CN109299814A - A kind of meteorological effect quantity division prediction technique - Google Patents
A kind of meteorological effect quantity division prediction technique Download PDFInfo
- Publication number
- CN109299814A CN109299814A CN201811000055.7A CN201811000055A CN109299814A CN 109299814 A CN109299814 A CN 109299814A CN 201811000055 A CN201811000055 A CN 201811000055A CN 109299814 A CN109299814 A CN 109299814A
- Authority
- CN
- China
- Prior art keywords
- month
- electricity
- meteorological
- meteorological effect
- correlation
- 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
- 230000000694 effects Effects 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 18
- 230000005611 electricity Effects 0.000 claims abstract description 79
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims description 12
- 238000012958 reprocessing Methods 0.000 claims description 6
- 238000009795 derivation Methods 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000010206 sensitivity analysis Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 2
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of meteorological effect quantity division prediction techniques, comprising the following steps: S1: basic month is arranged: basic month in default spring is May, and basis month in autumn is October;S2: it calculates meteorological correlation: being divided into two parts of winter and summer and calculate separately data, if place month belongs to 11-4 month, calculate winter correlation, if place month belongs to 6-9 month, summer correlation is then calculated, is then not involved in calculating basic month, correlation calculations formula isObtain correlation data;S3: it calculates monthly meteorological effect electricity growth rate: y is passed through to the correlation data in S2t=yi‑yjWith δ=(yt/yj) * 100% formula calculated, obtain monthly meteorological effect electricity growth rate and show related coefficient.According to the rationale of science, being inferred to meteorologic factor is to influence the significant consideration of load forecast, the accuracy rate of increasing productivity prediction, and error is smaller.
Description
Technical field
The present invention relates to connect welding technology field more particularly to a kind of meteorological effect quantity division prediction technique.
Background technique
Prediction is basis, premise and the foundation of correct decisions, and correctly predicted area electricity needs level is that electric power at different levels are public
Department instructs the important foundation of Power System Planning and operation.Electric load analysis prediction needs to combine past and currently known warp
Situation, social development and the electricity market situation of helping are explored by the analysis and research to historical data and grasp each correlative factor and electricity
The inner link of power load and development and change rule, to be pushed away according to the prediction to economic situation in project period and social development
Calculate following electricity needs situation.
Power system reform further deeply, electricity market today for gradually forming, Utilities Electric Co. is in power Transmission ring
The service function of section is more prominent, carries out the load forecast of lean, and increasing productivity predictablity rate is under market environment
Layout operation plan, power supply plan, trading program basis.Conventional prediction technique combines one by the practical experience of prognosticator
Relationship between a little simple variables, is often a lack of the theoretical foundation of science, causes to predict that error is larger.The variation of electric load
It is influenced by multiple factors such as economy, meteorologies, especially as the raising and economic rapid development of Living consumption, so that
Electricity needs rapidly increases, and in summer and winter, meteorologic factor is to influence the significant consideration of load forecast.
Summary of the invention
Technical problems based on background technology, the invention proposes a kind of meteorological effect quantity division prediction techniques.
A kind of meteorological effect quantity division prediction technique proposed by the present invention, comprising the following steps:
S1: basic month is arranged: basic month in default spring is May, and basis month in autumn is October;
S2: it calculates meteorological correlation: being divided into two parts of winter and summer and calculate separately data, if place month belongs to
11-4 month winter correlation is then calculated, if place month belongs to 6-9 month, calculates summer correlation, basic month is then
It is not involved in calculating, correlation calculations formula isObtain correlation data;
S3: it calculates monthly meteorological effect electricity growth rate: y is passed through to the correlation data in S2t=yi-yjWith δ=(yt/
yj) * 100% formula calculated, obtain monthly meteorological effect electricity growth rate and show related coefficient;
S4: display: the related coefficient in display S3 judges the related coefficient of meteorological effect electricity Yu all kinds of meteorologies respectively,
The related coefficient of meteorological effect electricity growth rate and all kinds of meteorologies, the two same type are compared, and show biggish one group of related coefficient;
S5: calculating electricity influences: calculating the relationship between leading meteorologic factor and meteorological effect electricity, establishes leading meteorology
Polynomial-fitting function between factor and meteorological effect electricity, is calculated using multiple linear regression equations:With
S6: reprocessing processing reprocessing: is carried out to the data of output.
Preferably, in the S2, the electricity of every month is yi, i=1,2, L, 12, remove basic month yj, j=5,10 is not
Consider outer, other, electricity should subtract the historical basis moon electricity y nearest apart from the month every monthsj, constitute monthly meteorological
Influence electricity yt, t=1, L, 4,6, L 9,11,12.
Preferably, in the S3, for winter correlation calculations in the presence of across year property.
Preferably, in the S5, x is main weather factor, ytFor meteorological effect electricity, δ is the growth of meteorological effect electricity
Rate.
Preferably, it in the S5, is calculated using meteorological sensitivity analysis algorithm, to yt, derivation of δ obtain meteorology
The amplification that influence electricity or meteorological effect electricity growth rate are changed with meteorologic factor.
Preferably, in the S5, if prediction month is in winter, the high index of winter correlation is calculated, otherwise is calculated
The high index of summer correlation, basic month do not calculate.
Preferably, in the S6, the meteorological index of output should be integer, should not be decimal.
Preferably, it in the S6, if input quantity is meteorological effect electricity growth rate, needs to convert, meteorological effect
Electricity=meteorological effect electricity growth rate * nearest historical basis moon electricity.
Beneficial effects of the present invention: according to the rationale of science, being inferred to meteorologic factor is to influence load forecast
Significant consideration, the accuracy rate of increasing productivity prediction, error is smaller.
Specific embodiment
Combined with specific embodiments below the present invention is made further to explain.
Embodiment 1
A kind of meteorological effect quantity division prediction technique is proposed in the present embodiment, comprising the following steps:
S1: basic month is arranged: basic month in default spring is May, and basis month in autumn is October;
S2: it calculates meteorological correlation: being divided into two parts of winter and summer and calculate separately data, if place month belongs to
11-4 month winter correlation is then calculated, if place month belongs to 6-9 month, calculates summer correlation, basic month is then
It is not involved in calculating, correlation calculations formula isObtain correlation data;
S3: it calculates monthly meteorological effect electricity growth rate: y is passed through to the correlation data in S2t=yi-yjWith δ=(yt/
yj) * 100% formula calculated, obtain monthly meteorological effect electricity growth rate and show related coefficient;
S4: display: the related coefficient in display S3 judges the related coefficient of meteorological effect electricity Yu all kinds of meteorologies respectively,
The related coefficient of meteorological effect electricity growth rate and all kinds of meteorologies, the two same type are compared, and show biggish one group of related coefficient;
S5: calculating electricity influences: calculating the relationship between leading meteorologic factor and meteorological effect electricity, establishes leading meteorology
Polynomial-fitting function between factor and meteorological effect electricity, is calculated using multiple linear regression equations:With
S6: reprocessing processing reprocessing: is carried out to the data of output.
In the present embodiment, in the S2, the electricity of every month is yi, i=1,2, L, 12, remove basic month yj, j=5,
10 do not consider outer, other, electricity should subtract the historical basis moon electricity y nearest apart from the month every monthsj, constitute monthly
Meteorological effect electricity yt, t=1, L, 4,6, L 9,11,12, it is the presence of across year property for winter correlation calculations in the S3
, in the S5, x is main weather factor, ytFor meteorological effect electricity, δ is meteorological effect electricity growth rate, in the S5,
It is calculated using meteorological sensitivity analysis algorithm, to yt, derivation of δ show that meteorological effect electricity or meteorological effect electricity increase
The amplification that long rate is changed with meteorologic factor in the S5, if prediction month is in winter, calculates the high finger of winter correlation
Mark, on the contrary the high index of summer correlation is calculated, it does not calculate in basic month, in the S6, the meteorological index of output should be whole
Number, should not be decimal, in the S6, if input quantity is meteorological effect electricity growth rate, need to convert, meteorological effect
Electricity=meteorological effect electricity growth rate * nearest historical basis moon electricity.
Embodiment 2
With the data instance of somewhere 2014-2017, table 1 is the moon electricity of somewhere business over the years, and monthly number of days is rolled over
Be counted as average daily electricity, be shown in Table 2, select month based on May, October, other every months electricity subtract it is nearest apart from the month
The historical basis moon, electricity obtained meteorological effect electricity, was shown in Table 3, and table 4 is that somewhere 2014-2017 commercial weather influences electricity and increases
Long rate calculates separately summer meteorology index of correlation and meteorological effect electricity, winter meteorology index of correlation and meteorological effect electricity
Correlativity, in order to which unified each year all takes standardization, analysis the results are shown in Table 5, table 6.
Table 1
Average daily electricity | 2014 | 2015 | 2016 | 2017 |
January | 16.34 | 20.33 | 21.09 | 24.52 |
2 months | 19.39 | 22.39 | 24.97 | 29.39 |
March | 14.07 | 17.39 | 20.16 | 24.37 |
April | 14.19 | 17.62 | 19.31 | 23.21 |
May | 12.10 | 14.55 | 16.52 | 18.43 |
June | 14.38 | 15.46 | 18.38 | 21.94 |
July | 15.11 | 16.93 | 19.38 | 23.35 |
August | 18.60 | 21.45 | 23.61 | 27.03 |
September | 19.43 | 21.60 | 24.82 | 26.69 |
October | 13.63 | 15.93 | 17.99 | 20.31 |
November | 14.95 | 17.38 | 19.16 | 22.88 |
December | 17.06 | 17.95 | 21.81 | 25.79 |
Table 2
Table 3
Table 4
Table 5
Table 6
Participating in the charge value that related coefficient calculates has two classes: one is monthly meteorological effect electricity related coefficient, and one is
Monthly meteorological effect electricity growth rate related coefficient;Participating in the meteorological data that related coefficient calculates has four classes: the monthly mean temperature (moon
The average value of interior each mean daily temperature), monthly mean of daily maximum temperature (average value of each max. daily temperature in the moon), monthly average lowest temperature
(average value of each Daily minimum temperature in the moon), monthly total precipitation (aggregate-value of each intra day ward in the moon) are spent, when calculating meteorological
Need calculate within wrong one month, i.e., meteorology in May corresponds to electricity in June, and the highest index of summer correlation is meteorological effect electricity
With summer average maximum, and winter several meteorological index are not very high with meteorological effect electricity correlation, therefore following
Summer correlation models are only established, fitting of a polynomial is established, it is optimal as follows to obtain fitting effect:
Y=-0.0181x2-0.7699x+8.3066
To above formula equation derivation, sensitivity equation is obtained:
Y '=0.0362x-0.77.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (8)
1. a kind of meteorological effect quantity division prediction technique, which comprises the following steps:
S1: basic month is arranged: basic month in default spring is May, and basis month in autumn is October;
S2: it calculates meteorological correlation: being divided into two parts of winter and summer and calculate separately data, if place month belongs to 11-4
Month winter correlation is then calculated, if place month belongs to 6-9 month, calculates summer correlation, do not join then in basic month
With calculating, correlation calculations formula isObtain correlation data;
S3: it calculates monthly meteorological effect electricity growth rate: y is passed through to the correlation data in S2t=yi-yjWith δ=(yt/yj)*
100% formula is calculated, and is obtained monthly meteorological effect electricity growth rate and is shown related coefficient;
S4: display: the related coefficient in display S3 judges the related coefficient of meteorological effect electricity Yu all kinds of meteorologies respectively, meteorological
The related coefficient of electricity growth rate and all kinds of meteorologies is influenced, the two same type is compared, and shows biggish one group of related coefficient;
S5: calculating electricity influences: calculating the relationship between leading meteorologic factor and meteorological effect electricity, establishes leading meteorologic factor
Polynomial-fitting function between meteorological effect electricity, is calculated using multiple linear regression equations:
With
S6: reprocessing processing reprocessing: is carried out to the data of output.
2. a kind of meteorological effect quantity division prediction technique according to claim 1, which is characterized in that in the S2, often
A month electricity is yi, i=1,2, L, 12, remove basic month yj, j=5,10 do not consider outer, other, electricity should every months
Subtract the historical basis moon electricity y nearest apart from the monthj, constitute monthly meteorological effect electricity yt, t=1, L, 4,6, L 9,11,
12。
3. a kind of meteorological effect quantity division prediction technique according to claim 1, which is characterized in that right in the S3
In winter correlation calculations in the presence of across year property.
4. a kind of meteorological effect quantity division prediction technique according to claim 1, which is characterized in that in the S5, x is
Main weather factor, ytFor meteorological effect electricity, δ is meteorological effect electricity growth rate.
5. a kind of meteorological effect quantity division prediction technique according to claim 1, which is characterized in that in the S5, benefit
It is calculated with meteorological sensitivity analysis algorithm, to yt, derivation of δ show that meteorological effect electricity or meteorological effect electricity increase
The amplification that rate is changed with meteorologic factor.
6. a kind of meteorological effect quantity division prediction technique according to claim 1, which is characterized in that in the S5, such as
Fruit predicts month in winter, then calculates the high index of winter correlation, otherwise calculates the high index of summer correlation, basic month
It does not calculate.
7. a kind of meteorological effect quantity division prediction technique according to claim 1, which is characterized in that defeated in the S6
Meteorological index out should be integer, should not be decimal.
8. a kind of meteorological effect quantity division prediction technique according to claim 1, which is characterized in that in the S6, such as
Fruit input quantity is meteorological effect electricity growth rate, is needed to convert, and meteorological effect electricity=meteorological effect electricity growth rate * is most
Close historical basis moon electricity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811000055.7A CN109299814B (en) | 2018-08-30 | 2018-08-30 | Meteorological influence electric quantity decomposition prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811000055.7A CN109299814B (en) | 2018-08-30 | 2018-08-30 | Meteorological influence electric quantity decomposition prediction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109299814A true CN109299814A (en) | 2019-02-01 |
CN109299814B CN109299814B (en) | 2024-02-02 |
Family
ID=65165862
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811000055.7A Active CN109299814B (en) | 2018-08-30 | 2018-08-30 | Meteorological influence electric quantity decomposition prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109299814B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110795698A (en) * | 2019-10-30 | 2020-02-14 | 国网重庆市电力公司电力科学研究院 | Summer electric quantity analysis method and readable storage medium |
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 |
CN111563644A (en) * | 2020-02-24 | 2020-08-21 | 中国气象局公共气象服务中心 | Method for determining summer electricity utilization index, computer-readable storage medium and electronic device |
CN111598349A (en) * | 2020-05-22 | 2020-08-28 | 国网重庆市电力公司电力科学研究院 | Short-term power consumption prediction method and device and readable storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105825294A (en) * | 2016-03-10 | 2016-08-03 | 国家电网公司 | Meteorological-factor-based grid power load prediction method and system |
CN106408223A (en) * | 2016-11-30 | 2017-02-15 | 华北电力大学(保定) | Short-term load prediction based on meteorological similar day and error correction |
CN107248013A (en) * | 2017-06-21 | 2017-10-13 | 国网安徽省电力公司芜湖供电公司 | A kind of monthly electricity demand forecasting method for considering diversified economy factor |
-
2018
- 2018-08-30 CN CN201811000055.7A patent/CN109299814B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105825294A (en) * | 2016-03-10 | 2016-08-03 | 国家电网公司 | Meteorological-factor-based grid power load prediction method and system |
CN106408223A (en) * | 2016-11-30 | 2017-02-15 | 华北电力大学(保定) | Short-term load prediction based on meteorological similar day and error correction |
CN107248013A (en) * | 2017-06-21 | 2017-10-13 | 国网安徽省电力公司芜湖供电公司 | A kind of monthly electricity demand forecasting method for considering diversified economy factor |
Non-Patent Citations (1)
Title |
---|
江宇飞 等: "基于多层次气象指标体系的电力负荷特性和负荷预测研究" * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110795698A (en) * | 2019-10-30 | 2020-02-14 | 国网重庆市电力公司电力科学研究院 | Summer electric quantity analysis method and readable storage medium |
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 |
CN111563644A (en) * | 2020-02-24 | 2020-08-21 | 中国气象局公共气象服务中心 | Method for determining summer electricity utilization index, computer-readable storage medium and electronic device |
CN111598349A (en) * | 2020-05-22 | 2020-08-28 | 国网重庆市电力公司电力科学研究院 | Short-term power consumption prediction method and device and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109299814B (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109299814A (en) | A kind of meteorological effect quantity division prediction technique | |
CN102930356B (en) | short-term load forecasting method based on meteorological factor sensitivity | |
Bretschger et al. | Climate change and uneven development | |
Zhang et al. | GEFCom2014 probabilistic solar power forecasting based on k-nearest neighbor and kernel density estimator | |
Bernstein et al. | Residential natural gas demand elasticities in OECD countries: an ARDL bounds testing approach | |
CN105069536B (en) | A kind of power demand prediction technique based on temperature and economic growth | |
CN104318322B (en) | Festivals or holidays load forecasting method based on lunar date | |
CN110620397B (en) | Peak regulation balance evaluation method for high-proportion renewable energy power system | |
Jang et al. | On the long-term density prediction of peak electricity load with demand side management in buildings | |
CN103617457A (en) | Method for predicting weather sensitivity load related to temperature in electric system | |
CN109598408B (en) | Annual water quantity scheduling plan compilation method considering water use fairness and importance | |
CN109617048B (en) | Power grid planning typical scene selection method based on multi-target linear programming | |
Zipp | Revenue prospects of photovoltaic in Germany—Influence opportunities by variation of the plant orientation | |
Li et al. | Dynamics and uncertainty in land use conversion for perennial energy crop production: exploring effects of payments for ecosystem services policies | |
CN103853939A (en) | Combined forecasting method for monthly load of power system based on social economic factor influence | |
CN111860985B (en) | Day-ahead power load prediction method based on load decomposition | |
CN104834975A (en) | Power network load factor prediction method based on intelligent algorithm optimization combination | |
CN104601104A (en) | Ultra-short term photovoltaic prediction method with ARMA correction based on LSSVM | |
CN111612244A (en) | QRA-LSTM-based method for predicting nonparametric probability of photovoltaic power before day | |
CN107480810B (en) | Monthly power consumption prediction method for improving secondary index smoothness by utilizing seasonal index | |
CN112508281B (en) | Time sequence rolling overall optimization method for medium and long term transaction of electric power | |
Brown et al. | The value of electricity reliability: Evidence from battery adoption | |
Şişman | A comparison of ARIMA and grey models for electricity consumption demand forecasting: The case of Turkey | |
CN112465266A (en) | Bus load prediction accuracy analysis method and device and computer equipment | |
CN112036686A (en) | Low-voltage distribution station area line loss evaluation method based on theoretical line loss interval calculation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |