Power supply system scheduling method and power supply system thereof
Through the distributed multi-power supply system scheduling method, the RBF neural network is used to predict the power consumption and power supply, and the power supply equipment is scheduled in real time, and energy storage is used to assist power supply when the power supply is insufficient, which solves the problem that traditional scheduling methods are difficult to cope with complex power supply systems. , improves the safety and efficiency of the system.
Patent Information
- Application Number
- CN202410932837.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional power supply system scheduling methods are difficult to adapt to complex and changeable power supply systems, lack effective utilization of new energy and energy storage, and cannot respond to emergencies in a timely manner, resulting in low safety and efficiency of power supply systems.
The distributed multi-power supply system scheduling method is adopted, and the power consumption data is collected through the monitoring module. The data prediction module uses the RBF neural network to predict the power consumption and power supply. The dispatching module dispatches the power supply equipment in real time. The early warning module uses energy storage when the power supply is insufficient. Equipment assists in power supply.
It improves the safety and efficiency of the power supply system, effectively utilizes wind and photovoltaic power supply, reduces dependence on fuel, reduces carbon emissions, and realizes intelligent scheduling and emergency response capabilities.
Smart Images

Figure CN118920599A_ABST
Abstract
Description
[0001] The present invention relates to the technical field of electric power dispatching, and in particular to a power supply system dispatching method and a power supply system thereof. Background Art
[0002] With the continuous development of power systems, higher requirements are placed on the reliability, economy and safety of power supply systems. Traditional dispatching methods rely on experience and rules, which are difficult to adapt to complex and changeable power supply systems. They lack effective utilization mechanisms for new power resources such as new energy and energy storage, and are insufficient in ensuring the safety of power supply systems. They are unable to respond to emergencies in a timely manner. In order to improve the efficiency and safety of power supply systems, the development and application of distributed multi-power supply system dispatching methods have important practical significance. Summary of the invention
[0003] The purpose of the present invention is to provide a power supply system scheduling method and a power supply system thereof, so as to solve the deficiencies in the background technology.
[0004] In order to achieve the above object, the present invention provides the following technical solution: a power supply system, comprising:
[0005] A monitoring module is used to collect the power consumption of electrical equipment in the industrial park, including the power consumption of electrical equipment in the factory area and the dormitory area of the industrial park;
[0006] The data prediction module is connected to the monitoring module to obtain the sunshine data and wind data of the industrial park, analyze the power consumption, sunshine data and wind data of the power equipment in the factory area and dormitory area of the industrial park, and predict the power consumption required by the power equipment in the industrial park in the next time period, the estimated power supply of the photovoltaic power supply equipment and the estimated power supply of the wind power supply equipment as the prediction data;
[0007] The scheduling module is connected with the monitoring module and the data prediction module, compares the predicted data with the power consumption to obtain a comparison result, obtains a power supply plan based on the comparison result, and dispatches the power supply equipment in real time;
[0008] The early warning module is connected to the scheduling module. After the power supply plan is enabled, when the power supply equipment in the power supply plan cannot meet the actual power consumption of the power equipment in the industrial park, the energy storage device starts to provide auxiliary power supply to the power equipment in the industrial park.
[0009] In a preferred embodiment, the monitoring module includes:
[0010] The power consumption of multiple electrical equipment in industrial parks is obtained in units of minutes, the locations of multiple electrical equipment in industrial parks are obtained, and the locations of the electrical equipment in the industrial park factory area and dormitory area are divided into the electrical equipment in the industrial park factory area and the electrical equipment in the dormitory area;
[0011] Based on the power consumption equipment in the factory area of the industrial park and the power consumption equipment in the dormitory area, the power consumption of the power consumption equipment in the factory area of the industrial park and the power consumption equipment in the dormitory area are obtained respectively, and recorded as the power consumption of the power consumption equipment in the factory area of the industrial park P f And the power consumption of electrical equipment in the dormitory area of the industrial park P d , and upload it to the data prediction module.
[0012] In a preferred embodiment, the data prediction module includes:
[0013] Data preparation: Process electricity consumption, sunshine data, and wind power data in a unified scale;
[0014] Network design: Determine the structure of the RBF neural network. The structure of the RBF neural network includes an input layer, a hidden layer, and an output layer. The nodes of the hidden layer are set using the trial and error method. By changing the number of nodes in the hidden layer and observing the performance of the neural network on the training set and the test set, the optimal number of nodes is selected.
[0015] Hidden layer node initialization: Use the k-means clustering algorithm to cluster the training set and use the cluster center as the center point;
[0016] Training adjustment: The historical power consumption of the power equipment in the industrial park is divided into a first training set and a first test set. The neural network is trained using the error back propagation algorithm through the first training set to obtain a prediction model for the power consumption of the power equipment in the industrial park.
[0017] The historical power consumption of the electrical equipment in the dormitory area of the industrial park is divided into a second training set and a second test set, and the neural network is trained by using the error back propagation algorithm through the second training set to obtain the power consumption prediction model of the electrical equipment in the dormitory area of the industrial park;
[0018] The historical sunlight data is divided into a third training set and a third test set, and the neural network is trained by using the error propagation algorithm through the third training set to obtain a prediction model for the estimated power supply of photovoltaic power supply equipment;
[0019] The historical wind power data is divided into a fourth training set and a fourth test set, and a neural network is trained by using the fourth training set using an error back propagation algorithm to obtain a predicted model for the estimated power supply of wind power supply equipment;
[0020] Model evaluation: The first test set is used to evaluate the power consumption prediction model of the power equipment in the factory area of the industrial park; the second test set is used to evaluate the power consumption prediction model of the power equipment in the dormitory area of the industrial park; the third test set is used to evaluate the power consumption prediction model of the photovoltaic power supply equipment; the fourth test set is used to evaluate the power consumption prediction model of the wind power supply equipment;
[0021] Model application: The power consumption prediction model for electrical equipment in the factory area of the industrial park, the power consumption prediction model for electrical equipment in the dormitory area of the industrial park, the power supply prediction model for photovoltaic power supply equipment, and the power supply prediction model for wind power supply equipment are used to perform regression prediction on the power consumption of electrical equipment in the industrial park, sunlight data, and wind data to obtain the planned power consumption of electrical equipment in the industrial park and the planned power generation of power supply equipment.
[0022] In a preferred embodiment, the steps of constructing the RBF neural network are:
[0023] Input layer: takes electricity consumption, sunshine data and wind power data as input;
[0024] Hidden layer: The hidden layer nodes are connected to the output layer nodes using Gaussian radial basis function As the activation function, x represents the input of the input layer, β i represents the width of the Gaussian function, c i Represents the center point of a neural network neuron;
[0025] Output layer: The output layer nodes are connected to the hidden layer nodes, and the output layer function is expressed as Where q represents the number of neurons in the neural network, w i Represents the weights of the neural network.
[0026] In a preferred embodiment, the steps of applying the model are:
[0027] Based on the power consumption of electrical equipment in the industrial park P f The power consumption P of the power equipment in the industrial park is estimated by the power consumption prediction model of the power equipment in the industrial park in the next period of time. fr ;
[0028] Based on the power consumption of electrical equipment in the dormitory area of the industrial park P d The power consumption prediction model of the power equipment in the dormitory area of the industrial park is used to estimate the power consumption P of the power equipment in the dormitory area of the industrial park in the next period of time. dr ;
[0029] Based on the sunlight data, the power supply prediction model of the photovoltaic power supply equipment is used to estimate the power supply P of the photovoltaic power supply equipment in the next time period. s ;
[0030] Based on the wind power data, the wind power supply equipment power supply prediction model is used to estimate the power supply P of the wind power supply equipment in the next time period. w .
[0031] In a preferred embodiment, the scheduling module includes:
[0032] When estimating the power supply of photovoltaic power supply equipment Ps and the estimated power supply of wind power equipment P w When the sum is greater than or equal to the estimated total power consumption of the power equipment in the industrial park, that is, P s +P w ≥P fr +P dr , the wind power supply equipment and photovoltaic power supply equipment are used to supply power to all electrical equipment in the industrial park, and the excess power is used to charge the energy storage equipment;
[0033] When estimating the power supply of photovoltaic power supply equipment P s and the estimated power supply of wind power equipment P w The sum is greater than the planned power consumption P of the electrical equipment in the dormitory area of the industrial park dr , and less than the planned power consumption P of the power equipment in the industrial park fr , that is, P fr >P s +P w >P dr , the municipal power supply equipment is used to supply power to the electrical equipment in the factory area of the industrial park, the photovoltaic power supply equipment and the wind power supply equipment are used to supply power to the electrical equipment in the dormitory area of the industrial park, and the excess power of the photovoltaic power supply equipment and the wind power supply equipment is used to charge the energy storage device;
[0034] When estimating the power supply of photovoltaic power supply equipment P s and the estimated power supply of wind power equipment P w The sum is less than the planned power consumption P of the electrical equipment in the dormitory area of the industrial park dr , that is, P s +P w <P dr , then use the municipal power supply equipment to supply power to the power equipment in the industrial park and determine the estimated power supply capacity P of the photovoltaic power supply equipment s , Estimated power supply of wind power supply equipment P w and the power supply of the energy storage device P b / t, that is, when P s +P w +P b / t>P dr , the photovoltaic power supply equipment, the wind power supply equipment and the energy storage equipment are used to supply power to the electrical equipment in the dormitory area of the industrial park, wherein P b is the maximum storage energy of the energy storage device, P b / t is the power supply of the energy storage device in the time period t. s +P w +P b / t <P dr, the municipal power supply equipment, the photovoltaic power supply equipment and the wind power supply equipment are used to supply power to the electrical equipment in the dormitory area of the industrial park.
[0035] In a preferred embodiment, the early warning module includes:
[0036] After the scheduling plan is activated, the actual power consumption of the electrical equipment in the factory area of the industrial park and the electrical equipment in the dormitory area is monitored in real time. When the actual power consumption of the electrical equipment in the factory area of the industrial park and the electrical equipment in the dormitory area does not meet the rated power consumption of the electrical equipment in the industrial park, the energy storage device is used to provide auxiliary power supply to the electrical equipment in the industrial park.
[0037] The present invention also provides a power supply system scheduling method, comprising:
[0038] Collect the electricity consumption of electrical equipment in the industrial park, including the electricity consumption of electrical equipment in the factory area and dormitory area of the industrial park;
[0039] Obtain sunlight data and wind data of the industrial park, analyze the power consumption, sunlight data and wind data of the power equipment in the factory area and dormitory area of the industrial park, predict the power consumption required by the power equipment in the industrial park in the next time period, the estimated power supply of the photovoltaic power supply equipment and the estimated power supply of the wind power supply equipment, and use the estimated power consumption of the power equipment in the industrial park, the estimated power supply of the photovoltaic power supply equipment and the estimated power supply of the wind power supply equipment as the prediction data;
[0040] Compare the predicted data with the power consumption to obtain a comparison result, obtain a power supply plan based on the comparison result, and dispatch the power supply equipment in real time;
[0041] After the power supply plan is activated, when the power supply equipment in the power supply plan cannot meet the actual power consumption of the power equipment in the industrial park, the energy storage device begins to provide auxiliary power supply to the power equipment in the industrial park.
[0042] In the above technical solution, the technical effects and advantages provided by the present invention are:
[0043] 1. The present invention improves the power supply system by introducing wind power supply equipment and photovoltaic power supply equipment into the power supply system. With the advancement of technology and economies of scale, the costs of wind power generation and photovoltaic power generation continue to decline. They can be used as a supplement to traditional power generation, and effectively reduce dependence on fuel, reduce carbon emissions, and protect the environment.
[0044] 2. The present invention introduces a neural network regression prediction model to perform regression prediction on the power consumption of electrical equipment in the industrial park, sunlight data and wind power data, thereby realizing the estimation of the power consumption of electrical equipment in the industrial park, the power generation of photovoltaic power supply equipment and the power generation of wind power supply equipment, and realizing online scheduling of the power supply system through the scheduling module. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0046] Figure 1 is a system block diagram of the present invention;
[0047] Figure 2 A block diagram of the method of the present invention. DETAILED DESCRIPTION
[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0049] Example 1, please refer to Figure 1 As shown, a power supply system described in this embodiment includes:
[0050] A monitoring module is used to collect the power consumption of electrical equipment in the industrial park, including the power consumption of electrical equipment in the factory area and the dormitory area of the industrial park;
[0051] The data prediction module is connected to the monitoring module to obtain the sunshine data and wind data of the industrial park, analyze the power consumption, sunshine data and wind data of the power equipment in the factory area and dormitory area of the industrial park, and predict the power consumption required by the power equipment in the industrial park in the next time period, the estimated power supply of the photovoltaic power supply equipment and the estimated power supply of the wind power supply equipment as the prediction data;
[0052] The scheduling module is connected with the monitoring module and the data prediction module, compares the predicted data with the power consumption to obtain a comparison result, obtains a power supply plan based on the comparison result, and dispatches the power supply equipment in real time;
[0053] The early warning module is connected to the scheduling module. After the power supply plan is enabled, when the power supply equipment in the power supply plan cannot meet the actual power consumption of the power equipment in the industrial park, the energy storage device starts to provide auxiliary power supply to the power equipment in the industrial park.
[0054] It is further explained that with the continuous development of the power system, higher requirements are placed on the reliability, economy and safety of the power supply system. The traditional scheduling method relies on experience and rules, and it is difficult to adapt to the complex and changeable power supply system. It lacks an effective utilization mechanism for new power resources such as new energy and energy storage, and the ability to ensure the safety of the power supply system is insufficient, and it is unable to respond to emergencies in a timely manner. The present invention can be used as a supplement to traditional power generation by introducing wind power supply equipment and photovoltaic power supply equipment into the power supply system, and effectively reduces dependence on fuel, reduces carbon emissions, and protects the environment; by introducing a neural network regression prediction model, the power consumption of industrial park power equipment, sunlight data and wind data are regressed and predicted, and the power consumption of industrial park power equipment, the power generation of photovoltaic power supply equipment, and the power generation of wind power supply equipment are estimated, and the intelligent scheduling of the power supply system is realized through the scheduling module.
[0055] In one embodiment, the monitoring module includes:
[0056] The power consumption of multiple electrical equipment in industrial parks is obtained in units of minutes, the locations of multiple electrical equipment in industrial parks are obtained, and the locations of the electrical equipment in the industrial park factory area and dormitory area are divided into the electrical equipment in the industrial park factory area and the electrical equipment in the dormitory area;
[0057] Based on the power consumption equipment in the factory area of the industrial park and the power consumption equipment in the dormitory area, the power consumption of the power consumption equipment in the factory area of the industrial park and the power consumption equipment in the dormitory area are obtained respectively, and recorded as the power consumption of the power consumption equipment in the factory area of the industrial park P f And the power consumption of electrical equipment in the dormitory area of the industrial park P d , and upload it to the data prediction module.
[0058] Further explanation: the location of the electrical equipment is determined based on the location sensor on the electrical equipment in the industrial park. The sensor signal uploads the location information of the equipment, and the electrical equipment is divided into factory area electrical equipment and dormitory area electrical equipment according to the location information; the power consumption is collected by using the current transformer on the electrical equipment to measure the current flowing through the electrical equipment, and using the voltage transformer to measure the voltage at both ends of the electrical equipment. According to the acquired current and voltage data, the power consumption calculation formula of power = voltage × current × time is used for real-time calculation and analysis to obtain the power consumption of the electrical equipment. The collected power consumption is divided into two parts according to the location information: the power consumption of the electrical equipment in the factory area of the industrial park and the power consumption of the electrical equipment in the dormitory area of the industrial park, and uploaded to the data prediction module.
[0059] In one embodiment, the data prediction module includes:
[0060] Data preparation: Process electricity consumption, sunshine data, and wind power data in a unified scale;
[0061] Network design: determine the structure of the RBF neural network, which includes input layer, hidden layer and output layer;
[0062] Hidden layer node initialization: Use the k-means clustering algorithm to cluster the training data and use the cluster center as the center point;
[0063] Training adjustment: The historical power consumption of the power equipment in the industrial park is divided into a first training set and a first test set. The neural network is trained using the error back propagation algorithm through the first training set to obtain a prediction model for the power consumption of the power equipment in the industrial park.
[0064] The historical power consumption of the electrical equipment in the dormitory area of the industrial park is divided into a second training set and a second test set, and the neural network is trained by using the error back propagation algorithm through the second training set to obtain the power consumption prediction model of the electrical equipment in the dormitory area of the industrial park;
[0065] The historical sunlight data is divided into a third training set and a third test set, and the neural network is trained by using the error propagation algorithm through the third training set to obtain a prediction model for the estimated power supply of photovoltaic power supply equipment;
[0066] The historical wind power data is divided into a fourth training set and a fourth test set, and a neural network is trained by using the fourth training set using an error back propagation algorithm to obtain a predicted model for the estimated power supply of wind power supply equipment;
[0067] Model evaluation: The first test set is used to evaluate the power consumption prediction model of the power equipment in the factory area of the industrial park; the second test set is used to evaluate the power consumption prediction model of the power equipment in the dormitory area of the industrial park; the third test set is used to evaluate the power consumption prediction model of the photovoltaic power supply equipment; the fourth test set is used to evaluate the power consumption prediction model of the wind power supply equipment;
[0068] Model application: The power consumption prediction model for electrical equipment in the factory area of the industrial park, the power consumption prediction model for electrical equipment in the dormitory area of the industrial park, the power supply prediction model for photovoltaic power supply equipment, and the power supply prediction model for wind power supply equipment are used to perform regression prediction on the power consumption of electrical equipment in the industrial park, sunlight data, and wind data to obtain the planned power consumption of electrical equipment in the industrial park and the planned power generation of power supply equipment.
[0069] It is further explained that the number of nodes in the output layer of the RBF neural network is slightly larger than the amount of input data; the setting of the hidden layer nodes is based on the complexity of the training set data and the number of samples, and the data complexity is based on the eigenvector, feature type, data distribution and data correlation of the data; the node of the output layer is set to one, and the outputs of the four models are respectively the planned power consumption of electrical equipment in the factory area of the industrial park, the planned power consumption of electrical equipment in the dormitory area of the industrial park, the planned power supply of photovoltaic power supply equipment and the planned power supply of wind power supply equipment; the model evaluation method is: the mean square error between the predicted value and the true value is calculated to measure the prediction accuracy of the model. The smaller the error, the more accurate the prediction. The degree of fit of the model to the data is checked, ranging from 0 to 1. If the value is closer to 1, the better the fit.
[0070] In one embodiment, the steps of constructing the RBF neural network are:
[0071] Input layer: takes electricity consumption, sunshine data and wind power data as input;
[0072] Hidden layer: The hidden layer nodes are connected to the output layer nodes using Gaussian radial basis function As the activation function, x represents the input of the input layer, β i represents the width of the Gaussian function, c i Represents the center point of a neural network neuron;
[0073] Output layer: The output layer nodes are connected to the hidden layer nodes, and the output layer function is expressed as Where q represents the number of neurons in the neural network, w i Represents the weights of the neural network.
[0074] In one embodiment, the model is applied in the following steps:
[0075] Based on the power consumption of electrical equipment in the industrial park P f The power consumption P of the power equipment in the industrial park is estimated by the power consumption prediction model of the power equipment in the industrial park in the next period of time. fr ;
[0076] Based on the power consumption of electrical equipment in the dormitory area of the industrial park P d The power consumption prediction model of the power equipment in the dormitory area of the industrial park is used to estimate the power consumption P of the power equipment in the dormitory area of the industrial park in the next period of time. dr ;
[0077] Based on the sunlight data, the power supply prediction model of the photovoltaic power supply equipment is used to estimate the power supply P of the photovoltaic power supply equipment in the next time period. s ;
[0078] Based on the wind power data, the wind power supply equipment power supply prediction model is used to estimate the power supply P of the wind power supply equipment in the next time period. w .
[0079] In one embodiment, the scheduling module includes:
[0080] When estimating the power supply of photovoltaic power supply equipment P s and the estimated power supply of wind power equipment P w When the sum is greater than or equal to the estimated total power consumption of the power equipment in the industrial park, that is, P s +P w ≥P fr +P dr , the wind power supply equipment and photovoltaic power supply equipment are used to supply power to all electrical equipment in the industrial park, and the excess power is used to charge the energy storage equipment;
[0081] When estimating the power supply of photovoltaic power supply equipment P s and the estimated power supply of wind power equipment P w The sum is greater than the planned power consumption P of the electrical equipment in the dormitory area of the industrial park dr , and less than the planned power consumption P of the power equipment in the industrial park fr , that is, P fr >P s +P w >P dr , the municipal power supply equipment is used to supply power to the electrical equipment in the factory area of the industrial park, the photovoltaic power supply equipment and the wind power supply equipment are used to supply power to the electrical equipment in the dormitory area of the industrial park, and the excess power of the photovoltaic power supply equipment and the wind power supply equipment is used to charge the energy storage device;
[0082] When estimating the power supply of photovoltaic power supply equipment P s and the estimated power supply of wind power equipment P w The sum is less than the planned power consumption P of the electrical equipment in the dormitory area of the industrial park dr , that is, P s +P w <P dr , then use the municipal power supply equipment to supply power to the power equipment in the industrial park and determine the estimated power supply capacity P of the photovoltaic power supply equipment s , Estimated power supply of wind power supply equipment P w and the power supply of the energy storage device P b / t, that is, when P s +P w +P b / t>P dr , the photovoltaic power supply equipment, the wind power supply equipment and the energy storage equipment are used to supply power to the electrical equipment in the dormitory area of the industrial park, wherein Pb is the maximum storage energy of the energy storage device, P b / t is the power supply of the energy storage device in the time period t. s +P w +P b / t <P dr , the municipal power supply equipment, the photovoltaic power supply equipment and the wind power supply equipment are used to supply power to the electrical equipment in the dormitory area of the industrial park.
[0083] To further explain, the power consumption of electrical equipment in the dormitory area of the industrial park is significantly lower than that of electrical equipment in the factory area of the industrial park. The power supply of photovoltaic power supply equipment and wind power supply equipment is unstable and lower than the city power supply. Therefore, the photovoltaic power supply equipment and wind power supply equipment must first meet the power supply of electrical equipment in the dormitory area of the industrial park. Therefore, the judgment scheme of the judgment module is based on the comparison between the power supply of photovoltaic power supply equipment and wind power supply equipment and the power consumption of electrical equipment in the industrial park. After meeting the power consumption of electrical equipment in the dormitory area of the industrial park, consider supplying power to electrical equipment or energy storage equipment in the factory area of the industrial park.
[0084] In one embodiment, the early warning module includes:
[0085] After the scheduling plan is activated, the actual power consumption of the electrical equipment in the factory area of the industrial park and the electrical equipment in the dormitory area is monitored in real time. When the actual power consumption of the electrical equipment in the factory area of the industrial park and the electrical equipment in the dormitory area does not meet the preset power consumption, the energy storage device is used to provide auxiliary power supply to the electrical equipment in the area.
[0086] A power supply system scheduling method, comprising:
[0087] Collect the electricity consumption of electrical equipment in the industrial park, including the electricity consumption of electrical equipment in the factory area and dormitory area of the industrial park;
[0088] Obtain sunlight data and wind data of the industrial park, analyze the power consumption, sunlight data and wind data of the power equipment in the factory area and dormitory area of the industrial park, predict the power consumption required by the power equipment in the industrial park in the next time period, the estimated power supply of the photovoltaic power supply equipment and the estimated power supply of the wind power supply equipment, and use the estimated power consumption of the power equipment in the industrial park, the estimated power supply of the photovoltaic power supply equipment and the estimated power supply of the wind power supply equipment as the prediction data;
[0089] Compare the predicted data with the power consumption to obtain a comparison result, obtain a power supply plan based on the comparison result, and dispatch the power supply equipment in real time;
[0090] After the power supply plan is activated, when the power supply equipment in the power supply plan cannot meet the actual power consumption of the power equipment in the industrial park, the energy storage device begins to provide auxiliary power supply to the power equipment in the industrial park.
[0091] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A power supply system, characterized in that: include: A monitoring module is used to collect the power consumption of electrical equipment in the industrial park, including the power consumption of electrical equipment in the factory area and dormitory area of the industrial park; The data prediction module is connected to the monitoring module to obtain sunlight data and wind data of the industrial park, analyze the power consumption, sunlight data and wind data of the electrical equipment in the factory area and dormitory area of the industrial park, and predict the power consumption required by the electrical equipment in the industrial park in the next time period, the estimated power supply of photovoltaic power supply equipment, and the estimated power supply of wind power supply equipment as prediction data; The scheduling module is connected to the monitoring module and the data prediction module, compares the predicted data with the power consumption to obtain a comparison result, and dispatches the power supply equipment in real time based on the power supply plan obtained from the comparison result; The early warning module is connected to the scheduling module. After the power supply plan is activated, when the power supply equipment in the power supply plan cannot meet the actual power consumption of the power equipment in the industrial park, the energy storage device starts to provide auxiliary power supply to the power equipment in the industrial park.
2. A power supply system according to claim 1, characterized in that: The monitoring module includes: Obtain the power consumption of electrical equipment in multiple industrial parks in units of minutes, obtain the locations of electrical equipment in multiple industrial parks, and divide the locations into factory and dormitory areas to obtain electrical equipment in the factory and dormitory areas of the industrial parks; Based on the power consumption of the industrial park factory area power equipment and the dormitory area power equipment, the power consumption of the industrial park factory area power equipment and the dormitory area power equipment are obtained respectively, and recorded as the power consumption of the industrial park factory area power equipment P f And the power consumption of electrical equipment in the dormitory area of the industrial park P d , and upload it to the data prediction module.
3. The power supply system according to claim 1, wherein: The data prediction module includes: Data preparation: Process electricity consumption, sunlight data, and wind power data in a unified scale; Network design: Determine the structure of the RBF neural network, which includes the input layer, hidden layer, and output layer; Hidden layer node initialization: Use the k-means clustering algorithm to cluster the training data and use the cluster center as the center point; Training adjustment: The historical electricity consumption of the industrial park's electrical equipment is divided into a first training set and a first test set. The neural network is trained using the error back propagation algorithm on the first training set to obtain a prediction model for the expected electricity consumption of the industrial park's electrical equipment. The historical electricity consumption of electrical equipment in the dormitory area of the industrial park is divided into a second training set and a second test set. The neural network is trained using the error back propagation algorithm on the second training set to obtain a prediction model for the expected electricity consumption of electrical equipment in the dormitory area of the industrial park. The historical sunlight data is divided into a third training set and a third test set. The neural network is trained using the error propagation algorithm on the third training set to obtain a photovoltaic power supply equipment power supply prediction model. The historical wind power data is divided into a fourth training set and a fourth test set, and a neural network is trained using the error back propagation algorithm on the fourth training set to obtain a wind power supply equipment power supply prediction model; Model evaluation: The first test set was used to evaluate the power consumption prediction model for electrical equipment in the industrial park factory area; the second test set was used to evaluate the power consumption prediction model for electrical equipment in the industrial park dormitory area; the third test set was used to evaluate the power consumption prediction model for photovoltaic power supply equipment; and the fourth test set was used to evaluate the power consumption prediction model for wind power supply equipment. Model application: The power consumption prediction model for electrical equipment in the industrial park factory area, the power consumption prediction model for electrical equipment in the industrial park dormitory area, the power supply prediction model for photovoltaic power supply equipment, and the power supply prediction model for wind power supply equipment are used to perform regression prediction on the power consumption of electrical equipment in the industrial park, sunlight data, and wind power data to obtain the planned power consumption of electrical equipment in the industrial park and the planned power generation of power supply equipment.
4. A power supply system according to claim 3, characterized in that: The steps of constructing the RBF neural network are as follows: Input layer: takes electricity consumption, sunshine data and wind power data as input; Hidden layer: The hidden layer nodes are connected to the output layer nodes using Gaussian radial basis function As the activation function, x represents the input of the input layer, β i represents the width of the Gaussian function, c i Represents the center point of a neural network neuron; Output layer: The output layer nodes are connected to the hidden layer nodes, and the output layer function is expressed as Where q represents the number of neurons in the neural network, w i Represents the neural network weights.
5. A power supply system according to claim 3, characterized in that: Steps to apply the model: Based on the power consumption of electrical equipment in the industrial park P f The planned power consumption P of the power equipment in the industrial park in the next time period is estimated by using the trained power consumption prediction model of the power equipment in the industrial park fr ; Based on the power consumption of electrical equipment in the dormitory area of the industrial park P d The power consumption forecast model of the electrical equipment in the dormitory area of the industrial park is used to estimate the power consumption P of the electrical equipment in the dormitory area of the industrial park in the next period of time. dr ; Based on the sunlight data, the power supply prediction model of the photovoltaic power supply equipment is used to estimate the power supply P of the photovoltaic power supply equipment in the next time period. s ; Based on the wind power data, the wind power supply equipment power supply prediction model is used to estimate the wind power supply equipment power supply P in the next time period. w .
6. A power supply system according to claim 1, characterized in that: The scheduling module includes: When estimating the power supply of photovoltaic power supply equipment P s and the estimated power supply of wind power equipment P w When the sum is greater than or equal to the estimated total power consumption of the electrical equipment in the industrial park, that is, P s +P w ≥P fr +P dr , the wind power supply equipment and photovoltaic power supply equipment are used to power all electrical equipment in the industrial park, and the excess electricity is used to charge the energy storage equipment; When estimating the power supply of photovoltaic power supply equipment P s and the estimated power supply of wind power equipment P w The sum is greater than the planned power consumption P of the electrical equipment in the dormitory area of the industrial park dr , and is less than the planned power consumption P of the electrical equipment in the industrial park fr , that is, P fr >P s +P w >P dr , the municipal power supply equipment is used to power the electrical equipment in the factory area of the industrial park, and the photovoltaic power supply equipment and the wind power supply equipment are used to power the electrical equipment in the dormitory area of the industrial park, and the excess electricity of the photovoltaic power supply equipment and the wind power supply equipment is used to charge the energy storage device; When estimating the power supply of photovoltaic power supply equipment P s and the estimated power supply of wind power equipment P w The sum is less than the planned power consumption P of the electrical equipment in the dormitory area of the industrial park dr , that is, P s +P w <P dr , then use the municipal power supply equipment to power the electrical equipment in the industrial park and factory area, and determine the estimated power supply capacity P of the photovoltaic power supply equipment. s , Estimated power supply capacity P of wind power supply equipment w and the power supply of the energy storage device P b / t, that is, when P s +P w +P b / t>P dr , the photovoltaic power supply equipment, the wind power supply equipment and the energy storage equipment are used to supply power to the electrical equipment in the dormitory area of the industrial park, wherein P b is the maximum storage energy of the energy storage device, P b / t is the power supply of the energy storage device in the time period t. s +P w +P b / t <P dr , the city power supply equipment, the photovoltaic power supply equipment and the wind power supply equipment are used to supply power to the electrical equipment in the dormitory area of the industrial park.
7. The power supply system according to claim 1, characterized in that: The early warning module includes: After the scheduling plan is activated, the actual power consumption of the electrical equipment in the industrial park factory area and the electrical equipment in the dormitory area is monitored in real time. When the actual power consumption of the electrical equipment in the industrial park factory area and the electrical equipment in the dormitory area does not meet the preset power consumption, the energy storage device is used to provide auxiliary power supply to the electrical equipment in the industrial park.
8. A power supply system scheduling method according to claim 1, used to implement a power supply system according to any one of claims 1 to 7, characterized in that: The following steps are involved: Collect electricity consumption of electrical equipment in industrial parks, including electricity consumption of electrical equipment in factory areas and dormitory areas of industrial parks; Obtain sunlight data and wind data for the industrial park, analyze the power consumption, sunlight data, and wind data of the electrical equipment in the factory area and dormitory area of the industrial park, and predict the power consumption required by the electrical equipment in the industrial park for the next time period, the estimated power supply of the photovoltaic power supply equipment, and the estimated power supply of the wind power supply equipment, and use the estimated power consumption of the electrical equipment in the industrial park, the estimated power supply of the photovoltaic power supply equipment, and the estimated power supply of the wind power supply equipment as the prediction data; Compare the predicted data with the power consumption to obtain a comparison result, obtain a power supply plan based on the comparison result, and dispatch the power supply equipment in real time; After the power supply plan is activated, when the power supply equipment in the power supply plan cannot meet the actual power consumption of the industrial park's electrical equipment, the energy storage device begins to provide auxiliary power supply to the industrial park's electrical equipment.
Citation Information
Cited By
Power supply system scheduling method and power supply system thereof
CN121749537A
