CN117638919A - Charging pile energy supplementing optimization method based on multi-energy complementation - Google Patents
Charging pile energy supplementing optimization method based on multi-energy complementation Download PDFInfo
- Publication number
- CN117638919A CN117638919A CN202311691457.7A CN202311691457A CN117638919A CN 117638919 A CN117638919 A CN 117638919A CN 202311691457 A CN202311691457 A CN 202311691457A CN 117638919 A CN117638919 A CN 117638919A
- Authority
- CN
- China
- Prior art keywords
- energy
- energy supply
- predicted
- points
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000001502 supplementing effect Effects 0.000 title claims abstract description 46
- 238000005457 optimization Methods 0.000 title claims abstract description 22
- 238000009826 distribution Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000005286 illumination Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000003213 activating effect Effects 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 230000000153 supplemental effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 12
- 230000008569 process Effects 0.000 description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 239000013589 supplement Substances 0.000 description 5
- 238000004146 energy storage Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
- H02J3/0075—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source according to economic or energy efficiency considerations, e.g. economic dispatch
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/40—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation wherein a plurality of decentralised, dispersed or local energy generation technologies are operated simultaneously
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, and provides a charging pile energy supplementing optimization method based on multi-energy complementation, which comprises the following steps: deploying distributed auxiliary energy supply points for the charging pile clusters, and predicting energy and demand in future time zones; if the predicted energy is not greater than the demand, calculating deviation to generate energy supplementing, and carrying out distribution network and distributed energy supply configuration; if the predicted energy is greater than the demand, distributed energy supply configuration is carried out, the problem that the stability of a power supply mode mainly comprising a single electric energy source is insufficient, the fluctuation of energy supplementing data of the power distribution network configuration is large, the definition degree of an energy supplementing strategy is low, and the controllability is weak is solved, future energy of the predicted distributed auxiliary energy supply point is realized, the mode of combined predicted energy is adopted, redundant electric energy is reasonably distributed, renewable energy sources are fully utilized, the dependence on the traditional energy sources is reduced, complementation and optimization are realized through the definition regulation and control of energy supply and energy supplementing, the energy supplementing efficiency of a charging pile is improved, and the technical effect of power supply stability is ensured.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a charging pile energy supplementing optimization method based on multi-energy complementation.
Background
In the use process of the charging pile, due to the fact that the electric energy requirements of different time periods and different regions are different, certain fluctuation exists in the electric energy supply of the charging pile, the traditional charging pile energy supplementing mode is mainly based on a single electric energy source, the cooperative utilization of multiple energy sources is lacked, for example, the electric energy requirement can be suddenly increased in the peak hours of working days, the charging pile can possibly not provide service for an electric automobile due to lack of electricity, and the use experience of the charging pile and the travel convenience of the electric automobile are affected; or, in the early morning or late night, the demand of electric energy can be greatly reduced, and the energy supplementing mode of the charging pile can not be timely adjusted, so that electric energy is wasted, and the redundant electric energy can not be fully utilized.
In summary, in the prior art, there is a technical problem that the stability of a power supply mode mainly comprising a single electric energy source is insufficient, the fluctuation of energy supplementing data of the power distribution network configuration is large, and the fineness degree of an energy supplementing strategy is low and the controllability is weak.
Disclosure of Invention
The utility model provides a fill electric pile benefit can optimization method based on multipotency complementation, aims at solving the power supply mode stability that single electric energy source is dominant in prior art and is not enough, and the benefit can data volatility of distribution network configuration is great, leads to the finer degree of benefit can the tactics lower, and the controllability is less technical problem.
In view of the above problems, the present application provides a charging pile energy supplementing optimization method based on multi-energy complementation.
In a first aspect of the present disclosure, a method for optimizing energy compensation of a charging pile based on multi-energy complementation is provided, wherein the method comprises: deploying distributed auxiliary energy supply points for the charging pile clusters; loading energy supply prediction demand of a preset future time zone of the charging pile cluster; performing redundant energy prediction of the preset future time zone through the distributed auxiliary energy supply points to generate a plurality of single-point predicted energies and combined predicted energies, wherein the combined predicted energies are the sum of the plurality of single-point predicted energies; verifying whether the jointly predicted energy is greater than or equal to the energy supply predicted demand; when the combined predicted energy is smaller than or equal to the energy supply predicted demand, calculating a model difference between the combined predicted energy and the energy supply predicted demand, and generating alternating current predicted energy supplementing; performing power distribution network energy supplementing configuration according to the alternating current prediction energy supplementing, and performing distributed energy supplying configuration according to the combined prediction energy; and when the joint predicted energy is larger than the energy supply predicted demand, carrying out distributed energy supply configuration according to the single-point predicted energy.
