CN105260803A - Power consumption prediction method for system - Google Patents
Power consumption prediction method for system Download PDFInfo
- Publication number
- CN105260803A CN105260803A CN201510752495.8A CN201510752495A CN105260803A CN 105260803 A CN105260803 A CN 105260803A CN 201510752495 A CN201510752495 A CN 201510752495A CN 105260803 A CN105260803 A CN 105260803A
- Authority
- CN
- China
- Prior art keywords
- user
- power consumption
- analysis
- influence factor
- power utilization
- 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.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
For accurately measuring the power consumption, the invention provides a power consumption prediction method for a system. The method comprises S1 data acquisition: acquiring the power utilization information of residents, industrial users and business users through an intelligent ammeter, acquiring the influence factor information through an external system, and generating a history table for the users at the same time; S2 analysis of power utilization rules for the users: performing fitting analysis of the acquired power utilization information of the users by means of combination with the history table, and obtaining the power utilization rules for the users through analysis; S3 analysis of influence factors: setting a load fluctuation range according to the user type, and performing analysis of influence factors for the time point surpassing the fluctuation range to obtain the influence value of each influence factor for the power consumption of the users; and S4 power consumption prediction for a system: predicting the future short-term power consumption for the system by means of combination of analysis of power utilization rules and analysis of influence factors. The prediction method shows a brand new development direction for short-term power consumption prediction in future, and can be widely applied to the prediction field with great significance.
Description
Technical field
The invention belongs to electric system analysis of electric power consumption field, relate to a kind of system power consumption Forecasting Methodology.
Background technology
The existing very long history of research of distribution network system short-term electricity demand forecasting, for a long time, the object of short-term electricity demand forecasting is confined to the system of the whole network usually, Chinese scholars to do the research work of a large amount of Theories and methods to this, propose the multiple Forecasting Methodology differed from one another, as time series method, expert system approach, artificial neural network method etc.
Short-term power consumption has obvious periodicity, as similarity, similarity, the similarity etc. of festivals or holidays of same type day in week of daily power consumption curve, in addition short-term power consumption is vulnerable to the impact of various environmental factor, as weather, recreational and sports activities etc., this makes the change of power consumption occur the stochastic process of non-stationary.Therefore the Forecasting Methodology existed at present, as time series method, expert system approach, artificial neural network method etc., its practical application effect is unsatisfactory, is difficult to set up the relational model between system power consumption and numerous influence factor.But, predict the outcome be formulate that electrical network is sent out, Transaction algorithm, Power System Planning, plan, electricity consumption, the department such as scheduling element task, therefore, can propose more reliably, accurately solution be the problem that people study always.
Summary of the invention
The object of the present invention is to provide a kind of new system power consumption Forecasting Methodology, the method can make up the deficiency of existing Forecasting Methodology.
A kind of system power consumption Forecasting Methodology, comprises the following steps:
S1 data acquisition
Gathered the power information of the users such as resident, industry, business by intelligent electric meter, obtain influence factor information by external system, generate this user's history lists simultaneously.
S2 user power utilization law-analysing
In conjunction with history lists, Fitting Analysis is carried out to the user power utilization information collected, analyze and obtain user power utilization rule.
S3 analysis of Influential Factors
Fluctuation of load scope is set according to user type, analysis of Influential Factors is carried out to the time point exceeding fluctuation range, obtain the influence value of each influence factor to this user power utilization amount.
S4 system power consumption is predicted
In conjunction with user power utilization law-analysing and analysis of Influential Factors, the following short-term power consumption of system is predicted.
The user power utilization information that step S1 obtains is real-time power information; The mode generating history lists is that the information of acquisition is formed this user power utilization information history table by timing.
Described in step S1, influence factor mainly comprises: weather, festivals or holidays, social event etc.
Preferably, described history lists comprises: user ID, user power utilization amount, Weather information, festivals or holidays type, relevant social event information.
Preferably, can every one hour statistics user power utilization amount and the Weather information obtained at that time forms the time historical statistics point of this user; When every day morning 0 ~ 4, the time historical statistics point of this user is merged formed this user when daily power consumption, Weather information, festivals or holidays type, relevant social event information day history lists.
Fitting analyzing method described in step S2 is linear analysis.
Preferably, described in step S2, linear analysis method is: according to step S1 gained history lists according to user type and electricity consumption type to user power utilization information with user's daily power consumption for y, take date as x, carry out linear fit analysis by following formula, analyze and obtain user power utilization law curve.
y(x)＝(x
x-n+…+x
x-2+x
x-1+x)/(n+1)
N value is the value number in sampling process, and span divides according to user type and electricity consumption type, and value quantity can be chosen according to system operations ability.General, for electricity consumption on working day value should not be less than 5 working day point, electricity consumption at weekend value should not be less than 6 weekend point, electricity consumption holiday value is that mean value, continuously the electricity consumption value being no more than 3 identical festivals or holidays should not be less than 15 data points.
Described in step S3, analysis of Influential Factors method is:
1) judge whether user is in active state, determination methods is judge that whether this daily power consumption of user is lower than threshold value according to user type.
2) as user is in active state, then judge whether this user power utilization amount of this time point exceeds fluctuation range.
3) influence factors such as weather, festivals or holidays, social event are carried out to the time point exceeding fluctuation range and carry out unicity analysis; Wherein weather conditions are mathematic interpolation, by calculating gas epidemic disaster, the wind-force difference of this time point and the previous day and whether there is the special change such as rainfall, snowfall.
4) mean value of user power utilization amount, maximal value and variance yields is affected as then added up this influence factor for single influence factor; Wherein weather conditions need to add up corresponding difference; Unifactor model is formed according to statistics.
5) as being multinomial influence factor, then integrating step 3) gained single factors adopts following method to judge the influence coefficient of each influence factor:
A. all possible array mode contained by multinomial influence factor is added up.
B. under each array mode of matching each influence factor mean value tire out and with the matching degree of actual value.
C. choose and add up each influence factor influence coefficient to user power utilization amount in multinomial influence factor closest to array mode matching; Wherein weather conditions coefficient is combined with difference; Form the statistical model under this multinomial influence factor.
D. each influence coefficient of same model is averaged.
Analyze and obtain the influence value of each influence factor to this user power utilization amount.
Further, described weather conditions are mainly: gas epidemic disaster, rainfall/snow and wind-force; Festivals or holidays, factor was mainly: common weekend, legal extra holiday, special event holiday; Social event factor mainly carries out correlating event division according to user type.
Preferably, analysis of Influential Factors described in step S3 can adopt Hadoop distributed computing framework to carry out.
Described in step S4, system power consumption Forecasting Methodology is:
First each influence factor information in a short time in future is obtained, then according to following short term memory influence factor select corresponding analogy model, in conjunction with user power utilization law curve and corresponding influence factor analogy model, the power consumption of following this user in a short time of simulation and forecast; Add up the electricity demand forecasting of all users in each system realm, the electricity demand forecasting of this system realm can be obtained.
Preferably, system power consumption Forecasting Methodology of the present invention can be used for the short-term forecasting of system power consumption.
Compared with existing Forecasting Methodology, Forecasting Methodology tool of the present invention has the following advantages:
1. analytical approach of the present invention is based on user power utilization information, because user determines by industry attribute, its activity has obvious regularity, influence factor is relatively single, the relation of power consumption and influence factor is simpler and regular, be easier to hold by electrical characteristics, therefore analytical approach of the present invention can grasp user power utilization rule more accurately.
2. the present invention has taken into full account the major influence factors affecting user power utilization amount, and the contribution proportion of each factor when the influence value of each influence factor of statistical computation and multinomial factor acting in conjunction, therefore, Forecasting Methodology of the present invention is more accurate compared with existing Forecasting Methodology.
3. invention introduces the large data technique of Hadoop framework, reduce the computing pressure of system, improve the performance of system.
4. Forecasting Methodology of the present invention has stronger learning ability, and along with the increase of statistical model can carry out electricity demand forecasting more accurately and effectively, the process increasing new forecast model is comparatively simple, and increase new model does not need to reanalyse yet.
5. Forecasting Methodology of the present invention is a brand-new developing direction of electric system electricity demand forecasting from now on, advantageously will improve stability and the economy of operation of power networks in grid company, in addition, the combination of the dimensional information such as user's electricity and industry attribute, GIS, the electricity consumption trend study in industry and plot can be realized, in prediction field, there is extensive use and significance.
Accompanying drawing explanation
Fig. 1 electricity demand forecasting method structural drawing;
Fig. 2 analysis of Influential Factors method structural drawing.
Specific embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with accompanying drawing, the present invention is described in more detail.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
Along with the large area installation of intelligent electric meter and the widespread use of power information acquisition system, obtain the power information of a large number of users, research user power utilization quantitative change law is made to become possibility, because user determines by industry attribute, its activity in production has that self is significantly regular, and influence factor is relatively single, and the relation of power consumption and influence factor is simpler, be easier to hold by electrical characteristics, therefore analysis of electric power consumption point more is more conducive to grasping electricity consumption variational regularity close to need for electricity.
Based on above analysis, applicants have invented a kind of system short-term electricity demand forecasting new method based on mass users electricity consumption data, this method is owing to relating to power grid user One's name is legion, data volume is large, calculated amount is large, traditional Computational frame cannot be competent at so a large amount of data evaluation works, therefore introduces the large data technique based on Hadoop framework.
According to one embodiment of present invention, the specific implementation flow process of system power consumption Forecasting Methodology of the present invention is as shown in Figure 1:
S1 data acquisition
This step mainly completes extraction to user power utilization information acquisition data such as resident, industry, business, storage and conversion.The user power utilization information that the present invention is obtained by intelligent electric meter, this information is real-time power information; Every one hour statistics user power utilization amount and the Weather information obtained at that time forms the time historical statistics point of this user; When every day morning 0 ~ 4, the time historical statistics point of this user is merged formed this user when daily power consumption, Weather information, festivals or holidays type, relevant social event information day history lists.Wherein, Weather information, festivals or holidays type, relevant social event information obtained by external system.
For No. 1st, community, garden, Jiahe, Chaoyang District, Beijing City building 0301 Room user, this user is resident, and user ID is A-BJCYJHY-01-0301, can form the time historical statistics point of this user every one hour system, as shown in the table:
Historical statistics point during table 1A-BJCYJHY-01-0301 user
| User ID | Time | Power consumption | Weather information |
| A-BCJ011-01-0301 | During 2015,03,21-14 | 4.223 degree | 18 DEG C, fine |
When every day morning 0 ~ 4, the time historical statistics point of this user is merged formed this user when daily power consumption, Weather information, festivals or holidays type, relevant social event information day history lists, as shown in the table:
Table 2A-BJCYJHY-01-0301 user day history lists
S2 user power utilization law-analysing
According to electricity consumption user type, preliminary classification is carried out to user power utilization type, as: resident's electricity consumption is divided into: electricity consumption on working day, electricity consumption at weekend, electricity consumption holiday; Industrial user does not carry out electricity consumption classification; Commercial user is divided into: electricity consumption on working day and electricity consumption holiday.
