CN115018376A - Load regulation and control optimization method considering novel power system characteristics - Google Patents
Load regulation and control optimization method considering novel power system characteristics Download PDFInfo
- Publication number
- CN115018376A CN115018376A CN202210773576.6A CN202210773576A CN115018376A CN 115018376 A CN115018376 A CN 115018376A CN 202210773576 A CN202210773576 A CN 202210773576A CN 115018376 A CN115018376 A CN 115018376A
- Authority
- CN
- China
- Prior art keywords
- charging
- power
- day
- time
- neural network
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000013528 artificial neural network Methods 0.000 claims description 40
- 238000010248 power generation Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 10
- 238000005286 illumination Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 2
- 239000011541 reaction mixture Substances 0.000 claims description 2
- 238000004146 energy storage Methods 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract description 3
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 abstract description 3
- 229910052799 carbon Inorganic materials 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- 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
- G06Q10/06313—Resource planning in a project environment
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
- Y04S20/20—End-user application control systems
- Y04S20/222—Demand response systems, e.g. load shedding, peak shaving
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention relates to load regulation and control optimization considering novel power system characteristics. According to the method, based on the load regulation strategy of new energy output and user-side conventional load prediction, the charging plan of the electric vehicle is combined with the new energy power data peak value and the user-side conventional load valley value, so that the new energy consumption is improved, the system load peak-valley difference value is reduced, and the stability of a novel power system is promoted. The invention can reduce the space-time characteristic of transferring the output of new energy by deploying energy storage equipment in a large scale, reduce the cost of system construction and maintenance, improve the utilization rate of the new energy, reduce the power demand on a superior power grid and promote the realization of a double-carbon target.
Description
Technical Field
The invention relates to a novel load regulation and control optimization method for characteristics of an electric power system, and belongs to the technical field of regulation and control optimization of the electric power system.
Background
New energy such as photovoltaic energy, wind power and the like has characteristics such as volatility and intermittence, and openness and uncertainty of access of equipment such as clustered/distributed energy storage and large-scale electric vehicles provide new challenges for planning, running, regulating and analyzing a novel power system.
In order to reduce the influence caused by the power generation volatility of new energy, energy storage equipment with a certain scale is often equipped for a system to transfer the time-space uncertainty of the new energy, so that the system construction and maintenance cost is increased, and the energy utilization rate is also reduced. In recent years, with the development of intelligent prediction means, the new energy power generation law is mastered more mature, and reasonable support can be provided for guiding the user side power utilization behavior. Therefore, the power generation capacity of new energy and traditional energy, the user side load and the energy consumption habit of the electric automobile can be considered comprehensively, the user side load regulation and control optimization strategy is designed reasonably, and the consumption level of a novel power system is improved.
The chinese patent application publication No. CN112134272A proposes a method for regulating and controlling the load of distribution network electric vehicles, which confirms the charging demand by monitoring the charging behavior of the electric vehicles in the system in real time and frequently requiring users to submit the charging price and the charging demand, but lacks consideration of the power supply capability in the system and the influence of the large-scale charging behavior on the peak-valley value of the power. The chinese patent application with publication number CN110807598A proposes a method for evaluating the user load regulation and control value participating in orderly power utilization, which takes the peak-to-valley value of the load on the user side into consideration and relates to a value evaluation system, but lacks the consideration of the non-traditional energy supply methods such as new energy and the like and the equipment such as electric vehicles and the like capable of having the characteristic of temporal and spatial change of standby energy, and cannot provide support for improving the 'absorption' capability of the novel power system by taking the profit of the power supply company and the cost of the power utilization of the user as the objective functions.
Disclosure of Invention
The purpose of the invention is: the characteristic of "two height" that high permeability renewable energy, high proportion power electronic equipment to novel electric power system connect is planned the consideration with ability custom in the system, design user side load regulation and control optimization strategy, promotes novel electric power system "consumption" level.
In order to achieve the above object, the technical solution of the present invention is to provide a load regulation and control optimization considering characteristics of a novel power system, which is characterized by comprising the following steps:
step 1: obtaining historical meteorological sample information, predicting the new energy power generation in the day ahead by using a BP neural network, and obtaining the new energy power generation data P in the day ahead re-power (t)；
Step 2: obtaining historical day type sample information, predicting the conventional power load of a transformer area by utilizing a time series neural network, and obtaining the conventional power load prediction data P of the user side in the day ahead consumption (t)；
And step 3: the method comprises the following steps of obtaining historical data and real-time data of the electric automobile in the transformer area, and estimating the charging requirement of the electric automobile in the day-ahead transformer area through a transformer area electric automobile charging requirement calculation model, wherein the method comprises the following steps:
step 301: n station area electric vehicles in an on-grid charging state and K station area electric vehicles in an off-grid state at the time of 0 day; the capacity of the ith electric vehicle in the on-grid charging state is Q i The charging power of the ith electric automobile in the on-grid charging state at the time 0 of the day is P i,t＝0 The SOC state is SOC i,t＝0 I ═ 1,2, … …, N; the capacity of the jth electric automobile in the off-grid state is Q j ，j＝1,2,……,K；
The time length T required by full charge of each electric vehicle in the on-grid charging state at the time of 0 point of the day is predicted through the formula (1) est,i,t＝0 ：
Step 302: SOC state SOC of jth electric vehicle in off-grid state at 0 point of the day j Below 20% charging will take place with a charging power P for recharging j And the charging demand time T of the jth electric automobile in the off-grid state in the same day est,j Calculating according to the formula (2):
in the formula (2), the charging power P for recharging the jth electric vehicle in the off-grid state at the time of day 0 is j The estimation is made from the sample historical charging behaviour data using equation (3):
in the formula (3), the reaction mixture is,
respectively obtaining the average value and the median of the mth charging of the jth electric vehicle in the sample historical charging behavior data, wherein M is the total charging frequency of the sample historical charging behavior data;
and 4, step 4: carrying out user side load regulation and control optimization, and calculating a plan containing charging power and charging time arrangement of the electric automobile in the transformer area, wherein the method specifically comprises the following steps:
the day-ahead new energy power generation data P obtained in the step 1 re-power (t) and the day-ahead user-side conventional power load prediction data P obtained in step 2 consumption (t) comparing according to the time dimension, and calculating the whole charging power margin of each time interval, wherein the whole charging power margin of the t time interval is represented as P total,t Then, there is the following formula (4):
in the formula (4), P t＝peak,peak-1,…,1 Representing the power generation amount of the new energy power generation data predicted in the step 1 from the power generation amount corresponding to the peak time to the power generation amount corresponding to the secondary peak time to the power generation amount corresponding to the valley time;
recharging and charging power P of K electric automobiles in an off-grid state at the time of 0 point of the day j After sorting from large to small, the principle of scheduling high charging power demand at high charging margin times, the charging behavior of a rechargeable electric vehicle is scheduled by the following equation (5):
in the formula (5), t j Planning a charging time t for the jth electric vehicle peak,peak-1,…,1 For the corresponding moment of charge margin from high to low, p j And planning charging power for the jth electric automobile.
The charging behavior of the rechargeable electric vehicle is constrained by the following equation (6), and the charging power sum sigma P is obtained in the same time interval j,t＝peak,peak-1,…,1 Not exceeding charging power margin P total,t The charging time is arranged in the new energy power generation P re-power (t) the capacity is more than 20%, so that the new energy power generation is ensured to be in a continuous stable state:
in the formula (6), P j,t＝peak,peak-1,…,1 Showing that the charging power, T, of the electric automobile corresponding to the peak value moment of the new energy power generation data predicted in the step 1 is gradually decreased one by one j Indicating the duration of recharging of the electric vehicle, P re-power-peak Representing the peak value of the new energy power generation data predicted in the step 1;
and 5: calculating the charging power P of the electric automobile according to the step 4 j And charging time t j And issuing a charging plan.
Preferably, the step 1 specifically comprises the following steps:
step 101: selecting illumination intensity information data and temperature information data as characteristic quantity input of a BP (back propagation) neural network, outputting the characteristic quantity by taking photovoltaic output as the characteristic quantity of the BP neural network, and filling historical data with a certain time interval into the BP neural network to train the BP neural network, so that a photovoltaic output prediction model based on the BP neural network is established;
step 102: selecting wind speed information data as characteristic quantity input of a BP (back propagation) neural network, taking fan output as characteristic quantity output of the BP neural network, and filling historical data with a certain time interval into the BP neural network to train the BP neural network, so that a fan output prediction model based on the BP neural network is established;
step 103: using weather information before the day as the input of the photovoltaic output prediction model and the fan output prediction model to obtain a photovoltaic output prediction result P output by the photovoltaic output prediction model and the fan output prediction model solar (t) and Fan output prediction result P wind (t) predicting the photovoltaic output P solar (t) and fan output prediction result P wind (t) overlapping according to time dimension to obtain day-ahead new energy power generation data P re-power (t)。
Preferably, the step 2 specifically includes the following steps:
step 201: selecting the highest temperature, the lowest temperature, the average relative humidity and the rainfall as characteristic quantity input of a time series neural network, outputting the characteristic quantity by taking the conventional power load of a transformer area as the characteristic quantity of the time series neural network, and filling historical data with a certain time interval into the time series neural network for training so as to establish a conventional power load prediction model based on the time series neural network;
step 202: using the day-ahead day type information as the input of a conventional power load prediction model to obtain day-ahead user-side conventional power load prediction data P output by the conventional power load prediction model consumption (t)。
Compared with the prior art, the invention has the following beneficial effects:
(1) based on a load regulation strategy of new energy output and user-side conventional load prediction, an electric vehicle charging plan is combined with a new energy electric power data peak value and a user-side conventional load valley value, so that the new energy consumption is improved, the system load peak-valley difference value is reduced, and the stability of a novel power system is promoted;
(2) the space-time characteristic that the energy storage equipment is deployed on a large scale to transfer the output of new energy is reduced, the construction and maintenance cost of the system is reduced, the utilization rate of the new energy can be improved, the power demand on a superior power grid is reduced, and the realization of a double-carbon target is promoted.
Drawings
FIG. 1 is a load regulation strategy architecture diagram designed in accordance with the present invention that takes into account the characteristics of the novel power system;
FIG. 2 is a graph comparing a predicted value and an actual value of photovoltaic output prediction based on a BP neural network according to the present invention;
FIG. 3 is a graph comparing the predicted value and the actual value of the fan output prediction based on the BP neural network according to the present invention;
FIG. 4 is a comparison graph of predicted values and actual values of load prediction based on a time series neural network according to the present invention;
FIG. 5 is a comparison chart of new energy generation and user side load prediction at the present day time;
FIG. 6 is a diagram illustrating a charging demand response of an electric vehicle of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention can be made by those skilled in the art after reading the teaching of the present invention, and these equivalents also fall within the scope of the claims appended to the present application.
The load regulation and control strategy architecture diagram considering the characteristics of a novel power system is shown in fig. 1, corresponding input is obtained through a new energy power generation prediction module, a user side load prediction module and a platform area electric vehicle charging demand estimation module, and calculated electric vehicle charging power and charging time are issued through a load regulation and control optimization module designed by considering a power peak-valley difference value in a time dimension in the system, so that the consumption of new energy power generation in the system is completed, and the platform area power peak-valley difference is reduced.
To facilitate understanding of the control scheme of the present invention, the strategy scheme of the present invention is explained below with reference to fig. 2, 3, 4, 5 and 6.
Firstly, building BP neural networks for training photovoltaic output and fan output respectively according to historical meteorological information, and selecting illumination intensity, temperature and wind speed as corresponding model characteristic quantities to be input respectively, wherein network parameters are as shown in the following table.
| Name (R) | Type (B) | Number of hidden layers | Number of nodes | Number of training sessions | Learning rate | Target minimum error |
| Photovoltaic system | BP neural network | 1 | 8 | 1000 | 0.01 | 0.000001 |
| Fan blower | BP neural network | 1 | 4 | 3000 | 0.05 | 0.000001 |
Historical data are input for training, the training results are respectively shown in fig. 2 and fig. 3, the average absolute errors are respectively 0.00139 and 0.025, and the prediction result is accurate. Part of the historical data is as follows:
| date | Time of day | Temperature of | Intensity of illumination | Photovoltaic output | Wind speed | Output of fan |
| 2020/3/1 | 11:30 | 25 | 531 | 677.03 | 8.72 | 693.26 |
| 2020/3/1 | 12:00 | 15 | 543 | 738.48 | 8.97 | 718.89 |
| 2020/3/1 | 12:30 | 26 | 537 | 680.11 | 9.49 | 761.25 |
Training a time series neural network built by a conventional power load at a user side according to historical day type information, and selecting the highest temperature, the lowest temperature, the average temperature, the relative humidity (average) and the rainfall as characteristic quantities to be input, wherein the network parameters are as follows:
| name(s) | Type (B) | HidingNumber of layers | Number of nodes | Number of training sessions | Learning rate | Target minimum error |
| Load(s) | Time series neural network | 2 | [6,6] | 3000 | 0.001 | 0.000001 |
Historical data are input for training, the training results are respectively shown in FIG. 4, the average absolute error is 0.00271, and the prediction result is accurate. Part of the historical load data is as follows:
| YMD | T0700 | T0730 | T0800 | T0830 | T0900 | T0930 |
| 20141201 | 4340.233 | 4833.116 | 6159.911 | 7581.279 | 8009.952 | 8253.632 |
| 20141202 | 5296.319 | 5713.094 | 6935.537 | 8158.838 | 8491.981 | 8688.653 |
| 20141203 | 5447.405 | 5866.201 | 6971.504 | 8273.659 | 8567.503 | 8745.38 |
part of the historical day type data is as follows:
| maximum temperature C | Minimum temperature C | Average temperature (. degree.C.) | Relative humidity (average) | Rainfall (mm) | |
| 20141201 | 25.6 | 16.5 | 19.9 | 70 | 0.3 |
| 20141202 | 16.5 | 12.4 | 13.9 | 82 | 3.6 |
| 20141203 | 17.9 | 12.8 | 15.1 | 92 | 6 |
Day-ahead meteorological information and day type information characteristic quantities are obtained from platforms such as a meteorological station and the like, and are given to a corresponding model for prediction, so that day-ahead new energy power generation data and user side conventional load data can be obtained, as shown in fig. 5.
Then, a total of 100 electric vehicles in the station area are set, and the capacity and the number of the electric vehicles are as follows:
| capacity (kWh) | Number of stations |
| 16 | 5 |
| 24 | 8 |
| 30 | 17 |
| 32 | 7 |
| 57 | 20 |
| 60 | 11 |
| 100 | 10 |
| 111.5 | 7 |
| 150 | 15 |
Setting 56 machines on the grid and 44 machines off the grid at the time of day 0, wherein the following parameters are set:
| automobile number | Capacity (kWh) | 0:00 state | SOC at access time |
| 2 | 16 | 1 | 0.61 |
| 7 | 111.5 | 1 | 0.44 |
| 15 | 24 | 1 | 0.82 |
| 16 | 24 | 1 | 0.69 |
| 23 | 100 | 1 | 0.37 |
According to the step 3, when the SOC of the electric automobile is set to be 10% -20%, recharging is carried out, and calculation is carried out to obtain the SOC of each electric automobile in the transformer areaT est,i,t＝0 、T est,j And P j Part of the results are given in the following table:
| automobile number | Capacity (kWh) | 0:00 state | SOC at access time | Power on time (kW) | Full of time (mins) | Switching in power (kW) | SOC at the time of re-access | Full of time (mins) after rejoining |
| 5 | 16 | 1 | 0.20 | 49 | 15.73 | 0 | 0.00 | 0.00 |
| 11 | 111.5 | 0 | 0.00 | 0 | 0 | 37 | 0.10 | 162.00 |
| 17 | 24 | 1 | 0.54 | 46 | 14.52 | 0 | 0.00 | 0.00 |
| 23 | 100 | 1 | 0.37 | 12 | 315.83 | 0 | 0.00 | 0.00 |
| 35 | 150 | 0 | 0.00 | 0 | 0 | 30 | 0.12 | 264.53 |
| 50 | 32 | 1 | 0.70 | 24 | 23.74 | 0 | 0.00 | 0.00 |
| 56 | 60 | 0 | 0.00 | 0 | 0 | 38 | 0.15 | 80.48 |
| 66 | 30 | 1 | 0.34 | 40 | 29.66 | 0 | 0.00 | 0.00 |
| 82 | 57 | 1 | 0.55 | 46 | 33.41 | 0 | 0.00 | 0.00 |
Then, according to the constraint conditions designed by the method in the step 4, the optimal regulation and control arrangement of the charging behavior is performed by taking the new energy power generation peak value as a central point, part of the optimization results are shown in the following table, and a comparison chart containing an electric vehicle charging demand plan is shown in fig. 6.
Claims (3)
1. A load regulation optimization considering novel power system characteristics, comprising the steps of:
step 1: obtaining historical meteorological sample information, predicting the new energy power generation in the day ahead by using a BP neural network, and obtaining the new energy power generation data P in the day ahead re-power (t)；
Step 2: obtaining historical day type sample information, predicting the conventional power load of a transformer area by utilizing a time series neural network, and obtaining the conventional power load prediction data P of the user side in the day ahead consumption (t)；
And 3, step 3: the method comprises the following steps of obtaining historical data and real-time data of the electric automobile in the transformer area, and estimating the charging requirement of the electric automobile in the day-ahead transformer area through a transformer area electric automobile charging requirement calculation model, wherein the method comprises the following steps:
step 301: n station area electric vehicles in an on-grid charging state and K station area electric vehicles in an off-grid state at the time of 0 day; the capacity of the ith electric vehicle in the on-grid charging state is Q i The charging power of the ith electric automobile in the on-grid charging state at the time 0 of the day is P i,t＝0 The SOC state is SOC i,t＝0 I ═ 1,2, … …, N; the capacity of the jth electric automobile in the off-grid state is Q j ，j＝1,2,……,K；
The required time T for each electric vehicle in the on-grid charging state at the time of 0 point of the day to be fully charged is predicted through the formula (1) est,i,t＝0 ：
Step 302: SOC state SOC of jth electric vehicle in off-grid state at 0 point of the day j Charging will be carried out below 20%, with charging power P for recharging j And the charging requirement time length T of the jth electric automobile in the off-grid state in the day est,j Calculating according to the formula (2):
in the formula (2), the charging power P for recharging the jth electric vehicle in the off-grid state at the time of day 0 is j The estimation is made from the sample historical charging behaviour data using equation (3):
in the formula (3), the reaction mixture is,
respectively obtaining the average value and the median of the mth charging of the jth electric vehicle in the sample historical charging behavior data, wherein M is the total charging frequency of the sample historical charging behavior data;
and 4, step 4: carrying out user side load regulation and control optimization, and calculating a plan containing charging power and charging time arrangement of the electric automobile in the transformer area, wherein the method specifically comprises the following steps:
the day-ahead new energy power generation data P obtained in the step 1 re-power (t) and the day-ahead user-side conventional power load prediction data P obtained in step 2 consumption (t) comparing according to the time dimension, and calculating the whole charging power margin of each time interval, wherein the whole charging power margin of the t time interval is represented as P total,t Then, there is the following formula (4):
in the formula (4), P t＝peak,peak-1,…,1 Representing the power generation amount of the new energy power generation data predicted in the step 1 from the power generation amount corresponding to the peak time to the power generation amount corresponding to the secondary peak time to the power generation amount corresponding to the trough time;
recharging and charging power P of K electric automobiles in an off-grid state at the time of 0 point of the day j After sorting from large to small, the principle of scheduling high charging power demand at high charging margin times, the charging behavior of a rechargeable electric vehicle is scheduled by the following equation (5):
in the formula (5), t j Planning a charging time t for the jth electric vehicle peak,peak-1,…,1 For the corresponding moment of charge margin from high to low, p j And planning charging power for the jth electric automobile.
The charging behavior of the rechargeable electric vehicle is constrained by the following equation (6), and the charging power sum sigma P is obtained in the same time interval j,t＝peak,peak-1,…,1 Not exceeding charging power margin P total,t The charging time is arranged in the new energy power generation P re-power (t) the capacity is more than 20%, so that the new energy power generation is ensured to be in a continuous stable state:
in the formula (6), P j,t＝peak,peak-1,…,1 Showing that the charging power, T, of the electric automobile corresponding to the peak value moment of the new energy power generation data predicted in the step 1 is gradually decreased one by one j Indicating the duration of recharging of the electric vehicle, P re-power-peak Representing the peak value of the new energy power generation data predicted in the step 1;
and 5: calculating the charging power P of the electric automobile according to the step 4 j And charging time t j And issuing a charging plan.
2. The load regulation optimization considering novel power system characteristics according to claim 1, wherein the step 1 specifically comprises the following steps:
step 101: selecting illumination intensity information data and temperature information data as characteristic quantity input of a BP (back propagation) neural network, taking photovoltaic output as characteristic quantity output of the BP neural network, and filling historical data with a certain time interval into the BP neural network to train the BP neural network, so that a photovoltaic output prediction model based on the BP neural network is established;
step 102: selecting wind speed information data as characteristic quantity input of a BP (back propagation) neural network, taking fan output as characteristic quantity output of the BP neural network, and filling historical data with a certain time interval into the BP neural network to train the BP neural network, so that a fan output prediction model based on the BP neural network is established;
step 103: using weather information before the day as the input of the photovoltaic output prediction model and the fan output prediction model to obtain a photovoltaic output prediction result P output by the photovoltaic output prediction model and the fan output prediction model solar (t) and Fan output prediction result P wind (t) predicting the photovoltaic output P solar (t) and fan output prediction result P wind (t) overlapping according to time dimension to obtain day-ahead new energy power generation data P re-power (t)。
3. The load regulation optimization considering novel power system characteristics according to claim 1, wherein the step 2 specifically comprises the following steps:
step 201: selecting the highest temperature, the lowest temperature, the average relative humidity and the rainfall as characteristic quantity input of a time series neural network, outputting the characteristic quantity by taking the conventional power load of a transformer area as the characteristic quantity of the time series neural network, and filling historical data with a certain time interval into the time series neural network for training so as to establish a conventional power load prediction model based on the time series neural network;
step 202: the day before day type letterThe information is used as the input of a conventional power load prediction model, and the day-ahead user-side conventional power load prediction data P output by the conventional power load prediction model is obtained consumption (t)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210773576.6A CN115018376A (en) | 2022-07-01 | 2022-07-01 | Load regulation and control optimization method considering novel power system characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210773576.6A CN115018376A (en) | 2022-07-01 | 2022-07-01 | Load regulation and control optimization method considering novel power system characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115018376A true CN115018376A (en) | 2022-09-06 |
Family
ID=83079246
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210773576.6A Pending CN115018376A (en) | 2022-07-01 | 2022-07-01 | Load regulation and control optimization method considering novel power system characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115018376A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116722605A (en) * | 2023-08-08 | 2023-09-08 | 武汉创星空间科技发展有限公司 | Power distribution network scheduling optimization method based on Internet of things |
-
2022
- 2022-07-01 CN CN202210773576.6A patent/CN115018376A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116722605A (en) * | 2023-08-08 | 2023-09-08 | 武汉创星空间科技发展有限公司 | Power distribution network scheduling optimization method based on Internet of things |
| CN116722605B (en) * | 2023-08-08 | 2023-10-17 | 武汉创星空间科技发展有限公司 | Power distribution network scheduling optimization method based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178619B (en) | Multi-objective optimization method considering distributed power supply and charging station joint planning | |
| CN109508857B (en) | Multi-stage planning method for active power distribution network | |
| CN112467722B (en) | Active power distribution network source-network-load-storage coordination planning method considering electric vehicle charging station | |
| CN110046773B (en) | Multi-main-body cooperation optimized operation and cost-benefit distribution method for comprehensive energy system | |
| CN109657993B (en) | Non-cooperative game-based automatic demand response method for energy local area network energy storage system | |
| CN109599856B (en) | Electric vehicle charging and discharging management optimization method and device in micro-grid multi-building | |
| CN109559035A (en) | A kind of urban power distribution network bi-level programming method considering flexibility | |
| CN111799827B (en) | Transformer area load regulation and control method containing optical storage charging station | |
| CN107104454A (en) | Meter and the optimal load flow node electricity price computational methods in electric automobile power adjustable control domain | |
| US20220036392A1 (en) | Deep Reinforcement Learning Based Real-time scheduling of Energy Storage System (ESS) in Commercial Campus | |
| CN111626527A (en) | Intelligent power grid deep learning scheduling method considering fast/slow charging/discharging form of schedulable electric vehicle | |
| CN111339689A (en) | Building comprehensive energy scheduling method, system, storage medium and computer equipment | |
| CN114914923B (en) | Grid method based variable-time-length two-stage electric vehicle scheduling method and system | |
| Negri et al. | Combined model predictive control and ANN-based forecasters for jointly acting renewable self-consumers: An environmental and economical evaluation | |
| CN114519449A (en) | Operation optimization method for park energy system | |
| CN112238781A (en) | Electric automobile ordered charging control method based on layered architecture | |
| CN114662762A (en) | Energy storage power station regulation and control method under electric power spot market background | |
| CN113326467A (en) | Multi-station fusion comprehensive energy system multi-target optimization method based on multiple uncertainties, storage medium and optimization system | |
| CN115018376A (en) | Load regulation and control optimization method considering novel power system characteristics | |
| Rocha et al. | Net Zero Energy cost Building system design based on Artificial Intelligence | |
| CN116061742B (en) | Charging control method and system for electric automobile in time-of-use electricity price photovoltaic park | |
| CN116683445A (en) | Model predictive control-based multi-time scale operation optimization method for park micro-grid | |
| CN116596252A (en) | Multi-target charging scheduling method for electric automobile clusters | |
| CN116579560A (en) | Virtual power plant energy distribution method considering multi-type load demand response | |
| CN116402307A (en) | Power grid planning capacity analysis method considering operation characteristics of schedulable flexible resources |
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 |