In another aspect of the present disclosure, a charging pile energy supplementing optimization system based on multi-energy complementation is provided, wherein the system comprises: the energy supply point deployment module is used for deploying distributed auxiliary energy supply points for the charging pile clusters; the demand loading module is used for loading energy supply prediction demand of a preset future time zone of the charging pile cluster; the energy prediction module is used for traversing the distributed auxiliary energy supply points to execute redundant energy prediction of the preset future time zone, and generating a plurality of single-point predicted energies and joint predicted energies, wherein the joint predicted energies are the sum of the plurality of single-point predicted energies; the verification module is used for verifying whether the jointly predicted energy is greater than or equal to the energy supply predicted demand; the module difference calculation module is used for calculating the module difference between the jointly predicted energy and the energy supply predicted demand and generating alternating current predicted energy supplementing when the jointly predicted energy is smaller than or equal to the energy supply predicted demand; the first energy supply configuration module is used for carrying out energy supply configuration of the power distribution network according to the alternating current prediction energy supply and carrying out distributed energy supply configuration according to the combined prediction energy supply; and the second energy supply configuration module is used for carrying out distributed energy supply configuration according to the plurality of single-point predicted energy sources when the joint predicted energy sources are larger than the energy supply predicted demand.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
and as the distributed auxiliary energy supply points are deployed for the charging pile clusters, the energy supply demand of the future time zone is predicted. Traversing the distributed auxiliary energy points, generating a plurality of single-point predicted energies and joint predicted energies. And checking whether the combined prediction energy meets the demand, if not, calculating deviation to generate supplementary energy, and carrying out distribution network and distributed energy supply configuration. If the combined prediction energy is excessive, distributed energy supply configuration is carried out according to a plurality of single-point prediction energy, future energy of the prediction distributed auxiliary energy supply points is realized, the excessive electric energy is reasonably distributed by adopting a combined prediction energy mode, renewable energy sources are fully utilized, dependence on traditional energy sources is reduced, and the technical effects of complementation and optimization are realized, the energy supplementing efficiency of the charging pile is improved, and the power supply stability is ensured through the fine regulation and control of energy supply and energy supplementing.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Fig. 1 is a schematic flow chart of a possible method for optimizing energy compensation of a charging pile based on multi-energy complementation according to an embodiment of the present application;
fig. 2 is a schematic diagram of a possible flow of generating ac predicted energy compensation in a multi-energy complementary-based charging pile energy compensation optimization method according to an embodiment of the present application;
fig. 3 is a schematic diagram of a possible structure of a charging pile energy supplementing optimization system based on multi-energy complementation according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an energy supply point deployment module 100, a demand loading module 200, an energy prediction module 300, a verification module 400, a module difference calculation module 500, a first energy supply configuration module 600 and a second energy supply configuration module 700.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Example 1
As shown in fig. 1, an embodiment of the present application provides a charging pile energy supplementing optimization method based on multi-energy complementation, where the method includes:
step-1: deploying distributed auxiliary energy supply points for the charging pile clusters;
step-2: loading energy supply prediction demand of a preset future time zone of the charging pile cluster;
in a charging pile cluster in a target charging station, deploying distributed auxiliary energy supply points for the charging pile cluster, wherein a plurality of charging piles in various states are arranged in the target charging station, and the distributed auxiliary energy supply points adopt various energy supply modes, including but not limited to hydraulic energy supply, photovoltaic energy supply and wind power energy supply; disposing other clean energy supply points such as hydraulic energy supply points, photovoltaic energy supply points, wind energy supply points and the like in the target charging station: and a control system and a connection interface of the distributed auxiliary energy supply points are configured to ensure that the distributed auxiliary energy supply points can communicate and interact with the charging pile clusters.
Based on the distributed auxiliary energy supply points, the energy supply prediction demand of the target charging station in a preset future time zone is obtained, the preset future time zone refers to a future period of time (one hour in the future), the energy supply prediction demand comprises prediction electric quantity demand data (the electric quantity demand prediction in the preset future time zone can be kilowatt-hour kWh or megawatt-hour MWh), prediction charging rate (the charging rate prediction in the preset future time zone can be charging quantity kWh/h or charging quantity kWh/min per minute), prediction charging time (the charging time prediction in the preset future time zone can be hour or minute), prediction battery energy storage state (the battery energy storage state prediction in the preset future time zone can be battery energy storage energy density Wh/kg), and the energy supply prediction demand in the preset future time zone is loaded into the multi-energy complementary-based charging pile energy supplementing optimizing system to serve as a reference basis for energy supply configuration.
Step-3: performing redundant energy prediction of the preset future time zone through the distributed auxiliary energy supply points to generate a plurality of single-point predicted energies and combined predicted energies, wherein the combined predicted energies are the sum of the plurality of single-point predicted energies;
based on the internet of things technology, collecting sensitive environment state data of each distributed auxiliary energy supply point, such as wind speed, wind direction, water level, flow speed, sunlight intensity and the like, traversing all the distributed auxiliary energy supply points, predicting redundant energy of each distributed auxiliary energy supply point according to historical data of each energy supply point and sensitive environment state data of a future time zone, and generating a plurality of single-point prediction energy according to a prediction result of each distributed auxiliary energy supply point; and adding the single-point prediction energy corresponding to all the distributed auxiliary energy supply points to obtain the combined prediction energy. And deploying distributed auxiliary energy supply points for the charging pile clusters, generating redundant energy prediction results meeting the requirements of a preset future time zone, and providing data support for distributed fine regulation and control of energy supply and energy supplement.
Step-4: verifying whether the jointly predicted energy is greater than or equal to the energy supply predicted demand;
Step-5: when the combined predicted energy is smaller than or equal to the energy supply predicted demand, calculating a model difference between the combined predicted energy and the energy supply predicted demand, and generating alternating current predicted energy supplementing;
step-6: performing power distribution network energy supplementing configuration according to the alternating current prediction energy supplementing, and performing distributed energy supplying configuration according to the combined prediction energy;
after the joint predicted energy and the energy supply predicted demand are obtained, the joint predicted energy is compared with the energy supply predicted demand, and whether enough redundant energy exists to meet the demand of the charging pile cluster is judged: if the combined predicted energy is greater than the energy predicted demand, indicating that the electric energy of the target charging station is sufficient; if the combined predicted energy is smaller than or equal to the energy predicted demand, the energy of the target charging station is possibly insufficient, and the power distribution network is required to be used for supplementing the energy;
under the condition that the combined predicted energy is smaller than or equal to the energy supply predicted demand, obtaining a difference value between the combined predicted energy and the energy supply predicted demand, wherein the difference value between the combined predicted energy and the energy supply predicted demand is an instantaneous value, can be a positive value or a negative value, and depends on the positive and negative conditions of the difference value; in a preset future time zone, performing addition calculation based on the difference values of the plurality of jointly predicted energies and the energy supply predicted demand amounts to generate alternating current predicted energy supply,
And carrying out power distribution network energy supplementing configuration according to the alternating current prediction energy supplementing: judging whether the energy supply of the power distribution network needs to be increased or decreased according to the value and the direction of the alternating current predictive energy supplement; and according to the judging result, adjusting the energy configuration of the power distribution network based on the value of the alternating current predictive energy supplement and the electricity utilization characteristic of the charging pile cluster, such as increasing or decreasing the output power of a generator, adjusting the flow of a hydropower station and the like.
Distributed energy supply configuration is carried out according to the joint prediction energy: acquiring the value and the direction of the joint prediction energy; and carrying out distributed energy supply configuration according to the value and the direction of the jointly predicted energy and the requirement of the charging pile cluster, such as adjusting the output power of a distributed auxiliary energy supply point, adding additional energy storage equipment and the like.
Checking whether the combined prediction energy meets the energy supply prediction demand, generating alternating current prediction energy supplementing according to the difference value, and carrying out distribution network energy supplementing configuration and distributed energy supplying configuration, so that the charging pile clusters schedule and configure energy supply of distributed auxiliary energy supply points in advance, the condition of energy deficiency in peak hours is avoided, the energy demand of the charging pile clusters is ensured to be met in a preset time zone, and the energy supply of the charging pile clusters is sufficient and stable.
Step-7: and when the joint predicted energy is larger than the energy supply predicted demand, carrying out distributed energy supply configuration according to the single-point predicted energy.
If the combined predicted energy is larger than the energy supply predicted demand, the electric energy of the target charging station is sufficient, and a difference value between the combined predicted energy and the energy supply predicted demand, namely redundant energy, is obtained; and the distributed auxiliary energy supply points are sorted and configured by adopting the fitness function, and only the energy supply points with high energy supplementing efficiency in the energy supply configuration scheme are reserved under the condition of meeting the energy supply prediction demand, so that the overall energy supplementing efficiency of the charging pile cluster is improved.
Further, as shown in fig. 2, when the jointly predicted energy is less than or equal to the energy supply predicted demand, calculating a model difference between the jointly predicted energy and the energy supply predicted demand, and generating an ac predicted supplemental energy, the method of the present application includes:
performing energy supply fluctuation analysis on the distributed auxiliary energy supply points to generate error energy;
calculating the model difference between the combined predicted energy and the energy predicted demand to generate an energy model difference;
and adding the error energy and the energy supply module difference to generate the alternating current prediction energy compensation.
In general, certain loss exists in the energy supply process, for example, in the process of transmitting electric energy from a distributed auxiliary energy supply point to a charging pile cluster, loss may be generated due to factors such as resistance and transmission distance of a circuit; certain losses may also occur during the conversion of electrical energy from one form to another, such as from alternating current to direct current, or from direct current to alternating current; in the working process of the charging pile, the distributed auxiliary energy supply points and other equipment, certain heat energy loss can be generated by internal elements of the equipment, based on the heat energy loss, energy supply fluctuation conditions of the distributed auxiliary energy supply points are analyzed, error energy is generated, the error energy represents the deviation between actual energy and predicted energy, historical energy supply data (namely actual energy) of the distributed auxiliary energy supply points are required to be collected, an energy prediction channel is constructed based on the historical energy supply data, and the energy prediction channel can predict energy in a future time zone and generate error energy.
And calculating a difference value between the combined predicted energy and the predicted energy demand, namely an energy supply module difference, wherein the energy supply module difference can reflect a difference value of instantaneous energy supply, adding the error energy and the energy supply module difference to generate alternating current predicted energy supplement, and the predicted energy supplement refers to electric energy needed to be supplemented for meeting the predicted energy demand. According to the actual electric energy requirement and the energy supply condition of the available distributed auxiliary energy supply points, the required supplementary electric energy is calculated by introducing the concepts of error energy supply and energy supply module difference, the shortage of the supplementary electric energy caused by the loss of the energy supply process is avoided, and the accuracy of the alternating current prediction energy supply is improved.
Further, energy fluctuation analysis is performed on the distributed auxiliary energy supply points to generate error energy, and the method comprises the following steps:
based on the Internet of things, collecting the sensitive environment state of the preset future time zone of each distributed auxiliary energy supply point;
collecting first historical energy supply record data of the distributed auxiliary energy supply points according to the sensitive environment state, wherein the first historical energy supply record data comprises predicted energy supply record data and actual energy supply record data;
counting a first duty ratio coefficient of the total number of the recorded data of which the actual energy recorded data is larger than or equal to the predicted energy recorded data;
when the first duty ratio coefficient is larger than or equal to a duty ratio coefficient threshold value, setting the sub-error energy of the corresponding energy supply point to be zero;
when the first duty ratio coefficient is smaller than the duty ratio coefficient threshold value, extracting an energy supply deviation percentage set of historical energy supply record data of which the actual energy record data is smaller than the predicted energy record data;
performing concentrated trend analysis on the energy supply deviation percentage set to generate error percentages, performing error analysis on the error percentages and the corresponding single-point predicted energy, and generating sub-error energy of the corresponding functional points;
And adding the sub-error energy of all the energy supply points to generate the error energy.
The energy supply stability of water power, photovoltaic and wind power is insufficient, the energy supply quantity is dynamic change, such as water level, flow rate and the like of a water power energy supply point, illumination intensity, wind speed and the like of the photovoltaic and wind power energy supply point, correspondingly, based on the Internet of things, sensitive environment states of the preset future time zones of each distributed auxiliary energy supply point are collected, and sensitive environment state data comprise weather conditions (comprising illumination intensity and wind speed), geographical positions (comprising water level and flow rate) and the like and are used for evaluating fluctuation conditions of energy supply.
And selecting a corresponding distributed auxiliary energy supply point according to the sensitive environment state, and collecting first historical energy supply record data of the distributed auxiliary energy supply point, wherein the first historical energy supply record data is the historical energy supply record data after the energy prediction channel is deployed, and comprises a predicted energy record and an actual energy record.
Counting the collected historical energy supply record data, and calculating the proportion of the number of record data of the actual energy supply in the actual energy supply record data, which is larger than or equal to the predicted energy in the predicted energy record data, to the total record number under the condition that the actual energy supply in the actual energy supply record data is larger than or equal to the predicted energy in the predicted energy record data, so as to obtain a first duty ratio coefficient:
If the first duty ratio coefficient is larger than or equal to a preset duty ratio coefficient threshold value, the actual energy is larger than or equal to the predicted energy, the number of times is larger, the energy supply fluctuation is smaller, and therefore the sub-error energy of the energy supply point is set to be zero; if the first duty ratio coefficient is smaller than the duty ratio coefficient threshold value, indicating that the actual energy is smaller than the predicted energy more times and the energy fluctuation is larger, extracting an energy supply deviation percentage set of the history energy supply record data of which the actual energy record data is smaller than the predicted energy record data, wherein the energy supply deviation percentage= (predicted energy-actual energy)/predicted energy;
the method comprises the steps of carrying out concentrated trend analysis on the extracted energy supply deviation percentage set, for example, deleting outliers by using a statistical method such as a quartile range method, and calculating error percentages, wherein the method comprises the following steps: determining the quartiles of the energy supply deviation percentage set, wherein the quartiles are points for dividing the data into four equal parts and respectively represent the lower edge, the lower quartiles (25%) (namely the lower 25% of the first duty ratio coefficient), the upper quartiles (75%) (namely the upper 25% of the first duty ratio coefficient) and the upper edge of the data; calculating the Range (Range) of the upper quartile and the lower quartile, the Range representing the fluctuation Range of the quartile; when the range is calculated, it is possible to determine which data points are outliers, wherein outliers refer to those points far from other data points, which are generally determined according to their distance or deviation percentage, and to delete the outliers, a Box Plot (Box Plot) or a Box Plot (Box-Cox Plot) may be used to identify and process the points.
Performing error analysis according to the error percentage and the corresponding single-point prediction energy to generate sub-error energy of the corresponding functional point, including: once the outliers are deleted, a percentage error can be calculated, where the percentage error refers to the ratio of the deviation between the actual energy and the predicted energy to the predicted energy, where the percentage error is calculated as: percent energy bias = (predicted energy-actual energy)/predicted energy; and adding the sub-error energy of all the energy supply points of all the distributed auxiliary energy supply points to obtain the integral error energy, wherein the error energy is used for the following energy supplementing strategy and distribution network configuration.
Further, traversing the distributed auxiliary energy points to perform redundant energy prediction of the preset future time zone to generate a plurality of single-point predicted energies, the method comprises:
based on the Internet of things, collecting the sensitive environment state of the preset future time zone of each distributed auxiliary energy supply point;
activating an energy prediction channel associated with the distributed auxiliary energy supply point, receiving the sensitive environment state to perform training, and generating a plurality of single-point prediction initial energies;
Interacting each of the distributed auxiliary energy points to obtain a plurality of configured output energies for the preset future time zone, wherein the configured output energies characterize the energy of the preset future time zone in which the distributed auxiliary energy points have been pre-scheduled;
and generating the single-point predicted energies by differencing the single-point predicted initial energies and the configured output energies.
Various sensors and monitoring devices are used for acquiring sensitive environment state data of each distributed auxiliary energy supply point in a preset future time zone, the sensitive environment state data comprise weather conditions (such as temperature, humidity, illumination intensity and the like), geographic positions (such as altitude, longitude and latitude and the like) and the like, an Internet of things technology is adopted, and the sensitive environment state data are acquired in real time and are processed later.
After the sensitive environment state data are acquired, an energy prediction channel associated with each distributed auxiliary energy supply point is activated, a machine learning model of the energy prediction channel is used for obtaining a plurality of single-point prediction initial energies through inputting the sensitive environment state data and executing corresponding training or fitting processes, and the single-point prediction initial energies are output according to the current environment and equipment state predictions.
To obtain configured output energy for each distributed auxiliary energy point in a preset future time zone, interaction with each distributed auxiliary energy point is required, including: and reading configuration files, scheduling records or other related data of each distributed auxiliary energy supply point, and obtaining a plurality of configured output energy of each distributed auxiliary energy supply point in a preset future time zone through interaction, wherein the configured output energy refers to an energy supply plan or a scheduled output and is used for representing the energy of the preset future time zone of the distributed auxiliary energy supply point which is pre-scheduled, so as to obtain corresponding configured output energy.
Performing a difference operation on the plurality of single-point predicted initial energies and the configured output energies, specifically, subtracting the configured output energies from the single-point predicted initial energies to obtain a difference value: if the single point predicted initial energy is extracted-the configured output energy is greater than 0 and greater than a preset deviation (e.g., 10%), then the difference is used as part of the single point predicted energy to perform a differencing operation, resulting in a plurality of single point predicted energies reflecting the redundant supply capacity of the distributed auxiliary energy point in a preset future time zone. And traversing the distributed auxiliary energy supply points to execute redundant energy prediction of a preset future time zone, and providing data support for complementation and optimization.
Further, activating an energy prediction channel associated with the distributed auxiliary energy supply point, receiving the sensitive environment state to perform training, and generating a plurality of single-point prediction initial energies, wherein before the method comprises the following steps:
when the distributed auxiliary energy supply points are connected into the charging pile cluster, the distributed auxiliary energy supply points are interacted, and second historical energy supply record data are received;
and performing regression function fitting on the BP neural network by taking the energy record value of the second historical energy supply record data as supervision data and the sensitive environment state record value of the second historical energy supply record data as input data to generate the energy prediction channel.
Before the energy prediction channel of the distributed auxiliary energy supply point is activated, the sensitive environment state is received to perform training and generate a plurality of single-point prediction initial energies, the method further comprises the preparation steps that firstly, the distributed auxiliary energy supply point is connected with a charging pile cluster, the establishment of network connection is involved, the transmission of data and the setting of a communication protocol are carried out, and through interaction with the distributed auxiliary energy supply point, second historical energy supply record data can be obtained, wherein the second historical energy supply record data comprises past energy record values and corresponding sensitive environment state record values;
The energy log value of the second historical energy log data is used as supervisory data, which is typically used to train a machine learning model, containing the correct, known results (in this case, the actual energy) so that the model can learn how to predict the results correctly. Meanwhile, a sensitive environmental state record value of the second historical energy supply record data is used as input data, wherein the sensitive environmental state record value comprises various environmental factors such as temperature, humidity, illumination and the like, and can influence the energy of the distributed auxiliary energy supply points;
performing regression function fitting on the BP neural network by using the input data and the supervision data, and fitting the relationship between the input data and the output data by adjusting the network weight and the bias term; generating an energy prediction channel through regression function fitting, wherein the energy prediction channel receives sensitive environment state data as input and outputs predicted energy; once the above-described preparatory steps are completed, energy prediction channels associated with the distributed auxiliary energy supply points may be activated, sensitive environmental state data received, and predicted through the already trained energy prediction channels to generate a plurality of single point predicted initial energies. When the distributed auxiliary energy supply points are connected into the charging pile clusters, training of the energy prediction channel is performed through the BP neural network, a plurality of single-point prediction initial energies are generated, the electric energy supply and demand analysis efficiency is improved, and the electric energy supply and demand are managed better.
Further, based on the internet of things, collecting the sensitive environment state of the preset future time zone of each distributed auxiliary energy supply point, the method of the application comprises the following steps:
when the distributed auxiliary energy supply points are wind power energy supply points, the sensitive environment state is wind power state information;
when the distributed auxiliary energy supply points are hydraulic energy supply points, the sensitive environment state is hydraulic state information;
when the distributed auxiliary energy supply points are photovoltaic energy supply points, the sensitive environment state is illumination state information.
The type of each distributed auxiliary energy supply point, such as a wind power energy supply point, a hydraulic energy supply point or a photovoltaic energy supply point, is determined and can be obtained through identification of the energy supply points. And selecting corresponding sensitive environment state data to collect according to the type of the energy supply point. If the wind power supply point is a wind power supply point, wind power state information including wind speed, wind direction and the like is required to be collected; if the hydraulic power supply point is a hydraulic power supply point, hydraulic state information including water level, flow rate and the like is required to be collected; in the case of a photovoltaic energy supply point, illumination state information including sunlight intensity, spectral distribution and the like needs to be acquired. Through the internet of things technology, sensor and other equipment are used for collecting sensitive environment state data of each distributed auxiliary energy supply point in a preset future time zone in real time, classified storage and analysis are carried out according to the types and actual requirements of different energy supply points, and support is provided for subsequent energy prediction and optimization.
Further, when the jointly predicted energy is greater than the energy supply predicted demand, performing distributed energy supply configuration according to the plurality of single-point predicted energies, the method includes:
traversing the distributed auxiliary energy supply points, and matching the distributed position information of a plurality of energy supply points and the sub-error energy of a plurality of energy supply points;
traversing the distribution position information of the energy supply points, and carrying out scheduling distance statistics based on the position information of the charging pile clusters to generate a plurality of energy supply scheduling distances;
based on a coefficient of variation method, configuring a first weight for the energy supply scheduling distance, configuring a second weight for energy supply point sub-error energy supply, and constructing an adaptability function:
；
wherein,characterizing the fitness of a certain energy supply configuration scheme, +.>For the first weight, ++>For the second weight, ++>The distance of the ith energy supply point of the energy supply configuration scheme is characterized by +.>Sub-error energy representing the ith energy point of the energy supply arrangement, < +.>And->For normalizing the adjustment parameters, N represents the total number of energy supply points of the energy supply configuration scheme;
sorting based on the single-point predicted energy by taking the energy supply predicted demand as a constraint to generate a plurality of energy supply configuration schemes, wherein the sum of energy supply of any one energy supply configuration scheme is larger than or equal to 1.2 times of the energy supply predicted demand;
And according to the fitness function, traversing the energy supply configuration schemes to execute minimum fitness sorting, generating an energy supply configuration recommendation scheme, and carrying out distributed energy supply configuration.
Acquiring position information of each distributed auxiliary energy supply point, including longitude, latitude and the like; sub-error energy of each distributed auxiliary energy supply point is obtained, namely, a difference value obtained by carrying out difference according to a plurality of single-point predicted energy and configured output energy is obtained, wherein the sub-error energy refers to that the deviation between actual energy and predicted energy accounts for the predicted energy; and matching the position information with the sub-error energy to construct the position and error information of each energy supply point.
Calculating the distance between the position information of the charging pile clusters and the position information of each distributed auxiliary energy supply point according to the position information of the charging pile clusters; counting the scheduling distance of each energy supply point to generate a plurality of energy supply scheduling distances; the distribution position information of each energy supply point is traversed, and the scheduling distance is counted based on the position information of the charging pile clusters, wherein the scheduling distance refers to the direct distance or the path distance from the energy supply point to the demand point.
According to a variation coefficient method, a weight value is configured for the scheduling distance of each energy supply point, the variation coefficient method is a common weight determination method, the weight value represents the importance of the weight value in the fitness function, the variation coefficient method can configure the weight value according to the discrete degree of data, and the larger the discrete degree is, the larger the weight value is. Fitness function For measuring the quality of each energy supply configuration scheme, taking the influence of energy supply dispatching distance and sub-error energy into consideration, wherein,characterizing the fitness of a certain energy supply configuration scheme, +.>For the first weight, ++>For the second weight, ++>The distance of the ith energy supply point of the energy supply configuration scheme is characterized by +.>Sub-error energy representing the ith energy point of the energy supply arrangement, < +.>And->For normalizing the adjustment parameters, N represents the total number of energy supply points of the energy supply configuration scheme;
sorting based on a plurality of single-point predicted energies with the predicted energy demand as a constraint condition to generate a plurality of energy supply configuration schemes, wherein the sum of the energies of any one energy supply configuration scheme needs to be greater than or equal to 1.2 times of the predicted energy demand; calculating a fitness value for each generated energy supply configuration scheme, and sorting according to the fitness values; selecting a scheme with the minimum fitness value as a recommended scheme, and carrying out distributed energy supply configuration; and scheduling and configuring the distributed auxiliary energy supply points according to a recommended scheme so as to meet the energy supply prediction demand. The optimal configuration of the distributed auxiliary energy supply points based on the variation coefficient method is realized, and the recommended scheme is optimized from a plurality of energy supply configuration schemes, so that the higher energy demand is met, and the energy utilization efficiency is improved.
In summary, the charging pile energy supplementing optimization method based on multi-energy complementation provided by the embodiment of the application has the following technical effects:
1. by accurately predicting the future energy of the distributed auxiliary energy supply points, the accuracy of electric energy prediction can be improved, and the problem of unbalanced supply and demand of electric energy caused by insufficient or excessive energy supply can be effectively avoided.
2. Under the condition that the combined predicted energy is larger than the predicted energy demand, renewable energy sources can be fully utilized through a reasonable electric energy distribution strategy, dependence on traditional energy sources is reduced, and meanwhile, the load pressure of a power grid is reduced.
3. By cooperatively utilizing various energy sources, complementation and optimization can be realized, and the energy supplementing efficiency of the charging pile is improved.
4. Because the distributed auxiliary energy supply points are adopted as wind power energy supply points, the sensitive environment state is wind power state information; when the distributed auxiliary energy supply points are hydraulic energy supply points, the sensitive environment state is hydraulic state information; when the distributed auxiliary energy supply points are photovoltaic energy supply points, the sensitive environment state is illumination state information. Through the internet of things technology, sensor and other equipment are used for collecting sensitive environment state data of each distributed auxiliary energy supply point in a preset future time zone in real time, classified storage and analysis are carried out according to the types and actual requirements of different energy supply points, and support is provided for subsequent energy prediction and optimization.
Example two
Based on the same inventive concept as the charging pile energy supplementing optimization method based on the multi-energy complementation in the foregoing embodiment, as shown in fig. 3, an embodiment of the present application provides a charging pile energy supplementing optimization system based on the multi-energy complementation, where the system includes:
the energy supply point deployment module 100 is used for deploying distributed auxiliary energy supply points for the charging pile clusters;
the demand loading module 200 is used for loading the energy supply prediction demand of the charging pile cluster in a preset future time zone;
an energy prediction module 300, configured to perform redundant energy prediction of the preset future time zone by traversing the distributed auxiliary energy points, and generate a plurality of single-point predicted energies and a joint predicted energy, where the joint predicted energy is a sum of the plurality of single-point predicted energies;
a verification module 400 for verifying whether the jointly predicted energy is greater than or equal to the energy supply predicted demand;
the module 500 is configured to calculate a module difference between the jointly predicted energy and the energy supply predicted demand and generate ac predicted supplemental energy when the jointly predicted energy is less than or equal to the energy supply predicted demand;
the first energy supply configuration module 600 is configured to perform power distribution network energy supply configuration according to the alternating current prediction energy supply, and perform distributed energy supply configuration according to the joint prediction energy supply;
A second energy supply configuration module 700 configured to perform distributed energy supply configuration according to the plurality of single point predicted energies when the jointly predicted energies are greater than the energy supply predicted demands.
Further, the system further comprises:
performing energy supply fluctuation analysis on the distributed auxiliary energy supply points to generate error energy;
calculating the model difference between the combined predicted energy and the energy predicted demand to generate an energy model difference;
and adding the error energy and the energy supply module difference to generate the alternating current prediction energy compensation.
Further, the system further comprises:
based on the Internet of things, collecting the sensitive environment state of the preset future time zone of each distributed auxiliary energy supply point;
collecting first historical energy supply record data of the distributed auxiliary energy supply points according to the sensitive environment state, wherein the first historical energy supply record data comprises predicted energy supply record data and actual energy supply record data;
counting a first duty ratio coefficient of the total number of the recorded data of which the actual energy recorded data is larger than or equal to the predicted energy recorded data;
when the first duty ratio coefficient is larger than or equal to a duty ratio coefficient threshold value, setting the sub-error energy of the corresponding energy supply point to be zero;
When the first duty ratio coefficient is smaller than the duty ratio coefficient threshold value, extracting an energy supply deviation percentage set of historical energy supply record data of which the actual energy record data is smaller than the predicted energy record data;
performing concentrated trend analysis on the energy supply deviation percentage set to generate error percentages, performing error analysis on the error percentages and the corresponding single-point predicted energy, and generating sub-error energy of the corresponding functional points;
and adding the sub-error energy of all the energy supply points to generate the error energy.
Further, the system further comprises:
based on the Internet of things, collecting the sensitive environment state of the preset future time zone of each distributed auxiliary energy supply point;
activating an energy prediction channel associated with the distributed auxiliary energy supply point, receiving the sensitive environment state to perform training, and generating a plurality of single-point prediction initial energies;
interacting each of the distributed auxiliary energy points to obtain a plurality of configured output energies for the preset future time zone, wherein the configured output energies characterize the energy of the preset future time zone in which the distributed auxiliary energy points have been pre-scheduled;
and generating the single-point predicted energies by differencing the single-point predicted initial energies and the configured output energies.
Further, the system further comprises:
when the distributed auxiliary energy supply points are connected into the charging pile cluster, the distributed auxiliary energy supply points are interacted, and second historical energy supply record data are received;
and performing regression function fitting on the BP neural network by taking the energy record value of the second historical energy supply record data as supervision data and the sensitive environment state record value of the second historical energy supply record data as input data to generate the energy prediction channel.
Further, the system further comprises:
when the distributed auxiliary energy supply points are wind power energy supply points, the sensitive environment state is wind power state information;
when the distributed auxiliary energy supply points are hydraulic energy supply points, the sensitive environment state is hydraulic state information;
when the distributed auxiliary energy supply points are photovoltaic energy supply points, the sensitive environment state is illumination state information.
Further, the system further comprises:
traversing the distributed auxiliary energy supply points, and matching the distributed position information of a plurality of energy supply points and the sub-error energy of a plurality of energy supply points;
traversing the distribution position information of the energy supply points, and carrying out scheduling distance statistics based on the position information of the charging pile clusters to generate a plurality of energy supply scheduling distances;
Based on a coefficient of variation method, configuring a first weight for the energy supply scheduling distance, configuring a second weight for energy supply point sub-error energy supply, and constructing an adaptability function:
；
wherein,characterizing the fitness of a certain energy supply configuration scheme, +.>For the first weight, ++>For the second weight, ++>The distance of the ith energy supply point of the energy supply configuration scheme is characterized by +.>Sub-error energy representing the ith energy point of the energy supply arrangement, < +.>And->For normalizing adjustment parameters, N represents an energy supply configuration schemeIs a total number of energy supply points;
sorting based on the single-point predicted energy by taking the energy supply predicted demand as a constraint to generate a plurality of energy supply configuration schemes, wherein the sum of energy supply of any one energy supply configuration scheme is larger than or equal to 1.2 times of the energy supply predicted demand;
and according to the fitness function, traversing the energy supply configuration schemes to execute minimum fitness sorting, generating an energy supply configuration recommendation scheme, and carrying out distributed energy supply configuration.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any of the methods to implement embodiments of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (8)
1. The charging pile energy supplementing optimization method based on multi-energy complementation is characterized by comprising the following steps of:
deploying distributed auxiliary energy supply points for the charging pile clusters;
loading energy supply prediction demand of a preset future time zone of the charging pile cluster;
performing redundant energy prediction of the preset future time zone through the distributed auxiliary energy supply points to generate a plurality of single-point predicted energies and combined predicted energies, wherein the combined predicted energies are the sum of the plurality of single-point predicted energies;
verifying whether the jointly predicted energy is greater than or equal to the energy supply predicted demand;
when the combined predicted energy is smaller than or equal to the energy supply predicted demand, calculating a model difference between the combined predicted energy and the energy supply predicted demand, and generating alternating current predicted energy supplementing;
Performing power distribution network energy supplementing configuration according to the alternating current prediction energy supplementing, and performing distributed energy supplying configuration according to the combined prediction energy;
and when the joint predicted energy is larger than the energy supply predicted demand, carrying out distributed energy supply configuration according to the single-point predicted energy.