According to step S1 gained history lists according to user type and electricity consumption type to user power utilization information with user's daily power consumption for y, take date as x, carry out linear fit analysis by following formula, analyze and obtain user power utilization law curve.
y(x)＝(x
x-n+…+x
x-2+x
x-1+x)/(n+1)
N value is the value number in sampling process, and span divides according to user type and electricity consumption type, and value quantity can be chosen according to system operations ability.General, for electricity consumption on working day value should not be less than 5 working day point, electricity consumption at weekend value should not be less than 6 weekend point, electricity consumption holiday value is that mean value, continuously the electricity consumption value being no more than 3 identical festivals or holidays should not be less than 15 data points.
S3 analysis of Influential Factors
Influence factor comprises: date, weather, festivals or holidays, social event, and wherein weather conditions are mainly: gas epidemic disaster, rainfall/snow, wind-force etc.; Festivals or holidays, factor was mainly: weekend, legal extra holiday, special event holiday etc.; Social event factor mainly carries out correlating event division according to user type.Analysis of Influential Factors adopts Hadoop distributed computing framework to carry out, and first arranges fluctuation of load scope according to user type, then carries out analysis of Influential Factors to the time point exceeding fluctuation range.
As shown in Figure 2, analysis of Influential Factors method can be:
1) judge whether user is in active state, determination methods is judge that whether this daily power consumption of user is lower than threshold value according to user type.
2) then judge whether this time point user power utilization amount exceeds fluctuation range as user is in active state.
3) influence factors such as weather, festivals or holidays, social event are carried out to the time point exceeding fluctuation range and carry out unicity analysis; Wherein weather conditions are mathematic interpolation, by calculating gas epidemic disaster, the wind-force difference of this time point and the previous day and whether there is the special change such as rainfall, snowfall.
4) mean value of user power utilization amount, maximal value and variance yields is affected as then added up this influence factor for single influence factor; Wherein weather conditions need to add up corresponding difference; Unifactor model is formed according to statistics.
5) as being multinomial influence factor, then integrating step 3) gained single factors adopts following method to judge the influence coefficient of each influence factor:
A. all possible array mode contained by multinomial influence factor is added up.
B. under each array mode of matching each influence factor mean value tire out and with the matching degree of actual value.
C. choose and add up each influence factor influence coefficient to user power utilization amount in multinomial influence factor closest to array mode matching; Wherein weather conditions coefficient is combined with difference; Form the statistical model under this multinomial influence factor.
D. each influence coefficient of same model is averaged.
Analyze and obtain the influence value of each influence factor to this user power utilization amount.
For No. 1st, community, garden, Jiahe, Chaoyang District, Beijing City building 0301 Room user, this user is resident, user ID is A-BJCYJHY-01-0301, the power consumption fluctuation range arranging this resident according to Chaoyang District, Beijing City ordinarily resident's electricity consumption is ± 2 degree, activity threshold is 2 degree, and ordinarily resident associates social event and mainly comprises: business advertising campaign etc. in grave news, important competitive sports, peripheral extent.
On May 1st, 2015 be legal festivals and holidays-International Labour Day, add up this user spring-the mean value power consumption on-3 days legal festivals and holidays is 25 degree, 28 degree, 24 degree, actual this user spring-legal festivals and holidays-power consumption on International Labour Day is 24 degree, 28 degree, 24 degree, judges the analogy model using the mean value on-3 days legal festivals and holidays as-3 days legal festivals and holidays.
On May 9th, 2015 is weekend, and this user's linear analysis power consumption is 25 degree, but its actual power consumption is 28 degree, then carry out analysis of Influential Factors to this day: first analyze and show that this day exists 3 influence factors, be respectively: lower the temperature 3 DEG C, shower; Obtain cooling afterwards, shower affect statistical value to the independent of this user: cooling+0.7 degree/DEG C, shower+1.2 spends, it is electricity consumption at weekend mean value and cooling, shower influence value sum that Fitting Analysis to draw under these 3 influence factors closest to the analogy model of actual value.Calculate this analyze in the influence coefficient of each influence factor be: cooling+0.7 degree/DEG C, shower+1.2 spends, with the influence coefficient of the same affect factor of other same model average draw this user spring-weekend-cooling, shower analogy model be: electricity consumption at weekend mean value+0.7021 spends/DEG C /+1.2112 degree/shower of lowering the temperature.
On May 13rd, 2015 is common working day, this user's linear analysis power consumption is 15 degree, but its actual power consumption is 24 degree, then analysis of Influential Factors is carried out to this day: first analyze and show that this day exists 3 influence factors, be respectively: common working day, the moon ~ fine, intensification 9.5 DEG C; Judge cloudy ~ fine as common weather events, be not counted in analysis of Influential Factors, obtaining afterwards heats up affects statistical value to the independent of this user: heat up into+1 degree/DEG C, Fitting Analysis show that under logical working day, intensification influence factor this user power utilization amount is the daily level average of common work and intensification influence value sum closest to the analogy model of actual value.Calculate during this analyzes, the influence coefficient of intensification for draw after+0.9474 degree/DEG C to average with class model influence coefficient with other spring-common working day-Elevated Temperature Conditions Imitating model is common work daily power consumption+1.0211/ DEG C/heat up.
With economic and technological development zone, Beijing, Feitian, Beijing electronic medical instruments company limited is example, and Customs Assigned Number is B-BJJK0011, and arranging its fluctuation range according to economic and technological development zone, Beijing production class business electrical amount is ± 5%.
On May 1st, 2015, linear analysis show that this daily power consumption is 3230 degree, but its actual power consumption is 3782 degree, amplification is 17.09%, exceed fluctuation range, therefore analysis of Influential Factors is carried out to it: first analyze and draw existence 3 influence factors: rainfall, lower the temperature 2 DEG C, public holiday-International Labour Day, obtain rainfall afterwards, cooling, public holiday affects statistical value to the independent of this user: rainfall is+227 degree, lower the temperature is+26.3 degree/DEG C, there is not independent influence factor in the public holiday, Fitting Analysis draws rainfall, actual amplification that cooling influence value sum is not enough, judge public holiday-International Labour Day is special event, calculate public holiday-influence value on International Labour Day is for+62 degree/day, formed spring-public holiday-rainfall, the analogy model of cooling factor be electricity consumption mean value+227 degree/rainfall+26.3 degree/DEG C/cooling+62 degree/days/legal festivals and holidays.
For shop, Wangjing, Chaoyang District, Beijing City Carrefour hypermarket, Customs Assigned Number is C-BJCYJLF003, and arranging its fluctuation range according to the common trade company in Chaoyang District, Beijing City power consumption is ± 10%.
On May 1st, 2015, linear analysis show that this daily power consumption is 1112 degree, but its actual power consumption is 1521 degree, amplification is 36.78%, exceed fluctuation range, therefore analysis of Influential Factors is carried out to it: first analyze and draw existence 3 influence factors: rainfall, lower the temperature 2 DEG C, public holiday-International Labour Day, obtain rainfall afterwards, cooling, public holiday affects statistical value to the independent of this user: rainfall is-101 degree, lower the temperature is+18.9 degree/DEG C, public holiday+211 is spent, Fitting Analysis show that cooling influence value and public holiday sum are closest to actual value, judge that rainfall influence coefficient in this is analyzed is 0, judge there is not model of the same type, then with cooling for+18.9 degree/DEG C, public holiday+211 spend as spring-public holiday-rainfall, the analogy model of cooling.
S4 system power consumption is predicted
Forecasting Methodology of the present invention is:
First each influence factor information in a short time in future is obtained, then according to following short term memory influence factor select corresponding analogy model, in conjunction with user power utilization law curve and corresponding influence factor analogy model, the power consumption of following this user in a short time of simulation and forecast; Add up the electricity demand forecasting of all users in each system realm, the electricity demand forecasting of this system realm can be obtained.
For No. 1st, community, garden, Jiahe, Chaoyang District, Beijing City building 0301 Room user, this user is resident, and user ID is A-BJCYJHY-01-0301, needs prediction to play the power consumption of following 3 days these users on August 10th, 2015.Deterministic process is as follows:
Play following 3 days on August 10th, 1.2015 for common working day, transfer 27 ~ 31 July and totally 10 workaday power consumptions formation predicted mean votes in 3 ~ 7 August.
2. analyze to rise on August 10th, 2015 and within 3 days, surely cannot save vacation future, without relevant social event, Weather information is: there was thunder shower on August 13, the following average daily temperature temperature difference on the 3rd is all less than 3 DEG C, do not meet threshold value, the analogy model therefore choosing following 3 days is: August 11 summer-common working day, August 12 summer-common working day, August 13 for summer-common working day-thunder shower model.
The power consumption that analog computation obtains 3 days futures is respectively: 21 degree, 21 degree, 23 degree, its actual power consumption is 21 degree, 22 degree, 22 degree.
Compared with existing Forecasting Methodology, Forecasting Methodology tool of the present invention has the following advantages:
1. analytical approach of the present invention is based on user power utilization information, because user determines by industry attribute, its activity has obvious regularity, influence factor is relatively single, the relation of power consumption and influence factor is simpler and regular, be easier to hold by electrical characteristics, therefore analytical approach of the present invention can grasp user power utilization rule more accurately.
2. the present invention has taken into full account the major influence factors affecting user power utilization amount, and the contribution proportion of each factor when the influence value of each influence factor of statistical computation and multinomial factor acting in conjunction, therefore, Forecasting Methodology of the present invention is more accurate compared with existing Forecasting Methodology.
3. invention introduces the large data technique of Hadoop framework, reduce the computing pressure of system, improve the performance of system.
4. Forecasting Methodology of the present invention has stronger learning ability, and along with the increase of statistical model can carry out electricity demand forecasting more accurately and effectively, the process increasing new forecast model is comparatively simple, and increase new model does not need to reanalyse yet.
5. Forecasting Methodology of the present invention is a brand-new developing direction of electric system electricity demand forecasting from now on, advantageously will improve stability and the economy of operation of power networks in grid company, in addition, the combination of the dimensional information such as user power utilization amount and industry attribute, GIS, the electricity consumption trend study in industry and plot can be realized, in prediction field, there is extensive use and significance.
It should be noted that and understand, when not departing from the spirit and scope required by the claims in the present invention, various amendment and improvement can be made to the present invention of foregoing detailed description.Therefore, the scope of claimed technical scheme is not by the restriction of given any specific exemplary teachings.
Claims (10)
1. a system power consumption Forecasting Methodology, is characterized in that, comprises the following steps:
S1 data acquisition
Gathered the power information of the users such as resident, industry, business by intelligent electric meter, obtain influence factor information by external system, generate this user's history lists simultaneously;
S2 user power utilization law-analysing
In conjunction with history lists, Fitting Analysis is carried out to the user power utilization information collected, analyze and obtain user power utilization rule;
S3 analysis of Influential Factors
Fluctuation of load scope is set according to user type, analysis of Influential Factors is carried out to the time point exceeding fluctuation range, obtain the influence value of each influence factor to this user power utilization amount;
S4 system power consumption is predicted
In conjunction with user power utilization law-analysing and analysis of Influential Factors, the following short-term power consumption of system is predicted.
2. system power consumption Forecasting Methodology according to claim 1, is characterized in that, the user power utilization information that step S1 obtains is real-time power information; The mode generating history lists is that the information of acquisition is formed this user power utilization information history table by timing; Described influence factor mainly comprises: weather, festivals or holidays, social event etc.
3. system power consumption Forecasting Methodology according to claim 2, it is characterized in that, described weather conditions are mainly: gas epidemic disaster, rainfall/snow and wind-force; Festivals or holidays, factor was mainly: common weekend, legal extra holiday, special event holiday; Social event factor mainly carries out correlating event division according to user type.
4. system power consumption Forecasting Methodology according to claim 2, it is characterized in that, described history lists comprises: user ID, user power utilization amount, Weather information, festivals or holidays type, relevant social event information.
5. system power consumption Forecasting Methodology according to claim 4, it is characterized in that, the generating mode of described history lists can be: every one hour statistics user power utilization amount and the Weather information obtained at that time forms the time historical statistics point of this user; When every day morning 0 ~ 4, the time historical statistics point of this user is merged formed this user when daily power consumption, Weather information, festivals or holidays type, relevant social event information day history lists.
6. system power consumption Forecasting Methodology according to claim 1, it is characterized in that, fitting analyzing method described in step S2 is linear fit analysis.
7. system power consumption Forecasting Methodology according to claim 6, it is characterized in that, described in step, linear fit analytical approach is: according to step S1 gained history lists according to user type and electricity consumption type to user power utilization information with user's daily power consumption for y, take date as x, carry out linear fit analysis by following formula, analyze and obtain user power utilization law curve;
y(x)＝(x
x-n+…+x
x-2+x
x-1+x)/(n+1)
N value is the value number in sampling process, and span divides according to user type and electricity consumption type, and value quantity can be chosen according to system operations ability.
8. system power consumption Forecasting Methodology according to claim 2, it is characterized in that, described in step S3, analysis of Influential Factors method is:
1) judge whether user is in active state, determination methods is judge that whether this daily power consumption of user is lower than threshold value according to user type;
2) then judge whether this time point user power utilization amount exceeds fluctuation range as user is in active state;
3) influence factors such as weather, festivals or holidays, social event are carried out to the time point exceeding fluctuation range and carry out unicity analysis; Wherein weather conditions are mathematic interpolation, by calculating gas epidemic disaster, the wind-force difference of this time point and the previous day and whether there is the special change such as rainfall, snowfall;
4) mean value of user power utilization amount, maximal value and variance yields is affected as then added up this influence factor for single influence factor; Wherein weather conditions need to add up corresponding difference; Unifactor model is formed according to statistics;
5) as being multinomial influence factor, then integrating step 3) gained single factors adopts following method to judge the influence coefficient of each influence factor:
A. all possible array mode contained by multinomial influence factor is added up;
B. under each array mode of matching each influence factor mean value tire out and with the matching degree of actual value;
C. choose and add up each influence factor influence coefficient to user power utilization amount in multinomial influence factor closest to array mode matching; Wherein weather conditions coefficient is combined with difference; Form the statistical model under this multinomial influence factor;
D. each influence coefficient of same model is averaged.
9. system power consumption Forecasting Methodology according to claim 1, it is characterized in that, analysis of Influential Factors described in step S3 can adopt Hadoop distributed computing framework to carry out.
10. system power consumption Forecasting Methodology according to claim 1, it is characterized in that, described in step S4, system power consumption Forecasting Methodology is: first obtain each influence factor information in a short time in future, then according to following short term memory influence factor select corresponding analogy model, in conjunction with user power utilization law curve and corresponding influence factor analogy model, the power consumption of following this user in a short time of simulation and forecast; Add up the electricity demand forecasting of all users in each system realm, the electricity demand forecasting of this system realm can be obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510752495.8A CN105260803B (en) | 2015-11-06 | 2015-11-06 | A kind of system power consumption prediction technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510752495.8A CN105260803B (en) | 2015-11-06 | 2015-11-06 | A kind of system power consumption prediction technique |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105260803A true CN105260803A (en) | 2016-01-20 |
| CN105260803B CN105260803B (en) | 2019-04-19 |
Family
ID=55100482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510752495.8A Active CN105260803B (en) | 2015-11-06 | 2015-11-06 | A kind of system power consumption prediction technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105260803B (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809573A (en) * | 2016-03-02 | 2016-07-27 | 深圳供电局有限公司 | Big data analysis based load nature authentication method |
| CN106408183A (en) * | 2016-09-09 | 2017-02-15 | 国家电网公司 | Power supply index regulating method |
| CN106529747A (en) * | 2017-01-04 | 2017-03-22 | 成都四方伟业软件股份有限公司 | Power load predicting method and system based on large data |
| CN106992525A (en) * | 2017-05-26 | 2017-07-28 | 国网山东省电力公司泰安供电公司 | Management of power load method and apparatus |
| CN107273997A (en) * | 2016-06-30 | 2017-10-20 | 国网江苏省电力公司南通供电公司 | The Forecasting Methodology of platform area daily power consumption based on all a few coefficient linear regression model (LRM)s |
| CN107292455A (en) * | 2017-07-31 | 2017-10-24 | 华自科技股份有限公司 | Electricity demand forecasting method, device, readable storage medium storing program for executing and computer equipment |
| CN107808348A (en) * | 2017-09-28 | 2018-03-16 | 昆明能讯科技有限责任公司 | A kind of sale of electricity company provides the method that purchase of electricity declares prediction for client |
| CN108493946A (en) * | 2018-04-12 | 2018-09-04 | 辽宁石油化工大学 | Electric energy control method, device and equipment based on user power utilization analysis |
| CN108680805A (en) * | 2018-05-08 | 2018-10-19 | 广东昊阳电力建设有限公司 | Online power analysis forecasting system and electric system |
| CN109460849A (en) * | 2018-09-10 | 2019-03-12 | 杭州中恒云能源互联网技术有限公司 | A kind of user power utilization Deviation Analysis Method based on intelligent algorithm |
| CN109993424A (en) * | 2019-03-26 | 2019-07-09 | 广东艾胜物联网科技有限公司 | A kind of non-interfering formula load decomposition method based on width learning algorithm |
| CN110136024A (en) * | 2019-03-28 | 2019-08-16 | 创炘源智能科技(上海)有限公司 | Obtain the method and device with electrical feature, consumption habit and electricity demand forecasting value of user |
| CN110210672A (en) * | 2019-06-04 | 2019-09-06 | 北京百度网讯科技有限公司 | The method and apparatus of electricity demand forecasting, electronic equipment, computer-readable medium |
| CN110288215A (en) * | 2019-06-17 | 2019-09-27 | 国网甘肃省电力公司兰州供电公司 | A kind of power customer service Situation Awareness evaluation method based on entropy assessment |
| CN110414724A (en) * | 2019-07-10 | 2019-11-05 | 东软集团股份有限公司 | For predicting method, apparatus, readable storage medium storing program for executing and the electronic equipment of power consumption |
| CN110472991A (en) * | 2019-06-27 | 2019-11-19 | 拉扎斯网络科技（上海）有限公司 | Data processing method, device, server and storage medium |
| CN110689250A (en) * | 2019-09-20 | 2020-01-14 | 深圳供电局有限公司 | Method and system for processing user electricity consumption data and computer readable medium |
| CN111026791A (en) * | 2019-12-26 | 2020-04-17 | 广东电网有限责任公司电力科学研究院 | User type judgment method based on resident fine-grained electricity consumption data |
| CN111680938A (en) * | 2020-08-13 | 2020-09-18 | 国网浙江省电力有限公司 | Power flow type big data based rework and production monitoring method and system and readable medium |
| CN112070302A (en) * | 2020-09-08 | 2020-12-11 | 北京中宸泓昌科技有限公司 | Early warning method and system for power utilization safety of power grid |
| CN112434892A (en) * | 2020-12-21 | 2021-03-02 | 深圳供电局有限公司 | Differential power demand prediction method and system based on multi-factor combination learning |
| CN113239029A (en) * | 2021-05-18 | 2021-08-10 | 国网江苏省电力有限公司镇江供电分公司 | Completion method for missing daily freezing data of electric energy meter |
| CN113449919A (en) * | 2021-06-29 | 2021-09-28 | 国网山东省电力公司菏泽供电公司 | Power consumption prediction method and system based on feature and trend perception |
| CN113705999A (en) * | 2021-08-19 | 2021-11-26 | 国网河南省电力公司周口供电公司 | Electric power big data automatic reasoning platform and electric power distribution system |
| CN114169643A (en) * | 2021-12-31 | 2022-03-11 | 重庆跃达电力设备有限公司 | Photovoltaic integration scheme generation method and system based on big data prediction |
| CN114444397A (en) * | 2022-01-28 | 2022-05-06 | 国家电网有限公司 | Short-term power consumption prediction algorithm based on user portrait data model |
| CN114529072A (en) * | 2022-02-11 | 2022-05-24 | 杭州致成电子科技有限公司 | Regional electric quantity prediction method based on time series |
| CN114926213A (en) * | 2022-05-26 | 2022-08-19 | 北京中电普华信息技术有限公司 | Electricity purchasing information determining method and device based on proxy electricity purchasing |
| CN115423301A (en) * | 2022-09-01 | 2022-12-02 | 杭州达中科技有限公司 | Intelligent electric power energy management and control method, device and system based on Internet of things |
| CN115660225A (en) * | 2022-12-13 | 2023-01-31 | 浙江万胜智能科技股份有限公司 | Electricity load prediction management method and system based on ammeter communication module |
| CN115796404A (en) * | 2022-11-10 | 2023-03-14 | 国网江苏省电力有限公司营销服务中心 | Power utilization prediction method and system for agent electricity purchasing users |
| CN115829117A (en) * | 2022-11-29 | 2023-03-21 | 湖北华中电力科技开发有限责任公司 | Method and system for short-term prediction of electricity consumption in any area based on terminal electricity consumption information |
| CN116011685A (en) * | 2023-03-22 | 2023-04-25 | 国网陕西省电力有限公司西咸新区供电公司 | Electric quantity prediction method, electric quantity prediction device, computer equipment and storage medium |
| CN116526479A (en) * | 2023-07-03 | 2023-08-01 | 国网北京市电力公司 | Method, device, equipment and medium for predicting power supply quantity |
| CN116709062A (en) * | 2023-08-07 | 2023-09-05 | 安徽融兆智能有限公司 | Electricity consumption information acquisition equipment with detection function |
| CN116937569A (en) * | 2023-07-26 | 2023-10-24 | 广东永光新能源设计咨询有限公司 | Intelligent energy storage method and device for photovoltaic power generation and electronic equipment |
| CN117689070A (en) * | 2023-12-13 | 2024-03-12 | 北京朗杰科技有限公司 | Ammeter management system based on internet of things equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102723785A (en) * | 2012-07-03 | 2012-10-10 | 广东电网公司电力科学研究院 | Electric power load prediction method and electric power load prediction system based on collection of larger user intelligent terminal |
| US8600572B2 (en) * | 2010-05-27 | 2013-12-03 | International Business Machines Corporation | Smarter-grid: method to forecast electric energy production and utilization subject to uncertain environmental variables |
| CN104992239A (en) * | 2015-06-24 | 2015-10-21 | 国网山东省电力公司电力科学研究院 | Correlation coefficient-based industry electricity consumption law forecasting method |
-
2015
- 2015-11-06 CN CN201510752495.8A patent/CN105260803B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8600572B2 (en) * | 2010-05-27 | 2013-12-03 | International Business Machines Corporation | Smarter-grid: method to forecast electric energy production and utilization subject to uncertain environmental variables |
| CN102723785A (en) * | 2012-07-03 | 2012-10-10 | 广东电网公司电力科学研究院 | Electric power load prediction method and electric power load prediction system based on collection of larger user intelligent terminal |
| CN104992239A (en) * | 2015-06-24 | 2015-10-21 | 国网山东省电力公司电力科学研究院 | Correlation coefficient-based industry electricity consumption law forecasting method |
Non-Patent Citations (1)
| Title |
|---|
| 王德金: "基于大数据技术的短期负荷分析与预测", 《华东电力》 * |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809573A (en) * | 2016-03-02 | 2016-07-27 | 深圳供电局有限公司 | Big data analysis based load nature authentication method |
| CN107273997A (en) * | 2016-06-30 | 2017-10-20 | 国网江苏省电力公司南通供电公司 | The Forecasting Methodology of platform area daily power consumption based on all a few coefficient linear regression model (LRM)s |
| CN107273997B (en) * | 2016-06-30 | 2024-02-02 | 国网江苏省电力公司南通供电公司 | Method and system for predicting daily electricity consumption of platform area based on frequency coefficient linear regression model |
| CN106408183A (en) * | 2016-09-09 | 2017-02-15 | 国家电网公司 | Power supply index regulating method |
| CN106529747A (en) * | 2017-01-04 | 2017-03-22 | 成都四方伟业软件股份有限公司 | Power load predicting method and system based on large data |
| CN106992525B (en) * | 2017-05-26 | 2020-09-04 | 国网山东省电力公司泰安供电公司 | Power load management method and device |
| CN106992525A (en) * | 2017-05-26 | 2017-07-28 | 国网山东省电力公司泰安供电公司 | Management of power load method and apparatus |
| CN107292455A (en) * | 2017-07-31 | 2017-10-24 | 华自科技股份有限公司 | Electricity demand forecasting method, device, readable storage medium storing program for executing and computer equipment |
| CN107808348A (en) * | 2017-09-28 | 2018-03-16 | 昆明能讯科技有限责任公司 | A kind of sale of electricity company provides the method that purchase of electricity declares prediction for client |
| CN108493946A (en) * | 2018-04-12 | 2018-09-04 | 辽宁石油化工大学 | Electric energy control method, device and equipment based on user power utilization analysis |
| CN108680805A (en) * | 2018-05-08 | 2018-10-19 | 广东昊阳电力建设有限公司 | Online power analysis forecasting system and electric system |
| CN109460849A (en) * | 2018-09-10 | 2019-03-12 | 杭州中恒云能源互联网技术有限公司 | A kind of user power utilization Deviation Analysis Method based on intelligent algorithm |
| CN109993424A (en) * | 2019-03-26 | 2019-07-09 | 广东艾胜物联网科技有限公司 | A kind of non-interfering formula load decomposition method based on width learning algorithm |
| CN109993424B (en) * | 2019-03-26 | 2023-06-23 | 广东艾胜物联网科技有限公司 | Non-interference type load decomposition method based on width learning algorithm |
| CN110136024A (en) * | 2019-03-28 | 2019-08-16 | 创炘源智能科技(上海)有限公司 | Obtain the method and device with electrical feature, consumption habit and electricity demand forecasting value of user |
| CN110136024B (en) * | 2019-03-28 | 2023-10-10 | 上海芯联芯智能科技有限公司 | Method and device for acquiring electricity utilization characteristics, electricity utilization habits and electricity consumption predicted values of users |
| CN110210672A (en) * | 2019-06-04 | 2019-09-06 | 北京百度网讯科技有限公司 | The method and apparatus of electricity demand forecasting, electronic equipment, computer-readable medium |
| CN110288215A (en) * | 2019-06-17 | 2019-09-27 | 国网甘肃省电力公司兰州供电公司 | A kind of power customer service Situation Awareness evaluation method based on entropy assessment |
| CN110472991A (en) * | 2019-06-27 | 2019-11-19 | 拉扎斯网络科技（上海）有限公司 | Data processing method, device, server and storage medium |
| CN110472991B (en) * | 2019-06-27 | 2022-10-28 | 拉扎斯网络科技（上海）有限公司 | Data processing method, device, server and storage medium |
| CN110414724A (en) * | 2019-07-10 | 2019-11-05 | 东软集团股份有限公司 | For predicting method, apparatus, readable storage medium storing program for executing and the electronic equipment of power consumption |
| CN110689250A (en) * | 2019-09-20 | 2020-01-14 | 深圳供电局有限公司 | Method and system for processing user electricity consumption data and computer readable medium |
| CN110689250B (en) * | 2019-09-20 | 2023-04-14 | 深圳供电局有限公司 | Method and system for processing user electricity consumption data and computer readable medium |
| CN111026791A (en) * | 2019-12-26 | 2020-04-17 | 广东电网有限责任公司电力科学研究院 | User type judgment method based on resident fine-grained electricity consumption data |
| CN111680938A (en) * | 2020-08-13 | 2020-09-18 | 国网浙江省电力有限公司 | Power flow type big data based rework and production monitoring method and system and readable medium |
| CN112070302A (en) * | 2020-09-08 | 2020-12-11 | 北京中宸泓昌科技有限公司 | Early warning method and system for power utilization safety of power grid |
| CN112434892A (en) * | 2020-12-21 | 2021-03-02 | 深圳供电局有限公司 | Differential power demand prediction method and system based on multi-factor combination learning |
| CN113239029A (en) * | 2021-05-18 | 2021-08-10 | 国网江苏省电力有限公司镇江供电分公司 | Completion method for missing daily freezing data of electric energy meter |
| CN113449919A (en) * | 2021-06-29 | 2021-09-28 | 国网山东省电力公司菏泽供电公司 | Power consumption prediction method and system based on feature and trend perception |
| CN113705999A (en) * | 2021-08-19 | 2021-11-26 | 国网河南省电力公司周口供电公司 | Electric power big data automatic reasoning platform and electric power distribution system |
| CN114169643A (en) * | 2021-12-31 | 2022-03-11 | 重庆跃达电力设备有限公司 | Photovoltaic integration scheme generation method and system based on big data prediction |
| CN114444397A (en) * | 2022-01-28 | 2022-05-06 | 国家电网有限公司 | Short-term power consumption prediction algorithm based on user portrait data model |
| CN114529072A (en) * | 2022-02-11 | 2022-05-24 | 杭州致成电子科技有限公司 | Regional electric quantity prediction method based on time series |
| CN114926213A (en) * | 2022-05-26 | 2022-08-19 | 北京中电普华信息技术有限公司 | Electricity purchasing information determining method and device based on proxy electricity purchasing |
| CN115423301B (en) * | 2022-09-01 | 2023-04-25 | 杭州达中科技有限公司 | Intelligent electric power energy management and control method, device and system based on Internet of things |
| CN115423301A (en) * | 2022-09-01 | 2022-12-02 | 杭州达中科技有限公司 | Intelligent electric power energy management and control method, device and system based on Internet of things |
| CN115796404A (en) * | 2022-11-10 | 2023-03-14 | 国网江苏省电力有限公司营销服务中心 | Power utilization prediction method and system for agent electricity purchasing users |
| CN115829117B (en) * | 2022-11-29 | 2023-09-19 | 湖北华中电力科技开发有限责任公司 | Method and system for predicting electricity consumption in any area in short time based on terminal electricity consumption |
| CN115829117A (en) * | 2022-11-29 | 2023-03-21 | 湖北华中电力科技开发有限责任公司 | Method and system for short-term prediction of electricity consumption in any area based on terminal electricity consumption information |
| CN115660225A (en) * | 2022-12-13 | 2023-01-31 | 浙江万胜智能科技股份有限公司 | Electricity load prediction management method and system based on ammeter communication module |
| CN116011685A (en) * | 2023-03-22 | 2023-04-25 | 国网陕西省电力有限公司西咸新区供电公司 | Electric quantity prediction method, electric quantity prediction device, computer equipment and storage medium |
| CN116526479A (en) * | 2023-07-03 | 2023-08-01 | 国网北京市电力公司 | Method, device, equipment and medium for predicting power supply quantity |
| CN116526479B (en) * | 2023-07-03 | 2023-10-13 | 国网北京市电力公司 | Method, device, equipment and medium for predicting power supply quantity |
| CN116937569A (en) * | 2023-07-26 | 2023-10-24 | 广东永光新能源设计咨询有限公司 | Intelligent energy storage method and device for photovoltaic power generation and electronic equipment |
| CN116709062A (en) * | 2023-08-07 | 2023-09-05 | 安徽融兆智能有限公司 | Electricity consumption information acquisition equipment with detection function |
| CN116709062B (en) * | 2023-08-07 | 2023-10-20 | 安徽融兆智能有限公司 | Electricity consumption information acquisition equipment with detection function |
| CN117689070A (en) * | 2023-12-13 | 2024-03-12 | 北京朗杰科技有限公司 | Ammeter management system based on internet of things equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105260803B (en) | 2019-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105260803B (en) | A kind of system power consumption prediction technique | |
| CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
| Wang et al. | Electric load forecasting with recency effect: A big data approach | |
| CN107895283B (en) | Merchant passenger flow volume big data prediction method based on time series decomposition | |
| Hu et al. | A hybrid model based on CNN and Bi-LSTM for urban water demand prediction | |
| US20180351355A1 (en) | Method for identifying pattern of load cycle | |
| Pedregal et al. | Mid-term hourly electricity forecasting based on a multi-rate approach | |
| CN103226736B (en) | Based on the long-medium term power load forecasting method of cluster analysis and grey target theory | |
| CN105184455A (en) | High dimension visualized analysis method facing urban electric power data analysis | |
| CN109858728B (en) | Load prediction method based on industry-divided electricity utilization characteristic analysis | |
| US20210326696A1 (en) | Method and apparatus for forecasting power demand | |
| CN111896680B (en) | Greenhouse gas emission analysis method and system based on satellite remote sensing data | |
| CN103854068A (en) | Method for forecasting residential quarter short-term loads | |
| CN103413253A (en) | Method for performing classification prediction on annual maximum load based on economical and meteorological factors | |
| CN104537433A (en) | Sold electricity quantity prediction method based on inventory capacities and business expansion characteristics | |
| Zhang et al. | Impact of structure on unified efficiency for Chinese service sector—A two-stage analysis | |
| CN104657788A (en) | Method for predicting key industrial electricity consumption based on industrial condition index | |
| CN108256724B (en) | Power distribution network open capacity planning method based on dynamic industry coefficient | |
| CN105184388A (en) | Non-linear regression method for urban power load short-period prediction | |
| CN104881718A (en) | Regional power business index constructing method based on multi-scale leading economic indicators | |
| Zhang et al. | Effect of physical, environmental, and social factors on prediction of building energy consumption for public buildings based on real-world big data | |
| CN115759371A (en) | GCN-LSTM-based short-term load prediction method for power system | |
| Zhao et al. | Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression | |
| CN104715156A (en) | Building energy-saving potential dynamic assessment method | |
| CN105913366A (en) | Industrial electric power big data-based regional industry business climate index building method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |