CN104392274A - Urban short-term electrical load prediction method based on trend of electrical load and temperature - Google Patents
Urban short-term electrical load prediction method based on trend of electrical load and temperature Download PDFInfo
- Publication number
- CN104392274A CN104392274A CN201410591939.XA CN201410591939A CN104392274A CN 104392274 A CN104392274 A CN 104392274A CN 201410591939 A CN201410591939 A CN 201410591939A CN 104392274 A CN104392274 A CN 104392274A
- Authority
- CN
- China
- Prior art keywords
- load
- temperature
- city
- trend
- power load
- 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
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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses an urban short-term electrical load prediction method based on the trend of an electrical load and temperature. The method comprises the following steps that S01. a forecast day is confirmed, and historical urban electrical load and urban temperature data of S days before the forecast day and S days before and after the forecast day in total in the previous year; S02. power grid sudden increment data are inputted; S03. the trend change relation of the electrical load and urban temperature is judged; S04. when the trend change relation of the urban electrical load and temperature data of the S days before and after the forecast day in total in the previous year is trend correlation, urban forecast day electrical load accurate prediction of the forecast day is performed in combination with the inputted power grid sudden increment data in the step S02 via an urban load prediction model algorithm, or forecast day electrical load accurate prediction is calculated via an averaging urban load prediction algorithm; and S05. the result of urban electrical load prediction is outputted. The meteorological numerical forecast is used as meteorological forecast information so that the urban electrical load based on meteorological factors can be predicted in a high-precision way.
Description
Technical field
The present invention relates to electric system electro-load forecast technical field, particularly relate to a kind of city short-term electro-load forecast method based on power load and temperature trend.
Background technology
City short-term electro-load forecast is the routine work of power scheduling department, it comprises forecast day load prediction, and (peak load is predicted, average load is predicted), forecast day 96 point (every 15 minutes) electricity need load is predicted, keep predicting the outcome of high-accuracy, rational dispatching of power netwoks strategy can be formulated, increase economic benefit, the meteorologic factor on city short-term power load and city same day is closely related, the temperature in city directly affects the overall power load in city, other meteorologic factors are as wind speed, rainfalls etc. finally affect city load in the mode of temperature, in prior art, city short-term load forecasting calculates based on the mathematics of urban history load value mostly, some algorithm with reference to average daily temperature, but traditional algorithm is not considered the impact of meteorologic factor or is just simply used forecast day weather forecast data, forecast precision cannot be met consumers' demand, the too complicated practicality of traditional algorithm is poor on the other hand.
Such as, patent CN103514491A discloses a kind of Methods of electric load forecasting, comprise: step 1: utilize historical data, each year Load characteristics index and multiple influence factor are carried out tentative calculation, sets up the quantitative relation formula of each year Load characteristics index and multiple influence factor; Described historical data comprises in the past each year Load characteristics index data for many years and each factor to affect data; Step 2: utilize the quantitative relation formula obtained in step 1, predicts each year Load characteristics index in time to be predicted, and predicts the annual electricity generating capacity in time to be predicted according to each year Load characteristics index of prediction; Step 3: the annual electricity generating capacity of prediction is assigned to every month, annual electricity generating capacity prediction and moon generated energy prediction is carried out by this inventive method, but still utilize each year Load characteristics index data for many years and each factor to affect data, do not relate to meteorological factor influence, the accurately predicting of short-term city day power load can not be realized.
Current city short-term load forecasting calculates based on the mathematics of urban history load value mostly, and the method is not considered the impact of meteorologic factor or just simply used forecast day weather forecast data, makes Load Forecasting degree of accuracy not high.
Current Utilities Electric Co. at different levels uses maximum Forecasting Methodologies based on historical data " neural network " algorithm, the method considers the deviation of historical data and nearest predicted data and real data, continuous checking parameter, reduce error, the method calculation of complex, computational accuracy is smoothly changed to load higher, when load and responsive to temperature higher time or load change larger time precision not high, it is mathematical model method from essence.
Existing city short-term electro-load forecast major technique shortcoming is as follows:
Existing city load forecasting model is too much paid attention to historical data and is excavated, use multiple mathematical algorithm, find the relation of historical data and Future Data, but the principal element of electricity need load is environment and industrial development situation, these can cause precision of prediction not high by temporal data model.
Existing city load forecasting model, when using meteorologic factor, adopts history tendency similarity method determination meteorologic factor and city load relation, causes a large amount of calculating historical datas to calculate and fitting algorithm calculating, makes computation model lose actual use meaning.Such as, patent CN103606022A discloses a kind of short-term load forecasting method, comprising: the value obtaining the value of the forecast meteorological factor of day to be predicted and the meteorological factor of several history days; According to preset cumulative effect formula, the value of the forecast meteorological factor of day to be predicted and the value of the Practical Meteorological Requirements factor are revised; Obtain network load value and the short-term load forecasting data of several history day, contrast, and ask for its error; Matching is carried out to the value of the Practical Meteorological Requirements factor through several history days revised and network load value, obtains relational model between the two; The error between network load value and short-term load forecasting data is utilized to correct described relational model; According to the relational model after rectification, the network load of day to be predicted is predicted, although this invention relate to meteorologic factor, only considers the cumulative effect of meteorological factor, do not relate to the weather data of actual history point, can not accurately predicting short-term city day power load.
Existing city load forecasting model does not select suitable meteorologic factor forecasting procedure, and use weather data more with daily forecast data, to becoming more meticulous, Weather Forecast Information is not understood, and particularly the load prediction precision of 96 is lower to cause short-term load forecasting.
Summary of the invention
The present invention proposes a kind of city short-term electro-load forecast method based on power load and temperature trend, use refined temperature forecast value, the refined temperature forecast value (once per hour) of current meteorological department is very accurate, the basis that high-precision temperature predicted value is predicted as electricity need load; The meteorologic factor of electricity need load and forecast day is closely related, analysis city load and city temperature relation judge the variation tendency that load is nearest, and introduce dispatching of power netwoks department burst factor is affected, the input of this partial parameters is completed alternately by artificial data, burst factor is brought model into and is calculated, and participates in city carry calculation, and calculates future anticipation data based on this, far be better than the adaptation function of traditional algorithm to the long-term correction of this partial parameters, precision of prediction is high.
Technical solution of the present invention is as follows:
Based on a city short-term electro-load forecast method for power load and temperature trend, comprise the following steps,
S01, determine forecast day, to obtain before forecast day S days and the historical city power load of S days and city temperature data altogether before and after the previous year forecast day, as the value sequence that electro-load forecast calculates, foundation value sequence carries out power load and city temperature Long-term change trend Relationship Prediction;
Electricity need load prediction comprises 96 point load predictions, the prediction of forecast day peak load and average load prediction;
S02, the incremental data that happened suddenly by electrical network is input in the load forecasting model algorithm of city; To burst factor, (great user goes into operation, Generator Set burst is grid-connected in dispatching of power netwoks department, except electric network fault) impact can accurate assurance, the input of this partial parameters is completed alternately by artificial data, burst factor can be brought model immediately into and be calculated, and participates in city carry calculation, and calculates future anticipation data based on this, compare and the adaptation function of traditional algorithm to the long-term correction of this partial parameters, efficiency is high, and calculate simple, data are accurate.Because the historical data that the present invention is based on directly is imported by the data stored, do not need manual input, therefore, only manually input electrical network burst increment, simple to operate;
S03, according to the historical city power load of S days before step S01 forecast day and city temperature data, power load and city temperature Long-term change trend relation is carried out to judge, power load and city temperature Long-term change trend relation are divided into trend correlation and trend independence, when the historical city power load of S before forecast day days and the Long-term change trend of city temperature data close be trend correlation time, the electrical network burst incremental data of integrating step S02 input, by city load forecasting model algorithm, city forecast day power load accurately predicting is carried out to forecast day, otherwise, electricity need load and the temperature record Long-term change trend relation of carrying out before and after forecast day the previous year common S days judge,
Power load and the trend correlation of city temperature Long-term change trend relation comprise trend homogeny and trend phase reflexive, trend homogeny, trend phase reflexive and trend independence determination methods are as follows: the temperature of S days and load data are combined between two according to the adjacent date, be divided into S-1 group, when the group number identical with Calculating Temperature Variation when power load is more than or equal to Y group, power load is trend homogeny with the accumulated change effect of temperature; When the group number that temperature is contrary with power load variation tendency is more than or equal to Y group, power load is trend phase reflexive with the accumulated change effect of temperature; Otherwise power load is independence with the accumulated change effect of temperature.
