CN118095704A - Rural typical energy supply and demand balance method and system based on big data - Google Patents
Rural typical energy supply and demand balance method and system based on big data Download PDFInfo
- Publication number
- CN118095704A CN118095704A CN202410071493.1A CN202410071493A CN118095704A CN 118095704 A CN118095704 A CN 118095704A CN 202410071493 A CN202410071493 A CN 202410071493A CN 118095704 A CN118095704 A CN 118095704A
- Authority
- CN
- China
- Prior art keywords
- energy
- supply
- demand
- energy supply
- data
- 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 50
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 230000008859 change Effects 0.000 claims description 64
- 230000035772 mutation Effects 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000005265 energy consumption Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000004146 energy storage Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 8
- 230000008569 process Effects 0.000 description 10
- 239000007789 gas Substances 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000001556 precipitation Methods 0.000 description 6
- 230000005611 electricity Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 239000002028 Biomass Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000002803 fossil fuel Substances 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 230000003442 weekly effect Effects 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000002737 fuel gas Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- -1 solar energy Substances 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a rural typical energy supply and demand balance method and system based on big data, and relates to the technical field of energy supply, wherein the method comprises the following steps: acquiring energy demand information; acquiring energy supply information; carrying out data preprocessing on the energy demand information and the energy supply information to obtain an energy demand data sequence and an energy supply data sequence; based on the energy demand data sequence and the energy supply data sequence, combining regional characteristics of the village, carrying out energy demand and supply analysis, and constructing an energy supply prediction model; the energy supply prediction model is combined with the climate characteristics of the real-time region to perform energy demand supply prediction; and carrying out supply-demand balance compensation according to the supply-demand prediction result, and carrying out energy calling according to the compensation result. The invention solves the technical problems that in the prior art, because of the limitation of various factors such as geographic positions and the like, the energy supply and demand mainly depend on experience, and the accurate regulation and control of the energy supply and demand are difficult to realize, and achieves the technical effect of the accurate balance regulation and control of the energy supply and demand.
Description
Technical Field
The invention relates to the technical field of energy supply, in particular to a rural typical energy supply and demand balance method and system based on big data.
Background
With the rapid development of socioeconomic performance and the continuous growth of population, the energy demand is also increasing year by year, and the energy supply and demand balance problem has become a focus of attention in the global scope. In rural areas, the problem of energy supply and demand is more remarkable due to the limitation of various factors such as geographic positions, resource conditions and the like. The traditional energy supply and demand balance method mainly depends on experience and manual operation, and accurate supply and demand prediction and adjustment are difficult to realize.
Disclosure of Invention
The application provides a rural typical energy supply and demand balancing method and system based on big data, which are used for solving the technical problems that in the prior art, the energy supply and demand mainly depends on experience due to the limitation of various factors such as geographic positions and the like in rural areas, and accurate regulation and control of the energy supply and demand are difficult to realize.
In view of the above problems, the present application provides a method and system for rural typical energy supply and demand balancing based on big data.
In a first aspect of the present application, there is provided a method for rural power representative energy supply and demand balancing based on big data, the method comprising:
Acquiring typical energy demand information of a target country, wherein the typical energy demand information comprises energy demand types and corresponding energy demand information; acquiring typical energy supply information of a target country, wherein the typical energy supply information comprises energy supply types and corresponding energy supply amount information; preprocessing the data of the typical energy demand information and the typical energy supply information to obtain an energy demand data sequence and an energy supply data sequence; based on the energy demand data sequence and the energy supply data sequence, combining regional characteristics of the target village to perform energy demand and supply analysis and constructing an energy supply prediction model; the energy supply prediction model is combined with the climate characteristics of the real-time region to perform energy demand supply prediction, so that a supply and demand prediction result is obtained; and carrying out supply-demand balance compensation according to the supply-demand prediction result, and carrying out energy calling according to the compensation result.
