A multi-dimensional energy intelligent management and control system and method based on an adaptive optimization algorithm

Abstract

The present invention relates to the field of intelligent energy management and optimal scheduling, and particularly to a multi-dimensional energy intelligent control system and method based on an adaptive optimization algorithm. The content includes: real-time monitoring of multi-dimensional energy consumption data and preprocessing it, constructing a multi-dimensional energy state model based on the preprocessed multi-dimensional energy consumption data to obtain an energy state vector; introducing an adaptive weighting mechanism to dynamically adjust the energy state vector to obtain an adjusted energy state vector; performing a transition adjustment on the adjusted energy state vector, and based on the energy state vector after the transition adjustment, performing multi-stage path optimization to obtain an optimal scheduling plan. It solves the problems that traditional methods cannot respond to environmental changes in real time in multi-dimensional energy control, it is difficult to dynamically adjust the energy distribution ratio, resulting in energy waste or shortage; linear optimization methods are difficult to balance short-term and long-term scheduling goals in complex energy systems, resulting in low energy utilization rate and poor system robustness.

Description

Technical Field

[0001] The present invention relates to the field of intelligent energy management and optimal scheduling, and particularly to a multi-dimensional energy intelligent control system and method based on an adaptive optimization algorithm. Background Art

[0002] With the continuous growth of global energy demand and the diversified development of the energy structure, the intelligentization and optimal scheduling of energy management have become important issues to be solved urgently. The traditional energy management mode mainly relies on fixed rules or static optimization methods, which are difficult to meet the dynamics and complexity of modern energy systems. Currently, various energy forms such as electricity, heat energy, and gas are widely used in different application scenarios. However, due to the different supply and demand characteristics of various types of energy, how to achieve the efficient coordination and optimal scheduling of energy has become an important research direction for improving energy utilization efficiency and reducing operating costs. At the same time, the impact of environmental factors (such as climate change and load fluctuations) on energy demand is becoming increasingly significant, making it necessary for energy management systems to have stronger adaptability to maintain a stable and efficient energy supply-demand balance under different conditions.

[0003] In recent years, the development of technologies such as intelligent sensors, big data analysis, and artificial intelligence has provided new possibilities for the optimization of energy management. Through a distributed sensor network, real-time monitoring of various energy forms can be achieved, and dynamic data analysis can be carried out in combination with environmental factors, providing reliable data support for intelligent scheduling. In addition, the application of adaptive optimization algorithms in complex system optimization is becoming increasingly widespread. It can adjust the optimization strategy according to real-time data, enabling the energy scheduling plan to be dynamically optimized with the changes in the system state and environment, thus avoiding the local optimum problem that may occur in traditional methods and improving the flexibility and overall efficiency of energy management. Therefore, how to combine intelligent monitoring technology and adaptive optimization algorithms to construct an efficient, intelligent, and flexible multi-dimensional energy intelligent control system has become an important direction for the development of energy management technology.

[0004] Traditional methods have the following technical problems in multi-dimensional energy control: there are defects such as insufficient optimization ability, poor adaptability, serious local optimum problems, and inaccurate energy scheduling, and they cannot respond to environmental changes in real time and are difficult to dynamically adjust the energy distribution ratio, resulting in energy waste or shortage; linear optimization methods are prone to falling into local optima in complex energy systems, ignoring the long-term energy efficiency optimization requirements, lacking global search ability, being difficult to balance short-term and long-term scheduling goals, and unable to effectively predict future energy demand changes, resulting in low energy utilization efficiency, high operating costs, and poor system robustness. Summary of the Invention

[0005] The present invention provides a multi - dimensional energy intelligent management and control system and method based on an adaptive optimization algorithm to solve the defects of traditional methods in multi - dimensional energy management and control, such as insufficient optimization ability, poor adaptability, serious local - optimum problems, inaccurate energy scheduling, etc. These traditional methods cannot respond to environmental changes in real time, are difficult to dynamically adjust the energy distribution ratio, resulting in energy waste or shortage; linear optimization methods are prone to falling into local optima in complex energy systems, ignoring the need for long - term energy - efficiency optimization, lacking global search ability, being difficult to balance short - term and long - term scheduling goals, and unable to effectively predict future energy - demand changes, resulting in low energy utilization rate, high operating costs, and poor system robustness.

[0006] A multi - dimensional energy intelligent management and control system and method based on an adaptive optimization algorithm of the present invention specifically include the following technical solutions:

[0007] A multi - dimensional energy intelligent management and control method based on an adaptive optimization algorithm includes the following steps:

[0008] S1. Real - time monitor multi - dimensional energy consumption data and perform pre - processing to obtain pre - processed multi - dimensional energy consumption data; based on the pre - processed multi - dimensional energy consumption data, construct a multi - dimensional energy state model to obtain an energy state vector; introduce an adaptive weighting mechanism to dynamically adjust the energy state vector to obtain an adjusted energy state vector.

[0009] S2. Perform transition adjustment on the adjusted energy state vector to obtain a transition - adjusted energy state vector; based on the transition - adjusted energy state vector, perform multi - stage path optimization to obtain an optimal scheduling plan.

[0010] Preferably, S1 specifically includes:

[0011] Based on the energy state vector, calculate the instantaneous consumption rate of energy and set the supply - demand balance constraint.

[0012] Preferably, S1 specifically includes:

[0013] The adaptive weighting mechanism, based on the energy state vector, introduces a time - adaptive weighting matrix and an energy - state adjustment term, and combines the instantaneous consumption rate of energy to calculate the expected state of energy at the next moment to obtain an adjusted energy state vector.

[0014] Preferably, S1 specifically includes:

[0015] By introducing a scheduling adaptability coefficient, calculate the scheduling weights of different energies to obtain a time - adaptive weighting matrix.

[0016] Preferably, S1 specifically includes:

[0017] By introducing external environmental impact factors and calculating in combination with the total energy demand, an energy state adjustment term is obtained.

[0018] Preferably, the S2 specifically includes:

[0019] Introduce a non-linear state transition operator to perform transition adjustment on the adjusted energy state vector to obtain the energy state vector after transition adjustment. The specific formula is as follows:

[0020] ,

[0021] where, is the energy state vector after transition adjustment at time is the non-linear state transition operator; and respectively represent the minimum and maximum energy consumption states of the energy system; is the energy state vector at time is the adjusted energy state vector at time

[0022] Preferably, the S2 specifically includes:

[0023] Based on the energy state vector after transition adjustment, combined with the target energy state vector, calculate the energy scheduling deviation, and introduce a weighting factor to construct an objective optimization function.

[0024] Preferably, the S2 specifically includes:

[0025] Solve the optimization objective function to obtain the optimal time-adaptive weighting matrix and the instantaneous consumption rate of energy, and generate an energy scheduling plan; when the energy scheduling deviation exceeds a preset threshold, enter the secondary optimization mode to adjust the energy scheduling plan.

[0026] Preferably, the S2 specifically includes:

[0027] In the process of realizing the secondary optimization mode, adjust the energy state vector after transition adjustment through the gradient descent strategy with an adaptive step size to obtain the optimal energy scheduling plan; according to the optimal energy scheduling plan, adjust the supply ratio of different energy forms to ensure that the energy distribution reaches the optimal state.

[0028] A multi-dimensional energy intelligent management and control system based on an adaptive optimization algorithm includes the following parts:

[0029] Data acquisition and preprocessing module, energy state modeling and dynamic adjustment module, non-linear transition adjustment module, optimization calculation and scheduling decision module, energy scheduling execution module;

[0030] The data acquisition and preprocessing module monitors multi-dimensional energy consumption data in real time and performs preprocessing, including time synchronization, outlier removal, and missing data interpolation, to obtain preprocessed multi-dimensional energy consumption data; the preprocessed multi-dimensional energy consumption data is transmitted to the energy state modeling and dynamic adjustment module;

[0031] The energy state modeling and dynamic adjustment module analyzes the energy consumption state information based on the preprocessed multi-dimensional energy consumption data, constructs a multi-dimensional energy state model, and calculates the energy state vectors at different time steps; introduces a time-adaptive weighting matrix to adjust the consumption ratios of different energy forms, and combines the energy state adjustment term to adjust the energy state vectors to obtain adjusted energy state vectors; the adjusted energy state vectors are transmitted to the non-linear transition adjustment module;

[0032] The non-linear transition adjustment module randomly perturbs the energy state through a non-linear state transition operator to obtain the energy state vectors after transition adjustment; the energy state vectors after transition adjustment are transmitted to the optimization calculation and scheduling decision module;

[0033] The optimization calculation and scheduling decision module calculates the energy scheduling deviation based on the energy state vectors after transition adjustment, combines with the target energy state vectors, introduces a weighting factor, and constructs an optimization objective function; solves the optimization objective function to generate an energy scheduling plan; when the energy scheduling deviation exceeds a preset threshold, it enters the secondary optimization mode, and adjusts the energy scheduling plan through a gradient descent strategy with an adaptive step size to obtain the optimal energy scheduling plan; the optimal energy scheduling plan is transmitted to the energy scheduling execution module and feedback to the non-linear transition adjustment module;

[0034] The energy scheduling execution module adjusts the supply ratios of different energy forms according to the optimal energy scheduling plan and feeds back the actual execution situation to the data acquisition and preprocessing module.

[0035] The beneficial effects of the technical solution of the present invention are:

[0036] 1. By defining multi-dimensional energy state variables, calculating the instantaneous consumption rate of energy, and setting the supply-demand balance constraint, the present invention ensures that at any moment, the total energy supply always meets the demand, avoiding energy waste and shortage; by introducing a time-adaptive weighting matrix on the basis of energy state modeling, the scheduling weights of different energy forms can be dynamically adjusted according to real-time energy consumption data, demand changes, and environmental impact factors, thereby optimizing the energy allocation ratio and improving the utilization efficiency of the overall energy system.

[0037] 2. In response to the dynamic changes of the energy system in a complex environment, the present invention introduces an energy state adjustment term, enabling the energy scheduling scheme to adapt to changes in external conditions, optimize and adjust the energy consumption path, dynamically correct the energy scheduling scheme, endowing the energy system with stronger environmental adaptability, thereby reducing unnecessary energy consumption and improving energy utilization efficiency.

[0038] 3. To avoid falling into local optima, the present invention introduces a non-linear state transition operator, which adjusts the energy state vector by making transitions during each optimization process to explore a better energy scheduling trajectory. The transition operator can perform global searches among different energy scheduling schemes through a non-linear jump mechanism, preventing long-term energy efficiency degradation caused by short-term optimization, ensuring the flexibility of the energy system during the optimization process, making resource allocation more balanced, and further enhancing the global optimality of energy scheduling.

[0039] 4. During the energy scheduling process, the present invention adopts a multi-stage path optimization method to ensure that the energy consumption path gradually approaches the optimal scheduling trajectory. By comprehensively considering the evolution of the energy state within different time steps, the energy scheduling can be adjusted smoothly, optimizing the trade-off between short-term and long-term scheduling objectives, ensuring the stability of the energy system, making the energy scheduling scheme applicable not only to the current energy demand but also to predicting future energy usage trends based on historical data, thereby enabling early optimization and adjustment and improving the sustainability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a structural diagram of a multi-dimensional energy intelligent management and control system based on an adaptive optimization algorithm according to the present invention;

[0041] Figure 2 It is a flowchart of a multi-dimensional energy intelligent management and control method based on an adaptive optimization algorithm according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0044] The following specifically describes the specific solutions of a multi-dimensional energy intelligent management and control system and method provided by the present invention in conjunction with the accompanying drawings.

[0045] Refer to the attached Figure 1 , which shows the structural diagram of a multi-dimensional energy intelligent management and control system provided by an embodiment of the present invention. The system includes the following parts:

[0046] Data acquisition and preprocessing module, energy status modeling and dynamic adjustment module, non-linear transition adjustment module, optimization calculation and scheduling decision-making module, energy scheduling execution module;

[0047] The data acquisition and preprocessing module monitors the multi-dimensional energy consumption situation in real time through a distributed sensor network, comprehensively obtains the current energy consumption data, obtains the multi-dimensional energy consumption data, and performs preprocessing, including time synchronization, outlier removal, and missing data interpolation, to establish a complete energy consumption data stream and obtain the preprocessed multi-dimensional energy consumption data; transmits the preprocessed multi-dimensional energy consumption data to the energy status modeling and dynamic adjustment module;

[0048] The energy status modeling and dynamic adjustment module analyzes the energy consumption status information based on the preprocessed multi-dimensional energy consumption data, constructs a multi-dimensional energy status model, calculates the energy status vectors at different time steps to ensure that the energy system meets the supply-demand balance constraint; introduces a time-adaptive weighted matrix to adjust the consumption ratio of different energy forms, and combines the energy status adjustment term to adjust the energy status vector to adapt to external environmental changes and improve energy utilization efficiency, obtaining the adjusted energy status vector; transmits the adjusted energy consumption vector to the non-linear transition adjustment module;

[0049] The non-linear transition adjustment module randomly perturbs the adjusted energy status vector through a non-linear state transition operator to prevent the optimization from falling into a local optimum, obtaining the energy status vector after transition adjustment; transmits the energy status vector after transition adjustment to the optimization calculation and scheduling decision-making module;

[0050] The optimization calculation and scheduling decision-making module calculates the energy scheduling deviation based on the energy status vector after transition adjustment and in combination with the target energy status vector, introduces a weighting factor, and constructs an optimization objective function; solves the optimization objective function to generate an energy scheduling plan; judges whether the current energy scheduling plan meets the optimization objective by calculating the energy scheduling deviation. If it does not meet the requirement, it enters the secondary optimization mode, optimizes the energy scheduling trajectory through a gradient descent strategy with an adaptive step size, adjusts the energy scheduling plan, obtains the optimal energy scheduling plan, and realizes reasonable energy allocation; transmits the optimal energy scheduling plan to the energy scheduling execution module and feeds it back to the non-linear transition adjustment module;

[0051] The energy dispatch execution module adjusts the supply ratios of different energy forms according to the optimal energy dispatch plan, ensures that the energy distribution reaches the optimal state, and feeds back the actual execution situation to the data acquisition and preprocessing module for real-time monitoring and optimization adjustment.

[0052] Refer to the appendix Figure 2 , which shows a flowchart of a multi-dimensional energy intelligent control method based on an adaptive optimization algorithm provided by an embodiment of the present invention. The method includes the following steps:

[0053] S1. Real-time monitor and preprocess multi-dimensional energy consumption data to obtain preprocessed multi-dimensional energy consumption data; based on the preprocessed multi-dimensional energy consumption data, construct a multi-dimensional energy state model to obtain an energy state vector; introduce an adaptive weighting mechanism to dynamically adjust the energy state vector to obtain an adjusted energy state vector;

[0054] Real-time monitor the consumption of various energy forms through a distributed sensor network to ensure that the acquired data can comprehensively reflect the operating state of the current energy system. Various sensors are installed on the energy supply equipment, the load side of the user terminal, and the environmental monitoring points to obtain key data such as energy consumption, supply capacity, and external environment parameters.

[0055] For electric energy, the acquisition device records the instantaneous power, voltage, current, and the operating state of the device, and stores the power curve for subsequent analysis; for thermal energy, the sensor monitors the heat load demand, transmission temperature, and heat exchange efficiency to ensure the rationality of energy distribution; for gas energy, obtain the gas flow rate, pressure change, and the operating state of the transmission pipeline to evaluate the supply-demand balance in real time. In addition, environmental parameters (such as temperature, humidity, wind speed) are obtained by an independent sensing module and synchronized with the energy consumption data to support environmental adaptability calculations. During the data transmission process, preprocess all multi-dimensional energy consumption data, including time synchronization, outlier removal, and missing data interpolation, to obtain preprocessed multi-dimensional energy consumption data, so as to ensure the stability and reliability of the input data received during the subsequent optimization dispatch process and provide accurate real-time information for energy optimization dispatch.

[0056] Based on the preprocessed multi-dimensional energy consumption data, define multi-dimensional energy state variables, including real-time data in multiple dimensions such as electric energy, thermal energy, and gas energy, and construct a multi-dimensional energy state model to obtain the energy state vector of the energy system :

[0057] ,

[0058] wherein, represents at time The consumption status of different types of energy; is the total number of energy types; the instantaneous consumption rate of energy is expressed as:

[0059] ,

[0060] where, is the change in the energy state at time , that is, the instantaneous consumption rate; is the instantaneous consumption rate of the

[0061] th type of energy at time

[0062] . The instantaneous consumption rate of energy is affected by the total demand of the energy system and needs to satisfy the energy supply - demand balance constraint: is the total energy demand at time

[0063] . The energy supply - demand balance constraint ensures that at any time, the total energy supply in the energy system is equal to the demand, avoiding energy waste or shortage. After the multi - dimensional energy state model is completed, by introducing an adaptive weighting mechanism, the consumption ratio of different energy forms is dynamically adjusted according to the current consumption status of energy to ensure that while meeting the overall energy demand, the utilization efficiency of various types of energy is optimized as much as possible; specifically, at each time step, according to the current consumption status of each energy and the instantaneous consumption rate of energy, the expected state of energy at the next time step is calculated. Since the conversion efficiency, usage patterns, and environmental impact factors of different energies are different, direct linear adjustment will lead to local optimality or resource waste. Therefore, during the energy state adjustment process, a time - adaptive weighting matrix is introduced to optimize the energy allocation ratio. The adjustment formula for the energy state at

[0064] is as follows:

[0065] where, is the energy state vector at time , that is, the adjusted energy state vector; is the energy state adjustment term at time ; is

[0066] the time - adaptive weighting matrix at time

[0067] used to determine the scheduling weights of different energies, and the calculation method of each element represent the consumption status of the nth type of energy at the indicate the status difference between the nth type of energy and the mth type of energy; is the scheduling adaptability coefficient, obtained through experiments;

[0068] During the energy state adjustment process, in order to adapt to external environmental changes, an energy state adjustment term is introduced:

[0069] ,

[0070] wherein, is the external environment impact factor, calculated by the empirical regression method from real-time environmental data (such as temperature, wind speed); reflects the change rate of energy demand, indicating the future trend; is the environmental impact matrix at the

[0071] S2. Perform transition adjustment on the adjusted energy state vector to obtain the energy state vector after transition adjustment; based on the energy state vector after transition adjustment, perform multi-stage path optimization to obtain the optimal scheduling plan.

[0072] To prevent the energy system from falling into a locally optimal state and enhance its optimization ability in a complex dynamic environment, on the basis of energy state adjustment, a non-linear state transition operator is introduced, enabling the energy state to perform transition adjustment during the optimization process to obtain the energy state vector after transition adjustment, thereby exploring a better energy scheduling trajectory; through the non-linear state transition operator, the energy state not only updates the energy consumption distribution according to the traditional gradient optimization during each iterative adjustment process, but also introduces non-linear transitions during the optimization process, so as to have an adaptive trajectory correction ability, thus avoiding the imbalance of energy resource allocation caused by local extreme value traps. Specifically, the mathematical expression of the energy state transition adjustment is as follows:

[0073] ,

[0074] wherein, is the energy state vector after transition adjustment at the is the non-linear state transition operator, used to control the non-linear degree of energy trajectory adjustment, obtained through experiments; and They represent the minimum and maximum energy consumption states of the energy system respectively, which are obtained based on the statistical analysis of historical energy consumption data. The energy state transition can ensure that the energy scheduling does not fall into a fixed pattern, but randomly transitions within the optimal scheduling region continuously to guarantee the diversity of the optimization effect.

[0075] After the energy state transition adjustment, multi-stage path optimization is carried out to ensure that the energy consumption path gradually approaches the optimal scheduling trajectory within multiple time steps, so as to avoid the local optimum problem caused by short-term optimization, and at the same time ensure the dynamic adaptability of energy distribution. The optimal scheduling trajectory represents the time series of the target energy state vector. Due to the certain volatility of energy demand and environmental conditions, single-step adjustment may lead to the mismatch between the optimal state in the short term and the global optimum in the long term. Therefore, it is necessary to comprehensively consider the evolution of energy states within different time steps so that the energy scheduling scheme can be optimized and adjusted. Define the optimization objective within the future time steps to make the energy state at the current moment gradually approach the optimal energy state predicted from history. The optimization objective function is constructed as follows:

[0076] ,

[0077] where is the optimization objective function, which is used to measure the energy state vector after the moment and the target energy state vector The ultimate optimization goal is to minimize the optimization objective function to achieve optimal energy scheduling; represents the th future time step predicted from the current moment ; is the weighting factor for the th time step, which is used to control the trade-off between short-term and long-term optimization goals and can be obtained through experiments; is the expected target energy state vector for the th time step predicted from the current moment

[0078] and is calculated by performing regression analysis on historical energy consumption data and combining the influence of environmental factors on energy demand. The optimization objective function enables the energy scheduling to have a smooth adjustment trajectory within multiple time steps. After solving the optimization objective function, the optimal time-adaptive weighting matrix and the instantaneous consumption rate of energy are obtained and form the energy scheduling scheme. If the optimization objective fails to meet the scheduling requirements, that is, the predicted energy state vector If the energy scheduling deviation between them exceeds the allowable threshold, it will enter the secondary optimization mode to further adjust the energy scheduling plan to make it more in line with the dynamic characteristics of actual energy demand and environmental changes; the gradient descent method is used to adjust the energy scheduling trajectory to ensure that the system gradually converges to the optimal scheduling trajectory and obtain the optimal energy scheduling plan, where the energy scheduling trajectory represents the time series of the energy state vector. Specifically, first calculate the gradient of the optimization objective function and then correct the predicted energy state vector based on the gradient to reduce the energy scheduling deviation. The correction method adopts the gradient descent strategy with an adaptive step size, making the energy state vector after each correction closer to the global optimal solution and avoiding the oscillation problem caused by large step size updates. The correction process is as follows:

[0079] ,

[0080] where is the adjustment step size, used to control the amplitude of the energy state vector update, and is obtained through experiments; is the gradient of the optimization objective function, representing the sensitivity of the energy state vector to the optimization objective function.

[0081] During the optimization process, continuously evaluate whether the corrected energy state vector is closer to the target energy state vector, and decide whether to further adjust the step size according to the optimization convergence situation to improve the convergence stability, ensuring the rationality of energy distribution among various energy forms and maximizing the overall energy efficiency.

[0082] In summary, a multi-dimensional energy intelligent management and control system and method based on an adaptive optimization algorithm are completed.

[0083] The sequence of the invention embodiments is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be beneficial.

[0084] Each embodiment in this specification is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

[0085] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; 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 various embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A multi-dimensional energy intelligent management and control method based on an adaptive optimization algorithm, characterized in that: The following steps are involved: S1. Real-time monitoring of multi-dimensional energy consumption data and pre-processing. Based on the pre-processed multi-dimensional energy consumption data, a multi-dimensional energy state model is constructed to obtain an energy state vector. Based on the energy state vector, the instantaneous energy consumption rate is calculated, and supply and demand balance constraints are set. An adaptive weighting mechanism is introduced to dynamically adjust the energy state vector based on the instantaneous energy consumption rate, combined with a time adaptive weighting matrix and an energy state adjustment item, calculate the expected state of energy at the next moment, and obtain the adjusted energy state vector. The time adaptive weighted matrix is ​​obtained by introducing a scheduling adaptability coefficient and calculating the scheduling weights of different energy sources; the energy state adjustment item is calculated based on external environmental impact factors, energy demand change rate and environmental impact matrix, wherein the external environmental impact factors are calculated by real-time environmental data through an empirical regression method; S2. Introduce a nonlinear state transition operator to perform transition adjustment on the adjusted energy state vector to obtain the energy state vector after transition adjustment. The specific formula is as follows: ， in, yes Energy state vector after time transition adjustment; is a nonlinear state transition operator; and They represent the lowest and highest energy consumption states of the energy system respectively; yes Energy state vector at the moment; yes The energy state vector after adjustment at each moment; Based on the energy state vector adjusted by the transition, multi-stage path optimization is performed, combined with the target energy state vector, the energy scheduling deviation is calculated, and the target optimization function is constructed. : ， in, represents the total number of future time steps predicted; yes Energy state vector after time transition adjustment; It is The weighting factor for each time step; yes The target energy state vector expected at every moment; Solve the optimization objective function, obtain the optimal time-adaptive weighting matrix and the instantaneous energy consumption rate, and generate an energy scheduling plan.

2. According to claim 1, a multi-dimensional energy intelligent management and control method based on an adaptive optimization algorithm is characterized in that: The S2 specifically includes: When the energy scheduling deviation exceeds the preset threshold, it enters the secondary optimization mode and adjusts the energy scheduling plan.

3. According to claim 2, a multi-dimensional energy intelligent management and control method based on an adaptive optimization algorithm is characterized in that: The S2 specifically includes: In the process of implementing the secondary optimization mode, the energy state vector after transition adjustment is adjusted through the gradient descent strategy with adaptive step size to obtain the optimal energy scheduling plan; according to the optimal energy scheduling plan, the supply ratio of different energy forms is adjusted to ensure that the energy distribution reaches the optimal state.

4. A multi-dimensional energy intelligent management and control system based on an adaptive optimization algorithm, applied to a multi-dimensional energy intelligent management and control method based on an adaptive optimization algorithm as claimed in claim 1, characterized in that: Includes the following sections: Data acquisition and preprocessing module, energy state modeling and dynamic adjustment module, nonlinear transition adjustment module, optimization calculation and scheduling decision module, energy scheduling execution module; The data acquisition and preprocessing module monitors multi-dimensional energy consumption data in real time and performs preprocessing, including time synchronization, outlier removal, and missing data interpolation, to obtain preprocessed multi-dimensional energy consumption data; The pre-processed multi-dimensional energy consumption data is transmitted to the energy state modeling and dynamic adjustment module; The energy state modeling and dynamic adjustment module analyzes the energy consumption state information based on the pre-processed multi-dimensional energy consumption data, builds a multi-dimensional energy state model, and calculates the energy state vectors at different time steps; introduces a time-adaptive weighting matrix to adjust the consumption ratio of different energy forms, and adjusts the energy state vector in combination with the energy state adjustment item to obtain the adjusted energy state vector; transmits the adjusted energy state vector to the nonlinear transition adjustment module; The nonlinear transition adjustment module randomly perturbs the energy state through the nonlinear state transition operator to obtain the energy state vector after the transition adjustment; the energy state vector after the transition adjustment is transmitted to the optimization calculation and scheduling decision module; The optimization calculation and scheduling decision module calculates the energy scheduling deviation based on the energy state vector after transition adjustment and the target energy state vector, introduces weighting factors, and constructs the optimization objective function; solves the optimization objective function and generates an energy scheduling plan; when the energy scheduling deviation exceeds the preset threshold, it enters the secondary optimization mode, adjusts the energy scheduling plan through the gradient descent strategy with adaptive step size, and obtains the optimal energy scheduling plan; transmits the optimal energy scheduling plan to the energy scheduling execution module, and feeds it back to the nonlinear transition adjustment module; The energy scheduling execution module adjusts the supply ratio of different energy forms according to the optimal energy scheduling plan, and feeds back the actual execution status to the data acquisition and preprocessing module.

Images