CN107704966A - A kind of Energy Load forecasting system and method based on weather big data - Google Patents
A kind of Energy Load forecasting system and method based on weather big data Download PDFInfo
- Publication number
- CN107704966A CN107704966A CN201710964258.7A CN201710964258A CN107704966A CN 107704966 A CN107704966 A CN 107704966A CN 201710964258 A CN201710964258 A CN 201710964258A CN 107704966 A CN107704966 A CN 107704966A
- Authority
- CN
- China
- Prior art keywords
- data
- weather
- energy load
- temperature
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000005286 illumination Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000003062 neural network model Methods 0.000 claims abstract description 5
- 238000010606 normalization Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000013277 forecasting method Methods 0.000 claims description 4
- 238000009529 body temperature measurement Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012731 temporal analysis Methods 0.000 abstract 1
- 238000000700 time series analysis Methods 0.000 abstract 1
- 238000005303 weighing Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 4
- 238000003672 processing method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction 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"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of Energy Load forecasting system and method based on weather big data, and system includes three data acquisition, model learning and load prediction modules, and method key step includes:First, the characteristics such as temperature, humidity, wind-force, rainfall and intensity of illumination are included according to Energy Load location, wherein the temperature-sensitive value of acquisition synoptic weather observation data, temperature sensor thermometric value and the smart mobile phone of local user, synoptic weather observation data;Secondly, the weather data of acquisition is normalized, forms weather big data training set;Then, weighing factor value of the weather data to Energy Load data is extracted with XGBoost gradients boosting algorithm, then using the forecast model based on LSTM neural network models structure Energy Load;Finally, with reference to the data of weather forecast of one's respective area, the Energy Load that prediction area is treated with the forecast model of Energy Load is predicted.The present invention effectively improves the single Time series analysis method of traditional Energy Load, improves Energy Load precision of prediction.
Description
Technical Field
The invention relates to the technical field of energy load prediction, in particular to an energy load prediction system and method based on weather big data.
Background
With the development of economy, the demand of various industries on energy sources such as electric power and the like is increasing. The energy loads such as electric power and the like are effectively analyzed and accurately predicted, and the production and reasonable configuration of energy sources are facilitated.
At present, most energy load prediction methods are based on time series classical processing methods, namely, a prediction model is established by analyzing historical data of energy loads, and common technologies include an ARMA model, wavelet analysis, a BP neural network and the like. Although these methods have better and better fitting effect on data, in practice, the prediction of energy load is influenced by a plurality of uncertainty factors including environmental factors, so that a large error exists in prediction accuracy.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an energy load prediction method based on weather big data, wherein weather historical data (such as temperature, humidity, wind power, rainfall, illumination intensity and the like) and historical energy load data are combined to establish a model, and weather forecast information and the model are used for prediction during prediction, so that the effect of energy load prediction is improved.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention discloses an energy load prediction system based on weather big data, which comprises a data acquisition module, a model learning module and a load prediction module, wherein the data acquisition module is used for acquiring weather big data; the data acquisition module is used for acquiring weather historical data and historical energy load data, the weather historical data comprises air temperature, humidity, wind power, rainfall and illumination intensity, and the energy load historical data comprises historical observation data of a meteorological bureau on a local area, a measured value of a local area temperature sensor device and a temperature sensing value of a local user smart phone; in addition, the data acquisition module is also required to acquire historical energy load data according to a time sequence;
the model learning module is used for taking the acquired data as a training data set so as to learn a model for predicting the energy load; the model for predicting the energy load is used for carrying out normalization processing on the obtained weather data to form a weather big data training set which takes temperature, humidity, wind power, rainfall and illumination intensity as characteristics and time as a sequence; acquiring historical energy load data, analyzing the correlation between the historical energy load data and the historical weather data by using a gradient lifting algorithm, and extracting weather characteristic weight values influencing different energy loads; establishing a prediction model of the energy load based on the extracted weather characteristics;
and the load prediction module is used for providing a predicted energy load result according to the prediction model of the energy load and by combining weather forecast data of the region to be predicted.
Preferably, in the load prediction module, the time-series data of the date to be predicted and the weather forecast data of the date to be predicted are used as the input of a load prediction model, and the model calculates the predicted energy load result.
The invention also discloses a forecasting method of the energy load forecasting system based on the weather big data, which comprises the following steps:
step 1: acquiring weather observation data of a weather bureau about local temperature, humidity, wind power, rainfall and illumination intensity according to an area where an energy load is located; secondly, acquiring a temperature measurement value of a temperature sensor at the location of the energy load; in addition, acquiring a temperature sensing value of the smart phone of the user in the region;
step 2: carrying out normalization processing on the obtained weather data to form a weather big data training set which takes temperature, humidity, wind power, rainfall and illumination intensity as characteristics and takes time as a sequence;
and step 3: acquiring historical energy load data, and extracting weather characteristic weight values influencing different energy loads to further form a complete characteristic data set;
and 4, step 4: establishing a prediction model of the energy load based on the extracted weather characteristics;
and 5: and predicting the energy load of the area to be predicted by combining the weather forecast information.
As an optimal technical scheme, in order to unify weather data from different sources, characteristic data of temperature, humidity, wind power, rainfall and illumination intensity are collected at certain time intervals; the meteorological bureau observation data is obtained through an application program interface API, the temperature sensor data of the place where the energy load is located is obtained through an instrument device, the temperature sensing value of the user smart phone is obtained by converting the measured temperature of the mobile phone battery or the temperature sensor data into the environmental temperature, and the conversion method adopts the following model:
in the formulaIs the average ambient temperature for a time interval,is the average cell phone battery temperature or cell phone temperature sensor temperature over the space area A and time interval h, T0Is a fixed equilibrium temperature constant, mjTo estimate the coefficients, ∈j,hFor random perturbation terms, j is the sample number.
As a preferred technical solution, in the step 2, normalization processing is performed on weather data including five characteristics of temperature, humidity, wind power, rainfall and illumination intensity, and the normalization processing method adopts the following calculation formula:
xi=(xi-μ)/(max-min) (2)
in the formula xiAnd μ is the mean value of all sample data under the characteristic, and max and min represent the maximum value and the minimum value of the sample data under the characteristic respectively.
As a preferred technical scheme, in the step 3, weather characteristic weight values influencing different energy loads are extracted, so as to provide reference for establishing a prediction model; the XGboost algorithm is adopted to extract features, namely, the extreme gradient lifting algorithm, and the target function of the XGboost algorithm is as follows according to the idea of gradient lifting decision tree:
wherein,t represents the number of leaf nodes, wjRepresenting the weight of each leaf node, and gamma and lambda are parameters for controlling the specific gravity of different parts in the model; by making a pair of wjTaking the derivative and making it equal to 0, one can solve:
when the original training data is used as the input of the XGboost algorithm, 3 parts of data are used as characteristics: historical energy load sequence data, time sequence data and weather sequence data, wherein the historical energy load sequence data and the time sequence data are indispensable characteristics, so that the characteristic importance weights of different weather characteristics in the weather sequence data are obtained according to the XGboost algorithm; the different weather characteristics comprise temperature, humidity, wind power, rainfall and illumination intensity;
as a preferred technical scheme, in the step 4, a load prediction model is constructed by using an LSTM neural network model, and a formed matrix is used as an input, and a prediction model of the energy load is obtained by adjusting and setting appropriate LSTM neural network parameters through training.
Preferably, in step 5, weather forecast information of the forecast area is first acquired, and when the energy load is forecast, the weather forecast data of the date to be forecasted and the time series data of the date to be forecasted are used as input variables, and the load forecasting model in step 4 is used for calculation and output as a result of the forecast energy load.
Compared with the prior art, the invention has the following advantages and effects:
according to the method, historical weather data of an area where the energy load is located are obtained through multiple sources, including but not limited to meteorological bureau observation data, temperature sensor data and area user smart phone data, a weather characteristic weight value related to the energy load data is extracted by adopting an XGboost gradient lifting algorithm, the energy load data, the weather characteristic and the weight data are combined, and an LSTM neural network is used for constructing a load prediction model, so that the defect of the traditional energy load single time sequence analysis method in the prediction effect is overcome, the energy load prediction precision is effectively improved, and particularly, better robustness is reflected when the energy load is influenced by weather environmental factors and has larger fluctuation.
Drawings
FIG. 1 is a principal schematic of the present invention;
FIG. 2 is a flow chart of an energy load prediction implementation of the present invention;
FIG. 3 is a diagram of a load prediction model constructed using an LSTM-based neural network model according to the present invention.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
As shown in fig. 1, the energy load prediction system based on weather big data in the embodiment includes a data acquisition module, a model learning module and a load prediction module;
the data acquisition module is used for acquiring weather historical data and energy load historical data, the weather historical data comprises air temperature, humidity, wind power, rainfall and illumination intensity, and the energy load historical data comprises historical observation data of a meteorological bureau on a local area, a measured value of a local area temperature sensor device and a temperature sensing value of a local user smart phone; in addition, the data acquisition module is also required to acquire historical energy load data according to a time sequence;
the model learning module is used for taking the acquired data as a training data set so as to learn a model for predicting the energy load; the model for predicting the energy load is used for carrying out normalization processing on the obtained weather data to form a weather big data training set which takes temperature, humidity, wind power, rainfall and illumination intensity as characteristics and time as a sequence; acquiring historical energy load data, analyzing the correlation between the historical energy load data and the historical weather data by using an XGboost gradient lifting algorithm, and extracting weather characteristic weight values influencing different energy loads; establishing a prediction model of the energy load by using an LSTM neural network based on the extracted weather characteristics;
and the load prediction module is used for providing a predicted energy load result according to the prediction model of the energy load and by combining weather forecast data of the region to be predicted.
As shown in fig. 2, the energy load prediction method based on the weather big data includes the following steps:
step 1: acquiring weather observation data of a weather bureau about local temperature, humidity, wind power, rainfall and illumination intensity according to an area where an energy load is located; secondly, acquiring a temperature measurement value of a temperature sensor at the location of the energy load; in addition, acquiring a temperature sensing value of the smart phone of the user in the region;
step 2: carrying out normalization processing on the obtained weather data to form a weather big data training set which takes temperature, humidity, wind power, rainfall and illumination intensity as characteristics and takes time as a sequence;
and step 3: acquiring historical energy load data, and extracting weather characteristic weight values influencing different energy loads to further form a complete characteristic data set;
and 4, step 4: establishing a prediction model of the energy load based on the extracted weather characteristics;
and 5: and predicting the energy load of the area to be predicted by combining the weather forecast information.
In the step 1, in order to unify weather data from different sources, data such as air temperature, humidity, wind power, rainfall, illumination intensity and the like are collected at certain time intervals. The meteorological bureau observation data can be obtained through an Application Program Interface (API), the temperature sensor data of the energy load location can be obtained through an instrument device, and the temperature sensing value of the user smart phone is obtained by converting the measured mobile phone battery temperature or the temperature sensor data into the environmental temperature, wherein the conversion method comprises the following models:
in the formulaIs the average ambient temperature for a time interval,the average mobile phone battery temperature or the temperature of the mobile phone temperature sensor (in the space area A and the time interval h), T, of a certain time interval0Is a fixed equilibrium temperature constant, mjTo estimate the coefficients, ∈j,hFor random perturbation terms, j is the sample number.
In the step 2, the weather data including the characteristics of temperature, humidity, wind power, rainfall, illumination intensity and the like are normalized, and the normalization processing method includes, but is not limited to, the following calculation formula:
xi=(xi-μ)/(max-min) (2)
in the formula xiFor the ith sample data, μ is the mean of all sample data under the characteristic, and max and min representMaximum and minimum values of sample data under this feature.
In the step 3, the weather characteristic weight values influencing different energy loads are extracted, and reference is further provided for building a prediction model. An XGboost (eXtreme Gradient Boosting) algorithm is adopted for feature extraction, and a target function of the XGboost algorithm is as follows according to the idea of Gradient Boosting decision trees:
wherein,t represents the number of leaf nodes, wjRepresenting the weight of each leaf node, and gamma and lambda are parameters in the model that control the specific gravity of the different parts. By making a pair of wjTaking the derivative and making it equal to 0, one can solve:
when the original training data is used as the input of the XGBoost algorithm, there are mainly 3 parts of data that can be used as features: historical energy load sequence data, time sequence data and weather sequence data are indispensable characteristics, so that the characteristic importance weights of different weather characteristics (temperature, humidity, wind power, rainfall and illumination intensity) in the weather sequence data are mainly obtained according to the XGboost algorithm.
In the step 4, a load prediction model is constructed by using an LSTM neural network model, as shown in fig. 3, a matrix composed of a time sequence, a historical energy load sequence, a weather feature sequence and a weight is used as an input, and a prediction model of the energy load can be obtained by training by adjusting and setting appropriate LSTM neural network parameters. In the LSTM neural network parameter setting process, the important parameter setting and description are as follows:
in the step 5, weather forecast information of a forecast area is firstly acquired, and when energy load forecast is performed, weather forecast data of a date to be forecasted and time series data of the date to be forecasted are used as input variables, and the load forecasting model in the step 4 is used for calculation and output as a forecast energy load result.
The above embodiments are not intended to limit the present invention, and any other changes, modifications, substitutions, combinations and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents and fall within the scope of the present invention.
Claims (8)
1. An energy load prediction system based on weather big data is characterized by comprising a data acquisition module, a model learning module and a load prediction module; the data acquisition module is used for acquiring weather historical data and historical energy load data, the weather historical data comprises air temperature, humidity, wind power, rainfall and illumination intensity, and the energy load historical data comprises historical observation data of a meteorological bureau on a local area, a measured value of a local area temperature sensor device and a temperature sensing value of a local user smart phone; in addition, the data acquisition module is also required to acquire historical energy load data according to a time sequence;
the model learning module is used for taking the acquired data as a training data set so as to learn a model for predicting the energy load; the model for predicting the energy load is used for carrying out normalization processing on the obtained weather data to form a weather big data training set which takes temperature, humidity, wind power, rainfall and illumination intensity as characteristics and time as a sequence; acquiring historical energy load data, analyzing the correlation between the historical energy load data and the historical weather data by using a gradient lifting algorithm, and extracting weather characteristic weight values influencing different energy loads; establishing a prediction model of the energy load based on the extracted weather characteristics;
and the load prediction module is used for providing a predicted energy load result according to the prediction model of the energy load and by combining weather forecast data of the region to be predicted.
2. The weather big data-based energy load prediction system according to claim 1, wherein the load prediction module takes time series data of a date to be predicted and weather forecast data of the date to be predicted as inputs of a load prediction model, and the model obtains a predicted energy load result through calculation.
3. The forecasting method of the energy load forecasting system based on the weather big data as claimed in claim 1, characterized by comprising the following steps:
step 1: acquiring weather observation data of a weather bureau about local temperature, humidity, wind power, rainfall and illumination intensity according to an area where an energy load is located; secondly, acquiring a temperature measurement value of a temperature sensor at the location of the energy load; in addition, acquiring a temperature sensing value of the smart phone of the user in the region;
step 2: carrying out normalization processing on the obtained weather data to form a weather big data training set which takes temperature, humidity, wind power, rainfall and illumination intensity as characteristics and takes time as a sequence;
and step 3: acquiring historical energy load data, and extracting weather characteristic weight values influencing different energy loads to further form a complete characteristic data set;
and 4, step 4: establishing a prediction model of the energy load based on the extracted weather characteristics;
and 5: and predicting the energy load of the area to be predicted by combining the weather forecast information.
4. The weather big data-based energy load forecasting method according to claim 3, wherein in the step 1, in order to unify weather data from different sources, characteristic data of temperature, humidity, wind power, rainfall and illumination intensity are collected at certain time intervals; the meteorological bureau observation data is obtained through an application program interface API, the temperature sensor data of the place where the energy load is located is obtained through an instrument device, the temperature sensing value of the user smart phone is obtained by converting the measured temperature of the mobile phone battery or the temperature sensor data into the environmental temperature, and the conversion method adopts the following model:
in the formulaIs the average ambient temperature for a time interval,is the average cell phone battery temperature or cell phone temperature sensor temperature over the space area A and time interval h, T0Is a fixed equilibrium temperature constant, mjTo estimate the coefficients, ∈j,hFor random perturbation terms, j is the sample number.
5. The weather big data-based energy load prediction method according to claim 3, wherein in the step 2, the weather data including five characteristics of temperature, humidity, wind power, rainfall and illumination intensity is normalized by using the following calculation formula:
xi=(xi-μ)/(max-min) (2)
in the formula xiAnd μ is the mean value of all sample data under the characteristic, and max and min represent the maximum value and the minimum value of the sample data under the characteristic respectively.
6. The weather big data-based energy load forecasting method according to claim 3, wherein in the step 3, weather characteristic weight values affecting different energy loads are extracted to provide reference for building a forecasting model; the XGboost algorithm is adopted to extract features, namely, the extreme gradient lifting algorithm, and the target function of the XGboost algorithm is as follows according to the idea of gradient lifting decision tree:
wherein,t represents the number of leaf nodes, wjRepresenting the weight of each leaf node, and gamma and lambda are parameters for controlling the specific gravity of different parts in the model; by making a pair of wjTaking the derivative and making it equal to 0, one can solve:
when the original training data is used as the input of the XGboost algorithm, 3 parts of data are used as characteristics: historical energy load sequence data, time sequence data and weather sequence data, wherein the historical energy load sequence data and the time sequence data are indispensable characteristics, so that the characteristic importance weights of different weather characteristics in the weather sequence data are obtained according to the XGboost algorithm; the different weather characteristics include temperature, humidity, wind, rainfall and illumination intensity.
7. The weather big data-based energy load prediction method according to claim 3, wherein in the step 4, the load prediction model is constructed by using the LSTM-based neural network model, and the formed matrix is used as input, and the prediction model of the energy load is obtained by adjusting and setting appropriate LSTM neural network parameters.
8. The weather big data-based energy load prediction method according to claim 3, wherein in the step 5, weather forecast information of a prediction region is first acquired, and when energy load prediction is performed, the weather forecast data of a date to be predicted and time series data of the date to be predicted are used as input variables, and calculation is performed by using the load prediction model in the step 4, and the result is output as a predicted energy load result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710964258.7A CN107704966A (en) | 2017-10-17 | 2017-10-17 | A kind of Energy Load forecasting system and method based on weather big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710964258.7A CN107704966A (en) | 2017-10-17 | 2017-10-17 | A kind of Energy Load forecasting system and method based on weather big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107704966A true CN107704966A (en) | 2018-02-16 |
Family
ID=61184413
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710964258.7A Pending CN107704966A (en) | 2017-10-17 | 2017-10-17 | A kind of Energy Load forecasting system and method based on weather big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107704966A (en) |
Cited By (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108764517A (en) * | 2018-04-08 | 2018-11-06 | 中南大学 | A kind of blast furnace molten iron silicon content trend method, equipment and storage medium |
CN108876019A (en) * | 2018-05-31 | 2018-11-23 | 中国电力科学研究院有限公司 | A kind of electro-load forecast method and system based on big data |
CN108921279A (en) * | 2018-03-26 | 2018-11-30 | 西安电子科技大学 | Reservoir day enters water prediction technique |
CN109034398A (en) * | 2018-08-10 | 2018-12-18 | 深圳前海微众银行股份有限公司 | Feature selection approach, device and storage medium based on federation's training |
CN109165683A (en) * | 2018-08-10 | 2019-01-08 | 深圳前海微众银行股份有限公司 | Sample predictions method, apparatus and storage medium based on federation's training |
CN109285589A (en) * | 2018-10-31 | 2019-01-29 | 重庆邮电大学 | A kind of aluminium electroloysis degree of superheat prediction technique based on Spark big data platform |
CN109444232A (en) * | 2018-12-26 | 2019-03-08 | 苏州同阳科技发展有限公司 | A kind of multichannel intelligent polluted gas monitoring device and diffusion source tracing method |
CN109615226A (en) * | 2018-12-12 | 2019-04-12 | 焦点科技股份有限公司 | A kind of operation indicator method for monitoring abnormality |
CN110084424A (en) * | 2019-04-25 | 2019-08-02 | 国网浙江省电力有限公司 | A kind of Methods of electric load forecasting based on LSTM and LGBM |
CN110443460A (en) * | 2019-07-08 | 2019-11-12 | 北京市天元网络技术股份有限公司 | A kind of heat exchange station heat exchange amount artificial intelligence analysis method and device based on weather and cell thermal losses |
CN110472778A (en) * | 2019-07-29 | 2019-11-19 | 上海电力大学 | A kind of short-term load forecasting method based on Blending integrated study |
CN110543987A (en) * | 2019-08-28 | 2019-12-06 | 向波 | Intelligent climate prediction system |
CN110601193A (en) * | 2019-10-09 | 2019-12-20 | 中电科新型智慧城市研究院有限公司 | Power load prediction system and method based on environment variable perception and hysteresis |
CN110998648A (en) * | 2018-08-09 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | System and method for distributing orders |
CN111008661A (en) * | 2019-12-04 | 2020-04-14 | 哈尔滨工业大学 | Croston-XGboost prediction method for reserve demand of aircraft engine |
CN111161178A (en) * | 2019-12-25 | 2020-05-15 | 湖南大学 | Single low-light image enhancement method based on generation type countermeasure network |
CN111561734A (en) * | 2020-05-18 | 2020-08-21 | 瑞纳智能设备股份有限公司 | Heating household valve adjusting method, system and equipment based on artificial intelligence |
CN111667187A (en) * | 2020-06-10 | 2020-09-15 | 中交第二公路勘察设计研究院有限公司 | Road landslide risk evaluation method based on multi-source remote sensing data |
CN112116153A (en) * | 2020-09-18 | 2020-12-22 | 上海电力大学 | Park multivariate load joint prediction method for coupling Copula and stacked LSTM network |
CN112381266A (en) * | 2020-10-22 | 2021-02-19 | 国网湖北省电力有限公司武汉供电公司 | System and method for predicting future power supply amount based on historical power supply and weather data |
CN112529298A (en) * | 2020-12-11 | 2021-03-19 | 北京邮电大学 | Method, apparatus, electronic device, and medium for predicting power load |
CN112531683A (en) * | 2020-11-19 | 2021-03-19 | 国网湖北省电力有限公司电力科学研究院 | Distribution network line load prediction method based on solution of Ornstein-Urnbek process |
CN112734096A (en) * | 2020-12-31 | 2021-04-30 | 国网山东省电力公司青岛供电公司 | Urban saturation load prediction method and system |
CN113793052A (en) * | 2021-09-23 | 2021-12-14 | 长沙理工大学 | Robust optimization scheduling method for regional comprehensive energy system |
CN113961620A (en) * | 2021-10-19 | 2022-01-21 | 阳光电源股份有限公司 | Method and device for determining numerical weather forecast result |
CN114091361A (en) * | 2022-01-24 | 2022-02-25 | 中汽数据(天津)有限公司 | Weather event based transformer model construction method |
CN114442704A (en) * | 2021-12-31 | 2022-05-06 | 华能山东发电有限公司 | Intelligent power production monitoring method and system based on big data |
CN114626640A (en) * | 2022-04-27 | 2022-06-14 | 西安建筑科技大学 | Natural gas load prediction method and system based on characteristic engineering and LSTM neural network |
CN110826795B (en) * | 2019-10-31 | 2023-06-09 | 国网辽宁省电力有限公司经济技术研究院 | Day-ahead load prediction method for extreme temperature weather day bus |
CN116565865A (en) * | 2023-07-11 | 2023-08-08 | 湖南大学 | Wind power prediction method based on deep error feedback learning |
-
2017
- 2017-10-17 CN CN201710964258.7A patent/CN107704966A/en active Pending
Cited By (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108921279A (en) * | 2018-03-26 | 2018-11-30 | 西安电子科技大学 | Reservoir day enters water prediction technique |
CN108764517A (en) * | 2018-04-08 | 2018-11-06 | 中南大学 | A kind of blast furnace molten iron silicon content trend method, equipment and storage medium |
CN108764517B (en) * | 2018-04-08 | 2020-12-04 | 中南大学 | Method, equipment and storage medium for predicting change trend of silicon content in molten iron of blast furnace |
CN108876019A (en) * | 2018-05-31 | 2018-11-23 | 中国电力科学研究院有限公司 | A kind of electro-load forecast method and system based on big data |
CN110998648A (en) * | 2018-08-09 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | System and method for distributing orders |
CN109165683B (en) * | 2018-08-10 | 2023-09-12 | 深圳前海微众银行股份有限公司 | Sample prediction method, device and storage medium based on federal training |
CN109165683A (en) * | 2018-08-10 | 2019-01-08 | 深圳前海微众银行股份有限公司 | Sample predictions method, apparatus and storage medium based on federation's training |
CN109034398A (en) * | 2018-08-10 | 2018-12-18 | 深圳前海微众银行股份有限公司 | Feature selection approach, device and storage medium based on federation's training |
CN109034398B (en) * | 2018-08-10 | 2023-09-12 | 深圳前海微众银行股份有限公司 | Gradient lifting tree model construction method and device based on federal training and storage medium |
CN109285589A (en) * | 2018-10-31 | 2019-01-29 | 重庆邮电大学 | A kind of aluminium electroloysis degree of superheat prediction technique based on Spark big data platform |
CN109615226A (en) * | 2018-12-12 | 2019-04-12 | 焦点科技股份有限公司 | A kind of operation indicator method for monitoring abnormality |
CN109444232A (en) * | 2018-12-26 | 2019-03-08 | 苏州同阳科技发展有限公司 | A kind of multichannel intelligent polluted gas monitoring device and diffusion source tracing method |
CN109444232B (en) * | 2018-12-26 | 2024-03-12 | 苏州同阳科技发展有限公司 | Multichannel intelligent polluted gas monitoring device and diffusion tracing method |
CN110084424A (en) * | 2019-04-25 | 2019-08-02 | 国网浙江省电力有限公司 | A kind of Methods of electric load forecasting based on LSTM and LGBM |
CN110443460A (en) * | 2019-07-08 | 2019-11-12 | 北京市天元网络技术股份有限公司 | A kind of heat exchange station heat exchange amount artificial intelligence analysis method and device based on weather and cell thermal losses |
CN110443460B (en) * | 2019-07-08 | 2022-08-23 | 北京市天元网络技术股份有限公司 | Artificial intelligent analysis method and device for heat exchange quantity of heat exchange station based on weather and community heat loss |
CN110472778A (en) * | 2019-07-29 | 2019-11-19 | 上海电力大学 | A kind of short-term load forecasting method based on Blending integrated study |
CN110543987A (en) * | 2019-08-28 | 2019-12-06 | 向波 | Intelligent climate prediction system |
CN110601193A (en) * | 2019-10-09 | 2019-12-20 | 中电科新型智慧城市研究院有限公司 | Power load prediction system and method based on environment variable perception and hysteresis |
CN110826795B (en) * | 2019-10-31 | 2023-06-09 | 国网辽宁省电力有限公司经济技术研究院 | Day-ahead load prediction method for extreme temperature weather day bus |
CN111008661A (en) * | 2019-12-04 | 2020-04-14 | 哈尔滨工业大学 | Croston-XGboost prediction method for reserve demand of aircraft engine |
CN111161178A (en) * | 2019-12-25 | 2020-05-15 | 湖南大学 | Single low-light image enhancement method based on generation type countermeasure network |
CN111561734A (en) * | 2020-05-18 | 2020-08-21 | 瑞纳智能设备股份有限公司 | Heating household valve adjusting method, system and equipment based on artificial intelligence |
CN111667187A (en) * | 2020-06-10 | 2020-09-15 | 中交第二公路勘察设计研究院有限公司 | Road landslide risk evaluation method based on multi-source remote sensing data |
CN111667187B (en) * | 2020-06-10 | 2023-09-15 | 中交第二公路勘察设计研究院有限公司 | Highway landslide risk evaluation method based on multi-source remote sensing data |
CN112116153A (en) * | 2020-09-18 | 2020-12-22 | 上海电力大学 | Park multivariate load joint prediction method for coupling Copula and stacked LSTM network |
CN112116153B (en) * | 2020-09-18 | 2022-10-04 | 上海电力大学 | Park multivariate load joint prediction method coupling Copula and stacked LSTM network |
CN112381266A (en) * | 2020-10-22 | 2021-02-19 | 国网湖北省电力有限公司武汉供电公司 | System and method for predicting future power supply amount based on historical power supply and weather data |
CN112381266B (en) * | 2020-10-22 | 2024-01-09 | 国网湖北省电力有限公司武汉供电公司 | System and method for predicting future power supply quantity based on historical power supply and weather data |
CN112531683A (en) * | 2020-11-19 | 2021-03-19 | 国网湖北省电力有限公司电力科学研究院 | Distribution network line load prediction method based on solution of Ornstein-Urnbek process |
CN112529298A (en) * | 2020-12-11 | 2021-03-19 | 北京邮电大学 | Method, apparatus, electronic device, and medium for predicting power load |
CN112734096A (en) * | 2020-12-31 | 2021-04-30 | 国网山东省电力公司青岛供电公司 | Urban saturation load prediction method and system |
CN113793052A (en) * | 2021-09-23 | 2021-12-14 | 长沙理工大学 | Robust optimization scheduling method for regional comprehensive energy system |
CN113961620A (en) * | 2021-10-19 | 2022-01-21 | 阳光电源股份有限公司 | Method and device for determining numerical weather forecast result |
CN114442704A (en) * | 2021-12-31 | 2022-05-06 | 华能山东发电有限公司 | Intelligent power production monitoring method and system based on big data |
CN114091361B (en) * | 2022-01-24 | 2022-05-17 | 中汽数据(天津)有限公司 | Weather event-based transform model construction method |
CN114091361A (en) * | 2022-01-24 | 2022-02-25 | 中汽数据(天津)有限公司 | Weather event based transformer model construction method |
CN114626640A (en) * | 2022-04-27 | 2022-06-14 | 西安建筑科技大学 | Natural gas load prediction method and system based on characteristic engineering and LSTM neural network |
CN116565865A (en) * | 2023-07-11 | 2023-08-08 | 湖南大学 | Wind power prediction method based on deep error feedback learning |
CN116565865B (en) * | 2023-07-11 | 2023-09-26 | 湖南大学 | Wind power prediction method based on deep error feedback learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107704966A (en) | A kind of Energy Load forecasting system and method based on weather big data | |
CN108280552B (en) | Power load prediction method and system based on deep learning and storage medium | |
CN109002915B (en) | Photovoltaic power station short-term power prediction method based on Kmeans-GRA-Elman model | |
CN107730031B (en) | Ultra-short-term peak load prediction method and system | |
CN113554466B (en) | Short-term electricity consumption prediction model construction method, prediction method and device | |
CN102183621A (en) | Aquaculture dissolved oxygen concentration online forecasting method and system | |
CN113505923B (en) | Regional power grid short-term load prediction method and system | |
CN109035067A (en) | Building energy consumption processing method and processing device based on RF and ARMA algorithm | |
CN110017901A (en) | The infared spectrum diagnostic method of electric equipment operation state in a kind of electric system | |
CN110826784B (en) | Method and device for predicting energy use efficiency, storage medium and terminal equipment | |
CN110781595B (en) | Method, device, terminal and medium for predicting energy use efficiency (PUE) | |
CN109858700A (en) | BP neural network heating system energy consumption prediction technique based on similar screening sample | |
CN114297907A (en) | Greenhouse environment spatial distribution prediction method and device | |
CN111639803A (en) | Prediction method applied to future vegetation index of area under climate change scene | |
CN109214591B (en) | Method and system for predicting aboveground biomass of woody plant | |
CN114021830A (en) | Multi-time-range wind speed prediction method based on CNN-LSTM | |
CN106919645A (en) | The sight spot meteorological element Intelligent fine Forecasting Methodology at the big scenic spot of complex landform | |
WO2020228568A1 (en) | Method for training power generation amount prediction model of photovoltaic power station, power generation amount prediction method and device of photovoltaic power station, training system, prediction system and storage medium | |
CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
CN115563848A (en) | Distributed photovoltaic total radiation prediction method and system based on deep learning | |
CN111612648B (en) | Training method and device for photovoltaic power generation prediction model and computer equipment | |
CN113112085A (en) | New energy station power generation load prediction method based on BP neural network | |
KR20220146158A (en) | Apparatus for predicting solar radiation and method thereof | |
CN116167508B (en) | Short-term photovoltaic output rapid prediction method and system based on meteorological factor decomposition | |
CN117076738A (en) | Medium-long term weather prediction method, system and medium based on variable grid model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180216 |
|
RJ01 | Rejection of invention patent application after publication |