Power distribution network multi-target scheduling method, system, equipment and medium

Abstract

The invention discloses a power distribution network multi-target scheduling method, system and device and a medium, and the method comprises the steps: carrying out the data collection processing of a distributed energy unit, and obtaining original data; performing preprocessing and feature extraction processing on the original data to obtain feature data; performing multi-objective optimization processing on the characteristic data according to an economic cost optimization objective, a carbon emission optimization objective and a system stability optimization objective to obtain an optimization model; solving the optimization model according to the deep learning model to obtain a scheduling strategy; adjusting the distributed energy unit according to the scheduling strategy, and controlling the distributed energy unit to access the power distribution network; and monitoring the operation state of the power distribution network to obtain feedback information, and returning the feedback information to the deep learning model to iteratively update the scheduling strategy. The embodiment of the invention can improve the dispatching efficiency of the power distribution network, and can be widely applied to the technical field of power grid dispatching.

Description

Technical Field

[0001] The present application relates to the technical field of power grid dispatching, and in particular to a distribution network multi-objective dispatching method, system, equipment and medium. Background Art

[0002] With the development of renewable energy technology and the construction of smart grids, how to efficiently and reliably integrate distributed generation resources, such as wind and solar energy, into distribution networks has become an important issue. In related technologies, scheduling methods often fail to meet multiple goals, such as economy, reliability, and environmental sustainability, resulting in inflexible operation of the power system and affecting the efficiency of resource scheduling.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a distribution network multi-objective scheduling method, system, equipment and medium, which can improve the scheduling efficiency.

[0005] To achieve the above object, an embodiment of the present application provides a multi-objective scheduling method for a distribution network, the method comprising:

[0006] Collect and process data of distributed energy units to obtain original data;

[0007] Preprocessing and feature extraction are performed on the original data to obtain feature data;

[0008] Performing multi-objective optimization processing on the characteristic data according to an economic cost optimization target, a carbon emission optimization target, and a system stability optimization target to obtain an optimization model;

[0009] Solving the optimization model according to the deep learning model to obtain a scheduling strategy;

[0010] Adjusting the distributed energy unit according to the scheduling strategy, and controlling the distributed energy unit to access the distribution network;

[0011] The operating status of the distribution network is monitored and processed to obtain feedback information, and the feedback information is returned to the deep learning model to iteratively update the scheduling strategy.

[0012] In some embodiments, performing multi-objective optimization processing on the characteristic data according to the economic cost optimization target, the carbon emission optimization target and the system stability optimization target to obtain the optimization model comprises the following steps:

[0013] Performing function modeling processing on the characteristic data according to the economic cost optimization objective to obtain an economic cost objective function;

[0014] Performing function modeling processing on the characteristic data according to the carbon emission optimization target to obtain a carbon emission target function;

[0015] Performing function modeling processing on the characteristic data according to the system stability optimization objective to obtain a system stability objective function;

[0016] The economic cost objective function, the carbon emission objective function and the system stability objective function are optimized according to a multi-objective evolutionary algorithm to obtain the optimization model.

[0017] In some embodiments, performing function modeling processing on the characteristic data according to the economic cost optimization objective to obtain an economic cost objective function comprises the following steps:

[0018] Determine the power generation of the distributed energy unit within the scheduling period according to the characteristic data;

[0019] The power generation power and the cost coefficient are calculated and processed according to the economic cost optimization target to obtain the economic cost target function.

[0020] In some embodiments, performing function modeling on the characteristic data according to the carbon emission optimization target to obtain a carbon emission target function comprises the following steps:

[0021] Determine the power generation of the distributed energy unit within the scheduling period according to the characteristic data;

[0022] The power generation power and the carbon emission coefficient are calculated and processed according to the economic cost optimization target to obtain the carbon emission target function.

[0023] In some embodiments, performing function modeling processing on the characteristic data according to the system stability optimization target to obtain a system stability target function includes the following steps:

[0024] Determine the power generation of the distributed energy unit within the scheduling period according to the characteristic data;

[0025] Calculate the average power of the distributed energy unit according to the generated power;

[0026] The generated power and the average power are calculated and processed according to the system stability optimization target to obtain the system stability target function.

[0027] In some embodiments, before solving the optimization model according to the deep learning model to obtain the scheduling strategy, the method further includes pre-training the deep learning model, specifically including the following steps:

[0028] Get historical scheduling data;

[0029] Tuning the hyperparameters of the deep learning model according to the Bayesian optimization algorithm to obtain a training model;

[0030] The model parameters of the training model are subjected to supervised learning processing according to the historical scheduling data to obtain the trained deep learning model.

[0031] In some embodiments, the monitoring and processing of the operating status of the distribution network to obtain feedback information comprises the following steps:

[0032] Performing energy storage dispatching control and microgrid coordination processing on the distribution network according to the dispatching strategy to obtain a dispatching distribution network;

[0033] Fault detection and environmental assessment are performed on the operating status of the dispatching distribution network to obtain the feedback information.

[0034] To achieve the above object, another aspect of the embodiment of the present application provides a distribution network multi-objective dispatching system, the system comprising:

[0035] A data collection module is used to collect and process data from distributed energy units to obtain original data;

[0036] A preprocessing and feature extraction module, used for preprocessing and feature extraction of the raw data to obtain feature data;

[0037] A multi-objective optimization module, used to perform multi-objective optimization processing on the characteristic data according to an economic cost optimization objective, a carbon emission optimization objective and a system stability optimization objective to obtain an optimization model;

[0038] A deep learning optimization module, used to solve the optimization model according to the deep learning model to obtain a scheduling strategy;

[0039] A scheduling execution module, used to adjust the distributed energy unit according to the scheduling strategy and control the distributed energy unit to access the distribution network;

[0040] A monitoring and feedback module is used to monitor the operating status of the distribution network to obtain feedback information, and return the feedback information to the deep learning model to iteratively update the scheduling strategy.

[0041] In some embodiments, the multi-objective optimization module is used to perform multi-objective optimization processing on the characteristic data according to the economic cost optimization target, the carbon emission optimization target and the system stability optimization target to obtain an optimization model, and includes the following units:

[0042] The first unit is used to perform function modeling processing on the characteristic data according to the economic cost optimization target to obtain an economic cost target function;

[0043] The second unit is used to perform function modeling processing on the characteristic data according to the carbon emission optimization target to obtain a carbon emission target function;

[0044] The third unit is used to perform function modeling processing on the characteristic data according to the system stability optimization target to obtain a system stability target function;

[0045] The fourth unit is used to optimize the economic cost objective function, the carbon emission objective function and the system stability objective function according to a multi-objective evolutionary algorithm to obtain the optimization model.

[0046] In some embodiments, the first unit, used to perform function modeling processing on the feature data according to the economic cost optimization objective to obtain an economic cost objective function, includes the following subunits:

[0047] A first subunit, configured to determine the power generation of the distributed energy unit within a scheduling period according to the characteristic data;

[0048] The second subunit is used to calculate and process the power generation power and the cost coefficient according to the economic cost optimization target to obtain the economic cost target function.

[0049] In some embodiments, the second unit, used to perform function modeling processing on the characteristic data according to the carbon emission optimization target to obtain a carbon emission target function, includes the following subunits:

[0050] A third subunit is used to determine the power generation of the distributed energy unit within the scheduling period according to the characteristic data;

[0051] The fourth subunit is used to calculate and process the power generation power and the carbon emission coefficient according to the economic cost optimization target to obtain the carbon emission target function.

[0052] In some embodiments, the third unit is used to perform function modeling processing on the characteristic data according to the system stability optimization target to obtain a system stability target function, and includes the following subunits:

[0053] A fifth subunit, configured to determine the power generation of the distributed energy unit within a scheduling period according to the characteristic data;

[0054] A sixth subunit, configured to calculate the average power of the distributed energy unit according to the generated power;

[0055] The seventh subunit is used to calculate and process the generated power and the average power according to the system stability optimization target to obtain the system stability target function.

[0056] In some embodiments, before the deep learning optimization module is used to solve the optimization model according to the deep learning model to obtain the scheduling strategy, the system also includes a model training module, which specifically includes the following units:

[0057] The fifth unit is used to obtain historical scheduling data;

[0058] The sixth unit is used to tune the hyperparameters of the deep learning model according to the Bayesian optimization algorithm to obtain a training model;

[0059] The seventh unit is used to perform supervised learning processing on the model parameters of the training model according to the historical scheduling data to obtain the trained deep learning model.

[0060] In some embodiments, the monitoring and feedback module is used to monitor the operating status of the distribution network to obtain feedback information, and includes the following units:

[0061] An eighth unit is used to perform energy storage dispatching control and microgrid coordination processing on the distribution network according to the dispatching strategy to obtain a dispatching distribution network;

[0062] The ninth unit is used to perform fault detection and environmental assessment on the operating status of the dispatching distribution network to obtain the feedback information.

[0063] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned method when executing the computer program.

[0064] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0065] The embodiments of the present application include at least the following beneficial effects: The present application provides a distribution network multi-objective scheduling method, system, equipment and medium, which performs multi-objective optimization processing on feature data according to the economic cost optimization target, carbon emission optimization target and system stability optimization target to obtain an optimization model, which can simultaneously consider the three key aspects of economic cost, carbon emission and system stability to achieve simultaneous optimization of multiple objectives; in addition, the scheme solves the optimization model according to the deep learning model to obtain a scheduling strategy, which can automatically adjust the model parameters, reduce manual intervention, and improve the efficiency and accuracy of scheduling decisions; furthermore, the scheme obtains feedback information by monitoring the operating status of the distribution network, and returns the feedback information to the deep learning model to iteratively update the scheduling strategy, which can adjust the scheduling strategy according to the feedback to enable the system to continue to operate efficiently, thereby improving the stability and safety of the distribution network operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a flow chart of a distribution network multi-objective scheduling method provided by an embodiment of the present application;

[0067] Figure 2 yes Figure 1 Flow chart of step S103 in FIG.

[0068] Figure 3 yes Figure 2 Flow chart of step S201 in FIG.

[0069] Figure 4 yes Figure 2 Flow chart of step S202 in FIG.

[0070] Figure 5 yes Figure 2 Flow chart of step S203 in FIG.

[0071] Figure 6 This is a flowchart of using a Bayesian optimization algorithm to find optimal hyperparameter settings provided by an embodiment of the present application;

[0072] Figure 7 yes Figure 1 Flow chart of step S106 in FIG.

[0073] Figure 8 It is a framework diagram of a distributed new energy distribution network multi-objective dispatching system provided in an embodiment of the present application;

[0074] Fig. 9 It is a structural schematic diagram of a distribution network multi-objective dispatching system provided in an embodiment of the present application;

[0075] Fig.10 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of systems and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0077] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0078] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0079] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0080] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0081] 1) Deep learning (DL) refers specifically to machine learning based on deep neural network models and methods. It is developed based on statistical machine learning, artificial neural network and other algorithmic models, combined with the development of contemporary big data and large computing power. Deep learning enables machines to imitate human activities such as seeing, hearing and thinking, solves many complex pattern recognition problems, and can be applied in computer vision, natural language processing, multimodal data analysis, scientific exploration and other fields.

[0082] 2) Artificial Intelligence (AI) is an important driving force for the new round of scientific and technological revolution and industrial transformation. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. It attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial Intelligence is a very broad science, including robots, speech recognition, image recognition, natural language processing, expert systems, machine learning, computer vision, etc.

[0083] 3) Smart distribution network refers to a distribution network management system built using modern information technology. It uses computer technology, sensor technology, information transmission technology, and automation control technology to achieve intelligent information processing and automated management and control effects in power dispatching.

[0084] With the development of renewable energy technology and the construction of smart grids, how to efficiently and reliably integrate distributed generation resources (such as wind power and solar energy) into distribution networks has become an important issue. Traditional scheduling methods often find it difficult to simultaneously meet multiple goals such as economy, reliability, and environmental sustainability. In related technologies, there is a multi-objective optimization scheduling method for an integrated energy distribution network, comprising the following steps: establishing a coordinated scheduling model for an integrated energy system in a park; establishing a multi-objective optimization scheduling model for a distribution network system; solving the multi-objective optimization scheduling model of the distribution network system in combination with a particle swarm algorithm to obtain the optimal solution; solving the overall model based on the target cascade analysis (ATC) method. The multi-objective optimization scheduling method in the above method has the following shortcomings: it is not effective in dealing with complex, discrete, or high-dimensional optimization problems, especially in the actual operation of the power system, it may be inflexible or inefficient.

[0085] In view of this, a multi-objective scheduling method, system, device and medium for a distribution network are provided in an embodiment of the present application. The scheme performs multi-objective optimization processing on characteristic data according to the economic cost optimization target, the carbon emission optimization target and the system stability optimization target to obtain an optimization model, which can simultaneously consider the three key aspects of economic cost, carbon emission and system stability to achieve simultaneous optimization of multiple objectives; in addition, the scheme solves the optimization model according to the deep learning model to obtain a scheduling strategy, which can automatically adjust the model parameters, reduce manual intervention, and improve the efficiency and accuracy of scheduling decisions; furthermore, the scheme obtains feedback information by monitoring the operating status of the distribution network, and returns the feedback information to the deep learning model to iteratively update the scheduling strategy, and can adjust the scheduling strategy according to the feedback to enable the system to continue to operate efficiently, thereby improving the stability and safety of the distribution network operation.

[0086] A distribution network multi-objective scheduling method provided in an embodiment of the present application relates to the field of power grid scheduling technology. A distribution network multi-objective scheduling method provided in an embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements a distribution network multi-objective scheduling method, etc., but is not limited to the above forms.

[0087] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0088] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0089] Figure 1 is an optional flow chart of a distribution network multi-objective scheduling method provided in an embodiment of the present application. Figure 1The method may include but is not limited to steps S101 to S106.

[0090] Step S101, collecting and processing data of distributed energy units to obtain original data;

[0091] Step S102, preprocessing and feature extraction processing are performed on the original data to obtain feature data;

[0092] Step S103, performing multi-objective optimization processing on the characteristic data according to the economic cost optimization target, the carbon emission optimization target and the system stability optimization target to obtain an optimization model;

[0093] Step S104, solving the optimization model according to the deep learning model to obtain a scheduling strategy;

[0094] Step S105, adjusting the distributed energy unit according to the scheduling strategy, and controlling the distributed energy unit to access the distribution network;

[0095] Step S106: Monitor the operating status of the distribution network to obtain feedback information, and return the feedback information to the deep learning model to iteratively update the scheduling strategy.

[0096] In the steps S101 to S106 shown in the embodiment of the present application, raw data is obtained by collecting and processing data of distributed energy units, wherein the raw data includes real-time power generation data, load demand information and other data of distributed energy units. Then, the raw data is preprocessed and feature extracted to obtain feature data, and the collected data can be cleaned and normalized, and key features can be extracted for subsequent analysis. In the embodiment of the present application, the feature data is multi-objective optimized according to the economic cost optimization target, the carbon emission optimization target and the system stability optimization target to obtain an optimization model, thereby establishing a mathematical model including economic cost, carbon emission and system stability. Then, the optimization model is solved according to the deep learning model to obtain a scheduling strategy, and a deep neural network can be used to solve the multi-objective optimization problem and output the optimal scheduling strategy. The embodiment of the present application also adjusts the distributed energy unit according to the scheduling strategy, and controls the distributed energy unit to access the distribution network, and can adjust the power generation plan of each distributed energy unit according to the scheduling strategy, and control its access to the distribution network. Finally, the operating status of the distribution network is monitored and processed to obtain feedback information, which is then returned to the deep learning model to iteratively update the scheduling strategy. It can monitor the operating status of the system in real time and collect scheduling effect feedback for the model to iteratively update the scheduling strategy.

[0097] In step S101 of some embodiments, data collection and processing is performed on the distributed energy units to obtain raw data. The raw data includes information such as meter data, power generation, load demand, weather conditions, etc., which can be obtained through sensor networks and communication technologies, etc., to ensure the timeliness and accuracy of the data. It can also be obtained through other methods such as from a database, and the database is used to store and manage historical operation data, including past power generation, consumption patterns, equipment status, etc., and the database is regularly updated to optimize the data retrieval and analysis process, but is not limited thereto.

[0098] In step S102 of some embodiments, the raw data is preprocessed and feature extracted to obtain feature data. In an embodiment of the present application, the collected raw data is cleaned, and methods such as median filtering, Kalman filtering, etc. can be used to remove outliers and noise from the raw data, and the cleaned data is converted into a standard format to eliminate the influence of different dimensions. The conversion method can use methods such as minimum-maximum standardization or Z-score standardization. Then, key features are extracted from the raw data through statistical analysis, frequency domain analysis and other techniques, and deeper insights are provided by analyzing the time series correlation and spatial distribution characteristics of the data.

[0099] See also Figure 2 In step S103 of some embodiments, the multi-objective optimization processing of the characteristic data according to the economic cost optimization target, the carbon emission optimization target and the system stability optimization target to obtain the optimization model includes the following steps:

[0100] Step S201, performing function modeling processing on the characteristic data according to the economic cost optimization target to obtain an economic cost target function;

[0101] Step S202, performing function modeling processing on the characteristic data according to the carbon emission optimization target to obtain a carbon emission target function;

[0102] Step S203, performing function modeling processing on the characteristic data according to the system stability optimization target to obtain a system stability target function;

[0103] Step S204: optimizing the economic cost objective function, the carbon emission objective function and the system stability objective function according to a multi-objective evolutionary algorithm to obtain the optimization model.

[0104] In the embodiment of the present application, the characteristic data is subjected to multi-objective optimization processing according to the economic cost optimization target, the carbon emission optimization target and the system stability optimization target, respectively, and the objective function of economic cost, carbon emission and system stability is constructed, and then the optimization model is determined by analyzing the trade-off relationship between different targets according to the multi-objective evolutionary algorithm. It can be imagined that the embodiment of the present application can verify the accuracy of the optimization model and make necessary adjustments by comparing and analyzing the simulation data and historical data. The embodiment of the present application can directly solve the optimization model, specifically by clarifying the economic cost, environmental impact, and system stability optimization targets, and setting corresponding operating constraints, including the upper and lower limits of power generation capacity, grid load capacity, and carbon emission standards, using the multi-objective evolutionary algorithm to solve the Pareto frontier, by determining the trade-off relationship between each target, find the Pareto optimal solution set, which is a set of Pareto optimal solutions in a multi-objective problem, representing the best trade-off between multiple targets. According to the information provided by the Pareto solution set, combined with the forecast data and real-time feedback, it can provide support for the final scheduling decision. The embodiment of the present application achieves simultaneous optimization of multiple objectives by simultaneously considering three key aspects: economic cost, carbon emissions, and system stability, thereby improving the stability and safety of distribution network operation.

[0105] See also Figure 3 In step S201 of some embodiments, performing function modeling on the characteristic data according to the economic cost optimization objective to obtain an economic cost objective function includes the following steps:

[0106] Step S301, determining the power generation of the distributed energy unit within a scheduling period according to the characteristic data;

[0107] Step S302: Calculate and process the power generation and cost coefficient according to the economic cost optimization objective to obtain the economic cost objective function.

[0108] In the embodiment of the present application, an economic cost objective function is established according to the economic cost optimization target, wherein the power generation of the distributed energy unit in the scheduling period is determined according to the characteristic data, and the power generation of each distributed energy unit is calculated in combination with its cost coefficient to obtain the economic cost objective function, wherein the expression of the economic cost objective function is as follows:

[0109]

[0110] In the formula, C is the total cost, T is the duration of the dispatch cycle, N is the total number of distributed energy units, t and i are independent variables, and P i,t is the power generation of the i-th energy unit at time t, a i , b i , ci is the cost coefficient of the i-th energy unit, and Δt is the time interval. The embodiment of the present application can provide a data basis for subsequent multi-objective optimization by constructing an economic cost objective function, thereby performing multi-objective scheduling of the distribution network according to the economic cost, thereby reducing the economic cost of scheduling.

[0111] See also Figure 4 In step S202 of some embodiments, the function modeling process is performed on the characteristic data according to the carbon emission optimization target to obtain the carbon emission target function, including the following steps:

[0112] Step S401, determining the power generation of the distributed energy unit within a scheduling period according to the characteristic data;

[0113] Step S402: Calculate and process the power generation and carbon emission coefficient according to the economic cost optimization target to obtain the carbon emission target function.

[0114] In the embodiment of the present application, a carbon placement objective function is established according to the carbon emission optimization target, the power generation of the distributed energy unit in the scheduling period is determined according to the characteristic data, and the obtained power generation power is calculated with the carbon emission coefficient per unit power of each energy unit to obtain the carbon emission objective function, wherein the expression of the carbon emission objective function is as follows:

[0115]

[0116] Where E is the total carbon emissions, T is the duration of the dispatch cycle, N is the total number of distributed energy units, t and i are independent variables, and P i,t is the power generation of the i-th energy unit at time t, d i is the carbon emission coefficient per unit power of the i-th energy unit, and Δt is the time interval. The embodiment of the present application performs function modeling on the characteristic data according to the carbon emission optimization target to obtain the carbon emission target function, which can provide a data basis for subsequent multi-objective optimization, thereby performing multi-objective scheduling on the distribution network according to carbon emissions, reducing the carbon emissions of the system and improving the degree of environmental protection.

[0117] See also Figure 5 In step S203 of some embodiments, performing function modeling on the characteristic data according to the system stability optimization objective to obtain a system stability objective function includes the following steps:

[0118] Step S501, determining the power generation of the distributed energy unit within a scheduling period according to the characteristic data;

[0119] Step S502, calculating the average power of the distributed energy unit according to the generated power;

[0120] Step S503: Calculate and process the generated power and the average power according to the system stability optimization target to obtain the system stability target function.

[0121] In the embodiment of the present application, a system stability objective function is established according to the system stability optimization target, the power generation of each distributed energy unit in the scheduling period is determined according to the characteristic data, and the average power generation of each distributed energy unit in the scheduling period is calculated according to the calculated power generation, so as to obtain the system stability objective function by calculating and processing according to the power generation and the average power, wherein the expression of the system stability objective function is as follows:

[0122]

[0123] In the formula, S is the system stability index, T is the duration of the dispatch cycle, N is the total number of distributed energy units, t and i are independent variables, and P i,t is the power generation of the i-th energy unit at time t, P avg,i is the average power generation of the i-th energy unit, P rated The embodiment of the present application performs function modeling on the characteristic data according to the system stability optimization objective to obtain the system stability optimization objective function, which can provide a data basis for subsequent multi-objective optimization, thereby performing multi-objective scheduling on the distribution network according to the system stability, thereby improving the scheduling efficiency of the system.

[0124] In some embodiments, in step S104, before solving the optimization model according to the deep learning model to obtain the scheduling strategy, the method further includes pre-training the deep learning model, specifically including the following steps:

[0125] Get historical scheduling data;

[0126] Tuning the hyperparameters of the deep learning model according to the Bayesian optimization algorithm to obtain a training model;

[0127] The model parameters of the training model are subjected to supervised learning processing according to the historical scheduling data to obtain the trained deep learning model.

[0128] In the embodiment of the present application, historical scheduling data can be obtained from the database, and the deep learning network can be trained using the historical scheduling data to automatically adjust the model parameters to obtain the training model. At the same time, algorithms such as grid search and Bayesian optimization can be used to find the optimal hyperparameter settings. Specifically, the embodiment of the present application uses the Bayesian optimization algorithm to find the optimal hyperparameter settings. Please refer to Figure 6 , the embodiment of the present application initializes the probability model of the hyperparameter space by using a Bayesian network, and then uses the posterior distribution of the probability model to select new hyperparameter points, then trains the model on the selected hyperparameters, and evaluates its performance on the validation set, and updates the training model by using the new hyperparameters and the corresponding performance results, and repeats the above steps until the stopping criterion is met. It is conceivable that the embodiment of the present application can set the number of cycles as the stopping criterion, such as stopping the training after reaching fifty times, and using the model finally obtained by training as the deep learning model that has completed the training. In the embodiment of the present application, the radial basis function is used as the kernel function in Bayesian optimization. The radial basis function is a special kernel function that defines the similarity between two points in the input space by the distance between them. In the Gaussian process, this distance is usually converted into a similarity value, which determines the correlation between the random variables corresponding to the two points. Among them, the expression of the kernel function is as follows:

[0129]

[0130] Where k(x,x′) represents the radial basis function value, σ 2 represents the variance of the signal, l represents the length scale, x and x ′ Respectively represent any two points in the input space. In the embodiment of the present application, by combining deep learning and Bayesian optimization algorithm, the system can automatically adjust the model parameters, reduce manual intervention, and improve the efficiency and accuracy of scheduling decisions.

[0131] In step S104 of some embodiments, the optimization model is solved according to the deep learning model to obtain a scheduling strategy. In an embodiment of the present application, a deep learning model is obtained by designing a deep neural network structure, specifically selecting a suitable activation function, number of hidden layers and number of nodes, and using historical data for supervised learning, and using a deep learning framework TensorFlow or PyTorch to implement model training; by introducing techniques to prevent overfitting, including Dropout, weight regularization, and early stopping strategies, a deep learning model is constructed. The embodiment of the present application uses Bayesian optimization, grid search and other methods to find the optimal hyperparameter settings, including learning rate, batch size, and number of iterations, and evaluates the performance of different hyperparameter combinations through cross-validation, selects the optimal model configuration, and then deploys the trained model to the production environment, processes new data input in real time to solve the optimization model, and can continuously adjust the model output according to real-time data to optimize scheduling decisions.

[0132] In step S105 of some embodiments, the distributed energy unit is adjusted and processed according to the dispatching strategy, and the distributed energy unit is controlled to access the distribution network. In the embodiment of the present application, the dispatching strategy is obtained according to the output of the deep learning model, and a specific dispatching instruction is generated. The dispatching instruction is distributed to each energy unit through the automation system, the distributed energy unit is controlled to access the distribution network, and the execution of the dispatching instruction is monitored to ensure the correct implementation of the dispatching strategy. It is conceivable that the embodiment of the present application can also make real-time adjustments according to the actual execution situation to optimize the dispatching strategy.

[0133] See also Figure 7 In step S106 of some embodiments, the monitoring and processing of the operating status of the distribution network to obtain feedback information includes the following steps:

[0134] Step S701, performing energy storage dispatching control and microgrid coordination processing on the distribution network according to the dispatching strategy to obtain a dispatching distribution network;

[0135] Step S702: Perform fault detection and environmental assessment on the operating status of the dispatching distribution network to obtain the feedback information.

[0136] In an embodiment of the present application, the charging and discharging meters of each energy storage device in the distribution network are controlled according to the dispatching strategy to balance the supply and demand relationship, optimize energy use and adjust the grid load, and reduce energy waste. Then monitor the operating status of the power grid, detect and prevent power grid failures and anomalies in real time, quickly identify abnormal events in the system by using fault detection algorithms, and evaluate the impact of the dispatching strategy on the environment. Use models and sensor data to monitor the environmental impact of the operation of renewable energy facilities, ensure that all operations are carried out within acceptable environmental standards, and obtain final feedback information, so as to adjust and optimize the dispatching strategy based on the feedback information. The embodiment of the present application can collect system operation data in real time, and adjust the dispatching strategy based on feedback to ensure that the system continues to operate efficiently; the embodiment of the present application not only improves the ability to handle complex problems, but also enables the system to learn from historical data and continuously optimize its dispatching strategy.

[0137] The following is a detailed description of the embodiments of the present invention with reference to specific application examples:

[0138] The embodiments of the present application can be applied to the dispatching scenarios of distribution networks. By collecting a large amount of historical and real-time data from the data collection module, data cleaning technology and data normalization can be used to improve data quality, and feature extraction technology can be applied to reduce data dimensions and extract the most influential features. According to the economic cost optimization goal, carbon emission optimization goal and system stability optimization goal, the extracted feature data is subjected to multi-objective optimization processing to establish an optimization model. The optimization model simultaneously considers the three key aspects of economic cost, carbon emission and system stability to achieve simultaneous optimization of multiple objectives. Then, by combining deep learning and Bayesian optimization algorithms, the system can automatically adjust the model parameters to solve the optimization model to obtain a dispatching strategy, thereby improving the efficiency and accuracy of dispatching decisions. Thereby, the distributed energy units are adjusted and processed according to the dispatching strategy, and the distributed energy units are controlled to be connected to the distribution network. Finally, the operating status of the distribution network is monitored and processed to obtain feedback information, and the feedback information is returned to the deep learning model to iteratively update the dispatching strategy. Please refer to Figure 8 , Figure 8It is a framework diagram of a distributed new energy distribution network multi-objective dispatching system provided by an embodiment of the present application. At the data level, it includes a data collection module, a preprocessing and feature extraction module, a real-time data monitoring unit and a historical data integration unit, wherein the data collection module is used to collect real-time power generation data and load demand information of distributed energy units; the preprocessing and feature extraction module is used to clean and normalize the collected data, and extract key features for subsequent analysis; the real-time data monitoring unit is used to collect meter data, power generation, load demand, weather conditions and other information in real time; the historical data integration unit is used to store and manage historical operation data, including past power generation, consumption patterns, equipment status, etc. At the optimization and intelligent decision-making level, it includes a multi-objective optimization module and a deep learning optimization module, wherein the multi-objective optimization module is used to establish a mathematical model including economic costs, carbon emissions and system stability, and the deep learning optimization module is used to solve multi-objective optimization problems using deep neural networks and output the best dispatching strategy. At the execution and management level, it includes a dispatch execution module, a demand response management module, a microgrid coordination module and an energy storage management module. Among them, the dispatch execution module is used to adjust the power generation plan of each distributed energy unit according to the optimization results and control its access to the distribution network. The demand response management module is used to adjust the power consumption behavior of end users through incentives or direct control to adapt to the operation needs of the power grid. This module analyzes the user's electricity usage habits and preferences, designs demand response strategies, and guides users to reduce electricity consumption or transfer to low-load periods during high-load periods of the power grid. The microgrid coordination module is used to coordinate the energy exchange and scheduling between microgrids when there are multiple microgrids in the distribution network. At the monitoring and feedback level, a monitoring and feedback module is provided, in which the monitoring and feedback module is used to monitor the system operation status in real time, collect the scheduling effect and feedback it to the model to iteratively update the scheduling strategy. At the safety and environmental protection level, a safety and protection module and an environmental impact assessment module are provided, in which the safety and protection module is used to monitor the operation status of the power grid, detect and prevent power grid failures and anomalies in real time; the environmental impact assessment module is used to evaluate the impact of the dispatch strategy on the environment, use models and sensor data to monitor the environmental impact of the operation of renewable energy facilities, and ensure that all operations are carried out within acceptable environmental standards. A prediction module is provided at the prediction and coordination level. The prediction module integrates a prediction algorithm based on machine learning to predict future energy output and consumption load. Specifically, the prediction module uses machine learning technology to analyze historical electricity consumption data, identify electricity consumption patterns, and process time series data through an autoregressive integrated moving average model. The expression of the autoregressive integrated moving average model is as follows:

[0139] Y t =c+φ1Y t-1 +φ2Y t-2 +…+φ p Yt-p +e t +θ1e t-1 +θ2e t-2 ++θ q e t-q ;

[0140] Where Y t is the observed value at time t, c is a constant, φ p is the autoregressive coefficient, θ q is the moving average coefficient, e t is the error term.

[0141] See also Fig. 9 The embodiment of the present application further provides a distribution network multi-objective scheduling system, which can implement the above-mentioned distribution network multi-objective scheduling method, and the system includes:

[0142] The data collection module 901 is used to collect and process data of the distributed energy units to obtain raw data;

[0143] A preprocessing and feature extraction module 902 is used to perform preprocessing and feature extraction on the raw data to obtain feature data;

[0144] The multi-objective optimization module 903 is used to perform multi-objective optimization processing on the characteristic data according to the economic cost optimization target, the carbon emission optimization target and the system stability optimization target to obtain an optimization model;

[0145] A deep learning optimization module 904 is used to solve the optimization model according to the deep learning model to obtain a scheduling strategy;

[0146] A scheduling execution module 905, configured to adjust the distributed energy unit according to the scheduling strategy and control the distributed energy unit to access the distribution network;

[0147] The monitoring and feedback module 906 is used to monitor the operating status of the distribution network to obtain feedback information, and return the feedback information to the deep learning model to iteratively update the scheduling strategy.

[0148] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0149] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned distribution network multi-objective scheduling method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0150] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0151] See also Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0152] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0153] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the distribution network multi-objective scheduling method of the embodiment of this application;

[0154] Input / output interface 1003, used to implement information input and output;

[0155] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0156] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0157] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0158] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned distribution network multi-objective scheduling method is implemented.

[0159] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0160] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0161] The embodiments of the present application provide a distribution network multi-objective scheduling method, system, equipment and medium. The scheme performs multi-objective optimization processing on characteristic data according to the economic cost optimization target, carbon emission optimization target and system stability optimization target to obtain an optimization model, which can simultaneously consider the three key aspects of economic cost, carbon emission and system stability to achieve simultaneous optimization of multiple objectives; in addition, the scheme solves the optimization model according to the deep learning model to obtain a scheduling strategy, which can automatically adjust the model parameters, reduce manual intervention, and improve the efficiency and accuracy of scheduling decisions; furthermore, the scheme obtains feedback information by monitoring the operating status of the distribution network, and returns the feedback information to the deep learning model to iteratively update the scheduling strategy, and can adjust the scheduling strategy according to the feedback to enable the system to continue to operate efficiently, thereby improving the stability and safety of the distribution network operation.

[0162] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0163] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0164] The system embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0165] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0166] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0167] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0168] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0169] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0171] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0172] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A multi-objective dispatching method for a distribution network, characterized in that: The method comprises the following steps: Collect and process data of distributed energy units to obtain original data; Preprocessing and feature extraction are performed on the original data to obtain feature data; Performing multi-objective optimization processing on the characteristic data according to an economic cost optimization target, a carbon emission optimization target, and a system stability optimization target to obtain an optimization model; Solving the optimization model according to the deep learning model to obtain a scheduling strategy; Adjusting the distributed energy unit according to the scheduling strategy, and controlling the distributed energy unit to access the distribution network; The operating status of the distribution network is monitored and processed to obtain feedback information, and the feedback information is returned to the deep learning model to iteratively update the scheduling strategy.

2. The method according to claim 1, characterized in that The multi-objective optimization process of the characteristic data is performed according to the economic cost optimization target, the carbon emission optimization target and the system stability optimization target to obtain the optimization model, including the following steps: Performing function modeling processing on the characteristic data according to the economic cost optimization objective to obtain an economic cost objective function; Performing function modeling processing on the characteristic data according to the carbon emission optimization target to obtain a carbon emission target function; Performing function modeling processing on the characteristic data according to the system stability optimization objective to obtain a system stability objective function; The economic cost objective function, the carbon emission objective function and the system stability objective function are optimized according to a multi-objective evolutionary algorithm to obtain the optimization model.

3. The method according to claim 2, characterized in that The step of performing function modeling on the characteristic data according to the economic cost optimization objective to obtain an economic cost objective function comprises the following steps: Determine the power generation of the distributed energy unit within the scheduling period according to the characteristic data; The power generation power and the cost coefficient are calculated and processed according to the economic cost optimization target to obtain the economic cost target function.

4. The method according to claim 2, characterized in that: The step of performing function modeling on the characteristic data according to the carbon emission optimization target to obtain a carbon emission target function comprises the following steps: Determine the power generation of the distributed energy unit within the scheduling period according to the characteristic data; The power generation power and the carbon emission coefficient are calculated and processed according to the economic cost optimization target to obtain the carbon emission target function.

5. The method according to claim 2, characterized in that: The step of performing function modeling on the characteristic data according to the system stability optimization objective to obtain a system stability objective function comprises the following steps: Determine the power generation of the distributed energy unit within the scheduling period according to the characteristic data; Calculate the average power of the distributed energy unit according to the generated power; The generated power and the average power are calculated and processed according to the system stability optimization target to obtain the system stability target function.

6. The method according to any one of claims 1 to 5, characterized in that: Before solving the optimization model according to the deep learning model to obtain the scheduling strategy, the method further includes pre-training the deep learning model, which specifically includes the following steps: Get historical scheduling data; Tuning the hyperparameters of the deep learning model according to the Bayesian optimization algorithm to obtain a training model; The model parameters of the training model are subjected to supervised learning processing according to the historical scheduling data to obtain the trained deep learning model.

7. The method according to any one of claims 1 to 5, characterized in that: The step of monitoring the operating status of the distribution network to obtain feedback information comprises the following steps: Performing energy storage dispatching control and microgrid coordination processing on the distribution network according to the dispatching strategy to obtain a dispatching distribution network; Fault detection and environmental assessment are performed on the operating status of the dispatching distribution network to obtain the feedback information.

8. A distribution network multi-objective dispatching system, characterized in that: The system comprises: A data collection module is used to collect and process data from distributed energy units to obtain raw data; A preprocessing and feature extraction module, used for preprocessing and feature extraction of the raw data to obtain feature data; A multi-objective optimization module, used to perform multi-objective optimization processing on the characteristic data according to an economic cost optimization objective, a carbon emission optimization objective and a system stability optimization objective to obtain an optimization model; A deep learning optimization module, used to solve the optimization model according to the deep learning model to obtain a scheduling strategy; A scheduling execution module, used to adjust the distributed energy unit according to the scheduling strategy and control the distributed energy unit to access the distribution network; A monitoring and feedback module is used to monitor the operating status of the distribution network to obtain feedback information, and return the feedback information to the deep learning model to iteratively update the scheduling strategy.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images