CN117689160A - Window visual method and system based on power scheduling day plan - Google Patents
Window visual method and system based on power scheduling day plan Download PDFInfo
- Publication number
- CN117689160A CN117689160A CN202311693822.8A CN202311693822A CN117689160A CN 117689160 A CN117689160 A CN 117689160A CN 202311693822 A CN202311693822 A CN 202311693822A CN 117689160 A CN117689160 A CN 117689160A
- Authority
- CN
- China
- Prior art keywords
- power
- time
- power supply
- plan
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000000007 visual effect Effects 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000012423 maintenance Methods 0.000 claims description 27
- 238000007794 visualization technique Methods 0.000 claims description 19
- 230000015654 memory Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012800 visualization Methods 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 108700041286 delta Proteins 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000013439 planning Methods 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 230000001932 seasonal effect Effects 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- 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
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a window visual method and a system based on a power dispatching daily plan, comprising the following steps: collecting real-time power supply data; training according to the historical power supply requirements to obtain a prediction model, and predicting the power supply requirements; generating a power dispatching day plan according to a predicted result, and generating a temporary plan through quasi operation; and presenting the power dispatching daily plan through a visual interface. By combining advanced prediction technology and intelligent scheduling and real-time visual feedback, the efficiency and reliability of power scheduling are greatly improved, and the requirements of a power grid on intelligence and automation are met. Meanwhile, the work of daily planning can be guaranteed not to influence the timely supply of electric power, equipment indexes to be scheduled can be obtained according to an algorithm, and the stability of power supply can be guaranteed.
Description
Technical Field
The invention relates to the technical field of power dispatching, in particular to a window visual method and system based on a power dispatching daily plan.
Background
In recent years, with rapid development of economy and improvement of living standard of people, the demand of electric power is continuously increasing, and the electric power dispatching plan of the electric power supply department is particularly important. The power dispatching plan refers to reasonably arranging time, place and scale of power production and consumption according to power demand and supply conditions so as to ensure the stability and reliability of power supply.
Before a power dispatch plan is established, a detailed analysis of power demand and supply is first required. The power demand is affected by a variety of factors, such as seasonal changes, weather conditions, economic development levels, and the like. The power supply is dependent on the power production capacity, the transport capacity and the operating conditions of the power plant.
The power dispatch plan should be formulated to follow certain guidelines to ensure a stable and reliable power supply. First, it is necessary to reasonably schedule the time of power production and consumption to meet the needs of different time periods. Secondly, the sites for power production and consumption are reasonably arranged according to the operation condition and maintenance plan of the power equipment. In addition, the limitation of the power transmission capacity is considered, and the overload of the power grid is avoided.
To effectively implement a power dispatch plan, the power supply may take a series of actions. First, the power production capacity can be increased by increasing the operating efficiency and the load factor of the power plant. And secondly, the overhaul and maintenance work of the power equipment can be enhanced, and the equipment faults and the downtime are reduced. Information technology means may also be employed for better implementation of power dispatch plans. By establishing the power dispatching management system, the real-time monitoring and dispatching of power production and consumption are realized.
Efficient implementation of power dispatch plans would bring many benefits. Firstly, the stability and reliability of power supply can be ensured, and the requirements of people on power are met. And secondly, the power utilization efficiency can be improved, and the energy waste and the environmental pollution are reduced. In addition, the operation efficiency and economic benefit of the power supply department can be improved.
Disclosure of Invention
The present invention has been made in view of the above-described problems.
Therefore, the technical problems solved by the invention are as follows: the existing day plan generation method has the problems of higher cost loss, untimely power recovery and the like
In order to solve the technical problems, the invention provides the following technical scheme: a window visualization method based on a power dispatch day plan, comprising:
collecting real-time power supply data;
training according to the historical power supply requirements to obtain a prediction model, and predicting the power supply requirements;
generating a power dispatching day plan according to a predicted result, and generating a temporary plan through quasi operation;
and presenting the power dispatching daily plan through a visual interface.
As a preferable mode of the window visualization method based on the power schedule day plan according to the present invention, wherein: the power supply data includes power supply requirements, operating conditions of the power equipment, and productivity of the power equipment.
As a preferable mode of the window visualization method based on the power schedule day plan according to the present invention, wherein: the prediction model comprises the steps of preprocessing data, preparing and cleaning the data;
the characteristic engineering of model training extracts time characteristics and special events of meteorological data according to historical power demand data;
capturing time sequence characteristics in the power demand data by using a long-short-term memory network LSTM;
H t ＝LSTM(X t ，H t-1 )
wherein H is t Indicating the LSTM hidden state at time t; x is X t An input feature vector representing time t, including historical power demand and other features; h t-1 Representing the hidden state of the previous time step;
using a self-attention mechanism;
A t ＝Attention(H t ，H)
wherein A is t The hidden state at the time t weighted by the self-attention mechanism is represented, and H represents a set of historical hidden states;
analyzing the influence of external factors on the power demand through an external factor influence module;
E t ＝NN ext (X ext,t )
wherein E is t An output representing the influence of an external factor; x is X ext,t Input data representing external factors;
combining the time dependence with the influence of external factors to make a final prediction;
wherein,representing a final predicted output representing a predicted power demand at time t; [ A ] t ；E t ]Representing stitching the self-attentive output with the output affected by the external factor; w and b are the weight and bias parameters of the model; σ is an activation function for converting the linear output into a predicted value.
As a preferable mode of the window visualization method based on the power schedule day plan according to the present invention, wherein: the loss function of the prediction model includes:
Loss＝α·MSE+(1-α)·SmoothL1
wherein for the predicted valueAnd an actual value Y t MSE is defined as: /> Where N is the number of samples; />
As a preferable mode of the window visualization method based on the power schedule day plan according to the present invention, wherein: the power dispatching date plan comprises a planned maintenance work, an operation mode change, live working and a temporary task;
wherein the temporary plan is an alternative formulated according to the problem conditions of the simulated operation;
when the power supply task can be completed without live working, the equipment changes the operation mode from live working to non-live working.
As a preferable mode of the window visualization method based on the power schedule day plan according to the present invention, wherein: evaluating the total power supply capability of the devices includes dividing the operating devices into a live-operable device set E live And a non-live working equipment set E nolive The method comprises the steps of carrying out a first treatment on the surface of the Set S i Representing the performance of device i, where S i =1 indicates that the device can perform live working, S i =0 indicates that live-line work is not possible;
power supply capability during service:
wherein I represents the number of devices, C i Indicating the power supply capability of device i.
As a preferable mode of the window visualization method based on the power schedule day plan according to the present invention, wherein: the power dispatch day schedule also includes, if it is constant during the time of completion of maintenance of all equipmentThe equipment capable of carrying out live working is preferentially maintained, and other equipment is maintained sequentially from short time to long time by taking the average maintenance time of each equipment in the history record as a standard; if there is +.>Intelligent scheduling is performed:
let the current time be TdrawThe method comprises the steps that at a point T1 closest to the current time in a time domain, the maximum power supply capacity C which can be subjected to wining maintenance in the time of T1-T is matched, after one schedule is finished, the power supply capacity D' =D+C at the time of T1 is updated, and if the predicted requirement of power supply at the time of T1 is met, the subsequent schedules are sequentially carried out from the time of T1 according to the updated power supply capacity; if the predicted requirement of power supply at the time T1 is not met, recording a difference delta 1, updating the power supply capacity D' =D+C+δ1 at the time T1 again, and sequentially performing subsequent scheduling according to the updated power supply capacity at the time T1; all differences δtotal=δ1+δ2 were recorded after the scheduling was completed; where k represents k differences;
the maintenance time to complete all the equipment is expressed as:
wherein t is i The maintenance average time of the ith equipment is represented, and R represents the number of maintenance personnel;
generating a temporary plan from all differences delta totals: scheduling the standby equipment with power supply capacity reaching delta total for the first timeIs engaged in powering up before the time node of (c).
A window visualization system based on a power dispatch day plan employing the method of the present invention, characterized by:
the data acquisition module acquires real-time power supply data;
the prediction module is used for obtaining a prediction model according to the historical power supply demand training and predicting the power supply demand;
the plan generation module generates a power dispatching day plan according to the predicted result and generates a temporary plan through the quasi-operation;
and the visualization module is used for presenting the power dispatching daily plan through a visualization interface.
A computer device, comprising: a memory and a processor; the memory stores a computer program characterized in that: the processor, when executing the computer program, implements the steps of the method of any of the present invention.
A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program, when executed by a processor, implements the steps of the method of any of the present invention.
The invention has the beneficial effects that: according to the window visual method based on the power dispatching daily plan, the efficiency and the reliability of power dispatching are greatly improved by combining an advanced prediction technology and intelligent dispatching and real-time visual feedback, and the requirements of a power grid on intellectualization and automation are met. Meanwhile, the work of daily planning can be guaranteed not to influence the timely supply of electric power, equipment indexes to be scheduled can be obtained according to an algorithm, and the stability of power supply can be guaranteed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is an overall flowchart of a window visualization method based on a power schedule day plan according to a first embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Referring to fig. 1, for one embodiment of the present invention, there is provided a window visualization method based on a power schedule day plan, including:
s1: real-time power supply data is collected.
Further, the power supply data includes power supply requirements, operation of the power device, and productivity of the power device.
It is to be appreciated that knowing the power demand is the core of power scheduling. It involves the consumer's consumption of electricity over different time periods, which helps predict daily and seasonal patterns of electricity consumption. By analyzing this data, future demand trends can be predicted, ensuring a balance between power supply and demand. In addition, prediction of peak demand in emergency situations is also important in order to formulate a countermeasure strategy. Knowledge of the operating conditions of the various devices in the power grid is critical to ensure the reliability and efficiency of the power grid. This includes the operating status, maintenance records and fault history of the transformer, generator, transmission line etc. equipment. Monitoring the performance of these devices can help identify and repair faults in time, reduce the likelihood of a power outage, and improve the efficiency of the overall power grid. Knowledge of the power plant's productivity (e.g., the power plant's output capacity) is critical to power scheduling. This involves evaluating the available power resources and determining which power supplies are most economical and efficient at any given time. Furthermore, the reliance on renewable energy sources (such as wind and solar) has also made understanding of real-time productivity more important, as the output of these sources may fluctuate due to weather or other environmental factors.
S2: and training according to the historical power supply demand to obtain a prediction model, and predicting the power supply demand.
Further, the prediction model comprises the steps of firstly preprocessing data, preparing and cleaning the data, and ensuring that the data input into the model are clean, complete and uniform in format. Feature engineering of model training, extracting features in historical power demand data, time features (hours, days, weeks, months, quarters and the like), meteorological data (temperature and humidity) and special events (holidays and weekends).
The long-term memory network LSTM is utilized to capture time series characteristics, particularly long-term dependencies, in the power demand data.
H t ＝LSTM(X t ，H t-1 )
Wherein H is t Indicating the LSTM hidden state at time t; x is X t An input feature vector representing time t, including historical power demand and other features; h t-1 Representing the hidden state of the previous time step.
The self-attention mechanism is utilized to enable the model to focus on the historical moments that are most important for current predictions.
A t ＝Attention(H t ，H)
Wherein A is t Represents the hidden state at time t weighted by the self-attention mechanism, and H represents the set of historical hidden states.
The influence of external factors such as weather and special events on the power demand is analyzed by an external factor influence module.
E t ＝NN ext (X ext,t )
Wherein E is t An output representing the influence of an external factor; x is X ext,t Input data representing external factors such as weather and holiday information.
The time dependence and the influence of external factors are integrated to make the final prediction.
Wherein,representing a final predicted output representing a predicted power demand at time t; [ A ] t ；E t ]Representing stitching the self-attentive output with the output affected by the external factor; w and b are the weight and bias parameters of the model; σ is an activation function for converting the linear output into a predicted value.
It should be noted that, in the training process of the model, after the data are arranged in time sequence, a time point is selected, the data before the time point are used as a training set, and the data after the time point are used as a verification set. 80/20, most of which are used for training and the rest are used for verification. The choice of proportions may be affected by the amount of data and the seasonal or trending nature of the data. The setting is performed according to the use condition of the technician. In partitioning the data, it should be ensured that both the training set and the validation set contain complete seasonal periods so that the model can learn these patterns. The model is iteratively trained using the training set data, each iteration requiring the calculation of the loss on the training set and the updating of the model parameters. To prevent overfitting, early stop techniques are used during training. If the performance on the validation set does not improve in consecutive iterations, training is stopped.
Calculating a loss function for the loss includes:
Loss＝α·MSE+(1-α)·SmoothL1
wherein for the predicted valueAnd an actual value Y t MSE is defined as: /> Where N is the number of samples. />
It is to be appreciated that the MSE portion is to ensure prediction accuracy of the model in most cases, especially for small errors. The smoothed L1 portion is more robust to outliers. When the error is small, it behaves like MSE; when the error is large, it then behaves like an L1 penalty; is to increase the robustness of the model to outliers or noise, which is important in actual power demand predictions, as the data may contain the effects of emergencies or anomalies. The weight coefficient alpha allows flexible adjustment between the two losses and can be optimized according to specific data distribution and requirements.
S3: and generating a power dispatching day plan according to the predicted result, and generating a temporary plan through the planned operation.
Further, the power dispatching date plan includes a planned maintenance work, an operation mode change, live working, and a temporary task. The three planning contents of the scheduled maintenance work, the running mode change and the live working are directly generated, and the temporary plan is an alternative scheme formulated according to the problem condition of the simulated running. And when the power supply task can be completed without live working, the equipment changes the operation mode from live working to non-live working.
First, the operating devices are divided into a live-line operating device set E live And a non-live working equipment set E nolive The method comprises the steps of carrying out a first treatment on the surface of the Set S i Representing the performance of device i, where S i =1 indicates that the device can perform live working, S i Table=0No live working is shown.
Power supply capability during service:
wherein I represents the number of devices, C i Indicating the power supply capability of device i.
If the maintenance time of all the equipment is finished, the equipment is alwaysThe equipment capable of carrying out live working is preferentially maintained, and other equipment is maintained sequentially from short time to long time by taking the average maintenance time of each equipment in the history record as a standard; if there is +.>Intelligent scheduling is performed:
let the current time be TdrawThe method comprises the steps that at a point T1 closest to the current time in a time domain, the maximum power supply capacity C which can be subjected to wining maintenance in the time of T1-T is matched, after one schedule is finished, the power supply capacity D' =D+C at the time of T1 is updated, and if the predicted requirement of power supply at the time of T1 is met, the subsequent schedules are sequentially carried out from the time of T1 according to the updated power supply capacity; if the predicted requirement of power supply at the time T1 is not met, recording a difference delta 1, updating the power supply capacity D' =D+C+δ1 at the time T1 again, and sequentially performing subsequent scheduling according to the updated power supply capacity at the time T1; all differences δtotal=δ1+δ2 were recorded after the scheduling was completed; where k represents k differences.
Generating a temporary plan from all differences delta totals: scheduling the standby equipment with power supply capacity reaching delta total for the first timeIs engaged in powering up before the time node of (c).
The maintenance time to complete all the equipment is expressed as:
wherein t is i The i-th equipment maintenance average time is represented, and R represents the number of maintenance personnel.
S4: and presenting the power dispatching daily plan through a visual interface.
Further, a graph of power demand and supply is displayed, which helps a user to intuitively understand the power balance condition of the whole power grid. The demand forecast and the actual supply amount may be represented in different colors or lines. The interface should be updated in real time to reflect the latest scheduling situation.
For any emergency situation that may affect the power supply, the warning system is used to highlight and alert the user. And allows the user to make basic scheduling controls and adjustments through the interface, such as rescheduling certain tasks or updating device states.
The visualized daily schedule also shows the specific contents of the power scheduling daily schedule one by one, and comprises comparison of data before and after scheduling and predicted power supply requirements. Schedule records for standby devices, etc. At the end of the job, the time threshold is checked and a cause is generated at the time of timeout.
In another aspect, the present embodiment further provides a window visual system based on a power schedule day plan, including:
and the data acquisition module acquires real-time power supply data.
And the prediction module is used for obtaining a prediction model according to the historical power supply demand training and predicting the power supply demand.
And the plan generation module is used for generating a power dispatching day plan according to the predicted result and generating a temporary plan through the quasi-operation.
And the visualization module is used for presenting the power dispatching daily plan through a visualization interface.
The above functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Example 2
In the following, for one embodiment of the present invention, a window visualization method based on a power dispatching daily plan is provided, and in order to verify the beneficial effects of the present invention, scientific demonstration is performed through economic benefit calculation and simulation experiments.
The traditional daily schedule was compared with the present invention by simulation experiments, as shown in table 1.
Table 1 data comparison table
| Performance index | Conventional method | The method of the invention |
| Prediction accuracy (%) | 75％ | 90％ |
| Day plan generation time (minutes) | 60 | 15 |
| Scheduling response time (minutes) | 30 | 5 |
| Average power failure time (hours) during maintenance | 2 | 0.5 |
| Annual operating costs (millions of dollars) | 10 | 7 |
| Number of system stability events | 5 times/month | 1 time/month |
| Annual energy conservation (megawatt-hour) | 500MWh | 750MWh |
It can be seen that the present invention improves the prediction accuracy from 75% to 90% by using LSTM and self-attention mechanisms. This means fewer prediction errors, more accurate matching of power supply and demand is possible, and resource waste is reduced. While the conventional method takes 60 minutes to generate a daily schedule, the present invention takes only 15 minutes. The working efficiency is greatly improved, and power grid dispatching personnel can be quickly adapted to market and system changes. The scheduling response time of the conventional method is 30 minutes, while the method of the present invention is reduced to 5 minutes. This fast response capability is critical to handling emergency situations or incidents. The invention reduces the average power failure time caused by maintenance from 2 hours to 0.5 hour through intelligent scheduling. This helps to improve the reliability of the grid and consumer satisfaction. Annual operating costs are reduced from $ 10 million to $ 7 million. By optimizing resource allocation and improving operating efficiency, the invention saves significant cost for the electric company. The invention can reduce the occurrence frequency of the system stability event from 5 times per month to 1 time. This means that the stability of the whole grid is enhanced, reducing potential losses and risks. And simultaneously, the energy cost is reduced.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. A window visualization method based on a power dispatch day plan, comprising:
collecting real-time power supply data;
training according to the historical power supply requirements to obtain a prediction model, and predicting the power supply requirements;
generating a power dispatching day plan according to a predicted result, and generating a temporary plan through quasi operation;
and presenting the power dispatching daily plan through a visual interface.
2. The power scheduling day plan-based window visualization method of claim 1, wherein: the power supply data includes power supply requirements, operating conditions of the power equipment, and productivity of the power equipment.
3. The power scheduling day plan-based window visualization method of claim 2, wherein: the prediction model comprises the steps of preprocessing data, preparing and cleaning the data;
the characteristic engineering of model training extracts time characteristics, meteorological data and special events according to historical power demand data;
capturing time sequence characteristics in the power demand data by using a long-short-term memory network LSTM;
H t ＝LSTM(X t ，H t-1 )
wherein H is t Indicating the LSTM hidden state at time t; x is X t An input feature vector representing time t, including historical power demand and other features; h t-1 Representing the hidden state of the previous time step;
using a self-attention mechanism;
A t ＝Attention(H t ，H)
wherein A is t The hidden state at the time t weighted by the self-attention mechanism is represented, and H represents a set of historical hidden states;
analyzing the influence of external factors on the power demand through an external factor influence module;
E t ＝NN ext (X ext,t )
wherein E is t An output representing the influence of an external factor; x is X ext,t Input data representing external factors;
combining the time dependence with the influence of external factors to make a final prediction;
wherein,representing a final predicted output representing a predicted power demand at time t; [ A ] t ；E t ]Representing stitching the self-attentive output with the output affected by the external factor; w and b are the weight sums of the modelsA bias parameter; σ is an activation function for converting the linear output into a predicted value.
4. A window visualization method based on a power scheduling day plan as recited in claim 3, wherein: the loss function of the prediction model includes:
Loss＝α·MSE+(1-α)·SmoothL1
wherein for the predicted valueAnd an actual value Y t MSE is defined as: /> Where N is the number of samples; />
5. The power scheduling day plan-based window visualization method of claim 4, wherein: the power dispatching date plan comprises a planned maintenance work, an operation mode change, live working and a temporary task;
wherein the temporary plan is an alternative formulated according to the problem conditions of the simulated operation;
when the power supply task can be completed without live working, the equipment changes the operation mode from live working to non-live working.
6. The power scheduling day plan-based window visualization method of claim 5, wherein: evaluating the total power supply capability of the devices includes dividing the operating devices into a live-operable device set E live And a non-live working equipment set E nolive The method comprises the steps of carrying out a first treatment on the surface of the Set S i Representing the performance of device i, whichS in (2) i =1 indicates that the device can perform live working, S i =0 indicates that live-line work is not possible;
power supply capability during service:
wherein I represents the number of devices, C i Indicating the power supply capability of device i.
7. The power scheduling day plan-based window visualization method of claim 6, wherein: the power dispatch day schedule also includes, if it is constant during the time of completion of maintenance of all equipmentThe equipment capable of carrying out live working is preferentially maintained, and other equipment is maintained sequentially from short time to long time by taking the average maintenance time of each equipment in the history record as a standard; if there is +.>Intelligent scheduling is performed:
let the current time be TdrawThe method comprises the steps that at a point T1 closest to the current time in a time domain, the maximum power supply capacity C which can be subjected to wining maintenance in the time of T1-T is matched, after one schedule is finished, the power supply capacity D' =D+C at the time of T1 is updated, and if the predicted requirement of power supply at the time of T1 is met, the subsequent schedules are sequentially carried out from the time of T1 according to the updated power supply capacity; if the predicted requirement of power supply at the time T1 is not met, recording a difference delta 1, updating the power supply capacity D' =D+C+δ1 at the time T1 again, and sequentially performing subsequent scheduling according to the updated power supply capacity at the time T1; all differences δtotal=δ1+δ2 were recorded after the schedule was completedδk; where k represents k differences;
the maintenance time to complete all the equipment is expressed as:
wherein t is i The maintenance average time of the ith equipment is represented, and R represents the number of maintenance personnel;
generating a temporary plan from all differences delta totals: scheduling the standby equipment with power supply capacity reaching delta total for the first timeIs engaged in powering up before the time node of (c).
8. A window visualization system based on a power dispatch day plan employing the method of any of claims 1-7, wherein:
the data acquisition module acquires real-time power supply data;
the prediction module is used for obtaining a prediction model according to the historical power supply demand training and predicting the power supply demand;
the plan generation module generates a power dispatching day plan according to the predicted result and generates a temporary plan through the quasi-operation;
and the visualization module is used for presenting the power dispatching daily plan through a visualization interface.
9. A computer device, comprising: a memory and a processor; the memory stores a computer program characterized in that: the processor, when executing the computer program, implements the steps of a window visualization method based on a power dispatch day plan.
10. A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program when executed by a processor implements the steps of a window visualization method based on a power dispatch day plan.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311693822.8A CN117689160A (en) | 2023-12-11 | 2023-12-11 | Window visual method and system based on power scheduling day plan |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311693822.8A CN117689160A (en) | 2023-12-11 | 2023-12-11 | Window visual method and system based on power scheduling day plan |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117689160A true CN117689160A (en) | 2024-03-12 |
Family
ID=90127879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311693822.8A Pending CN117689160A (en) | 2023-12-11 | 2023-12-11 | Window visual method and system based on power scheduling day plan |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117689160A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117973806A (en) * | 2024-03-28 | 2024-05-03 | 浙江大有实业有限公司杭州科技发展分公司 | Method and system for generating electricity-retaining DRS (data processing system) plan |
-
2023
- 2023-12-11 CN CN202311693822.8A patent/CN117689160A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117973806A (en) * | 2024-03-28 | 2024-05-03 | 浙江大有实业有限公司杭州科技发展分公司 | Method and system for generating electricity-retaining DRS (data processing system) plan |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116646933B (en) | Big data-based power load scheduling method and system | |
| Zhou et al. | Electricity price forecasting with confidence-interval estimation through an extended ARIMA approach | |
| JP7051856B2 (en) | Systems and methods for controlling dynamic energy storage systems | |
| Abiri-Jahromi et al. | Optimized midterm preventive maintenance outage scheduling of thermal generating units | |
| CN117689160A (en) | Window visual method and system based on power scheduling day plan | |
| Du et al. | Prediction of electricity consumption based on GM (1, Nr) model in Jiangsu province, China | |
| CN112488427A (en) | ARIMA model-based medium-and-long-term photovoltaic available electric quantity prediction method | |
| CN116757465A (en) | Line risk assessment method and device based on double training weight distribution model | |
| He et al. | High frequency short-term demand forecasting model for distribution power grid based on ARIMA | |
| Zhang et al. | A novel decomposition and combination technique for forecasting monthly electricity consumption | |
| CN117200352A (en) | Photovoltaic power generation regulation and control method and system based on cloud edge fusion | |
| Sun et al. | Interval mixed-integer programming for daily unit commitment and dispatch incorporating wind power | |
| Zhang et al. | Economic dispatch considering volatile wind power generation with lower-semi-deviation risk measure | |
| Yanhui et al. | Forecasting hourly electricity demand with nonparametric functional data analysis | |
| Din et al. | Bivariate short-term electric power forecasting using LSTM network | |
| Zheng et al. | Data-Adaptive Robust Transmission Network Planning Incorporating Post-Contingency Demand Response | |
| Kalantayevskaya et al. | Design of decision-making support system in power grid dispatch control based on the forecasting of energy consumption | |
| Al-Abri et al. | Overview of the Global Electricity System in Oman Considering Energy Demand Model Forecast | |
| Vo | Forecast on electricity demand for industry and construction sectors in Vietnam by 2030 | |
| Usachev et al. | Software Package For Improving Financial And Technological Performance Of Microgrid Networks | |
| Hu et al. | Flexible Robust Unit Commitment Considering Sub-hourly Wind Power Ramp Behaviors | |
| Jin et al. | Day-ahead load probabilistic forecasting based on space-time correction | |
| Asthana | Economic Dispatch of Consumer Loads Using Machine Learning in Smart Grid Environment | |
| Jack et al. | Optimization scheme for intelligent master controller with collaboratives energy system | |
| Çetinkaya et al. | Next-Day Electricity Demand Forecasting Using Regression |
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 |