In a second aspect of the present application, there is provided a rural energy representative supply and demand balancing system based on big data, the system comprising:
the demand information acquisition module is used for acquiring typical energy demand information of a target country, including energy demand types and corresponding energy demand amount information; the supply information acquisition module is used for acquiring typical energy supply information of a target country, and comprises an energy supply type and corresponding energy supply amount information; the data preprocessing module is used for preprocessing the data of the typical energy demand information and the typical energy supply information to obtain an energy demand data sequence and an energy supply data sequence; the energy supply prediction model construction module is used for constructing an energy supply prediction model by combining the regional characteristics of the target village based on the energy demand data sequence and the energy supply data sequence and carrying out energy demand and supply analysis; the supply prediction module is used for carrying out energy demand supply prediction by combining the energy supply prediction model with the climate characteristics of the real-time region to obtain a supply and demand prediction result; and the supply-demand balance compensation module performs supply-demand balance compensation according to the supply-demand prediction result and performs energy calling according to the compensation result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
According to the application, the energy demand information is acquired; acquiring energy supply information; carrying out data preprocessing on the energy demand information and the energy supply information to obtain an energy demand data sequence and an energy supply data sequence; based on the energy demand data sequence and the energy supply data sequence, combining regional characteristics of the village, carrying out energy demand and supply analysis, and constructing an energy supply prediction model; the energy supply prediction model is combined with the climate characteristics of the real-time region to perform energy demand supply prediction; and carrying out supply-demand balance compensation according to the supply-demand prediction result, and carrying out energy calling according to the compensation result. The application solves the technical problems that in the prior art, because of the limitation of various factors such as geographic positions and the like, the energy supply and demand mainly depend on experience, and the accurate regulation and control of the energy supply and demand are difficult to realize, and achieves the technical effect of the accurate balance regulation and control of the energy supply and demand.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a typical energy supply and demand balance method for a country based on big data according to an embodiment of the present application;
fig. 2 is a schematic diagram of a flow chart of performing supply-demand balance compensation according to the supply-demand prediction result in the rural typical energy supply-demand balance method based on big data according to the embodiment of the present application;
fig. 3 is a schematic diagram of a rural typical energy supply and demand balance system based on big data according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a demand information acquisition module 11, a supply information acquisition module 12, a data preprocessing module 13, an energy supply prediction model construction module 14, a supply prediction module 15 and a supply and demand balance compensation module 16.
Detailed Description
The application provides a rural typical energy supply and demand balance method and system based on big data, which are used for solving the technical problems that in the prior art, the energy supply and demand mainly depends on experience and the accurate regulation and control of the energy supply and demand are difficult to realize due to the limitation of various factors such as geographic positions and the like in rural areas, and achieving the technical effect of the accurate balance regulation and control of the energy supply and demand.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides a rural typical energy supply and demand balancing method based on big data, which includes:
Step S100: acquiring typical energy demand information of a target country, wherein the typical energy demand information comprises energy demand types and corresponding energy demand information;
In the embodiment of the application, the energy demand information about the target village is acquired through the rural energy consumption statistical report, the consumption data provided by the energy suppliers, the field investigation and the like. The types of energy demand include, but are not limited to, electricity, gas, solar energy, biomass energy, and the like. The energy demand information needs to be specific to an accurate amount, such as monthly or yearly power consumption, gas consumption, and the like. The data can be monitored in real time or recorded regularly through intelligent electric meters, gas meters and other devices installed in the village.
Step S200: acquiring typical energy supply information of a target country, wherein the typical energy supply information comprises energy supply types and corresponding energy supply amount information;
In the embodiment of the application, the energy supply information of the target village is acquired through the rural energy supply statistical report, the data provided by the energy supplier, the field investigation and the like. The energy supply type is not limited to local solar energy, wind energy, water energy and the like, and furthermore, whether other special energy supplies exist in the country, such as self-produced biomass energy, needs to be known. The energy supply amount information includes total energy supply amounts of the country over a certain period of time, and supply amounts of different types of energy. Such as monthly or yearly power production, gas production, etc.
Step S300: preprocessing the data of the typical energy demand information and the typical energy supply information to obtain an energy demand data sequence and an energy supply data sequence;
In the embodiment of the application, the collected information is subjected to data preprocessing, and firstly, the data is cleaned, including missing value processing, namely, whether missing values exist in the data is checked, and filling missing values are selected according to the specific conditions of the data, such as filling by using average values and median values. And performing outlier processing, i.e., checking whether outliers exist in the data, which represent data errors, outlier events, or other unusual phenomena. Methods of handling outliers include deleting outliers, correcting using median or other statistical methods.
Since information comes from electricity, gas and suppliers from a number of different data sources, it is necessary to integrate these data sources into a unified data set. This process involves format conversion, field matching, and data alignment of the data. Different types of data are classified and encoded. For example, energy types, such as electricity, gas, and demand supply status, such as demand, supply, are converted into data tags in a unified format. Ensuring that all data is time stamped accurately so that it can be arranged in time order. If some data has no time stamp, it may be time stamped based on other relevant information. The data are arranged in time order to form time series data.
Step S400: based on the energy demand data sequence and the energy supply data sequence, combining regional characteristics of the target village to perform energy demand and supply analysis and constructing an energy supply prediction model;
in the embodiment of the application, the regional characteristics of the target village are analyzed, and the geographical position, the topography and the climate conditions of the target village are analyzed to understand the influence of the regional characteristics on the energy demand and supply. For example, the winter demand for energy in cold climates increases. The economic development status, the industrial structure and the living standard of the target village are studied, and the influence of the factors on the energy demand is known. For example, rural areas, where economies are fast developing, may have a greater demand for electricity. And meanwhile, social culture factors of villages, such as population structure, life style, custom and the like, are considered to influence energy demand and supply.
The long-term trend, seasonal and periodic variation of the energy demand data sequence is analyzed using a time series analysis method. Factors affecting energy demand, such as climate conditions, economics, population changes, etc., are identified and analyzed. And (3) quantifying the influence degree of the factors on the energy demand by establishing a regression model and other methods.
In analyzing the energy supply data sequence, it is necessary to know the capacity, operating efficiency and production costs of the energy production facilities of the target rural area, which information helps to evaluate the energy supply capacity and potential of the rural area. And meanwhile, the stability of the supply is analyzed, and the stability factors of the energy supply, such as supply sources, transportation and distribution networks and the like, are analyzed.
And selecting a proper prediction model for energy supply prediction according to the analysis results of energy demand and supply, wherein an LSTM model is selected as the prediction model. The method comprises the steps of dividing the characteristics of the energy demand data sequence and the energy supply data sequence after analysis into a training set and a testing set, training a model by using the training set, evaluating the trained model by using the testing set, optimizing the model according to an evaluation result, and finally completing the construction of an energy supply prediction model.
Step S500: the energy supply prediction model is combined with the climate characteristics of the real-time region to perform energy demand supply prediction, so that a supply and demand prediction result is obtained;
In the embodiment of the application, the real-time regional climate characteristic data is required to be input into the model, and the characteristics are capable of reflecting the influence of the current climate conditions on energy demand and supply, including real-time temperature, humidity, precipitation and the like. This effect can be captured and corresponding predictive adjustments made using the memory cell characteristics of the model.
And inputting the climate characteristic data of the real-time region and other related features into an energy supply prediction model to perform energy demand supply prediction, and obtaining an energy demand and supply prediction result in a future period through model calculation.
Step S600: and carrying out supply-demand balance compensation according to the supply-demand prediction result, and carrying out energy calling according to the compensation result.
In the embodiment of the application, the supply and demand prediction result is analyzed, the energy demand and supply condition in a future period of time are evaluated, and the difference between the demand and the supply is known. And according to the supply and demand prediction result, a corresponding supply and demand balance compensation strategy is formulated. Strategies include measures to increase energy production, store and release reserve energy, optimize energy scheduling, and the like. These strategies aim at adjusting the balance of energy supply and demand.
If the prediction indicates that demand exceeds supply, reserve energy needs to be called to make up for the gap. The reserve energy source may be fossil fuel, renewable energy, or other forms of energy storage. According to the actual situation, the release amount and release time of the reserve energy are adjusted to meet the energy demand.
Further, the method further comprises:
Cleaning the typical energy demand information and the typical energy supply information respectively to remove abnormal values, missing values and repeated values, so as to obtain pure energy demand information and pure energy supply information;
And carrying out serialization processing on the pure energy demand information and the pure energy supply information according to the energy type to obtain a plurality of energy demand data sequences and a plurality of energy supply data sequences.
In the embodiment of the application, when cleaning the typical energy demand information and the typical energy supply information, firstly, abnormal values are required to be identified, and the abnormal values are generated due to measurement errors, equipment faults or other abnormal conditions. And then according to the specific situation, selecting to delete records containing abnormal values, replacing the abnormal values by an average value or a median value, or performing smoothing treatment by using a statistical method.
After the abnormal values are removed, missing values in the data are found, filling missing values are selected according to the property and actual condition of the data, and the missing values can be predicted and filled by using means, medians, modes or through interpolation, regression and other methods when filling is carried out. Check for duplicate records in the data and delete duplicate rows or records. Finally, the data is normalized to a uniform range, such as between 0-1, for better comparison and calculation. Through the steps, abnormal values, missing values and repeated values can be removed, and pure energy demand information and pure supply information are obtained.
When the pure energy demand information and the pure energy supply information are processed in a serialization mode, the pure energy demand information and the pure energy supply information are firstly ordered according to a time sequence, so that the data are ensured to be arranged according to the time sequence, and time sequence analysis is conveniently carried out. The ordered data is partitioned into a plurality of data sequences as needed. Each sequence may represent demand or supply information for one energy type. For example, the data may be partitioned into a fossil fuel demand sequence, a renewable energy demand sequence, and so forth. During serialization, boundary conditions for the data need to be processed. For example, for the beginning and ending parts of the sequence, a padding or truncation process is required to avoid the influence of boundary effects on the analysis.
Through the steps, the pure energy demand information and the pure energy supply information can be subjected to serialization processing according to the energy types, and a plurality of energy demand data sequences and a plurality of energy supply data sequences are obtained.
Further, the method further comprises:
Drawing an energy demand change curve and an energy supply change curve based on the energy demand data sequence and the energy supply data sequence;
collecting regional climate change data of a target country, and drawing a climate change curve;
and carrying out energy demand and supply analysis based on the energy demand change curve, the energy supply change curve and the climate change curve, and constructing an energy supply prediction model.
In embodiments of the present application, a suitable time scale is selected, such as daily, weekly or monthly, to plot the change curve. Consistency of the time scale is ensured for ease of comparison and analysis. The energy demand and supply profiles are plotted using a suitable chart tool or software, such as Excel or the like. The time is taken as the horizontal axis, the energy demand or supply is taken as the vertical axis, and the data points are connected into a line to form a trend curve.
When the climate change curve is drawn, it is necessary to determine the geographical range of the target country and collect relevant climate data in that area. These data include temperature, precipitation, wind speed, etc. And (5) finishing the acquired climate data, and ensuring the accuracy and the integrity of the data. A time scale consistent with the energy demand and supply data is selected, such as daily, weekly, or monthly. Ensuring uniformity of time scale. The climate change curve is plotted using a suitable chart tool or software. And connecting data points into lines by taking time as a horizontal axis and taking climate variables such as temperature, precipitation and the like as a vertical axis to obtain a climate change trend curve.
When an energy supply prediction model is formulated, firstly, the energy demand and supply trend are analyzed, the trend of an energy demand change curve and an energy supply change curve is observed, and the seasonal, periodic and long-term change rules of the energy demand are analyzed. At the same time, stability, adjustability and sustainability of the energy supply are considered. And (3) taking the influence of climate factors into consideration, and comparing and analyzing the climate change curve with the energy demand and supply curve. How climate factors influence the trend of energy demand and supply. For example, climate factors such as temperature, precipitation, etc. may have a direct or indirect impact on energy demand. And determining key influencing factors, and identifying key climate factors influencing energy requirements and supply and an action mechanism thereof. These factors include temperature, precipitation, wind speed, etc., which have a direct impact on the production of renewable energy sources, such as solar, wind.
Based on the analysis, an energy supply prediction model is formulated. The model should take into account the change law of the energy demand, the constraint conditions of the energy supply and the influence of climatic factors. The model may be constructed using time series analysis, machine learning, etc., where convolutional neural network models are used. Key features including time series data, temperature, precipitation, wind speed, etc. are extracted from the energy demand profile, the energy supply profile, and the climate profile. These data are divided into training and validation sets. And training the model by using the training set, evaluating the model by using the verification set, optimizing and improving the model according to the evaluation result, improving the prediction capability of the model, and finally obtaining the prediction model capable of predicting the energy demand and supply in a future period of time.
Further, the method further comprises:
according to the energy demand change curve and the energy supply change curve, respectively extracting change nodes to obtain a plurality of demand mutation nodes and a plurality of supply mutation nodes;
According to the climate change curve, climate change node extraction is carried out, and a plurality of climate change nodes are obtained;
Performing association mapping on the plurality of demand mutation nodes and the plurality of supply mutation nodes and the plurality of climate mutation nodes respectively to obtain a plurality of climate association data sets;
According to the multiple demand mutation nodes and the multiple supply mutation nodes, data sequence segmentation is carried out to obtain multiple energy demand data subsequences and multiple energy supply data subsequences;
The energy supply prediction model is constructed based on the plurality of climate-related data sets, the plurality of energy demand data subsequences, and the plurality of energy supply data subsequences.
In the embodiment of the application, the energy demand change curve is analyzed, and the inflection point or the violent fluctuation point of the demand change is identified. These points may be sudden changes in energy demand due to sudden events, policy adjustments, or marketing factors. These points are taken as demand mutation nodes. The energy supply change curve is analyzed, and the inflection point or the sharp fluctuation point of the supply change is identified. These points may be abrupt energy supply due to production accidents, resource shortages or technological advances. These points were taken as feed mutation nodes.
And identifying inflection points or abnormal values of the climate change according to the climate change curve. These points may represent abrupt changes in climate conditions, such as extreme weather events, long-term climate change, and the like. These points were taken as climate change nodes. And carrying out association mapping on the extracted multiple demand mutation nodes and multiple supply mutation nodes and the climate mutation nodes respectively by a statistical method to obtain multiple climate association data sets.
According to the demand mutation node, the energy demand data sequence is divided into a plurality of subsequences, and each subsequence represents a relatively stable demand phase. This allows for a better analysis of the demand change characteristics of the different phases. Likewise, the energy supply data sequence is divided into a plurality of sub-sequences according to the supply abrupt node, each sub-sequence representing a relatively smooth supply phase. This allows a better analysis of the supply change characteristics of the different phases.
Based on the above steps we obtain a plurality of climate-related data sets, a plurality of energy demand data sub-sequences and a plurality of energy supply data sub-sequences. These datasets provide rich information for building energy supply prediction models. In constructing the energy supply prediction model, reference may be made to any of the methods described above.
Further, the method comprises the steps of:
based on the multiple energy demand data subsequences and multiple climate associated data corresponding to the multiple climate associated data sets, training to obtain multiple energy demand predictor models by combining machine learning;
Training to obtain a plurality of energy supply prediction sub-models by combining machine learning based on the plurality of energy supply data subsequences and a plurality of climate correlation data corresponding to the plurality of climate correlation data sets;
and forming the energy supply prediction model according to the plurality of energy demand prediction sub-models and the plurality of energy supply prediction sub-models.
In the embodiment of the application, corresponding climate-related data is selected as a characteristic from a plurality of energy demand data subsequences and a plurality of climate-related data sets, and the energy demand data is used as a target variable. And performing necessary characteristic processing on the climate-related data, selecting a proper mechanical learning algorithm for training, selecting a convolutional neural network for model training, and obtaining a plurality of energy demand predictor models in the training process consistent with the method.
From the plurality of sub-sequences of energy supply data and the plurality of climate-related data sets, corresponding climate-related data is likewise selected as a feature, the energy supply data being the target variable. And performing feature processing on the climate-related data, selecting a proper mechanical learning algorithm for training, selecting a convolutional neural network for model training, and obtaining a plurality of energy supply predictor models in the training process consistent with the method.
Based on the multiple energy demand predictor models and the multiple energy supply predictor models obtained through training, an integrated learning method, such as Bagging, can be adopted to integrate the multiple energy demand predictor models and the multiple energy supply predictor models into a unified energy supply predictor model. By combining the prediction results of multiple models, the risk of a single model can be reduced, and the accuracy of overall prediction can be improved.
Further, the method further comprises:
Acquiring real-time regional characteristics of a target village, including real-time regional climate data and real-time regional time periods;
based on the real-time regional period, combining the energy supply prediction model, and matching an energy demand prediction sub-model with an energy supply prediction sub-model to obtain a target energy demand prediction sub-model and a target energy supply prediction sub-model;
and carrying out energy demand supply prediction by combining the target energy demand prediction sub-model and the target energy supply prediction sub-model with the real-time regional climate data to obtain a supply and demand prediction result.
In the embodiment of the application, real-time climate data of the target village, including temperature, humidity, wind speed, rainfall and the like, is acquired from a relevant meteorological department or data platform. A real-time period of the target country, such as day, night, or other specific time period, is determined.
And based on the acquired real-time regional period, combining the previously constructed energy supply prediction model, and matching the energy demand prediction sub-model and the energy supply prediction sub-model. A subset of models that is most relevant to the current time period and climate conditions is selected. In the matching process, an energy demand predictor model applicable to the current period and climate conditions is selected. These sub-models will be used to predict energy demands over a period of time in the future. Likewise, an energy supply predictor model is selected that is applicable to the current time period and climate conditions. These sub-models will be used to predict the energy supply in the future for a period of time.
And predicting the energy demand by using a target energy demand predictor model and combining the real-time regional climate data. And using a target energy supply prediction sub-model to predict the energy supply by combining the real-time regional climate data. And comparing and analyzing the results of the energy demand prediction and the energy supply prediction to obtain a supply and demand prediction result. The supply and demand prediction result comprises supply and demand balance conditions, possible supply and demand gaps, the occurrence time of the gaps and the like.
Further, as shown in fig. 2, step S600 in the method provided in the application embodiment further includes:
the supply and demand prediction result comprises an energy prediction demand and an energy prediction supply;
Based on the energy prediction demand and the energy prediction supply quantity, carrying out supply-demand balance calculation to obtain an energy supply-demand difference value;
according to the energy supply and demand difference value, combining energy consumption coefficients, and calculating to obtain a supply and demand balance compensation value;
And carrying out surplus energy storage or standby energy calling based on the supply and demand balance compensation value.
In the embodiment of the application, the energy prediction demand is the demand including electric power, fuel gas and heat energy. The predicted energy supply amount is a supply amount including electric power, gas, and heat energy. And determining the energy supply and demand relation in a future period of time through supply and demand balance calculation. The supply-demand balance calculation process calculates a supply-demand difference by comparing the energy prediction demand and the energy prediction supply. If the difference is positive, indicating that the demand exceeds the supply, and a supply-demand gap exists; if the difference is negative, this indicates that the supply exceeds demand and that there is a rich source of energy.
Since there is a loss in the supply of energy during actual power supply, it is necessary to define a power supply consumption coefficient for adjusting the predicted supply-demand relationship to more accurately reflect the actual situation, which is empirically given by an expert.
And calculating a supply-demand balance compensation value according to the energy supply-demand difference value and the energy consumption coefficient. This value is used to adjust the actual energy supply process to make up for supply and demand gaps or to make full use of the surplus energy. And then, according to the supply and demand balance compensation value, the surplus energy reserve or standby energy is called. If it is predicted that there is a surplus of energy, this part of the energy can be stored for future use. If there is a supply and demand gap, the standby energy can be invoked to make up the deficiency. Through reasonable surplus energy reserve and standby energy calling, stable energy supply in the village can be ensured, and unnecessary energy waste or shortage is avoided.
In summary, the embodiment of the application has at least the following technical effects:
According to the application, the energy demand information is acquired; acquiring energy supply information; carrying out data preprocessing on the energy demand information and the energy supply information to obtain an energy demand data sequence and an energy supply data sequence; based on the energy demand data sequence and the energy supply data sequence, combining regional characteristics of the village, carrying out energy demand and supply analysis, and constructing an energy supply prediction model; the energy supply prediction model is combined with the climate characteristics of the real-time region to perform energy demand supply prediction; and carrying out supply-demand balance compensation according to the supply-demand prediction result, and carrying out energy calling according to the compensation result. The application solves the technical problems that in the prior art, because of the limitation of various factors such as geographic positions and the like, the energy supply and demand mainly depend on experience, and the accurate regulation and control of the energy supply and demand are difficult to realize, and achieves the technical effect of the accurate balance regulation and control of the energy supply and demand.
Example two
Based on the same inventive concept as the rural typical energy supply and demand balancing method based on big data in the foregoing embodiments, as shown in fig. 3, the present application provides a rural typical energy supply and demand balancing system based on big data, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
The demand information acquisition module 11 is configured to acquire typical energy demand information of a target country, where the demand information acquisition module 11 includes an energy demand type and corresponding energy demand information;
A supply information acquisition module 12, wherein the supply information acquisition module 12 is used for acquiring typical energy supply information of a target country, including energy supply types and corresponding energy supply amount information;
the data preprocessing module 13 performs data preprocessing on the typical energy demand information and the typical energy supply information by the data preprocessing module 13 to obtain an energy demand data sequence and an energy supply data sequence;
The energy supply prediction model construction module 14, wherein the energy supply prediction model construction module 14 is used for carrying out energy supply demand and supply analysis according to the energy supply data sequence and the regional characteristics of the target village so as to construct an energy supply prediction model;
The supply prediction module 15 is used for carrying out supply prediction on energy demand by combining the energy supply prediction model with the climate characteristics of the real-time region to obtain a supply and demand prediction result;
and the supply-demand balance compensation module 16 performs supply-demand balance compensation according to the supply-demand prediction result by the supply-demand balance compensation module 16, and performs energy call according to the compensation result.
Further, the system further comprises:
Cleaning the typical energy demand information and the typical energy supply information respectively to remove abnormal values, missing values and repeated values, so as to obtain pure energy demand information and pure energy supply information;
And carrying out serialization processing on the pure energy demand information and the pure energy supply information according to the energy type to obtain a plurality of energy demand data sequences and a plurality of energy supply data sequences.
Further, the system further comprises:
Drawing an energy demand change curve and an energy supply change curve based on the energy demand data sequence and the energy supply data sequence;
collecting regional climate change data of a target country, and drawing a climate change curve;
and carrying out energy demand and supply analysis based on the energy demand change curve, the energy supply change curve and the climate change curve, and constructing an energy supply prediction model.
Further, the system further comprises:
according to the energy demand change curve and the energy supply change curve, respectively extracting change nodes to obtain a plurality of demand mutation nodes and a plurality of supply mutation nodes;
According to the climate change curve, climate change node extraction is carried out, and a plurality of climate change nodes are obtained;
Performing association mapping on the plurality of demand mutation nodes and the plurality of supply mutation nodes and the plurality of climate mutation nodes respectively to obtain a plurality of climate association data sets;
According to the multiple demand mutation nodes and the multiple supply mutation nodes, data sequence segmentation is carried out to obtain multiple energy demand data subsequences and multiple energy supply data subsequences;
The energy supply prediction model is constructed based on the plurality of climate-related data sets, the plurality of energy demand data subsequences, and the plurality of energy supply data subsequences.
Further, the system further comprises:
according to the energy demand change curve and the energy supply change curve, respectively extracting change nodes to obtain a plurality of demand mutation nodes and a plurality of supply mutation nodes;
According to the climate change curve, climate change node extraction is carried out, and a plurality of climate change nodes are obtained;
Performing association mapping on the plurality of demand mutation nodes and the plurality of supply mutation nodes and the plurality of climate mutation nodes respectively to obtain a plurality of climate association data sets;
According to the multiple demand mutation nodes and the multiple supply mutation nodes, data sequence segmentation is carried out to obtain multiple energy demand data subsequences and multiple energy supply data subsequences;
The energy supply prediction model is constructed based on the plurality of climate-related data sets, the plurality of energy demand data subsequences, and the plurality of energy supply data subsequences.
Further, the system further comprises:
Acquiring real-time regional characteristics of a target village, including real-time regional climate data and real-time regional time periods;
based on the real-time regional period, combining the energy supply prediction model, and matching an energy demand prediction sub-model with an energy supply prediction sub-model to obtain a target energy demand prediction sub-model and a target energy supply prediction sub-model;
and carrying out energy demand supply prediction by combining the target energy demand prediction sub-model and the target energy supply prediction sub-model with the real-time regional climate data to obtain a supply and demand prediction result.
Further, the system further comprises:
the supply and demand prediction result comprises an energy prediction demand and an energy prediction supply;
Based on the energy prediction demand and the energy prediction supply quantity, carrying out supply-demand balance calculation to obtain an energy supply-demand difference value;
according to the energy supply and demand difference value, combining energy consumption coefficients, and calculating to obtain a supply and demand balance compensation value;
And carrying out surplus energy storage or standby energy calling based on the supply and demand balance compensation value.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. The rural typical energy supply and demand balance method based on big data is characterized by comprising the following steps of:
Acquiring typical energy demand information of a target country, wherein the typical energy demand information comprises energy demand types and corresponding energy demand information;
acquiring typical energy supply information of a target country, wherein the typical energy supply information comprises energy supply types and corresponding energy supply amount information;
Preprocessing the data of the typical energy demand information and the typical energy supply information to obtain an energy demand data sequence and an energy supply data sequence;
Based on the energy demand data sequence and the energy supply data sequence, combining regional characteristics of the target village to perform energy demand and supply analysis and constructing an energy supply prediction model;
The energy supply prediction model is combined with the climate characteristics of the real-time region to perform energy demand supply prediction, so that a supply and demand prediction result is obtained;
And carrying out supply-demand balance compensation according to the supply-demand prediction result, and carrying out energy calling according to the compensation result.
2. The method of claim 1, wherein preprocessing the typical energy demand information and the typical energy supply information to obtain an energy demand data sequence and an energy supply data sequence, comprising:
Cleaning the typical energy demand information and the typical energy supply information respectively to remove abnormal values, missing values and repeated values, so as to obtain pure energy demand information and pure energy supply information;
And carrying out serialization processing on the pure energy demand information and the pure energy supply information according to the energy type to obtain a plurality of energy demand data sequences and a plurality of energy supply data sequences.
3. The method of claim 1, wherein performing energy demand and supply analysis in conjunction with regional climate characteristics of a target country based on the energy demand data sequence and energy supply data sequence, further comprising:
Drawing an energy demand change curve and an energy supply change curve based on the energy demand data sequence and the energy supply data sequence;
collecting regional climate change data of a target country, and drawing a climate change curve;
and carrying out energy demand and supply analysis based on the energy demand change curve, the energy supply change curve and the climate change curve, and constructing an energy supply prediction model.
4. The method of claim 3, wherein performing energy demand and supply analysis based on the energy demand profile, energy supply profile, and climate profile, further comprising:
according to the energy demand change curve and the energy supply change curve, respectively extracting change nodes to obtain a plurality of demand mutation nodes and a plurality of supply mutation nodes;
According to the climate change curve, climate change node extraction is carried out, and a plurality of climate change nodes are obtained;
Performing association mapping on the plurality of demand mutation nodes and the plurality of supply mutation nodes and the plurality of climate mutation nodes respectively to obtain a plurality of climate association data sets;
According to the multiple demand mutation nodes and the multiple supply mutation nodes, data sequence segmentation is carried out to obtain multiple energy demand data subsequences and multiple energy supply data subsequences;
The energy supply prediction model is constructed based on the plurality of climate-related data sets, the plurality of energy demand data subsequences, and the plurality of energy supply data subsequences.
5. The method of claim 4, wherein constructing the energy supply prediction model based on the plurality of climate-related data sets, the plurality of energy demand data subsequences, and a plurality of energy supply data subsequences, further comprises:
based on the multiple energy demand data subsequences and multiple climate associated data corresponding to the multiple climate associated data sets, training to obtain multiple energy demand predictor models by combining machine learning;
Training to obtain a plurality of energy supply prediction sub-models by combining machine learning based on the plurality of energy supply data subsequences and a plurality of climate correlation data corresponding to the plurality of climate correlation data sets;
and forming the energy supply prediction model according to the plurality of energy demand prediction sub-models and the plurality of energy supply prediction sub-models.
6. The method of claim 5, wherein the energy demand supply prediction is performed by the energy supply prediction model in combination with real-time regional characteristics to obtain a supply-demand prediction result, further comprising:
Acquiring real-time regional characteristics of a target village, including real-time regional climate data and real-time regional time periods;
based on the real-time regional period, combining the energy supply prediction model, and matching an energy demand prediction sub-model with an energy supply prediction sub-model to obtain a target energy demand prediction sub-model and a target energy supply prediction sub-model;
and carrying out energy demand supply prediction by combining the target energy demand prediction sub-model and the target energy supply prediction sub-model with the real-time regional climate data to obtain a supply and demand prediction result.
7. The method of claim 1, wherein the supply-demand balance compensation is performed according to the supply-demand prediction result, and the energy call is performed according to the compensation result, further comprising:
the supply and demand prediction result comprises an energy prediction demand and an energy prediction supply;
Based on the energy prediction demand and the energy prediction supply quantity, carrying out supply-demand balance calculation to obtain an energy supply-demand difference value;
according to the energy supply and demand difference value, combining energy consumption coefficients, and calculating to obtain a supply and demand balance compensation value;
And carrying out surplus energy storage or standby energy calling based on the supply and demand balance compensation value.
8. A rural typical energy balance system based on big data, the system comprising:
The demand information acquisition module is used for acquiring typical energy demand information of a target country, including energy demand types and corresponding energy demand amount information;
the supply information acquisition module is used for acquiring typical energy supply information of a target country, and comprises an energy supply type and corresponding energy supply amount information;
the data preprocessing module is used for preprocessing the data of the typical energy demand information and the typical energy supply information to obtain an energy demand data sequence and an energy supply data sequence;
the energy supply prediction model construction module is used for constructing an energy supply prediction model by combining the regional characteristics of the target village based on the energy demand data sequence and the energy supply data sequence and carrying out energy demand and supply analysis;
The supply prediction module is used for carrying out energy demand supply prediction by combining the energy supply prediction model with the climate characteristics of the real-time region to obtain a supply and demand prediction result;
And the supply-demand balance compensation module performs supply-demand balance compensation according to the supply-demand prediction result and performs energy calling according to the compensation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410071493.1A CN118095704A (en) | 2024-01-18 | 2024-01-18 | Rural typical energy supply and demand balance method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410071493.1A CN118095704A (en) | 2024-01-18 | 2024-01-18 | Rural typical energy supply and demand balance method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118095704A true CN118095704A (en) | 2024-05-28 |
Family
ID=91146858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410071493.1A Pending CN118095704A (en) | 2024-01-18 | 2024-01-18 | Rural typical energy supply and demand balance method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118095704A (en) |
-
2024
- 2024-01-18 CN CN202410071493.1A patent/CN118095704A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116646933B (en) | Big data-based power load scheduling method and system | |
| Khan et al. | Genetic algorithm based optimized feature engineering and hybrid machine learning for effective energy consumption prediction | |
| CN108053082B (en) | Power grid medium and long term load prediction method based on temperature interval decomposition | |
| CN111915083B (en) | Wind power prediction method and prediction system based on time layered combination | |
| CN102426674A (en) | Power system load prediction method based on Markov chain | |
| CN102509173A (en) | Markov chain based method for accurately forecasting power system loads | |
| CN110909958A (en) | Short-term load prediction method considering photovoltaic grid-connected power | |
| CN116227637A (en) | Active power distribution network oriented refined load prediction method and system | |
| JP2006011715A (en) | Estimation method for resource consumption, and device | |
| CN112085285A (en) | Bus load prediction method and device, computer equipment and storage medium | |
| CN115796915A (en) | Electricity price prediction method and system for electricity trading market | |
| CN115481918A (en) | Active sensing and predictive analysis system for unit state based on source network load storage | |
| CN108346009A (en) | A kind of power generation configuration method and device based on user model self study | |
| CN117407681B (en) | Time sequence data prediction model establishment method based on vector clustering | |
| CN114186733A (en) | Short-term load prediction method and device | |
| CN113313312A (en) | Spring festival load rolling prediction method based on short, medium and long time scales | |
| CN118095704A (en) | Rural typical energy supply and demand balance method and system based on big data | |
| JP3754267B2 (en) | Water distribution prediction system | |
| CN111368257B (en) | Analysis and prediction method and device for coal-to-electricity load characteristics | |
| CN110909916B (en) | Wind power generation month electric quantity interval prediction method based on entropy weight method | |
| CN110175705B (en) | Load prediction method and memory and system comprising same | |
| Deng et al. | Medium-term rolling load forecasting based on seasonal decomposition and long short-term memory neural network | |
| Ye et al. | Short term output prediction method of runoff type medium and small hydropower stations | |
| CN118071089A (en) | LNG receiving station pipe network pressure scheduling method based on artificial intelligence | |
| CN113537575B (en) | Trend load prediction method containing distributed photovoltaic and electric automobile grid connection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |