AI-based distributed energy optimization scheduling and management method and platform

Abstract

The application provides an AI-based distributed energy optimization scheduling and management method and platform, which comprises the following steps: collecting data from multiple heterogeneous data sources and preprocessing to obtain a data set; constructing a multi-objective optimization scheduling model according to the data set to determine an optimization scheduling scheme; obtaining the optimization scheduling scheme, designing a cooperation measurement function, and designing a shared optimization target function to optimize energy flow; collecting real-time feedback of the updated scheduling scheme, dynamically adjusting the scheduling scheme by measuring the difference between power demand and actual scheduling power. The application comprehensively uses multi-objective optimization, intelligent cooperation mechanism and big data analysis technology, not only optimizes the scheduling and management of distributed energy, but also improves the intelligent level and flexibility of the system.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of distributed energy optimization, and particularly relates to an AI-based distributed energy optimization scheduling and management method and platform. BACKGROUND

[0002] With the gradual transformation of global energy structure, the application of renewable energy has become an important direction for promoting energy revolution worldwide. Distributed energy system, as a core component of smart grid, has broad prospects and potential. Distributed energy system usually includes solar energy, wind energy, energy storage devices, micro combined heat and power and other forms of energy production and storage units, and its biggest feature is widely distributed, flexible and can realize two-way interaction with the power grid. With the rapid development of information technology and smart grid, the production and consumption management of distributed energy has become more fine and intelligent. However, there are still many bottlenecks in the existing technology in the scheduling and management of distributed energy, which hinders its wide application and optimization.

[0003] Firstly, the existing distributed energy scheduling method mainly focuses on the traditional centralized scheduling framework, which usually schedules each energy node through a central control system. Although this method can optimize energy scheduling to a certain extent, it lacks sufficient flexibility and the ability to respond to changes, and cannot well adapt to the diversified and complex demands and changes in the distributed energy system. For example, the traditional centralized scheduling system often relies on relatively fixed parameters and rules, and cannot reflect the actual demand and running state changes of each node (such as users, production equipment, energy storage systems, etc.) in the system in real time, resulting in the inability to achieve global optimization scheduling. In addition, this method usually ignores the coordination between distributed nodes, and cannot fully exert the advantages of each node, resulting in low efficiency of energy sharing and insufficient resource utilization.

[0004] Secondly, the existing distributed energy management platform generally has insufficient data processing capacity and serious information island problems. Traditional energy scheduling platforms often lack the ability to quickly process large amounts of heterogeneous data from different nodes in large-scale distributed systems. Especially in the face of highly dynamic user demand, weather conditions, power market price fluctuations and other variable factors, the existing system often lacks flexible scheduling strategies and response mechanisms. In addition, the information exchange and coordination mechanism between distributed energy nodes is relatively weak, which makes it impossible for each node to achieve intelligent collaborative scheduling. Energy sharing and optimal scheduling in distributed systems have not been fully utilized, resulting in energy waste and system instability.

[0005] Finally, current research on intelligent scheduling of distributed energy systems mostly focuses on single objective optimization, such as cost, efficiency, load balancing, etc. However, few methods can simultaneously consider multiple optimization objectives, for example, how to reduce energy costs while ensuring the stability of the power grid, reducing carbon emissions, and ensuring that each user's energy demand is met. Existing technologies often optimize for a single objective, ignoring the overall coordination and stability of the system, and the solution to the multi-objective optimization problem often does not take into account the dynamics and real-time nature of the system. Traditional methods fail to effectively balance the contradiction between short-term economic benefits and long-term environmental protection and system stability under multi-objective scheduling, resulting in less-than-expected results in the practical application of distributed energy. SUMMARY

[0006] The purpose of the present application is to propose an AI-based distributed energy optimization scheduling and management method and platform, which optimizes the scheduling and management of distributed energy by comprehensively using multi-objective optimization, intelligent collaboration mechanism and big data analysis technology, and improves the intelligence level and flexibility of the system.

[0007] To achieve the above purpose, in the first aspect of the present application, an AI-based distributed energy optimization scheduling and management method is provided, which comprises the following steps:

[0008] Collect data from multiple heterogeneous data sources and preprocess to obtain a data set;

[0009] Construct a multi-objective optimization scheduling model according to the data set to determine an optimization scheduling scheme; wherein the objectives of the multi-objective optimization scheduling model include energy cost, energy efficiency, load balancing and green energy usage ratio; the optimization scheduling scheme includes node power production, consumption and load information;

[0010] Obtain the optimization scheduling scheme, design a collaboration measurement function, dynamically adjust the collaboration weight between nodes based on the collaboration measurement function, optimize the energy transmission and sharing strategy between multiple nodes, and obtain an updated scheduling scheme; after obtaining the updated scheduling scheme, design a sharing optimization objective function to optimize energy flow in the case of possible energy redundancy or deficiency between nodes;

[0011] Collect real-time feedback of the updated scheduling scheme, dynamically adjust the scheduling scheme by measuring the difference between power demand and actual scheduling power, and design an adjustment factor to adjust node power output according to the difference between power demand and actual scheduling power; combine the real-time feedback and the adjustment factor to further update the updated scheduling scheme, introduce multi-objective optimization to further optimize the scheduling scheme, obtain the final scheduling scheme, and ensure that the final scheduling scheme meets all constraint conditions, including power upper limit, load balancing and transmission loss.

[0012] Further, the data collected from the plurality of heterogeneous data sources includes weather, load, battery status and power market price;

[0013] The preprocessing includes:

[0014] The weight of the corresponding data source is determined based on the quality, timeliness and historical performance of the data source;

[0015] The different data are weighted and fused according to the weight of the corresponding data source to obtain the fused data;

[0016] The fused data is obtained, and an adaptive weighted Kalman filtering method is used to remove noise to obtain filtered data.

[0017] Further, after obtaining the preprocessed data, a feature selection method based on mutual information maximization and regularization is used to screen out the most effective feature set as the data set; the feature selection method based on mutual information maximization and regularization is represented as:

[0018]

[0019] Where I(X i ;Y) represents the mutual information between the feature X i and the target variable Y, P(x i ,y) is the joint probability distribution of the feature X i and the target variable Y, P(x i ) and P(y) are their marginal probability distributions, respectively.

[0020] A regularization term L reg is introduced to reduce the influence of redundant features on the model:

[0021]

[0022] Where λ is the regularization coefficient, and Redundancy(X i ) represents the redundancy of the feature X i and other features.

[0023] Further, the comprehensive objective function of the multi-objective optimization scheduling model is the weighted sum of the objectives of the multi-objective optimization scheduling model, and the weights are adjusted according to real-time data and state:

[0024]

[0025] Where w1(t), w2(t), w3(t), w4(t) are the dynamic weights of the objectives, and the specific values are adjusted according to real-time data and system state.

[0026] Further, the multi-objective optimization scheduling model is constructed according to the data set, and the optimization scheduling scheme is determined, and specifically includes:

[0027] A feedback mechanism is designed for the dynamic weight of the target, and the feedback mechanism automatically adjusts the weight of the target according to real-time data; wherein the real-time data includes market price and device health status;

[0028] In the optimization process, it is necessary to ensure that the constraints are met, including: power balance constraint, energy storage device constraint and green energy proportion;

[0029] Among them,

[0030] The power balance constraint is used to ensure that the total amount of generated power is equal to the demand power;

[0031] The energy storage device constraint is used to limit the charging and discharging capacity of the energy storage device to avoid overcharging or overdischarging;

[0032] The green energy proportion is used to ensure that the use amount of green energy reaches a predetermined proportion;

[0033] For the comprehensive objective function, an adaptive particle swarm optimization algorithm is adopted, which combines a feedback mechanism to dynamically adjust the search strategy of the particles; wherein the adaptive particle swarm optimization algorithm updates the rules as follows:

[0034] v i (t+1)=w(t)·v i (t)+c1·r1·(p i -x i (t))+c2·r2·(g-x i (t))

[0035] Among them, v i (t+1) is the updated particle velocity, v i (t) is the particle velocity, x i (t) is the particle position, p i and g are the historical best and global best positions of the particles respectively, w(t) is the inertia weight, r1 and r2 are random numbers.

[0036] Further, the cooperation measurement function is represented as:

[0037]

[0038] Among them, w ij (t) is the cooperation weight of node i and node j, indicating the closeness of cooperation; γ ij (t) is a transmission loss factor, reflecting the energy transmission loss between node i and node j; α ij is an adjustment factor, controlling the influence of transmission loss on cooperation; Pi (t) and P j (t) are the power production or consumption of node i and node j, respectively;

[0039] Meanwhile, the cooperation weight is dynamically updated; when the cooperation demand of node i increases, its weight w ij (t) will increase, thereby enhancing cooperation with other nodes;

[0040] Combining the cooperation weight and the cooperation metric function, the scheduling scheme of the node is updated, denoted as:

[0041]

[0042] where P optimized (t) is the optimized scheduling scheme, and a is a regulation factor for balancing the relationship between the optimized scheme and the cooperation demand.

[0043] Further, the shared optimization objective function is denoted as:

[0044] Combining the transmission loss and the sharing efficiency,

[0045]

[0046] where η ij (t) is the sharing efficiency coefficient, indicating the efficiency of node i sharing energy with node j, considering the loss in transmission.

[0047] Further, the multi-objective optimization is denoted as:

[0048]

[0049] where, is the power loss of node i at time t; is the load fluctuation metric of node i at time t; a1 and a2 are weighting coefficients, controlling the importance of power loss and load fluctuation.

[0050] Further, when performing the multi-objective optimization adjustment, the constraints need to be met:

[0051]

[0052] where P max (t) is the maximum power output capability of node i; is the power constraint condition of node i, P new (t) is the final scheduling scheme.

[0053] In a second aspect of the present application, an AI-based distributed energy optimization scheduling and management platform is provided, which comprises:

[0054] A heterogeneous data source acquisition module is configured to acquire data from multiple heterogeneous data sources and perform preprocessing to obtain a data set.

[0055] A multi-objective optimization module is configured to construct a multi-objective optimization scheduling model according to the data set and determine an optimization scheduling scheme, wherein the objectives of the multi-objective optimization scheduling model include energy cost, energy efficiency, load balancing, and green energy usage ratio, and the optimization scheduling scheme includes node power production, consumption, and load information.

[0056] A collaborative scheduling module is configured to obtain the optimization scheduling scheme, design a collaboration measurement function, dynamically adjust the collaboration weight between nodes based on the collaboration measurement function, optimize the energy transmission and sharing strategy between multiple nodes, and obtain an updated scheduling scheme.

[0057] A scheduling optimization module is configured to collect real-time feedback of the updated scheduling scheme, dynamically adjust the scheduling scheme by measuring the difference between power demand and actual scheduling power, and design an adjustment factor to adjust node power output according to the difference between power demand and actual scheduling power.

[0058] The present application has at least the following beneficial technical effects:

[0059] Firstly, the present application introduces a multi-objective optimization algorithm to solve the problem that traditional methods cannot find a balance between multiple optimization objectives. The platform not only optimizes energy costs, but also considers various objectives such as system load balancing, stability, grid safety, environmental benefits, etc. Through advanced methods such as Pareto frontier optimization and particle swarm optimization algorithm (PSO), it ensures that the energy scheduling cost is minimized and carbon emissions are reduced to the maximum extent while ensuring grid stability. In addition, the system can dynamically schedule according to real-time electricity demand, renewable energy generation, weather changes, and other factors, improving the real-time and flexibility of scheduling.

[0060] Secondly, the present application breaks through the data island problem in the existing distributed energy management platform through intelligent collaboration mechanism and distributed ledger technology (such as blockchain). Energy sharing is realized between distributed nodes through smart contract or collaboration protocol, ensuring transparent, fair and safe energy exchange for each node. In the case of energy surplus, nodes can automatically distribute excess energy to other nodes in need according to the platform's scheduling recommendations, thus realizing the optimal scheduling of the whole system. This mechanism not only improves the utilization efficiency of energy, but also greatly improves the overall flexibility and intelligent collaboration ability of the distributed system. Through the automatic execution of energy transaction and scheduling instructions by smart contract, human operation interference and errors are effectively reduced.

[0061] Finally, the platform realizes intelligent decision-making in demand prediction and system optimization through big data analysis and collaborative filtering algorithm. The system can analyze and predict the energy demand of each node in real time according to historical data, weather information, power market prices and other multi-dimensional data, further improving the accuracy and predictability of scheduling. Collaborative filtering algorithm helps the platform intelligently predict future demand based on the demand and power consumption mode of different nodes, accurately allocate energy resources for each node, thus avoiding excessive scheduling or energy waste and ensuring the optimal operation of the whole distributed energy system. BRIEF DESCRIPTION OF DRAWINGS

[0062] The present application is further illustrated by the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present application. For those skilled in the art, other drawings can be obtained without creative labor on the basis of the following drawings.

[0063] Figure 1 The AI-based distributed energy optimization scheduling and management method flowchart disclosed in the embodiments of the present application

[0064] Figure 2 The AI-based distributed energy optimization scheduling and management platform framework diagram disclosed in the embodiments of the present application. DETAILED DESCRIPTION

[0065] The embodiments of the present application are described in detail below, and the examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation on the present application.

[0066] Embodiment one

[0067] As shown in Figure 1 The AI-based distributed energy optimization scheduling and management method provided by the embodiments of the present application comprises:

[0068] S1, collect data from multiple heterogeneous data sources and pre-process to obtain a dataset.

[0069] Specifically, in the distributed energy scheduling, the application faces heterogeneous data from different sources (such as weather, load, battery state, electricity market price, etc.). The quality, timeliness and importance of these data sources are different, so the application needs to perform data fusion to ensure that the data input into the model has consistency and reliability. To this end, the application proposes a dynamic weighted fusion model based on timeliness weight adjustment.

[0070] The application first defines the weight w i (t) of each data source, which is closely related to the quality, timeliness and historical performance of the data source. The weight formula is:

[0071]

[0072] where q i (t) represents the quality factor (including credibility and accuracy) of data source i at time t, a(t) is the timeliness factor (i.e. the deviation of the timestamp of the data source from the current time), w i (t) is the weighting coefficient of the data source, and n is the number of data sources. The data fusion formula is:

[0073]

[0074] where x fused (t) represents the fused data, x i (t) is the original data of the i-th data source, and w i (t) is the corresponding weight. This fusion method can dynamically adjust the different levels of trust in data sources under different behavior patterns, thereby reducing the impact of noise on subsequent models.

[0075] Further, in the data collection stage, especially for sensor data and weather forecast data, there is often noise. In order to improve data quality, the application uses an adaptive weighted Kalman filtering (AWKF, Adaptive Weighted Kalman Filtering) method to remove noise. This method adaptively adjusts the filtering parameters and dynamically responds to changes in the quality of the data source. The state update equation of the weighted Kalman filter is:

[0076] x filtered (t)=w i (t)·(A·x t-1 +B·u t )+(1-w i (t))·(C·y t )

[0077] where x filtered (t) is the filtered data, A, B are the state transition and control matrices of Kalman filter, u t is the control input, C is the measurement matrix, y t is the observation, w i (t) is the weighting coefficient of data source i, which is dynamically adjusted according to the data quality.

[0078] The innovation of the filtering method is to dynamically adjust the weighting coefficient of Kalman filter according to the quality of each data source, so that when processing sensor data and weather data, the noise can be adaptively removed according to the timeliness and reliability of the data source, and the problem that traditional Kalman filter cannot handle timeliness fluctuation and quality difference is reduced.

[0079] Further, in order to improve the learning efficiency of the subsequent model and reduce the influence of redundant data on the computing performance, the application designs a feature selection method based on mutual information maximization and regularization. This method calculates the correlation between each feature and the target variable, and introduces redundant regularization to select the most effective feature set. The mutual information calculation formula is:

[0080]

[0081] where I(X i ;Y) represents the mutual information between feature X i and target variable Y, P(x i ,y) is the joint probability distribution of feature X i and target variable Y, P(x i ) and P(y) are their marginal probability distributions, respectively.

[0082] In order to reduce the influence of redundant features on the model, the application introduces a regularization term:

[0083]

[0084] where λ is the regularization coefficient, Redundancy(X i ) represents the redundancy of feature X i and other features. In this way, the application can select features with high correlation to the target variable and low redundancy, providing efficient input for subsequent model training.

[0085] The final output is a data set that has been intelligently preprocessed, denoised, fused and feature selected. These data can be used as high-quality input for multi-objective scheduling optimization models.

[0086] S2, constructing a multi-objective optimization scheduling model according to the data set, and determining an optimization scheduling scheme; wherein the objectives of the multi-objective optimization scheduling model include energy cost, energy efficiency, load balancing, and green energy usage ratio; and the optimization scheduling scheme includes node power production, consumption, and load information.

[0087] In step 1: data collection and intelligent preprocessing, the time series data x fused (t) is obtained by fusion and weighting, which includes various features of the power system, such as energy consumption, device status, load, etc. This data set will be used as the input of this step for the construction of the multi-objective optimization scheduling model.

[0088] Further, the object of the present application is to construct a multi-objective optimization scheduling model to optimize energy cost, energy efficiency, load balancing, and green energy usage simultaneously. Since there is a certain conflict between these objectives, the model needs to be balanced. For this purpose, the present application defines a comprehensive objective function The function is the weighted sum of all objective functions.

[0089]

[0090] where w1(t), w2(t), w3(t), w4(t) are the dynamic weights of the objectives, and the specific values are adjusted according to real-time data and system state. The specific meaning of each objective is as follows:

[0091] Energy cost: reflects the economic burden of energy procurement.

[0092] Energy efficiency: evaluates the efficiency of energy use in the system, and tries to reduce energy waste.

[0093] Load balancing: reduces system load fluctuations and improves system stability.

[0094] Green energy usage ratio: promotes the use of green energy and reduces environmental impact.

[0095] Further, in order to adjust the importance of the objectives in real time, the present application designs a feedback mechanism that automatically adjusts the weights of the objectives according to real-time data (such as market price, device health status). The adjustment factor k (t) is used to control the dynamic weights of the objective function, and the calculation method is based on the system state and external environment (such as market fluctuations):

[0096] w k (t)=α k (t)·f adjust (x fused (t))

[0097] Here, α k(t) is the feedback calculated weight adjustment factor, and f adjust (x fused (t)) is the adaptive adjustment factor calculated based on x fused (t), which dynamically updates the weight according to real-time energy consumption, load and device status.

[0098] Further, in the optimization process, multiple constraints need to be considered, which ensure that the scheduling results of the model meet the actual operation requirements of the power system:

[0099] Power balance constraint: ensure that the total amount of generated power is equal to the demand power:

[0100]

[0101] Energy storage device constraint: limit the charging and discharging capacity of the energy storage device to avoid overcharging or overdischarging:

[0102] 0≤E i (t)≤E max (t)

[0103] Green energy ratio: ensure that the use of green energy reaches the predetermined proportion:

[0104] G usage (t)≥G min

[0105] Further, in order to efficiently solve the multi-objective optimization problem, the present application adopts the adaptive particle swarm optimization (APSO) algorithm, which combines a feedback mechanism to dynamically adjust the search strategy of the particles. Specifically, the update rule of the particle swarm optimization is as follows:

[0106] v i (t+1)=w(t)·v i (t)+c1·r1·(p i -x i (t))+c2·r2·(g-x i (t))

[0107] where v i (t) is the particle velocity, x i (t) is the particle position, p i and g are the historical best and global best positions of the particles, w(t) is the inertia weight, and r1 and r2 are random numbers. This algorithm can adaptively adjust the search strategy to avoid falling into local optimal solutions, while effectively balancing the weights between multiple objectives.

[0108] Further, through the solution of the optimization algorithm, the final output scheduling scheme x optimized(t) can effectively balance various goals and provide an optimized power scheduling scheme. This scheme can minimize energy costs, improve energy efficiency, reduce load fluctuations, and maximize the use of green energy.

[0109] S3, obtain an optimized scheduling scheme, design a cooperation measurement function, dynamically adjust the cooperation weight between nodes based on the cooperation measurement function, optimize the energy transmission and sharing strategy between multiple nodes, and obtain an updated scheduling scheme; after obtaining the updated scheduling scheme, in view of the possible energy redundancy or deficiency between nodes, design a sharing optimization target function to optimize energy flow.

[0110] The input of this step comes from the output of step 2, i.e. the optimized scheduling scheme x optimized (t), which contains information such as power production, consumption, load balancing, etc. of each node. These information will be used to adjust the cooperation mode and energy sharing strategy between nodes. The cooperation measurement function is designed to measure the cooperation efficiency between nodes, and a dynamic weight adjustment mechanism is introduced to define the cooperation measurement function:

[0111]

[0112] where: w ij (t) is the cooperation weight between node i and node j, indicating the closeness of cooperation; γ ij (t) is the transmission loss factor, reflecting the energy transmission loss between node i and node j; α ij is the adjustment factor, controlling the influence of transmission loss on cooperation; P i (t) and P j (t) are the power production or consumption of node i and node j respectively. The purpose of this function is to enhance the consideration of transmission loss between nodes, making cooperation more practical.

[0113] Further, based on the above cooperation measurement function, the cooperation weight between nodes is dynamically adjusted by the following rules:

[0114]

[0115] where β is the adjustment factor, used to control the change of cooperation weight. When the cooperation demand of node i increases, its weight w ij (t) will increase, thereby enhancing cooperation with other nodes.

[0116] Further, combined with dynamic weight and cooperation measurement, the scheduling state of the node is updated. The updated scheduling scheme is:

[0117]

[0118] where P optimized(t) is the optimized scheduling scheme of step 2, and a is an adjustment factor used to balance the relationship between the optimization scheme and the cooperation demand. This step updates the scheduling scheme by integrating cooperation information to improve energy utilization efficiency.

[0119] Further, in the environment of multiple energy nodes, there may be energy redundancy or insufficient conditions between nodes, so an energy sharing mechanism is introduced to optimize energy flow. The present application designs a sharing optimization objective function:

[0120]

[0121] where η ij (t) is the sharing efficiency coefficient, representing the efficiency of node i sharing energy with node j, considering the loss in transmission. This function considers both transmission loss and sharing efficiency, aiming to optimize the energy sharing strategy between multiple nodes.

[0122] Further, to further improve sharing efficiency, a decreasing sharing benefit factor η ij (t) is designed, whose expression is:

[0123]

[0124] where: P share (t) is the amount of electricity shared by node i to node j; P max (t) is the maximum power output capability of node i; and γ(t) is a sharing adjustment factor that dynamically adjusts the sharing capability. This step optimizes the sharing efficiency coefficient to control energy transmission between nodes, ensuring the efficiency and fairness of the sharing process.

[0125] After the optimization of intelligent cooperation and energy sharing mechanism, each node in the system will obtain an updated scheduling scheme P adjusted (t). This scheme fully considers the cooperation demand and sharing strategy between nodes, which can effectively reduce energy waste and improve the proportion of green energy use. Through the design of this step, the cooperation and energy sharing between nodes have been significantly improved. In particular, the introduction of dynamic weight adjustment, transmission loss factor and sharing efficiency coefficient and other innovative mechanisms provides an optimized path for energy scheduling and sharing in multiple energy systems, which can maintain the efficient operation of the system in various dynamic environments.

[0126] S4, collecting real-time feedback of the updated scheduling scheme, dynamically adjusting the scheduling scheme by measuring the difference between power demand and actual scheduling power, and designing an adjustment factor to adjust the node power output according to the difference between power demand and actual scheduling power, combining the real-time feedback and the adjustment factor to further update the updated scheduling scheme, introducing multi-objective optimization to further optimize the scheduling scheme, obtaining a final scheduling scheme, and ensuring that the final scheduling scheme meets all constraint conditions, the constraint conditions including power upper limit, load balancing and transmission loss.

[0127] The input of this step comes from the output of step 3, i.e. the optimized scheduling scheme P adjusted (t), as well as the cooperation measure and energy sharing information between nodes. These information will be used to further adjust the scheduling scheme and consider real-time changes.

[0128] Further, a real-time feedback mechanism is introduced to dynamically adjust the scheduling scheme based on the current energy demand and system state. In order to ensure the stability and efficiency of the system, the present application designs the following feedback adjustment function:

[0129]

[0130] Where, P demand (t) is the demand power of node i at time t; P current (t) is the actual scheduling power of node i at time t; η i (t) is the adjustment factor, dynamically adjusting the response speed of feedback. This feedback function is used to measure the difference between node power demand and current power, and guide the system to adjust according to the difference.

[0131] Further, in order to adjust the power output of the node according to the feedback signal, the present application designs an adjustment factor η i (t), whose formula is:

[0132]

[0133] Where, λ i is the response sensitivity factor of node i, controlling the reaction force of the system to demand difference; |P demand (t)-P current (t)| is the absolute difference between current demand and actual scheduling. This adjustment factor design allows the system to respond quickly when the load changes greatly, and to adjust smoothly when the load is stable.

[0134] Further, based on real-time feedback and adjustment factor, the present application can use the following rules to dynamically update the scheduling scheme:

[0135]

[0136] where P adjusted (t) is the scheduling scheme in step 3; η i (t) is the adjustment factor designed above; is the feedback signal. This rule updates the scheduling scheme according to real-time feedback signals, enabling the system to respond to changes in actual load.

[0137] Further, to balance the distribution of energy and further optimize the scheduling scheme, the present application introduces multi-objective optimization constraints. These objectives include minimizing power loss, balancing grid load, and reducing energy waste. The optimization objectives can be expressed as:

[0138]

[0139] where, is the power loss of node i at time t; is the load fluctuation metric of node i at time t; α1 and α2 are weighting coefficients that control the importance of power loss and load fluctuation. This objective function considers both power loss and load fluctuation during dynamic adjustment, providing a balanced and efficient solution for the system.

[0140] Further, when performing optimization adjustment, it must be ensured that the scheduling scheme meets the following constraints:

[0141] The actual output power of the node cannot exceed its maximum power capacity;

[0142] The load of the power network must be balanced to ensure the stability of the grid;

[0143] Transmission losses between nodes must be considered to avoid overloading.

[0144] These constraints can be expressed as:

[0145]

[0146] where P max (t) is the maximum power output capability of node i; is the power constraint condition of node i.

[0147] The system will perform feasibility checks on the scheduling scheme of each node according to these constraints, ensuring that all adjusted schemes are physically feasible.

[0148] After real-time feedback and optimization adjustment, the final scheduling scheme P final(t), which is subjected to real-time feedback and multi-objective optimization, and ensures that all constraint conditions are met. The scheduling strategy of each node will minimize power loss, balance load fluctuations, and improve overall system efficiency. This step enables the system to dynamically adjust the scheduling scheme and optimize energy distribution according to the actual load changes in operation through real-time feedback mechanisms and optimization adjustment rules. By designing specific feedback adjustment factors, constraint conditions, and multi-objective optimization targets, the system can adapt to different operating states in real time, maintaining stable and efficient energy scheduling.

[0149] Embodiment Two

[0150] As shown in Figure 2 , the present application also provides an AI-based distributed energy optimization scheduling and management platform, which includes:

[0151] A heterogeneous data source acquisition module 101 is used to collect data from multiple heterogeneous data sources and perform preprocessing to obtain a data set;

[0152] A multi-objective optimization module 102 is used to construct a multi-objective optimization scheduling model based on the data set and determine an optimization scheduling scheme; wherein the objectives of the multi-objective optimization scheduling model include energy cost, energy efficiency, load balancing, and green energy usage ratio; and the optimization scheduling scheme includes node power production, consumption, and load information;

[0153] A collaborative scheduling module 103 is used to obtain the optimization scheduling scheme, design a collaboration measurement function, dynamically adjust the collaboration weights between nodes based on the collaboration measurement function, optimize the energy transmission and sharing strategy between multiple nodes, and obtain an updated scheduling scheme; after obtaining the updated scheduling scheme, a shared optimization target function is designed to optimize energy flow in the case of possible energy redundancy or deficiency between nodes;

[0154] A scheduling optimization module 104 is used to collect real-time feedback of the updated scheduling scheme, dynamically adjust the scheduling scheme by measuring the difference between power demand and actual scheduling power, and design an adjustment factor to adjust node power output according to the difference between power demand and actual scheduling power; the real-time feedback and adjustment factor are combined to further update the updated scheduling scheme, and multi-objective optimization is introduced to further optimize the scheduling scheme, obtaining a final scheduling scheme that meets all constraint conditions, including power upper limit, load balancing, and transmission loss.

[0155] In summary, the present application optimizes the scheduling and management of distributed energy by comprehensively using multi-objective optimization, intelligent collaboration mechanism and big data analysis technology, and improves the intelligent level and flexibility of the system. It effectively solves a plurality of problems in the prior art, such as poor flexibility of centralized scheduling, insufficient collaboration between distributed nodes, single objective optimization, etc., and provides a new solution for realizing more efficient, safe and environmentally friendly distributed energy management.

[0156] The above describes certain embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different than the order in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily have to be performed in the specific order shown and / or sequentially. In certain implementations, multitasking and parallel processing can be advantageous.

[0157] The systems, apparatuses, modules or units illustrated by the above embodiments can be specifically implemented by a computer chip or entity, or by a product with certain functions. A typical implementation device is a computer. Specifically, the computer may, for example, be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0158] For the convenience of description, the above apparatus is described as various units divided by functions for description. Of course, the functions of each unit can be implemented in the same or more software and / or hardware in the implementation of the present specification.

[0159] Those skilled in the art should understand that the embodiments of the present specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of the present specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0160] The specification is presented with reference to flow diagrams and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing element or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more flow or multiple flows and / or blocks Figure 1 one or more flow or multiple flows and / or blocks

[0161] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more flow or multiple flows and / or blocks Figure 1 one or more flow or multiple flows and / or blocks

[0162] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more flow or multiple flows and / or blocks Figure 1 one or more flow or multiple flows and / or blocks

[0163] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0164] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, such as read-only memory (ROM), EPROM, and / or flash memory, etc. The memory is an example of computer readable media.

[0165] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0166] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to encompass non-exclusive inclusion, such that processes, methods, articles or devices that comprise a list of elements not only include those elements, but also include other elements not expressly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0167] The specification 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 specification can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0168] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment focuses on the difference from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0169] Finally, it should be noted that: the AI-based distributed energy optimization scheduling and management platform disclosed in the embodiments of the present application is only the preferred embodiment of the present application, and is only used to illustrate the technical solutions of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand; the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An AI-based method for optimized scheduling and management of distributed energy resources, characterized in that: The method includes the following steps: Data is collected from multiple heterogeneous data sources and preprocessed to obtain a dataset; A multi-objective optimization scheduling model is constructed based on the dataset to determine the optimal scheduling scheme. The objectives of the multi-objective optimization scheduling model include energy cost, energy efficiency, load balance, and the proportion of green energy use. The optimal scheduling scheme includes node power production, consumption, and load information. To obtain an optimized scheduling scheme, a cooperation metric function is designed. Based on the cooperation metric function, the cooperation weights between nodes are dynamically adjusted to optimize the energy transmission and sharing strategy among multiple nodes, resulting in an updated scheduling scheme. After obtaining the updated scheduling scheme, a sharing optimization objective function is designed to optimize energy flow, taking into account the potential energy redundancy or insufficiency among nodes. The system collects real-time feedback on the updated scheduling scheme, dynamically adjusts the scheduling scheme by measuring the difference between power demand and actual scheduled power, and designs adjustment factors to adjust node power output based on the difference between power demand and actual scheduled power. The real-time feedback and adjustment factors are combined to further update the updated scheduling scheme, and multi-objective optimization is introduced to further optimize the scheduling scheme to obtain the final scheduling scheme. The system ensures that the final scheduling scheme meets all constraints, including power limit, load balancing and transmission loss. Specifically, the step of constructing a multi-objective optimization scheduling model based on the dataset and determining the optimal scheduling scheme includes: A feedback mechanism is designed for the dynamic weight of the target, which automatically adjusts the weight of the target based on real-time data; wherein, the real-time data includes market price and equipment health status; During the optimization process, it is necessary to ensure that constraints are met, including: power balance constraints, energy storage device constraints, and the proportion of green energy. in, Electricity balance constraints are used to ensure that the total amount of electricity generated equals the amount of electricity demanded. Energy storage device constraints are used to limit the charging and discharging capabilities of energy storage devices to prevent overcharging or over-discharging. The green energy ratio is used to ensure that the amount of green energy used reaches a predetermined proportion. For the comprehensive objective function, an adaptive particle swarm optimization algorithm is adopted, which incorporates a feedback mechanism to dynamically adjust the particle search strategy; the update rule of the adaptive particle swarm optimization algorithm is as follows: ； in, For the updated particle velocity, For particle velocity, For the particle position, and These are the historical best and global best positions of the particle, respectively. It is inertial weight. and It is a random number; The collaboration metric function is expressed as: ； in, For nodes With nodes The collaboration weight represents the degree of closeness of the collaboration; The transmission loss factor reflects the node's transmission loss. To the node Energy transmission losses between them; As an adjustment factor, it controls the impact of transmission loss on cooperation; and They are nodes and nodes Electricity production or consumption; Simultaneously, the collaboration weights are dynamically updated; when a node When the need for collaboration increases, its weight This will increase, thereby enhancing cooperation with other nodes; Combining collaboration weights and collaboration metric functions, the node scheduling scheme is updated as follows: ； in, To optimize the scheduling scheme, It is a regulating factor used to balance the relationship between the optimization scheme and the collaboration requirements; The shared optimization objective function is expressed as: Combining transmission loss and sharing efficiency, ； in, To share the efficiency coefficient, the node represents... To the node The efficiency of shared energy should take into account losses during transmission.

2. The AI-based distributed energy optimization scheduling and management method according to claim 1, characterized in that, The data is collected from multiple heterogeneous data sources, including weather, load, battery status, and electricity market prices; The preprocessing includes: The weight of the corresponding data source is determined based on the quality, timeliness, and historical performance of the data source. The different data are weighted and merged according to the weight of the corresponding data source to obtain the merged data; After obtaining the fused data, noise is removed using an adaptive weighted Kalman filter to obtain the filtered data.

3. The AI-based distributed energy optimization scheduling and management method according to claim 2, characterized in that, After obtaining the preprocessed data, the most effective feature set is selected as the dataset based on a feature selection method that maximizes mutual information and uses regularization. The feature selection method based on maximizing mutual information and using regularization is expressed as follows: ； in, Representation of features With target variable Mutual information between them It is a feature and target variable The joint probability distribution, and These are their marginal probability distributions; At the same time, regularization is introduced. The impact of reducing redundant features on the model: ； in, It is the regularization coefficient. Representation of features Redundancy with other features.

4. The AI-based distributed energy optimization scheduling and management method according to claim 1, characterized in that, The comprehensive objective function of the multi-objective optimization scheduling model The objectives of the multi-objective optimization scheduling model are weighted sums, with weights adjusted based on real-time data and status. ； in, It is the dynamic weight of the target, and the specific value is adjusted according to real-time data and system status.

5. The AI-based distributed energy optimization scheduling and management method according to claim 1, characterized in that, The multi-objective optimization , represented as: ； in, For nodes At any moment Power loss; For nodes At any moment Load fluctuation measurement; and The weighting factor is used to control the importance of power loss and load fluctuation.

6. The AI-based distributed energy optimization scheduling and management method according to claim 1, characterized in that, In performing multi-objective optimization During adjustment, the following constraints must be met: ； in, For nodes Maximum power output capability; For nodes Power constraints, This is the final scheduling scheme.

7. A platform for implementing the AI-based distributed energy optimization scheduling and management method as described in claim 1, characterized in that the platform... include: The heterogeneous data source acquisition module is used to collect data from multiple heterogeneous data sources and preprocess it to obtain a dataset. The multi-objective optimization module is used to construct a multi-objective optimization scheduling model based on the dataset and determine the optimal scheduling scheme. The objectives of the multi-objective optimization scheduling model include energy cost, energy efficiency, load balance, and the proportion of green energy use. The optimal scheduling scheme includes node power production, consumption, and load information. The collaborative scheduling module is used to obtain an optimized scheduling scheme, design a collaborative metric function, dynamically adjust the collaborative weights between nodes based on the collaborative metric function, optimize the energy transmission and sharing strategy among multiple nodes, and obtain an updated scheduling scheme. After obtaining the updated scheduling scheme, a sharing optimization objective function is designed to optimize energy flow in the case of possible energy redundancy or insufficiency among nodes. The scheduling optimization module is used to collect real-time feedback on the updated scheduling scheme. By measuring the difference between power demand and actual scheduled power, it dynamically adjusts the scheduling scheme and designs adjustment factors to adjust node power output based on the difference between power demand and actual scheduled power. The real-time feedback and adjustment factors are combined to further update the updated scheduling scheme. Multi-objective optimization is introduced to further optimize the scheduling scheme to obtain the final scheduling scheme. The final scheduling scheme is ensured to meet all constraints, including power limit, load balancing, and transmission loss.

Images