Energy scheduling processing method and device, computer device and storage medium
By predicting the green energy consumption of industrial parks and optimizing load transfer models, the problem of overloaded new energy capacity has been solved, achieving optimized scheduling and consumption of green energy and reducing waste.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN POWER SUPPLY BUREAU
- Filing Date
- 2022-12-28
- Publication Date
- 2026-07-07
AI Technical Summary
In some regions, the installed capacity of new energy sources exceeds the carrying capacity, leading to the waste of new energy resources.
By predicting the amount of green energy absorbed by the industrial park per unit time, a predicted absorption curve is determined. Then, the target control scheme is optimized using a load transfer model and constraints to fit the load transfer amount with the absorption curve, thereby optimizing energy consumption changes and costs and achieving optimal scheduling of green energy.
It has increased the absorption of green energy, reduced energy waste, and achieved optimized scheduling of green energy.
Smart Images
Figure CN116090764B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of new energy technology, and in particular to an energy dispatching and processing method, apparatus, computer equipment, and storage medium. Background Technology
[0002] In recent years, the development of new energy sources has been rapid, playing a crucial role in reducing the use of non-renewable energy, ensuring the growing energy demand, and addressing air pollution and climate change. However, along with this development, some regions are experiencing a situation where the installed capacity of new energy sources exceeds their carrying capacity, leading to a waste of new energy resources.
[0003] To ensure the healthy development of new energy sources, it is necessary to optimize the allocation of new energy resources in various regions and minimize the waste of new energy resources. Summary of the Invention
[0004] Therefore, it is necessary to provide an energy dispatching method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can reduce energy waste, in order to address the above-mentioned technical problems.
[0005] Firstly, this application provides an energy dispatching processing method. The method includes:
[0006] The amount of green energy consumed per unit time in the industrial park is predicted to obtain the predicted consumption amount.
[0007] Determine the predicted energy consumption curve based on the predicted consumption amount;
[0008] Using a load transfer model, based on the predicted energy consumption curve, the first constraint, and the second constraint, a target control scheme is predicted and determined. When the target control scheme is executed, the curve formed by the load transfer volume generated within the industrial park fits the predicted energy consumption curve, the energy consumption change characterization parameter satisfies the first constraint, and the energy consumption cost characterization parameter satisfies the second constraint. The energy consumption change characterization parameter is used to quantify the energy consumption change within the industrial park; the energy consumption cost characterization parameter is used to quantify the energy consumption cost within the industrial park.
[0009] The target control scheme is executed within a unit of time in the industrial park.
[0010] In one embodiment, the step of predicting and determining the target control scheme based on the predicted energy consumption curve, the first constraint, and the second constraint using a load transfer model includes:
[0011] The objective function to be optimized is determined; the objective function includes an energy consumption change quantification function and an energy consumption cost quantification function; the energy consumption change quantification function is used to quantify and calculate the energy consumption change characterization parameters; the energy consumption cost quantification function is used to quantify and calculate the energy consumption cost characterization parameters.
[0012] Using the load transfer model, a control scheme is iteratively searched in the direction of fitting the load transfer curve and the predicted energy consumption curve, and in the direction of optimizing the objective function. For each searched control scheme, the parameter values of the energy consumption change characterization parameter and the energy consumption cost characterization parameter in the objective function are predicted when the control scheme is executed, so as to determine the value of the objective function under the control scheme.
[0013] When the load transfer curve is fitted to the predicted energy consumption curve, the control scheme that optimizes the objective function is taken as the target control scheme.
[0014] In one embodiment, when predicting the execution of each found control scheme, the parameter values of the energy consumption change characterization parameter and the energy consumption cost characterization parameter in the objective function include:
[0015] For each searched control scheme, the ratio of the total energy consumption change after implementing the control scheme to the original total energy consumption is predicted, thus obtaining the parameter value of the energy consumption change characterization parameter after implementing the control scheme; the total energy consumption change is the sum of the predicted energy consumption changes in each time period after implementing the control scheme; the original total energy consumption is the sum of the original energy consumption in each time period when the control scheme was not implemented;
[0016] For each searched control scheme, the ratio between the energy cost per unit time after implementing the control scheme and the original energy cost per unit time is predicted, and the parameter value of the energy cost characterization parameter after implementing the control scheme is obtained; the original energy cost per unit time is the energy cost per unit time when the control scheme is not implemented.
[0017] In one embodiment, the predicted energy consumption curve includes peak-hour consumption, normal-hour consumption, and off-peak-hour consumption; the step of fitting the load transfer curve with the predicted energy consumption curve includes:
[0018] For each searched control scheme, predict the load transfer amount generated in the industrial park when the control scheme is executed, and generate the load transfer amount curve based on the load transfer amount;
[0019] The peak, normal, and low periods in the load transfer curve are respectively fitted and approximated with the peak, normal, and low periods in the predicted energy consumption curve, so that the load transfer and predicted consumption in the same period are matched.
[0020] In one embodiment, the prediction of the green energy consumption per unit time in the industrial park, to obtain the predicted consumption, includes:
[0021] Determine the meteorological data, time type, and historical energy consumption corresponding to each unit of time in the industrial park;
[0022] The predicted energy consumption is obtained by performing nonlinear mapping processing on the meteorological data, time type and historical energy consumption through the energy prediction model.
[0023] The training steps for the energy prediction model include:
[0024] The energy-related data of the industrial park are smoothed to obtain sample energy-related data; the energy-related data refers to data related to the consumption of green energy.
[0025] The radial basis function neural network is trained and optimized based on the sample energy data to obtain an energy prediction model.
[0026] In one embodiment, the method further includes:
[0027] The actual energy consumption of the industrial park per unit time is uploaded to the first blockchain;
[0028] Upon receiving an energy transmission request and when the energy consumption capacity of the industrial park is saturated for the current period, energy transmission is performed to the initiator of the energy transmission request; the initiator is an authorized node object in the blockchain.
[0029] In one embodiment, the method further includes:
[0030] Based on preset rules, cross-regional virtual energy transmission is achieved through the interaction between multiple node objects in the second blockchain;
[0031] The plurality of node objects include energy issuers and energy operators; the interaction results recorded in the second blockchain are sent to the target platform, and the interaction results are used to indicate the energy issuance and operation status in the second blockchain; the issuance and operation authorization records generated on the target platform are uploaded to the second blockchain, and the issuance and operation authorization records are used to indicate the issuance and operation permissions of the node objects in the second blockchain.
[0032] In one embodiment, the method further includes:
[0033] During the execution of the target control plan, the load change in the current period compared to the previous period is determined;
[0034] If the load change is less than the change threshold, priority will be given to reducing the consumption of the first energy source; the first energy source is a non-green energy source.
[0035] If the load change exceeds the change threshold, priority will be given to increasing the consumption of the second energy source; the second energy source is green energy.
[0036] Secondly, this application also provides an energy dispatching and processing device. The device includes:
[0037] The prediction module is used to predict the amount of green energy consumed by the industrial park per unit time, and obtain the predicted consumption amount.
[0038] The determination module is used to determine the predicted energy consumption curve based on the predicted consumption amount;
[0039] The processing module is used to predict and determine a target control scheme based on the predicted energy consumption curve, a first constraint, and a second constraint using a load transfer model. When the target control scheme is executed, the curve formed by the load transfer volume generated within the industrial park fits the predicted energy consumption curve, the energy consumption change characterization parameter satisfies the first constraint, and the energy consumption cost characterization parameter satisfies the second constraint. The energy consumption change characterization parameter is used to quantify the energy consumption change within the industrial park; the energy consumption cost characterization parameter is used to quantify the energy consumption cost within the industrial park.
[0040] The execution module is used to execute the target control scheme in the industrial park within a unit of time.
[0041] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described above.
[0042] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described above.
[0043] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described above.
[0044] The aforementioned energy dispatching processing method, device, computer equipment, storage medium, and computer program product predict the amount of green energy consumed per unit time in the industrial park to obtain the predicted consumption amount; determine the predicted energy consumption curve based on the predicted consumption amount; and predict and determine the target control scheme through a load transfer model based on the predicted energy consumption curve, the first constraint condition, and the second constraint condition; wherein, when the target control scheme is executed, the curve formed by the load transfer amount generated in the industrial park fits the predicted energy consumption curve, the energy consumption change characterization parameter satisfies the first constraint condition, and the energy consumption cost characterization parameter satisfies the second constraint condition; the energy consumption change characterization parameter... This is used to quantify the energy consumption changes within industrial parks; the energy cost characterization parameter is used to quantify the energy cost within industrial parks; by comprehensively considering the predicted absorption capacity, the load transfer volume generated within the industrial park, the energy consumption changes within the industrial park, and the energy cost within the industrial park, a target control scheme is determined, and then the target control scheme is executed within a unit of time in the industrial park. This ensures that the energy cost meets the second constraint condition and the energy consumption changes meet the first constraint condition, so that the absorption capacity of green energy and the load transfer volume within the industrial park are matched as closely as possible, thereby achieving optimized scheduling of green energy, improving the absorption capacity of green energy, and reducing the waste of green energy. Attached Figure Description
[0045] Figure 1 This is a flowchart illustrating an energy dispatching method in one embodiment;
[0046] Figure 2 This is a schematic diagram of a flexible load in one embodiment;
[0047] Figure 3 This is a schematic diagram of the structure of a radial basis function neural network in one embodiment;
[0048] Figure 4 This is a schematic diagram of virtual energy transmission in one embodiment;
[0049] Figure 5 This is a schematic diagram of a process for adjusting energy consumption based on load changes in one embodiment;
[0050] Figure 6 This is a structural block diagram of an energy dispatch processing device in one embodiment;
[0051] Figure 7 This is an internal structural diagram of a computer device in one embodiment;
[0052] Figure 8 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation
[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0054] In one embodiment, such as Figure 1 As shown, an energy dispatching method is provided. Taking the application of this method to a computer device as an example, it is understood that the computer device may include at least one of a terminal or a server. This method can be applied to a terminal or a server, and can also be applied to a system including both a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:
[0055] S102, predict the amount of green energy consumed per unit time in the industrial park to obtain the predicted consumption amount.
[0056] For example, a computer device can determine the unit time to be predicted, and predict the amount of green energy consumption based on the meteorological data, time type and historical energy consumption corresponding to the unit time to be predicted in the industrial park, so as to obtain the predicted consumption amount.
[0057] In one embodiment, meteorological data may include the highest temperature, lowest temperature, maximum wind speed, and lowest wind speed within a unit of time. It can be understood that meteorological data refers to a set of data reflecting the weather in the industrial park within a unit of time.
[0058] In one embodiment, the time type is used to indicate the nature of the date corresponding to the unit of time. For example, the time type can be used to indicate whether it is a holiday or public holiday.
[0059] In one embodiment, historical energy consumption refers to the energy consumption of the industrial park per unit time period in history. For example, the unit time period can be one day, meaning the unit time period to be predicted corresponds to the prediction day. Historical energy consumption can include the maximum electricity consumption on the day before the prediction date, the maximum electricity consumption two days before the prediction date, or the maximum electricity consumption on the same day of the week preceding the prediction date.
[0060] In one embodiment, the terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle systems, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. The server can be implemented using a standalone server or a server cluster consisting of multiple servers.
[0061] S104, Determine the predicted energy consumption curve based on the predicted consumption amount.
[0062] For example, the predicted energy consumption can include peak-hour consumption, normal-hour consumption, and off-peak-hour consumption. Computer equipment can determine a predicted energy consumption curve that includes peak-hour consumption, normal-hour consumption, and off-peak-hour consumption.
[0063] S106, through the load transfer model, based on the predicted energy consumption curve, the first constraint condition and the second constraint condition, predicts and determines the target control scheme.
[0064] When the target control scheme is implemented, the curve representing the load transfer within the industrial park must fit the predicted energy consumption curve, and the energy consumption change characterization parameter must satisfy the first constraint condition, while the energy consumption cost characterization parameter must satisfy the second constraint condition. The energy consumption change characterization parameter is used to quantify the energy consumption change within the industrial park. The energy consumption cost characterization parameter is used to quantify the energy consumption cost within the industrial park. It can be understood that the first constraint condition is used to minimize the energy consumption change within the industrial park. The second constraint condition is used to minimize the energy consumption cost within the industrial park.
[0065] For example, the load transfer model is obtained by mathematically modeling the relationship between the load transfer volume generated in the industrial park and the control scheme, and can characterize the changes in the load transfer volume generated in the industrial park with the control scheme. It is understood that for different control schemes, the load transfer volume during peak hours, normal hours, and off-peak hours in the industrial park will be different. Computer equipment can use the load transfer model, based on the predicted energy consumption curve, the first constraint, and the second constraint, to predict and determine the target control scheme in a direction that aims to fit the curves of peak-hour load transfer volume, normal-hour load transfer volume, and off-peak load transfer volume as closely as possible to the predicted energy consumption curve, minimize the change in energy consumption within the industrial park, and minimize the energy cost within the industrial park.
[0066] S108 implements target control schemes within a unit of time in the industrial park.
[0067] For example, computer equipment can interconnect with other industrial parks outside the industrial park during the execution of the target control plan within a unit of time in the industrial park, and transmit excess green energy to other industrial parks to increase the consumption of green energy.
[0068] In one embodiment, the computer equipment can issue a power outage command to the central controller during the power outage period indicated by the target control scheme, instructing the central controller to cut off power to the industrial park. It is understood that power supply to the industrial park is stopped during the power outage period. After the power outage period has elapsed, the computer equipment can issue a power restoration command to the central controller, instructing the central controller to restore power to the industrial park.
[0069] In the aforementioned energy dispatching method, the amount of green energy consumed per unit time in the industrial park is predicted to obtain the predicted consumption amount; a predicted energy consumption curve is determined based on the predicted consumption amount; and a target control scheme is predicted and determined using a load transfer model based on the predicted energy consumption curve, a first constraint, and a second constraint. When the target control scheme is executed, the curve formed by the load transfer amount generated within the industrial park fits the predicted energy consumption curve, the energy consumption change characterization parameter satisfies the first constraint, and the energy consumption cost characterization parameter satisfies the second constraint. The energy consumption change characterization parameter is used to quantify the energy consumption within the industrial park. Energy consumption variation; energy cost characterization parameters are used to quantify the energy cost within the industrial park; by comprehensively considering the predicted absorption capacity, the load transfer volume generated within the industrial park, the energy consumption variation within the industrial park, and the energy cost within the industrial park, a target control scheme is determined, and then the target control scheme is executed within the industrial park per unit time. Under the premise that the energy cost meets the second constraint condition and the energy consumption variation meets the first constraint condition, the absorption capacity of green energy and the load transfer volume within the industrial park are matched as much as possible, thereby achieving optimized scheduling of green energy, improving the absorption capacity of green energy, and reducing the waste of green energy.
[0070] In one embodiment, the prediction and determination of the target control scheme based on the predicted energy consumption curve, the first constraint, and the second constraint, using a load transfer model, includes: determining the objective function to be optimized; the objective function includes an energy consumption change quantification function and an energy consumption cost quantification function; the energy consumption change quantification function is used to quantify the energy consumption change characterization parameters; the energy consumption cost quantification function is used to quantify the energy consumption cost characterization parameters; using the load transfer model, iteratively searching for control schemes in the direction of fitting the load transfer curve to the predicted energy consumption curve and in the direction of optimizing the objective function; for each searched control scheme, predicting the parameter values of the energy consumption change characterization parameters and the energy consumption cost characterization parameters in the objective function when the control scheme is executed, to determine the value of the objective function under the control scheme; and selecting the control scheme that optimizes the objective function by fitting the load transfer curve to the predicted energy consumption curve as the target control scheme.
[0071] For example, the energy consumption change quantification function and the energy consumption cost quantification function are used to optimize the two objectives of energy consumption change and energy consumption cost, respectively. The computer device can transform the energy consumption change quantification function and the energy consumption cost quantification function into a single objective function based on the membership function formula, the energy consumption change quantification function, and the energy consumption cost quantification function, thus obtaining the objective function to be optimized.
[0072] Computer equipment can use load transfer models to iteratively search for control schemes that are closer to the peak, normal, and low periods in the load transfer curve, respectively, and in the direction of optimizing the objective function.
[0073] For each searched control scheme, the computer equipment can predict the values of the parameters representing energy change and energy cost in the objective function when the control scheme is executed, thus determining the value of the objective function under the control scheme. By making the load transfer curve approximate the peak, normal, and off-peak periods in the predicted energy consumption curve, the computer equipment selects the control scheme that optimizes the objective function as the target control scheme.
[0074] In one embodiment, the load transfer curve being close to the peak, normal, and off-peak periods in the predicted energy consumption curve means that the differences between the load transfer curve and the predicted energy consumption curve in the peak, normal, and off-peak periods are less than a preset matching threshold.
[0075] In this embodiment, a load transfer model iteratively searches for control schemes in the direction of fitting the load transfer curve to the predicted energy consumption curve and optimizing the objective function. For each searched control scheme, the parameter values of the energy change characterization parameter and the energy cost characterization parameter in the objective function are predicted to be executed, thus determining the value of the objective function under the control scheme. When the load transfer curve fits the predicted energy consumption curve, the control scheme that yields the optimal value of the objective function is taken as the target control scheme. Such a target control scheme can make the green energy consumption and load transfer in the industrial park match as closely as possible, thereby achieving optimized scheduling of green energy.
[0076] In one embodiment, for each searched control scheme, when the control scheme is predicted to be executed, the parameter values of the energy consumption change characterization parameter and the energy consumption cost characterization parameter in the objective function include: for each searched control scheme, the ratio of the predicted total energy consumption change after the control scheme is executed to the original total energy consumption is predicted, thus obtaining the parameter value of the energy consumption change characterization parameter after the control scheme is executed; the total energy consumption change is the sum of the predicted energy consumption changes in each time period after the control scheme is executed; the original total energy consumption is the sum of the original energy consumption in each time period when the control scheme is not executed; for each searched control scheme, the ratio between the predicted unit-time energy consumption cost after the control scheme is executed and the original unit-time energy consumption cost is predicted, thus obtaining the parameter value of the energy consumption cost characterization parameter after the control scheme is executed; the original unit-time energy consumption cost is the unit-time energy consumption cost when the control scheme is not executed.
[0077] For example, the computer device can determine the change in energy consumption in each time period after implementing the control scheme compared to when the control scheme is not implemented for each searched control scheme. It can sum up the change in energy consumption in each time period to obtain the total change in energy consumption. By calculating the ratio of the total change in energy consumption after implementing the control scheme to the original total energy consumption, the parameter value of the energy consumption change characteristic parameter after implementing the control scheme can be obtained.
[0078] For each searched control scheme, the computer equipment can subtract the sum of power outage compensation for each time period from the sum of energy costs for each time period to obtain the unit energy cost after implementing the control scheme. By calculating the ratio between the unit energy cost and the original unit energy cost, the parameter value representing the energy cost after implementing the control scheme can be obtained.
[0079] In one embodiment, Equation (1) shows the energy change quantization function.
[0080]
[0081] in, The parameter characterizes the change in energy consumption. k represents the type of energy, which may include at least one of electrical energy, thermal energy, wind energy, or hydropower. This represents the total change in energy consumption. This represents the original total energy consumption.
[0082] In one embodiment, Equation (2) shows the energy cost quantification function.
[0083]
[0084] in, Characterize the energy cost of the parameter. Energy consumption before the implementation of the plan Energy consumption adjusted for energy costs in different time periods This refers to the amount of energy reduction after a power outage. The energy costs for each period prior to the implementation of the plan. This represents the energy cost for each period after the implementation of the plan. This is for power outage compensation during different time periods. It can be understood that in formula (2), the numerator is the energy cost per unit time, and the denominator is the original energy cost per unit time. If μ e A value greater than 1 indicates that the energy cost in the industrial park will increase after the implementation of the plan. If μ e If the value is less than 1, it indicates that the energy cost in the industrial park will be reduced after the implementation of the plan.
[0085] It should be noted that the control plan includes adjustments to energy costs for different time periods and power outages.
[0086] In one embodiment, Equation (3) shows the objective function.
[0087]
[0088]
[0089]
[0090] Where a1 and a2 are weighting coefficients, respectively. These are the parameters representing energy consumption change and energy consumption cost, respectively. k represents the type of energy. They are respectively Fuzzy membership function. These represent the maximum and minimum values of the parameter, respectively, characterized by energy changes. These represent the maximum and minimum values of the parameter characterized by energy cost, respectively. The parameter μ is characterized by energy change. s The acceptable minimum optimization value. Let μ be the energy cost characterization parameter e The acceptable minimum optimization value.
[0091] In this embodiment, for each searched control scheme, the ratio of the total change in energy consumption after implementing the control scheme to the original total energy consumption is predicted, thus obtaining the parameter value of the energy consumption change characterization parameter after implementing the control scheme; for each searched control scheme, the ratio of the unit time energy cost after implementing the control scheme to the original unit time energy cost is predicted, thus obtaining the parameter value of the energy cost characterization parameter after implementing the control scheme, so as to obtain the target control scheme that minimizes the change in energy consumption and energy cost after implementing the scheme, thereby ensuring normal energy consumption in the industrial park while achieving optimized scheduling of green energy.
[0092] In one embodiment, the predicted energy consumption curve includes peak-hour consumption, normal-hour consumption, and off-hour consumption; the step of fitting the load transfer curve with the predicted energy consumption curve includes: for each searched control scheme, predicting the load transfer generated in the industrial park when the control scheme is executed, and generating a load transfer curve based on the load transfer; fitting the peak-hour, normal-hour, and off-hour periods in the load transfer curve with the peak-hour, normal-hour, and off-hour periods in the predicted energy consumption curve, respectively, so that the load transfer and predicted consumption are matched for the same period.
[0093] The load transfer volume includes peak-hour load transfer volume, normal-hour load transfer volume, and off-hour load transfer volume. It can be understood that the load transfer volume is used to indicate the transfer of flexible loads within the industrial park.
[0094] For example, the computer equipment can predict the load transfer volume within the industrial park when each searched control scheme is implemented. The computer equipment can determine a load transfer volume curve including peak-hour load transfer volume, normal-hour load transfer volume, and off-hour load transfer volume. The computer equipment can approximate the peak-hour, normal-hour, and off-hour load transfer volume curves with the peak-hour, normal-hour, and off-hour load transfer volume curves, respectively, to match the predicted energy consumption volume for the same time period.
[0095] In one embodiment, such as Figure 2 The diagram illustrates flexible loads. Flexible loads include transferable loads, relocatable loads, and reduceable loads. Transferable loads include transferable electrical loads and transferable gas loads. Relocatable loads include transferable electrical loads and relocatable gas loads. Reduceable loads include reduceable electrical loads, reduceable gas loads, and reduceable heat loads.
[0096] In this embodiment, the peak, normal, and low periods in the load transfer curve are fitted and approximated with the peak, normal, and low periods in the predicted energy consumption curve, respectively, so that the load transfer volume and the predicted consumption volume in the same period match, thereby achieving optimized scheduling of green energy.
[0097] In one embodiment, predicting the amount of green energy consumed by an industrial park per unit time includes: determining the meteorological data, time type, and historical energy consumption corresponding to the industrial park per unit time; performing nonlinear mapping processing on the meteorological data, time type, and historical energy consumption through an energy prediction model to obtain the predicted consumption output by the energy prediction model; wherein, the training steps of the energy prediction model include: smoothing the energy-related data of the industrial park to obtain sample energy-related data; energy-related data refers to data related to the consumption of green energy; and training and optimizing the radial basis function neural network based on the sample energy data to obtain the energy prediction model.
[0098] For example, computer equipment can determine the meteorological data, time type, and historical energy consumption corresponding to a unit time in an industrial park as inputs to an energy prediction model, and then perform nonlinear mapping processing through the energy prediction model to obtain the predicted energy consumption output by the energy prediction model.
[0099] In one embodiment, energy-related data has a pre-defined range of values. For erroneous energy-related data exceeding this range, smoothing is required to obtain sample energy-related data. For example, if erroneous energy-related data exceeds the range, the average of data from the nearest few days can be used to replace the erroneous energy data. For missing energy-related data, an intermediate value can be calculated using numerical analysis based on data before and after the missing data, and this value can be used to fill the gap. If energy-related data for similar dates shows significant variations, the average of the preceding and following data can be taken, and then weighted in conjunction with energy-related data from the same time in the previous month. This weighted average can then replace the original value with the resulting data to obtain sample energy-related data.
[0100] In one embodiment, such as Figure 3 The diagram illustrates the structure of a radial basis function (RBF) neural network. The RBF neural network comprises an input layer, hidden layers, and an output layer. A computer can use a Gaussian function as the kernel function in the hidden layer nodes, and perform clustering analysis on the sample energy-related data using the mean clustering algorithm. After completing the clustering analysis, the connection weights between the output layer and the hidden layer are adjusted using the recursive least squares method to train and optimize the RBF neural network, resulting in an energy prediction model.
[0101] In one embodiment, the computer device may determine the predicted daily maximum temperature, predicted daily minimum temperature, predicted daily maximum wind force, predicted daily minimum wind force, the nature of the predicted day date, the maximum power consumption of the day before the predicted day, the maximum power consumption of the two days before the predicted day, and the maximum power consumption of the same day of the previous week as inputs to the energy forecasting model.
[0102] In this embodiment, the meteorological data, time type, and historical energy consumption corresponding to a unit time in the industrial park are determined. The meteorological data, time type, and historical energy consumption are then processed by a nonlinear mapping method using an energy prediction model to obtain the predicted consumption output by the energy prediction model. Subsequently, a target control scheme that matches the load transfer amount with the predicted consumption amount can be searched to achieve optimized scheduling of green energy.
[0103] In one embodiment, the method further includes: uploading the actual energy consumption of the industrial park per unit time to the first blockchain; and, upon receiving an energy transmission request and when the energy consumption of the industrial park is saturated for the current period, transmitting energy to the initiating object of the energy transmission request; the initiating object is an authorized node object in the first blockchain.
[0104] For example, the first blockchain is used for energy interconnection between industrial parks. Computer equipment can upload the actual energy consumption of an industrial park per unit time to the first blockchain. When the computer equipment receives an energy transfer request and the energy consumption of the industrial park at that time is saturated, it can transfer excess energy to the industrial park where the requester is located.
[0105] In one embodiment, the computer equipment can enable green energy to enter the grid and reduce the generation of other energy sources when the green energy generation in the industrial park increases; and reduce the entry of green energy into the grid and increase the generation of other energy sources when the green energy generation in the industrial park decreases.
[0106] Once the renewable energy generation capacity of an industrial park reaches saturation within a certain period, the excess power is transferred to another industrial park, or interconnected between three or more industrial parks.
[0107] In this embodiment, when an energy transmission request is received and the energy consumption of the industrial park is saturated at the current time, energy is transmitted to the object that initiated the energy transmission request. Blockchain is used to ensure security while promoting interconnection between multiple industrial parks.
[0108] In one embodiment, the method further includes: performing cross-regional virtual energy transmission through interaction between multiple node objects in a second blockchain based on preset rules; wherein the multiple node objects include energy issuers and energy operators; the interaction results recorded in the second blockchain are sent to a target platform, and the interaction results are used to indicate the energy issuance and operation status in the second blockchain; the issuance and operation authorization records generated on the target platform are uploaded to the second blockchain, and the issuance and operation authorization records are used to indicate the issuance and operation permissions possessed by the node objects in the second blockchain.
[0109] For example, such as Figure 4 The diagram illustrates virtual energy transmission. Preset rules include those for granting issuance and operation permissions on the target platform. Computer devices can perform cross-regional virtual energy transmission through interactions between multiple node objects in the second blockchain. The target platform can obtain the interaction results from the second blockchain. The second blockchain can obtain the issuance and operation authorization records from the target platform. It can be understood that Industrial Park A and Industrial Park B can obtain issuance and operation permissions on the target platform.
[0110] In one embodiment, the preset rule can be the green certificate rule.
[0111] In one embodiment, at time t, within region I, a green energy generator J entrusts green energy operator I to supply electricity to green energy generator J on its behalf. Simultaneously, within region J, green energy generator J entrusts green energy operator J to generate energy using electricity, and the amount of green energy stored by green energy operator J within region J is equal to the energy consumed by green energy storage operator I within sub-region I. Within region J, a green energy generator K entrusts green energy operator J to supply electricity to green energy generator K on its behalf. Simultaneously, within region K, green energy generator K entrusts green energy operator K to generate energy using electricity, and the amount of green energy stored by green energy operator K within region K is equal to the energy consumed by green energy storage operator J within region J. This completes the virtual transmission of electricity across regions I, J, and K at time t.
[0112] In this embodiment, based on preset rules, cross-regional virtual energy transmission is carried out through the interaction between multiple node objects in the second blockchain. Since the generation and consumption of electricity are completed in one go, the electrical connection between different regions is weak, and it is not very practical to transmit electricity across regions through power transmission lines. By using the second blockchain for virtual energy transmission, energy scheduling can be optimized.
[0113] In one embodiment, the method further includes: during the execution of the target control scheme, determining the load change in the current period compared to the previous period; if the load change is less than a change threshold, prioritizing the reduction of the consumption of a first energy source; the first energy source is a non-green energy source; if the load change is greater than the change threshold, prioritizing the increase of the consumption of a second energy source; the second energy source is a green energy source.
[0114] For example, such as Figure 5 The diagram illustrates a process for adjusting energy consumption based on load changes. During the execution of the target control plan, the computer equipment determines the load change compared to the previous period. The change threshold can be 0. A change greater than the threshold indicates increased energy consumption in the current period; otherwise, it indicates decreased energy consumption. When the load change is less than the threshold, the computer equipment can reduce the consumption of the first energy source. If the consumption of the first energy source decreases to a limit, the consumption of the second energy source is reduced. When the load change is greater than the threshold, the computer equipment can increase the consumption of the second energy source. Once the consumption of the second energy source reaches the required level, i.e., the target for green energy consumption is achieved, the consumption of the first energy source is then increased.
[0115] In this embodiment, during the execution of the target control scheme, the load change in the current period compared to the previous period is determined; if the load change is less than the change threshold, the consumption of the first energy source is reduced first; if the load change is greater than the change threshold, the consumption of the second energy source is increased first. This allows for timely adjustment of green energy and other energy sources to achieve a balance between energy supply and demand and reduce energy waste.
[0116] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0117] Based on the same inventive concept, this application also provides an energy dispatching processing apparatus for implementing the energy dispatching processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more energy dispatching processing apparatus embodiments provided below can be found in the limitations of the energy dispatching processing method described above, and will not be repeated here.
[0118] In one embodiment, such as Figure 6 As shown, an energy dispatching processing device 600 is provided, including: a prediction module 602, a determination module 604, and a processing module 606, wherein:
[0119] The prediction module 602 is used to predict the amount of green energy consumed in the industrial park per unit time, and obtain the predicted consumption amount.
[0120] Module 604 is used to determine the predicted energy consumption curve based on the predicted consumption amount;
[0121] Processing module 606 is used to predict and determine a target control scheme based on the predicted energy consumption curve, a first constraint, and a second constraint using a load transfer model. When the target control scheme is executed, the curve formed by the load transfer volume generated within the industrial park fits the predicted energy consumption curve, the energy consumption change characterization parameter satisfies the first constraint, and the energy consumption cost characterization parameter satisfies the second constraint. The energy consumption change characterization parameter is used to quantify the energy consumption change within the industrial park; the energy consumption cost characterization parameter is used to quantify the energy consumption cost within the industrial park.
[0122] The execution module is used to execute the target control plan within a unit of time in the industrial park.
[0123] In one embodiment, the processing module 606 is used to determine the objective function to be optimized; the objective function includes an energy consumption change quantification function and an energy consumption cost quantification function; the energy consumption change quantification function is used to quantify and calculate the energy consumption change characterization parameters; the energy consumption cost quantification function is used to quantify and calculate the energy consumption cost characterization parameters; through the load transfer model, the control scheme is iteratively searched in the direction of fitting the load transfer curve and the predicted energy consumption curve, and in the direction of optimizing the objective function; for each searched control scheme, the parameter values of the energy consumption change characterization parameters and the energy consumption cost characterization parameters in the objective function are predicted to be executed, so as to determine the value of the objective function under the control scheme; when the load transfer curve is fitted to the predicted energy consumption curve, the control scheme that makes the objective function obtain the optimal value is taken as the target control scheme.
[0124] In one embodiment, the processing module 606 is configured to, for each searched control scheme, predict the ratio of the total energy consumption change after implementing the control scheme to the original total energy consumption, thereby obtaining the parameter value of the energy consumption change characterization parameter after implementing the control scheme; the total energy consumption change is the sum of the predicted energy consumption changes in each time period after implementing the control scheme; the original total energy consumption is the sum of the original energy consumption in each time period when the control scheme is not implemented; for each searched control scheme, the processing module 606 is configured to, predict the ratio between the unit time energy cost after implementing the control scheme and the original unit time energy cost, thereby obtaining the parameter value of the energy cost characterization parameter after implementing the control scheme; the original unit time energy cost is the unit time energy cost when the control scheme is not implemented.
[0125] In one embodiment, the predicted energy consumption curve includes peak-hour consumption, normal-hour consumption, and off-hour consumption; the processing module 606 is used to predict the load transfer volume generated in the industrial park when the control scheme is executed for each searched control scheme, and generate a load transfer volume curve based on the load transfer volume; the peak-hour, normal-hour, and off-hour periods in the load transfer volume curve are respectively fitted and approximated with the peak-hour, normal-hour, and off-hour periods of the predicted energy consumption curve, so that the load transfer volume and the predicted consumption volume in the same period match.
[0126] In one embodiment, the prediction module 602 is used to determine the meteorological data, time type, and historical energy consumption corresponding to a unit time in the industrial park; to perform nonlinear mapping processing on the meteorological data, time type, and historical energy consumption through an energy prediction model to obtain the predicted energy consumption output by the energy prediction model; the prediction module 602 is also used to smooth the energy-related data of the industrial park to obtain sample energy-related data; the energy-related data refers to data related to the consumption of green energy; and to train and optimize the radial basis function neural network based on the sample energy data to obtain the energy prediction model.
[0127] In one embodiment, the processing module 606 is used to upload the actual energy consumption of the industrial park per unit time to the first blockchain; when an energy transmission request is received and the energy consumption of the industrial park is saturated at the current time, energy transmission is performed on the initiating object of the energy transmission request; the initiating object is an authorized node object in the blockchain.
[0128] In one embodiment, the processing module 606 is used to perform cross-regional virtual energy transmission based on preset rules through the interaction between multiple node objects in the second blockchain; wherein the multiple node objects include energy issuers and energy operators; the interaction results recorded in the second blockchain are sent to the target platform, and the interaction results are used to indicate the energy issuance and operation status in the second blockchain; the issuance and operation authorization records generated on the target platform are uploaded to the second blockchain, and the issuance and operation authorization records are used to indicate the issuance and operation permissions possessed by the node objects in the second blockchain.
[0129] In one embodiment, the processing module 606 is used to determine the load change of the current period compared to the previous period during the execution of the target control scheme; if the load change is less than the change threshold, the consumption of the first energy source is reduced firstly; the first energy source is non-green energy; if the load change is greater than the change threshold, the consumption of the second energy source is increased firstly; the second energy source is green energy.
[0130] Each module in the aforementioned energy dispatching and processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.
[0131] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores load balancing models. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements an energy dispatching method.
[0132] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an energy scheduling processing method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.
[0133] Those skilled in the art will understand that Figure 7 or Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0134] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.
[0135] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.
[0136] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.
[0137] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.
[0138] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0139] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0140] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. An energy dispatching and processing method, characterized in that, The method includes: The amount of green energy consumed per unit time in the industrial park is predicted to obtain the predicted consumption amount. Determine the predicted energy consumption curve based on the predicted consumption amount; Based on the predicted energy consumption curve, the first constraint, and the second constraint, the target control scheme is predicted and determined using the load transfer model. The steps for predicting and determining the target control scheme using the load transfer model, based on the predicted energy consumption curve, the first constraint, and the second constraint, include: The objective function to be optimized is determined; the objective function includes an energy consumption change quantification function and an energy consumption cost quantification function; the energy consumption change quantification function is used to quantify and calculate the energy consumption change characterization parameters; the energy consumption cost quantification function is used to quantify and calculate the energy consumption cost characterization parameters. Using the load transfer model, a control scheme is iteratively searched in the direction of fitting the load transfer curve and the predicted energy consumption curve, and in the direction of optimizing the objective function. For each searched control scheme, the parameter values of the energy consumption change characterization parameter and the energy consumption cost characterization parameter in the objective function are predicted when the control scheme is executed, so as to determine the value of the objective function under the control scheme. When the load transfer curve is fitted to the predicted energy consumption curve, the control scheme that optimizes the objective function is taken as the target control scheme. When the target control scheme is executed, the load transfer curve generated in the industrial park is fitted with the predicted energy consumption curve, the energy consumption change characterization parameter satisfies the first constraint condition, and the energy consumption cost characterization parameter satisfies the second constraint condition; the energy consumption change characterization parameter is used to quantify the energy consumption change in the industrial park; the energy consumption cost characterization parameter is used to quantify the energy consumption cost in the industrial park. Wherein, for each searched control scheme, when predicting that the control scheme will be executed, the parameter values of the energy consumption change characterization parameter and the energy consumption cost characterization parameter in the objective function include: For each searched control scheme, the ratio of the total energy consumption change after implementing the control scheme to the original total energy consumption is predicted, thus obtaining the parameter value of the energy consumption change characterization parameter after implementing the control scheme; the total energy consumption change is the sum of the predicted energy consumption changes in each time period after implementing the control scheme; the original total energy consumption is the sum of the original energy consumption in each time period when the control scheme was not implemented; For each searched control scheme, the ratio between the energy cost per unit time after implementing the control scheme and the original energy cost per unit time is predicted to obtain the parameter value of the energy cost characterization parameter after implementing the control scheme; the original energy cost per unit time is the energy cost per unit time when the control scheme is not implemented. The target control scheme is executed within a unit of time in the industrial park.
2. The method according to claim 1, characterized in that, The predicted energy consumption curve includes peak-hour consumption, normal-hour consumption, and off-peak-hour consumption; the step of fitting the load transfer curve with the predicted energy consumption curve includes: For each searched control scheme, predict the load transfer amount generated in the industrial park when the control scheme is executed, and generate the load transfer amount curve based on the load transfer amount; The peak, normal, and low periods in the load transfer curve are respectively fitted and approximated with the peak, normal, and low periods in the predicted energy consumption curve, so that the load transfer and predicted consumption in the same period are matched.
3. The method according to claim 1, characterized in that, The prediction of the green energy consumption per unit time in the industrial park yields the following predicted consumption amounts: Determine the meteorological data, time type, and historical energy consumption corresponding to each unit of time in the industrial park; The predicted energy consumption is obtained by performing nonlinear mapping processing on the meteorological data, time type and historical energy consumption through the energy prediction model. The training steps for the energy prediction model include: The energy-related data of the industrial park are smoothed to obtain sample energy-related data; the energy-related data refers to data related to the consumption of green energy. The radial basis function neural network is trained and optimized based on the energy-related sample data to obtain an energy prediction model.
4. The method according to claim 1, characterized in that, The method further includes: The actual energy consumption of the industrial park per unit time is uploaded to the first blockchain; Upon receiving an energy transmission request and when the energy consumption capacity of the industrial park is saturated for the current period, energy transmission is performed to the initiator of the energy transmission request; the initiator is an authorized node object in the blockchain.
5. The method according to claim 1, characterized in that, The method further includes: Based on preset rules, cross-regional virtual energy transmission is achieved through the interaction between multiple node objects in the second blockchain; The plurality of node objects include energy issuers and energy operators; the interaction results recorded in the second blockchain are sent to the target platform, and the interaction results are used to indicate the energy issuance and operation status in the second blockchain; the issuance and operation authorization records generated on the target platform are uploaded to the second blockchain, and the issuance and operation authorization records are used to indicate the issuance and operation permissions of the node objects in the second blockchain.
6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: During the execution of the target control plan, the load change in the current period compared to the previous period is determined; If the load change is less than the change threshold, priority will be given to reducing the consumption of the first energy source; the first energy source is a non-green energy source. If the load change exceeds the change threshold, priority will be given to increasing the consumption of the second energy source; the second energy source is green energy.
7. An energy dispatching and processing device, characterized in that, The device includes: The prediction module is used to predict the amount of green energy consumed by the industrial park per unit time, and obtain the predicted consumption amount. The determination module is used to determine the predicted energy consumption curve based on the predicted consumption amount; The processing module is used to predict and determine the target control scheme based on the predicted energy consumption curve, the first constraint, and the second constraint using the load transfer model. The processing module is further configured to: determine the objective function to be optimized; the objective function includes an energy consumption change quantification function and an energy consumption cost quantification function; the energy consumption change quantification function is used to quantify and calculate the energy consumption change characterization parameters; the energy consumption cost quantification function is used to quantify and calculate the energy consumption cost characterization parameters; Using the load transfer model, a control scheme is iteratively searched in the direction of fitting the load transfer curve and the predicted energy consumption curve, and in the direction of optimizing the objective function. For each searched control scheme, the parameter values of the energy consumption change characterization parameter and the energy consumption cost characterization parameter in the objective function are predicted when the control scheme is executed, so as to determine the value of the objective function under the control scheme. When the load transfer curve is fitted to the predicted energy consumption curve, the control scheme that optimizes the objective function is taken as the target control scheme. When the target control scheme is executed, the load transfer curve generated in the industrial park is fitted with the predicted energy consumption curve, the energy consumption change characterization parameter satisfies the first constraint condition, and the energy consumption cost characterization parameter satisfies the second constraint condition; the energy consumption change characterization parameter is used to quantify the energy consumption change in the industrial park; the energy consumption cost characterization parameter is used to quantify the energy consumption cost in the industrial park. The processing module is further configured to: for each searched control scheme, predict the ratio of the total energy consumption change after implementing the control scheme to the original total energy consumption, and obtain the parameter value of the energy consumption change characterization parameter after implementing the control scheme; the total energy consumption change is the sum of the predicted energy consumption changes in each time period after implementing the control scheme; the original total energy consumption is the sum of the original energy consumption in each time period when the control scheme was not implemented; For each found control scheme, the ratio of the energy cost per unit time after implementing the control scheme to the original energy cost per unit time is predicted, thus obtaining the parameter value of the energy cost characterizing parameter after implementing the control scheme; the original energy cost per unit time is the energy cost per unit time without implementing the control scheme. The execution module is used to execute the target control scheme in the industrial park within a unit of time.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.