S04, before and after the previous year forecast day, the electricity need load of S days and temperature record Long-term change trend close altogether when being trend correlation, the electrical network burst incremental data of integrating step S02 input, by city load forecasting model algorithm, city forecast day power load accurately predicting is carried out to forecast day, otherwise, calculate city forecast day power load accurately predicting by averaging method city Load Forecast Algorithm;
S05, electricity need load predicts the outcome output.
City load forecasting model algorithm described in step S03 and step S04 specifically comprises the following steps,
96 point load predictions, the prediction of forecast day peak load are with on average load forecasting method is all identical;
(301) temperature and power load variation tendency relevant group in value sequence is filtered out, suppose that the quantity of trend correlation group is r group, r group trend correlation group comprises n group data altogether, often organizes the city temperature that data include electricity need load and electricity need load metering correspondence;
When carrying out the prediction of forecast day peak load and average load prediction, the historical city power load of S days comprises S group data (peak load, average load and corresponding maximum temperature, temperature on average) altogether with city temperature data, the quantity of trend correlation group is r group, then r group trend correlation group comprises r group data altogether, namely carry out forecast day peak load prediction and average load prediction time n=r;
When carrying out 96 points, (within every 15 minutes, a point is counted at interval, one day 24 hours totally 96 electricity) load prediction time, n=96*r, n group data are the value data (at interval of the power load of 15 minutes moment point and the temperature value of moment point) at interval of 15 minutes in r days;
(302) average rate of change of power load
computing formula is formula (1):
In formula (1):
for power load is with the rate of change of temperature Change, wherein i is i-th group of data group of n group data; Δ P
ibe the difference of the power load value of i-th group of power load value and the i-th-1 group, Δ T
ithe difference of the temperature value of i-th group of temperature value and i-1 group;
N is the group number of the data that power load comprises with Calculating Temperature Variation relevant group;
(303) calculate electro-load forecast, be formula (2):
In formula:
P
in advancethe power load of-prediction day future position is unknown quantity, unit: MW;
P
realthe actual load of the last historical data of-future position is known quantity, unit: MW; Last historical data refers to previous data measuring point historical data;
T
in advancethe temperature value that becomes more meticulous of-prediction day future position is known quantity, unit: DEG C;
T
realthe live temperature of-future position last history measurement point is known quantity, unit: DEG C;
P
prominentthe electrical network burst incremental data of-operator input, unit: MW.
Step S04 averaging method city Load Forecast Algorithm calculates city forecast day power load accurately predicting, specifically comprises the following steps:
When power load is the Long-term change trend independence of power load with temperature, rule of thumb data, before selecting forecast day, the averaging method of the power load sequence of S day calculates city load prediction data, formula (3):
In formula:
P
in advancethe power load of-prediction day future position is unknown quantity, unit: MW;
P
ii-th group of power load value in-S day value sequence, unit: MW.
Compared with prior art, the present invention includes following beneficial effect:
The present invention uses meteorological numerical forecasting as Weather Forecast Information, fine temperature forecast information can reach several per hour, the electricity need load high-precision forecast based on meteorological (temperature) factor is made to become possibility, solve and only use degree/day forecast information, Weather Forecast Information is problem of rough too.
The present invention by recent temperature factor, the same period last year temperature and load tendency trend, judge that temperature is to city loading effects trend, solve the complicated algorithm that in Classical forecast model, searching is identical with history tendency.
The present invention inputs electrical network burst incrementation parameter by man-machine interactively mode, and based on interaction parameter, computing is participated in city load forecasting model algorithm calculates, make burst factor incorporate algorithm rapidly in prediction, solving conventional model affects the difficult problem that cannot overcome in a short time to burst factor (great user goes into operation, Generator Set happens suddenly grid-connected).
Accompanying drawing explanation
A kind of city short-term electro-load forecast method based on power load and temperature trend of Fig. 1 the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in further detail.
As shown in Figure 1, a kind of city short-term electro-load forecast method based on power load and temperature trend, comprises the following steps,
S01, determine forecast day, to obtain before forecast day S days and the historical city power load of S days and city temperature data altogether before and after the previous year forecast day, as the value sequence that electro-load forecast calculates, foundation value sequence carries out power load and city temperature Long-term change trend Relationship Prediction;
Electricity need load prediction comprises 96 point load predictions, the prediction of forecast day peak load and average load prediction;
The meteorologic factor of electricity need load and forecast day is closely related, but the change of electricity need load also has continuity and tendency, must recent or extract both trend relations of (generally getting ten days normal period one of meteorological department as a period of supervision) in the cycle of forecast day place the same period in former years in historical data, the present embodiment choose forecast day before the city load of 11 days and city temperature relation judge the variation tendency that load is nearest, this partial data contains electricity need load up-to-date information and the relation information with temperature, is the first weight.When nearest variation tendency is not obvious, the trend of current period is judged by the historical data of last year (same period last year forecast day before and after each five day data), it represents the variation tendency in the former years of same period, and the historical data of the present embodiment last year to be removed before and after prediction day in year 5 days and predicted that day (totally 11 days) data do identical judgement last year.
S02, the incremental data that happened suddenly by electrical network is input in the load forecasting model algorithm of city; To burst factor, (great user goes into operation, Generator Set burst is grid-connected in dispatching of power netwoks department, except electric network fault) impact can accurate assurance, the input of this partial parameters is completed alternately by artificial data, burst factor can be brought model immediately into and be calculated, and participates in city carry calculation, and calculates future anticipation data based on this, compare and the adaptation function of traditional algorithm to the long-term correction of this partial parameters, efficiency is high, and calculate simple, data are accurate.Because the historical data that the present invention is based on directly is imported by the data stored, do not need manual input, therefore, only manually input electrical network burst increment, simple to operate;
S03, according to the historical city power load of S days before step S01 forecast day and city temperature data, power load and city temperature Long-term change trend relation is carried out to judge, power load and city temperature Long-term change trend relation are divided into trend correlation and trend independence, when the historical city power load of S before forecast day days and the Long-term change trend of city temperature data close be trend correlation time, the electrical network burst incremental data of integrating step S02 input, by city load forecasting model algorithm, city forecast day power load accurately predicting is carried out to forecast day, otherwise, electricity need load and the temperature record Long-term change trend relation of carrying out before and after forecast day the previous year common S days judge,
Power load and the trend correlation of city temperature Long-term change trend relation comprise trend homogeny and trend phase reflexive: the temperature of S days and load data are combined between two according to the adjacent date, be divided into S-1 group, when the group number identical with Calculating Temperature Variation when power load is more than or equal to Y group, power load is trend homogeny with the accumulated change effect of temperature; When the group number that temperature is contrary with power load variation tendency is more than or equal to Y group, power load is trend phase reflexive with the accumulated change effect of temperature; Otherwise power load is independence with the accumulated change effect of temperature.
In the present embodiment, temperature and the power load data of 11 days combined between two according to the adjacent date, can be divided into 10 groups, and when the group number identical with Calculating Temperature Variation when load is more than or equal to 7 groups, load is homogeny with the accumulated change effect of temperature; When the group number that temperature is contrary with load variations trend is more than or equal to 7 groups, load is phase reflexive with the accumulated change effect of temperature; All the other situations are independence.After prediction 11 days a few days ago judgement trend is independence, remove before and after prediction day in year 5 days and predicted that day (totally 11 days) data did identical judgement with last year, Load Forecast Algorithm model is then entered as having tendency, otherwise will be judged as that this place time period prediction day and temperature variation have nothing to do, enter the day city load prediction of averaging method computational prediction.This algorithm by scope access time (namely aforesaid 11 days) and trend correlation judges time eigenwert (aforesaid 7 groups) be designed to configurable parameter, parameter is adjusted, to meet the load of different regions and Various Seasonal with temperature accumulated change effect analysis by long data verification.
S04, before and after the previous year forecast day, the electricity need load of S days and temperature record Long-term change trend close altogether when being trend correlation, the electrical network burst incremental data of integrating step S02 input, by city load forecasting model algorithm, city forecast day power load accurately predicting is carried out to forecast day, otherwise, calculate city forecast day power load accurately predicting by averaging method city Load Forecast Algorithm;
S05, electricity need load predicts the outcome output.
City load forecasting model algorithm described in step S03 and step S04 specifically comprises the following steps,
96 point load predictions, the prediction of forecast day peak load are with on average load forecasting method is all identical;
(301) temperature and power load variation tendency relevant group in value sequence is filtered out, suppose that the quantity of trend correlation group is r group, r group trend correlation group comprises n group data altogether, often organizes the city temperature that data include electricity need load and electricity need load metering correspondence;
When carrying out the prediction of forecast day peak load and average load prediction, the historical city power load of S days comprises S group data (peak load, average load and corresponding maximum temperature, temperature on average) altogether with city temperature data, the quantity of trend correlation group is r group, then r group trend correlation group comprises r group data altogether, namely carry out forecast day peak load prediction and average load prediction time n=r;
When carrying out 96 points, (within every 15 minutes, a point is counted at interval, one day 24 hours totally 96 electricity) load prediction time, n=96*r, n group data are the value data (at interval of the power load of 15 minutes moment point and the temperature value of moment point) at interval of 15 minutes in r days;
(302) average rate of change computing formula of power load is formula (1):
In formula (1):
for power load is with the rate of change of temperature Change, wherein i is i-th group of data group of n group data; Δ P
ibe the difference of the power load value of i-th group of power load value and the i-th-1 group, Δ T
ithe difference of the temperature value of i-th group of temperature value and i-1 group;
N is the group number of the data that power load comprises with Calculating Temperature Variation relevant group;
(303) calculate electro-load forecast, be formula (2):
In formula:
P
in advancethe power load of-prediction day future position is unknown quantity, unit: MW;
P
realthe actual load of the last historical data of-future position is known quantity, unit: MW;
T
in advancethe temperature value that becomes more meticulous of-prediction day future position is known quantity, unit: DEG C;
T
realthe live temperature of the last history of-future position is known quantity, unit: DEG C;
P
prominentelectrical network burst incremental data unit: the MW of-operator input.
Step S03 averaging method city Load Forecast Algorithm calculates city forecast day power load accurately predicting, specifically comprises the following steps:
When power load is the Long-term change trend independence of power load with temperature, rule of thumb data, before selecting forecast day, the averaging method of the power load sequence of S day calculates city load prediction data, formula (3):
In formula:
P
in advancethe power load of-prediction day future position is unknown quantity, unit: MW;
P
ii-th group of power load value of-S day value sequence, unit: MW.
Those skilled in the art can change the present invention or modification design but do not depart from thought of the present invention and scope.Therefore, if these amendments of the present invention and modification belong within the claims in the present invention and equivalent technical scope thereof, then the present invention is also intended to comprise these change and modification.
Claims (4)
1., based on a city short-term electro-load forecast method for power load and temperature trend, it is characterized in that, comprise the following steps,
S01, determine forecast day, to obtain before forecast day S days and the historical city power load of S days and city temperature data altogether before and after the previous year forecast day, the value sequence that described historical city power load and city temperature data calculate as electro-load forecast, carries out power load and city temperature Long-term change trend Relationship Prediction according to value sequence;
Described electricity need load prediction comprises 96 point load predictions, the prediction of forecast day peak load and average load prediction;
S02, the incremental data that happened suddenly by electrical network is input in the load forecasting model algorithm of city;
S03, according to the historical city power load of S days before forecast day described in step S01 and city temperature data, carry out power load and city temperature Long-term change trend relation judges, power load and city temperature Long-term change trend relation are divided into trend correlation and trend independence, when the historical city power load of S before forecast day days and the Long-term change trend of city temperature data close be trend correlation time, the electrical network burst incremental data of integrating step S02 input, by city load forecasting model algorithm, city forecast day power load accurately predicting is carried out to forecast day, otherwise, electricity need load and the temperature record Long-term change trend relation of carrying out before and after forecast day the previous year common S days judge,
S04, before and after the previous year forecast day, the electricity need load of S days and temperature record Long-term change trend close altogether when being trend correlation, in conjunction with the electrical network burst incremental data of described step S02 input, by city load forecasting model algorithm, city forecast day power load accurately predicting is carried out to forecast day, otherwise, calculate city forecast day power load accurately predicting by averaging method city Load Forecast Algorithm;
S05, electricity need load predicts the outcome output.
2. a kind of city short-term electro-load forecast method based on power load and temperature trend according to claim 1, it is characterized in that, it is identical contrary with trend that described step S03 power load and the trend correlation of city temperature Long-term change trend relation comprise trend;
The identical deterministic process contrary to trend of trend comprises: the temperature of described S days and load data are combined between two according to the adjacent date, be divided into S-1 group, when the group number identical with Calculating Temperature Variation when power load is more than or equal to Y group, power load is trend homogeny with the accumulated change effect of temperature; When the group number that temperature is contrary with power load variation tendency is more than or equal to Y group, power load is trend phase reflexive with the accumulated change effect of temperature; Otherwise power load is independence with the accumulated change effect of temperature.
3. a kind of city short-term electro-load forecast method based on power load and temperature trend according to claim 1, it is characterized in that, described in step S04, city load forecasting model algorithm specifically comprises the following steps,
(301) temperature and power load variation tendency relevant group in value sequence is filtered out, suppose that the quantity of trend correlation group is r group, r group trend correlation group comprises n group data altogether, often organizes the city temperature that data include electricity need load and described electricity need load metering correspondence;
(302) average rate of change computing formula of power load is formula (1):
In formula (1):
for power load is with the rate of change of temperature Change, wherein i represents i-th group of data group of n group data; Δ P
ibe the difference of the power load value of i-th group of power load value and the i-th-1 group, Δ T
ithe difference of the temperature value of i-th group of temperature value and i-1 group;
N is the group number of the data that power load comprises with Calculating Temperature Variation relevant group;
(303) calculate electro-load forecast, be formula (2):
In formula:
P
in advancethe power load of-prediction day future position;
P
realthe actual load of the last historical data of-future position;
T
in advancethe temperature value that becomes more meticulous of-prediction day future position;
T
realthe live temperature of the last history of-future position;
P
prominentthe electrical network burst incremental data of-operator input.
4. a kind of city short-term electro-load forecast method based on power load and temperature trend according to claim 1, it is characterized in that, described step S04 averaging method city Load Forecast Algorithm calculates city forecast day power load accurately predicting, specifically comprises the following steps:
When power load is the Long-term change trend independence of power load with temperature, rule of thumb data, before selecting forecast day, the averaging method of the power load sequence of S day calculates city load prediction data, and it is formula (3) that averaging method calculates city load prediction data:
In formula:
P
in advancethe power load of-prediction day future position;
P
ii-th group of power load value of-S day value sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410591939.XA CN104392274B (en) | 2014-10-29 | 2014-10-29 | The short-term electro-load forecast method in city based on power load and temperature trend |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410591939.XA CN104392274B (en) | 2014-10-29 | 2014-10-29 | The short-term electro-load forecast method in city based on power load and temperature trend |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104392274A true CN104392274A (en) | 2015-03-04 |
| CN104392274B CN104392274B (en) | 2017-10-31 |
Family
ID=52610174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410591939.XA Active CN104392274B (en) | 2014-10-29 | 2014-10-29 | The short-term electro-load forecast method in city based on power load and temperature trend |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104392274B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160588A (en) * | 2015-05-27 | 2015-12-16 | 南京国云电力有限公司 | Electricity load characteristic analysis method |
| CN105631483A (en) * | 2016-03-08 | 2016-06-01 | 国家电网公司 | Method and device for predicting short-term power load |
| CN107394890A (en) * | 2017-07-03 | 2017-11-24 | 三峡大学 | A kind of electricity dispatching method and device |
| CN107797006A (en) * | 2017-10-19 | 2018-03-13 | 国家电网公司 | Transformer load Forecasting Methodology and device |
| CN109546652A (en) * | 2018-12-24 | 2019-03-29 | 国网湖南省电力有限公司 | The Methods of electric load forecasting of distribute-electricity transformer district |
| CN110956298A (en) * | 2018-09-27 | 2020-04-03 | 上海博英信息科技有限公司 | Load prediction method based on air temperature confidence interval |
| CN111242805A (en) * | 2020-01-09 | 2020-06-05 | 南方电网科学研究院有限责任公司 | Method and device for calculating increase rate of power consumption |
| CN111626518A (en) * | 2020-05-29 | 2020-09-04 | 上海交通大学 | Urban daily water demand online prediction method based on deep learning neural network |
| CN112467723A (en) * | 2019-11-20 | 2021-03-09 | 乐清市泰博恒电子科技有限公司 | Power network processing method based on big data and database |
| CN117726195A (en) * | 2024-02-07 | 2024-03-19 | 创意信息技术股份有限公司 | City management event quantity change prediction method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103235981A (en) * | 2013-04-10 | 2013-08-07 | 东南大学 | Wind power quality trend predicting method |
| CN103268524A (en) * | 2013-06-03 | 2013-08-28 | 国家电网公司 | Method for improving power grid short-term load forecasting accuracy |
| CN103971296A (en) * | 2014-05-16 | 2014-08-06 | 国家电网公司 | Power purchase method for mathematic model based on electrical loads and temperature |
| CN104036327A (en) * | 2014-06-20 | 2014-09-10 | 国家电网公司 | Fast bus load forecasting method for smart distribution network |
-
2014
- 2014-10-29 CN CN201410591939.XA patent/CN104392274B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103235981A (en) * | 2013-04-10 | 2013-08-07 | 东南大学 | Wind power quality trend predicting method |
| CN103268524A (en) * | 2013-06-03 | 2013-08-28 | 国家电网公司 | Method for improving power grid short-term load forecasting accuracy |
| CN103971296A (en) * | 2014-05-16 | 2014-08-06 | 国家电网公司 | Power purchase method for mathematic model based on electrical loads and temperature |
| CN104036327A (en) * | 2014-06-20 | 2014-09-10 | 国家电网公司 | Fast bus load forecasting method for smart distribution network |
Non-Patent Citations (1)
| Title |
|---|
| 盛琼等: "湖州市用电需求特性及其与气象条件的关系", 《大气科学学报》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160588A (en) * | 2015-05-27 | 2015-12-16 | 南京国云电力有限公司 | Electricity load characteristic analysis method |
| CN105631483A (en) * | 2016-03-08 | 2016-06-01 | 国家电网公司 | Method and device for predicting short-term power load |
| CN105631483B (en) * | 2016-03-08 | 2019-03-12 | 国家电网公司 | A kind of short-term electro-load forecast method and device |
| CN107394890A (en) * | 2017-07-03 | 2017-11-24 | 三峡大学 | A kind of electricity dispatching method and device |
| CN107797006A (en) * | 2017-10-19 | 2018-03-13 | 国家电网公司 | Transformer load Forecasting Methodology and device |
| CN107797006B (en) * | 2017-10-19 | 2020-06-12 | 国家电网公司 | Transformer load prediction method and device |
| CN110956298A (en) * | 2018-09-27 | 2020-04-03 | 上海博英信息科技有限公司 | Load prediction method based on air temperature confidence interval |
| CN109546652A (en) * | 2018-12-24 | 2019-03-29 | 国网湖南省电力有限公司 | The Methods of electric load forecasting of distribute-electricity transformer district |
| CN109546652B (en) * | 2018-12-24 | 2022-04-08 | 国网湖南省电力有限公司 | Power load prediction method for distribution transformer area |
| CN112467723A (en) * | 2019-11-20 | 2021-03-09 | 乐清市泰博恒电子科技有限公司 | Power network processing method based on big data and database |
| CN111242805A (en) * | 2020-01-09 | 2020-06-05 | 南方电网科学研究院有限责任公司 | Method and device for calculating increase rate of power consumption |
| CN111242805B (en) * | 2020-01-09 | 2023-07-11 | 南方电网科学研究院有限责任公司 | Power consumption increase rate calculation method and device |
| CN111626518A (en) * | 2020-05-29 | 2020-09-04 | 上海交通大学 | Urban daily water demand online prediction method based on deep learning neural network |
| CN117726195A (en) * | 2024-02-07 | 2024-03-19 | 创意信息技术股份有限公司 | City management event quantity change prediction method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104392274B (en) | 2017-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104392274A (en) | Urban short-term electrical load prediction method based on trend of electrical load and temperature | |
| Lowery et al. | Impact of wind forecast error statistics upon unit commitment | |
| Bessa et al. | Reserve setting and steady-state security assessment using wind power uncertainty forecast: A case study | |
| Lannoye et al. | Power system flexibility assessment—State of the art | |
| CN102521674B (en) | Computer generating method for short-term load forecasting in summer in power consumer electricity-utilization information acquisition system | |
| CN103336891B (en) | A kind of pseudo-measurement generation method estimated for state of electric distribution network | |
| JP2012023816A (en) | Information processing equipment, and program thereof | |
| CN107403015B (en) | Short-term optical power prediction method based on time series similarity | |
| Hamann et al. | Real-time optimization of the mid-columbia hydropower system | |
| CN102509173A (en) | Markov chain based method for accurately forecasting power system loads | |
| CN103984986A (en) | Method for correcting wind power ultra-short-period prediction of self-learning ARMA model in real time | |
| Ward et al. | Simulating price-aware electricity storage without linear optimisation | |
| Liu et al. | A MILP-based battery degradation model for economic scheduling of power system | |
| CN104156885A (en) | Fast wind power capacity reliability calculating method based on reliability function | |
| Eltamaly | A novel energy storage and demand side management for entire green smart grid system for NEOM city in Saudi Arabia | |
| CN103984988A (en) | Method for correcting super-short-term prediction of photovoltaic power of ARMA module in real time through light metering network | |
| CN113689057A (en) | Photovoltaic power generation power prediction method and device | |
| Quoilin et al. | Evaluation of simplified flexibility evaluation tools using a unit commitment model | |
| CN105631762A (en) | Electric power retrieving method based on load curve | |
| CN104252647A (en) | Inverse distance weighting interpolation method-based electrical load prediction method | |
| KR102471609B1 (en) | Photovoltaics generation forecasting system | |
| Hajjaji et al. | Evaluation of artificial intelligence algorithms for predicting power consumption in university campus microgrid | |
| Hjelmeland et al. | Combined SDDP and simulator model for hydropower scheduling with sales of capacity | |
| CN104462839A (en) | Wind electricity uncertainty estimation method based on wind power fluctuation strength instant model | |
| CN113034018B (en) | Power grid supply and demand balance adjustment method based on power moment analysis |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Nan Shui Road Gulou District of Nanjing city of Jiangsu Province, No. 8 210000 Co-patentee after: STATE GRID WUHAN HIGH VOLTAGE Research Institute Patentee after: NARI Group Corp. Address before: Nan Shui Road Gulou District of Nanjing city of Jiangsu Province, No. 8 210000 Co-patentee before: STATE GRID WUHAN HIGH VOLTAGE Research Institute Patentee before: NARI Group CORPORATION STATE GRID ELECTRIC POWER INSTITUTE |