comfort factor alphaiDate difference factor deltaiWeek type factor lambdaiAnd a significant event factor thetai]Carrying out normalization processing to obtain characteristic data (human comfort factor)α′iDate difference factor delta'iDay type factor lambda'iAnd significant event factor θ'i]Wherein, is alpha'i=αi/max(α1,α2,...,αN),δ′i=δi/max(δ1,δ2,...,δN),λ′i=λi/max(λ1,λ2,...,λN),θ′i=θi/max(θ1,θ2,...,θN);
5. The power consumption load prediction method according to claim 4, characterized in that:
7. The power consumption load prediction method according to claim 4, characterized in that:
λi=1-|f(Ci)-f(C)|,wherein, CiAnd C are history date, respectivelyiA day type corresponding to the target date dest, w-1 indicates monday, w-2 indicates tuesday, w-3 indicates wednesday, w-4 indicates thursday, w-5 indicates friday, w-6 indicates saturday, and w-7 indicates sunday;
when historical dateiFalse time of the same section as the target date dest, thetai1, otherwise, θi=0。
8. An apparatus for predicting a power consumption load, comprising:
a data acquisition module for acquiring N historical date dataiN similarity factors s with the target date destiWherein the similarity factor siFor characterising historical dateiThe similarity degree with the target date dest, N and i are natural numbers, i is more than or equal to 1 and less than or equal to N;
a data screening module for selecting N similarity factors s based on a preset algorithmiSelecting a plurality of proximity similarity factors;
and the data processing module is used for generating the power consumption load data of the target date based on the power consumption load data of the plurality of historical dates corresponding to the plurality of proximity similarity factors one by one.
9. An electronic device, comprising:
a memory for storing executable instructions;
a processor for implementing the method of predicting power consumption load of any one of claims 1 to 7 when executing the executable instructions stored in the memory.
10. A storage medium storing executable instructions for causing a processor to perform the method of predicting power consumption load according to any one of claims 1 to 7 when executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110569405.7A CN113222270A (en) | 2021-05-25 | 2021-05-25 | Power consumption load prediction method, power consumption load prediction device, electronic device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110569405.7A CN113222270A (en) | 2021-05-25 | 2021-05-25 | Power consumption load prediction method, power consumption load prediction device, electronic device, and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113222270A true CN113222270A (en) | 2021-08-06 |
Family
ID=77098492
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110569405.7A Pending CN113222270A (en) | 2021-05-25 | 2021-05-25 | Power consumption load prediction method, power consumption load prediction device, electronic device, and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113222270A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115249093A (en) * | 2022-09-01 | 2022-10-28 | 安徽固太新能源有限公司 | Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium |
CN115859815A (en) * | 2022-12-07 | 2023-03-28 | 国网江苏省电力有限公司营销服务中心 | Short-term adjustable load prediction method and system based on SA-TCN model |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103606015A (en) * | 2013-11-26 | 2014-02-26 | 国网安徽省电力公司 | Short-term load forecasting method based on hourly comprehensive meteorological indexes |
CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
CN111160625A (en) * | 2019-12-10 | 2020-05-15 | 中铁电气化局集团有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
-
2021
- 2021-05-25 CN CN202110569405.7A patent/CN113222270A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103606015A (en) * | 2013-11-26 | 2014-02-26 | 国网安徽省电力公司 | Short-term load forecasting method based on hourly comprehensive meteorological indexes |
CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
CN111160625A (en) * | 2019-12-10 | 2020-05-15 | 中铁电气化局集团有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
朱云毓: ""自下而上的群体居民日负荷预测"", 《东南大学学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115249093A (en) * | 2022-09-01 | 2022-10-28 | 安徽固太新能源有限公司 | Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium |
CN115859815A (en) * | 2022-12-07 | 2023-03-28 | 国网江苏省电力有限公司营销服务中心 | Short-term adjustable load prediction method and system based on SA-TCN model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fan et al. | Short-term load forecasting based on an adaptive hybrid method | |
Lahouar et al. | Day-ahead load forecast using random forest and expert input selection | |
CN113222270A (en) | Power consumption load prediction method, power consumption load prediction device, electronic device, and storage medium | |
Song et al. | Hybrid load forecasting method with analysis of temperature sensitivities | |
El-Baz et al. | Short-term smart learning electrical load prediction algorithm for home energy management systems | |
Mandal et al. | A neural network based several-hour-ahead electric load forecasting using similar days approach | |
Bassamzadeh et al. | Robust scheduling of smart appliances with uncertain electricity prices in a heterogeneous population | |
Rajbhandari et al. | Load prioritization technique to guarantee the continuous electric supply for essential loads in rural microgrids | |
Zhai et al. | Analysis of dynamic appliance flexibility considering user behavior via non-intrusive load monitoring and deep user modeling | |
CN102868155A (en) | Power load forecasting control system and method | |
Pan et al. | Impacts of optimization interval on home energy scheduling for thermostatically controlled appliances | |
KR102495494B1 (en) | Method and apparatus for predicting home energy usage | |
Vedullapalli et al. | Optimal demand response in a building by battery and HVAC scheduling using model predictive control | |
Rafi | Highly efficient short term load forecasting scheme using long short term memory network | |
Haben et al. | Core Concepts and Methods in Load Forecasting: With Applications in Distribution Networks | |
CN113362103B (en) | Method for customizing peak-valley time-of-use electricity price of power grid through user electricity consumption behavior characteristics | |
Chren et al. | Local load optimization in smart grids with Bayesian networks | |
Winkler et al. | Intelligent energy management of electrical power systems with distributed feeding on the basis of forecasts of demand and generation | |
Ahmed et al. | Application of short term energy consumption forecasting for household energy management system | |
Mariano‐Hernández et al. | Comparative study of continuous hourly energy consumption forecasting strategies with small data sets to support demand management decisions in buildings | |
Perez | Application of support vector machines and ANFIS to the short-term load forecasting | |
Xia et al. | One-day-ahead load forecast using an adaptive approach | |
Mubarok et al. | Electrical load forecasting study using artificial neural network method for minimizing blackout | |
Amadeh et al. | Building cluster demand flexibility: An innovative characterization framework and applications at the planning and operational levels | |
Mbuwir et al. | Applying reinforcement learning to maximise photovoltaic self-consumption for electric vehicle charging |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210806 |
|
RJ01 | Rejection of invention patent application after publication |