CN114330771A - Power grid maintenance scheduling method based on load analysis - Google Patents
Power grid maintenance scheduling method based on load analysis Download PDFInfo
- Publication number
- CN114330771A CN114330771A CN202111627713.7A CN202111627713A CN114330771A CN 114330771 A CN114330771 A CN 114330771A CN 202111627713 A CN202111627713 A CN 202111627713A CN 114330771 A CN114330771 A CN 114330771A
- Authority
- CN
- China
- Prior art keywords
- overhaul
- data
- load
- neural network
- normalization processing
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000010606 normalization Methods 0.000 claims abstract description 28
- 238000013528 artificial neural network Methods 0.000 claims abstract description 27
- 238000005457 optimization Methods 0.000 claims abstract description 5
- 239000002245 particle Substances 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims abstract description 4
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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 provides a power grid maintenance scheduling method based on load analysis, which comprises the following steps: s1, acquiring historical meteorological data and load data of a power grid, and performing normalization processing on the meteorological data and the load data; s2, determining overhaul declaration data, S3, constructing a neural network, and inputting the weather data and the load data subjected to normalization processing into the neural network for training; s4, acquiring meteorological data and load data of the current power grid in real time, carrying out normalization processing, inputting the data subjected to normalization processing into a neural network for processing, and predicting the power supply amount of a maintenance day; s5, adopting an improved particle swarm optimization algorithm, adjusting the overhaul declaration data to enable the minimum overhaul daily power supply amount to be a target function, taking the overhaul declaration data determined when the overhaul daily power supply amount reaches the minimum as an overhaul scheduling basis, and accurately predicting the power supply amount of the overhaul day in an overhaul scheduling plan based on the load of a power distribution network and the influence of weather.
Description
Technical Field
The invention relates to a power dispatching method, in particular to a power grid maintenance dispatching method based on load analysis.
Background
The power grid maintenance mode is an important content in the operation plan of the power system, is directly related to the benefits of the power supply system and users, and has great influence on the reliability and the economy of the power system. The scientific and reasonable maintenance mode is an important guarantee for the economical and reliable operation of the power grid and the prevention of accidents.
However, the same maintenance work may involve a plurality of operation and maintenance stations, and the time allowed for maintenance and the number of repairable workers in each operation and maintenance station may be different, and meanwhile, the power outage loss caused by maintenance in different time periods is different, so how to accurately schedule to reduce the power outage loss is a technical problem.
Disclosure of Invention
In view of the above, the present invention provides a power grid maintenance scheduling method based on load analysis, which can accurately predict the power supply amount of a maintenance day in a maintenance scheduling plan based on the load of a power distribution network and the influence of weather, and determine the maintenance day with the minimum power supply amount as a maintenance scheduling basis based on the power supply amount, so as to minimize the loss caused by maintenance and power outage.
The invention provides a power grid maintenance scheduling method based on load analysis, which comprises the following steps:
s1, acquiring historical meteorological data and load data of a power grid, and performing normalization processing on the meteorological data and the load data;
s2, determining overhaul declaration data, wherein the overhaul declaration data comprises operation and maintenance station information, overhaul work items, overhaul work item priorities, application overhaul date and time periods of each overhaul work item, overhaul operation number required by the operation and maintenance station for completing each overhaul work item, an upper limit of allowable operation number per day of the operation and maintenance station and an allowable or forbidden overhaul time period per day of the operation and maintenance station;
s3, constructing a neural network, and inputting the meteorological data and the load data subjected to normalization processing into the neural network for training;
s4, acquiring meteorological data and load data of the current power grid in real time, carrying out normalization processing, inputting the data subjected to normalization processing into a neural network for processing, and predicting the power supply amount of a maintenance day;
and S5, adjusting the overhaul declaration data by adopting an improved particle swarm optimization algorithm to enable the minimum overhaul daily power supply amount to be a target function, and taking the overhaul declaration data determined when the overhaul daily power supply amount reaches the minimum as an overhaul scheduling basis.
Further, in step S1 and step S4, the normalization processing of the meteorological data and load data includes:
normalization processing is carried out by adopting a z-score function, and then:
wherein x is*To normalize the processed data, x is the input sample data before normalization, μ represents the sample mean, and σ represents the sample variance.
Further, before the meteorological data and the load data after the normalization processing are input to the neural network, data screening is further included, and the data screening specifically includes:
calculating the Euclidean distance between any two sample data;
and (4) sorting the Euclidean distances from small to large, screening n samples with the Euclidean distances smaller than a set threshold value, and inputting the n samples into the neural network.
Further, in step S3, the neural network is specifically constructed as follows:
the neural network comprises an input layer, a plurality of hidden layers and an output layer;
wherein, the transfer formula between the hidden layer and the hidden layer is as follows:
al=s(Wl-1al-1+bl-1)
wherein: a islRepresents the output of the l-th hidden layer neuron, Wl-1Weight matrix for connecting l-1 hidden layer and l hidden layer neurons, bl-1A bias term for a l-th layer hidden layer neuron;
the hidden layer activation function s (x) is shown below:
s (x) max (0.01x, x); wherein, x is input sample data;
the activation function of the output layer is: s (x) x.
Further, the predicted output of the power supply amount on the day of maintenance is as follows:
y=y*σ + μ, where y is the predicted output of the daily supply power, y*Is the neural network output.
The invention has the beneficial effects that: according to the invention, the power supply amount of the maintenance day in the maintenance scheduling plan can be accurately predicted based on the load of the power distribution network and the influence of weather, and the maintenance day with the minimum power supply amount is determined as the maintenance scheduling basis based on the power supply amount, so that the loss caused by maintenance power failure is minimum.
Drawings
The invention is further described below with reference to the following figures and examples:
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a comparison of the daily power supply for the service of the present invention.
Detailed Description
The invention is further illustrated below:
the invention provides a power grid maintenance scheduling method based on load analysis, which comprises the following steps:
s1, acquiring historical meteorological data and load data of a power grid, and performing normalization processing on the meteorological data and the load data;
s2, determining overhaul declaration data, wherein the overhaul declaration data comprises operation and maintenance station information, overhaul work items, overhaul work item priorities, application overhaul date and time periods of each overhaul work item, overhaul operation number required by the operation and maintenance station for completing each overhaul work item, an upper limit of allowable operation number per day of the operation and maintenance station and an allowable or forbidden overhaul time period per day of the operation and maintenance station;
s3, constructing a neural network, and inputting the meteorological data and the load data subjected to normalization processing into the neural network for training;
s4, acquiring meteorological data and load data of the current power grid in real time, carrying out normalization processing, inputting the data subjected to normalization processing into a neural network for processing, and predicting the power supply amount of a maintenance day;
s5, adopting an improved particle swarm optimization algorithm, adjusting the overhaul declaration data to enable the minimum overhaul daily power supply amount to be a target function, and taking the overhaul declaration data determined when the overhaul daily power supply amount reaches the minimum as an overhaul scheduling basis.
The improved particle swarm optimization algorithm is the prior art, and the specific process is not described herein in detail.
Specifically, the method comprises the following steps: in steps S1 and S4, the normalization processing of the meteorological data and load data includes:
normalization processing is carried out by adopting a z-score function, and then:
wherein x is*To normalize the processed data, x is the input sample data before normalization, μ represents the sample mean, and σ represents the sample variance.
Before the meteorological data and the load data after the normalization processing are input into the neural network, the method further comprises data screening, and specifically comprises the following steps:
calculating the Euclidean distance between any two sample data;
and (4) sorting the Euclidean distances from small to large, screening n samples with the Euclidean distances smaller than a set threshold value, and inputting the n samples into the neural network.
In step S3, the neural network is specifically constructed as follows:
the neural network comprises an input layer, a plurality of hidden layers and an output layer;
wherein, the transfer formula between the hidden layer and the hidden layer is as follows:
al=s(Wl-1al-1+bl-1)
wherein: a islRepresents the output of the l-th hidden layer neuron, Wl-1Weight matrix for connecting l-1 hidden layer and l hidden layer neurons, bl-1A bias term for a l-th layer hidden layer neuron;
the hidden layer activation function s (x) is shown below:
s (x) max (0.01x, x); wherein, x is input sample data;
the activation function of the output layer is: s (x) x.
The predicted output of the power supply amount on the inspection day is as follows:
y=y*σ + μ, where y is the predicted output of the daily supply power, y*Is the neural network output. Under the above method, the predicted daily power supply amount for service substantially coincides with the actual power supply amount, as shown in fig. 2, and therefore, the method provided by the present invention can provideAnd the prediction result is accurately ensured.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, 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 modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.
Claims (5)
1. A power grid maintenance scheduling method based on load analysis is characterized in that: the method comprises the following steps:
s1, acquiring historical meteorological data and load data of a power grid, and performing normalization processing on the meteorological data and the load data;
s2, determining overhaul declaration data, wherein the overhaul declaration data comprises operation and maintenance station information, overhaul work items, overhaul work item priorities, application overhaul date and time periods of each overhaul work item, overhaul operation number required by the operation and maintenance station for completing each overhaul work item, an upper limit of allowable operation number per day of the operation and maintenance station and an allowable or forbidden overhaul time period per day of the operation and maintenance station;
s3, constructing a neural network, and inputting the meteorological data and the load data subjected to normalization processing into the neural network for training;
s4, acquiring meteorological data and load data of the current power grid in real time, carrying out normalization processing, inputting the data subjected to normalization processing into a neural network for processing, and predicting the power supply amount of a maintenance day;
and S5, adjusting the overhaul declaration data by adopting an improved particle swarm optimization algorithm to enable the minimum overhaul daily power supply amount to be a target function, and taking the overhaul declaration data determined when the overhaul daily power supply amount reaches the minimum as an overhaul scheduling basis.
2. The load analysis-based power grid overhaul scheduling method according to claim 1, wherein: in steps S1 and S4, the normalization processing of the meteorological data and load data includes:
normalization processing is carried out by adopting a z-score function, and then:
wherein x is*To normalize the processed data, x is the input sample data before normalization, μ represents the sample mean, and σ represents the sample variance.
3. The load analysis-based power grid overhaul scheduling method according to claim 2, wherein: before the meteorological data and the load data after the normalization processing are input into the neural network, the method further comprises data screening, and specifically comprises the following steps:
calculating the Euclidean distance between any two sample data;
and (4) sorting the Euclidean distances from small to large, screening n samples with the Euclidean distances smaller than a set threshold value, and inputting the n samples into the neural network.
4. The load analysis-based power grid overhaul scheduling method according to claim 3, wherein: in step S3, the neural network is specifically constructed as follows:
the neural network comprises an input layer, a plurality of hidden layers and an output layer;
wherein, the transfer formula between the hidden layer and the hidden layer is as follows:
al=s(Wl-1al-1+bl-1)
wherein: a islRepresents the output of the l-th hidden layer neuron, Wl-1Weight matrix for connecting l-1 hidden layer and l hidden layer neurons, bl-1A bias term for a l-th layer hidden layer neuron;
the hidden layer activation function s (x) is shown below:
s (x) max (0.01x, x); wherein, x is input sample data;
the activation function of the output layer is: s (x) x.
5. The load analysis-based power grid overhaul scheduling method according to claim 4, wherein: the predicted output of the power supply amount on the inspection day is as follows:
y=y*σ + μ, where y is the predicted output of the daily supply power, y*Is the neural network output.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111627713.7A CN114330771A (en) | 2021-12-28 | 2021-12-28 | Power grid maintenance scheduling method based on load analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111627713.7A CN114330771A (en) | 2021-12-28 | 2021-12-28 | Power grid maintenance scheduling method based on load analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114330771A true CN114330771A (en) | 2022-04-12 |
Family
ID=81015425
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111627713.7A Pending CN114330771A (en) | 2021-12-28 | 2021-12-28 | Power grid maintenance scheduling method based on load analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114330771A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116596512A (en) * | 2023-05-22 | 2023-08-15 | 湖北华中电力科技开发有限责任公司 | Electric power operation and maintenance safety strengthening method and system based on information system |
-
2021
- 2021-12-28 CN CN202111627713.7A patent/CN114330771A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116596512A (en) * | 2023-05-22 | 2023-08-15 | 湖北华中电力科技开发有限责任公司 | Electric power operation and maintenance safety strengthening method and system based on information system |
CN116596512B (en) * | 2023-05-22 | 2024-05-10 | 湖北华中电力科技开发有限责任公司 | Electric power operation and maintenance safety strengthening method and system based on information system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Li et al. | Clothing sale forecasting by a composite GRU–Prophet model with an attention mechanism | |
CN105069525B (en) | Round-the-clock 96 Day Load Curve Forecastings and optimization update the system | |
CN111985701B (en) | Power consumption prediction method based on power supply enterprise big data model base | |
Lamedica et al. | A neural network based technique for short-term forecasting of anomalous load periods | |
Du et al. | Power load forecasting using BiLSTM-attention | |
CN111695731B (en) | Load prediction method, system and equipment based on multi-source data and hybrid neural network | |
CN107944604A (en) | A kind of weather pattern recognition methods and device for photovoltaic power prediction | |
Zeng et al. | A learning framework based on weighted knowledge transfer for holiday load forecasting | |
CN110807550A (en) | Distribution transformer overload identification early warning method based on neural network and terminal equipment | |
CN108694470A (en) | A kind of data predication method and device based on artificial intelligence | |
CN115796434A (en) | Management and control method and device for power distribution network, electronic equipment and storage medium | |
CN110210670A (en) | A kind of prediction technique based on power-system short-term load | |
CN111667090A (en) | Load prediction method based on deep belief network and weight sharing | |
CN114330771A (en) | Power grid maintenance scheduling method based on load analysis | |
Inteha | A GRU-GA hybrid model based technique for short term electrical load forecasting | |
CN114444660A (en) | Short-term power load prediction method based on attention mechanism and LSTM | |
CN116186548A (en) | Power load prediction model training method and power load prediction method | |
Staudt et al. | Predicting transmission line congestion in energy systems with a high share of renewables | |
Zhang et al. | An automatic real-time bus schedule redesign method based on bus arrival time prediction | |
CN112070307B (en) | Method and device for predicting energy source load in region | |
Gallina et al. | Work in progress level prediction with long short-term memory recurrent neural network | |
CN116644562B (en) | New energy power station operation and maintenance cost evaluation system | |
CN110648011B (en) | Feeder line short-term load prediction method considering photovoltaic users | |
CN110489893B (en) | Variable weight-based bus load prediction method and system | |
Rosienkiewicz | Artificial intelligence-based hybrid forecasting models for manufacturing systems |
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 |