2. The method of claim 1, wherein calculating a model difference between the jointly predicted energy and the energy supply predicted demand when the jointly predicted energy is less than or equal to the energy supply predicted demand, generating ac predicted supplemental energy comprises:
performing energy supply fluctuation analysis on the distributed auxiliary energy supply points to generate error energy;
calculating the model difference between the combined predicted energy and the energy predicted demand to generate an energy model difference;
and adding the error energy and the energy supply module difference to generate the alternating current prediction energy compensation.
3. The method of claim 2, wherein performing energy fluctuation analysis on the distributed auxiliary energy points to generate error energy comprises:
based on the Internet of things, collecting the sensitive environment state of the preset future time zone of each distributed auxiliary energy supply point;
Collecting first historical energy supply record data of the distributed auxiliary energy supply points according to the sensitive environment state, wherein the first historical energy supply record data comprises predicted energy supply record data and actual energy supply record data;
counting a first duty ratio coefficient of the total number of the recorded data of which the actual energy recorded data is larger than or equal to the predicted energy recorded data;
when the first duty ratio coefficient is larger than or equal to a duty ratio coefficient threshold value, setting the sub-error energy of the corresponding energy supply point to be zero;
when the first duty ratio coefficient is smaller than the duty ratio coefficient threshold value, extracting an energy supply deviation percentage set of historical energy supply record data of which the actual energy record data is smaller than the predicted energy record data;
performing concentrated trend analysis on the energy supply deviation percentage set to generate error percentages, performing error analysis on the error percentages and the corresponding single-point predicted energy, and generating sub-error energy of the corresponding functional points;
and adding the sub-error energy of all the energy supply points to generate the error energy.
4. The method of claim 1, wherein traversing the distributed auxiliary energy points to perform redundant energy predictions for the preset future time zone generates a plurality of single point predicted energies, comprising:
Based on the Internet of things, collecting the sensitive environment state of the preset future time zone of each distributed auxiliary energy supply point;
activating an energy prediction channel associated with the distributed auxiliary energy supply point, receiving the sensitive environment state to perform training, and generating a plurality of single-point prediction initial energies;
interacting each of the distributed auxiliary energy points to obtain a plurality of configured output energies for the preset future time zone, wherein the configured output energies characterize the energy of the preset future time zone in which the distributed auxiliary energy points have been pre-scheduled;
and generating the single-point predicted energies by differencing the single-point predicted initial energies and the configured output energies.
5. The method of claim 4, wherein activating the energy prediction channel associated with the distributed auxiliary energy point, receiving the sensitive environmental condition, performing training, generating a plurality of single point predicted initial energies, and prior comprising:
when the distributed auxiliary energy supply points are connected into the charging pile cluster, the distributed auxiliary energy supply points are interacted, and second historical energy supply record data are received;
and performing regression function fitting on the BP neural network by taking the energy record value of the second historical energy supply record data as supervision data and the sensitive environment state record value of the second historical energy supply record data as input data to generate the energy prediction channel.
6. The method of claim 3 or 4, wherein capturing the sensitive environmental status of the preset future time zone for each of the distributed auxiliary energy points based on the internet of things comprises:
when the distributed auxiliary energy supply points are wind power energy supply points, the sensitive environment state is wind power state information;
when the distributed auxiliary energy supply points are hydraulic energy supply points, the sensitive environment state is hydraulic state information;
when the distributed auxiliary energy supply points are photovoltaic energy supply points, the sensitive environment state is illumination state information.
7. The method of claim 1, wherein when the joint predicted energy is greater than the energy predicted demand, performing a distributed energy configuration from the plurality of single point predicted energies, comprising:
traversing the distributed auxiliary energy supply points, and matching the distributed position information of a plurality of energy supply points and the sub-error energy of a plurality of energy supply points;
traversing the distribution position information of the energy supply points, and carrying out scheduling distance statistics based on the position information of the charging pile clusters to generate a plurality of energy supply scheduling distances;
based on a coefficient of variation method, configuring a first weight for the energy supply scheduling distance, configuring a second weight for energy supply point sub-error energy supply, and constructing an adaptability function:
；
Wherein,characterizing the fitness of a certain energy supply configuration scheme, +.>For the first weight, ++>For the second weight, ++>The distance of the ith energy supply point of the energy supply configuration scheme is characterized by +.>Sub-error energy representing the ith energy point of the energy supply arrangement, < +.>And->For normalizing the adjustment parameters, N represents the total number of energy supply points of the energy supply configuration scheme;
sorting based on the single-point predicted energy by taking the energy supply predicted demand as a constraint to generate a plurality of energy supply configuration schemes, wherein the sum of energy supply of any one energy supply configuration scheme is larger than or equal to 1.2 times of the energy supply predicted demand;
and according to the fitness function, traversing the energy supply configuration schemes to execute minimum fitness sorting, generating an energy supply configuration recommendation scheme, and carrying out distributed energy supply configuration.
8. The charging pile energy supplementing optimization system based on the multi-energy complementation is characterized by being used for implementing the charging pile energy supplementing optimization method based on the multi-energy complementation, which is any one of claims 1-7, and comprises the following steps:
the energy supply point deployment module is used for deploying distributed auxiliary energy supply points for the charging pile clusters;
the demand loading module is used for loading energy supply prediction demand of a preset future time zone of the charging pile cluster;
The energy prediction module is used for traversing the distributed auxiliary energy supply points to execute redundant energy prediction of the preset future time zone, and generating a plurality of single-point predicted energies and joint predicted energies, wherein the joint predicted energies are the sum of the plurality of single-point predicted energies;
the verification module is used for verifying whether the jointly predicted energy is greater than or equal to the energy supply predicted demand;
the module difference calculation module is used for calculating the module difference between the jointly predicted energy and the energy supply predicted demand and generating alternating current predicted energy supplementing when the jointly predicted energy is smaller than or equal to the energy supply predicted demand;
the first energy supply configuration module is used for carrying out energy supply configuration of the power distribution network according to the alternating current prediction energy supply and carrying out distributed energy supply configuration according to the combined prediction energy supply;
and the second energy supply configuration module is used for carrying out distributed energy supply configuration according to the plurality of single-point predicted energy sources when the joint predicted energy sources are larger than the energy supply predicted demand.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311691457.7A CN117638919B (en) | 2023-12-11 | 2023-12-11 | Charging pile energy supplementing optimization method based on multi-energy complementation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311691457.7A CN117638919B (en) | 2023-12-11 | 2023-12-11 | Charging pile energy supplementing optimization method based on multi-energy complementation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117638919A true CN117638919A (en) | 2024-03-01 |
| CN117638919B CN117638919B (en) | 2024-09-17 |
Family
ID=90035570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311691457.7A Active CN117638919B (en) | 2023-12-11 | 2023-12-11 | Charging pile energy supplementing optimization method based on multi-energy complementation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117638919B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509240A (en) * | 2011-11-22 | 2012-06-20 | 天津市电力公司 | Grid investment benefit evaluation method based on multiple indexes and multiple levels |
| CN103326387A (en) * | 2013-06-09 | 2013-09-25 | 东北电力大学 | Source network coordinated dispatching method reducing wind electricity dispatching risks by means of stored energy |
| CN113379565A (en) * | 2021-06-08 | 2021-09-10 | 国网江苏省电力有限公司经济技术研究院 | Comprehensive energy system optimization scheduling method based on distributed robust optimization method |
| CN113537553A (en) * | 2021-05-31 | 2021-10-22 | 国网福建省电力有限公司经济技术研究院 | Regional power distribution network load demand hybrid prediction method |
| CN116388291A (en) * | 2023-03-13 | 2023-07-04 | 国家电网有限公司华中分部 | Large power grid new energy consumption capability calculation method, system, device and medium |
| CN116418001A (en) * | 2023-02-28 | 2023-07-11 | 河海大学 | Reservoir group multi-energy complementary scheduling method and system for coping with uncertainty of new energy |
| CN116629421A (en) * | 2023-05-18 | 2023-08-22 | 国网浙江省电力有限公司综合服务分公司 | Comprehensive energy system multi-target distribution robust optimization scheduling method considering comprehensive energy efficiency |
-
2023
- 2023-12-11 CN CN202311691457.7A patent/CN117638919B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509240A (en) * | 2011-11-22 | 2012-06-20 | 天津市电力公司 | Grid investment benefit evaluation method based on multiple indexes and multiple levels |
| CN103326387A (en) * | 2013-06-09 | 2013-09-25 | 东北电力大学 | Source network coordinated dispatching method reducing wind electricity dispatching risks by means of stored energy |
| CN113537553A (en) * | 2021-05-31 | 2021-10-22 | 国网福建省电力有限公司经济技术研究院 | Regional power distribution network load demand hybrid prediction method |
| CN113379565A (en) * | 2021-06-08 | 2021-09-10 | 国网江苏省电力有限公司经济技术研究院 | Comprehensive energy system optimization scheduling method based on distributed robust optimization method |
| CN116418001A (en) * | 2023-02-28 | 2023-07-11 | 河海大学 | Reservoir group multi-energy complementary scheduling method and system for coping with uncertainty of new energy |
| CN116388291A (en) * | 2023-03-13 | 2023-07-04 | 国家电网有限公司华中分部 | Large power grid new energy consumption capability calculation method, system, device and medium |
| CN116629421A (en) * | 2023-05-18 | 2023-08-22 | 国网浙江省电力有限公司综合服务分公司 | Comprehensive energy system multi-target distribution robust optimization scheduling method considering comprehensive energy efficiency |
Non-Patent Citations (1)
| Title |
|---|
| 谢毓广;郭力: "基于区域负荷预测值综合评价的大电网短期负荷预测", 电气应用, vol. 36, no. 011, 31 December 2017 (2017-12-31), pages 40 - 45 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117638919B (en) | 2024-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240294086A1 (en) | Charging and power supply optimization method and apparatus for charging management system | |
| CN107947165A (en) | A kind of power distribution network flexibility evaluation method towards regulatory demand | |
| CN116683500B (en) | Active power scheduling method and system for electrochemical energy storage power station | |
| CN117239740B (en) | Optimal configuration and flexibility improvement method and system for virtual power plant system | |
| CN113139711A (en) | Wisdom energy data center management system based on data integration | |
| CN117318111A (en) | Weather prediction-based dynamic adjustment method and system for light energy storage source | |
| CN118232343B (en) | Charging and discharging dynamic control method and system based on wind energy prediction | |
| Gazijahani et al. | Optimal multi-objective operation of multi microgrids with considering uncertainty | |
| CN117578534A (en) | Scheduling method, device, equipment and storage medium of photovoltaic energy storage system | |
| CN116255665A (en) | Heat supply combined control method and system based on load prediction of heat supply network system | |
| CN117175695B (en) | Photovoltaic micro-grid power generation method and system based on diesel generator set | |
| CN117973819A (en) | Energy storage management system and method for optimizing electric energy storage | |
| CN103199616A (en) | Monitoring and analyzing system for operating data of regional power grid wind power group | |
| CN117670299A (en) | Digital operation and maintenance supervision method and system for building park | |
| CN117638919B (en) | Charging pile energy supplementing optimization method based on multi-energy complementation | |
| CN116914738A (en) | New energy storage analysis method and system based on artificial intelligence | |
| CN113537575B (en) | Trend load prediction method containing distributed photovoltaic and electric automobile grid connection | |
| CN118469154B (en) | Intelligent micro-grid evaluation system and method based on distributed energy consumption | |
| Kumar et al. | Real-time implementation of an IoT-based intelligent source allocation system using machine learning technique in a commercial building | |
| CN113689045B (en) | Photovoltaic area grid-connected electric quantity prediction method, device and medium | |
| CN118300145B (en) | Unified underlying control system for energy storage systems | |
| CN118367593B (en) | Energy storage system operation mode and optimal scheduling method for power system requirements | |
| CN117663503B (en) | Method and system for intelligently adjusting molten salt heat storage rate | |
| CN118263908B (en) | Energy storage efficiency improving method and system combining energy management | |
| CN117610234A (en) | Time sequence production simulation method and system based on energy interconnection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |