Power optimization method and system based on intelligent data processing analysis and digital twin

Abstract

The present invention discloses an electric power optimization method and system based on intelligent data processing analysis and digital twins, which relates to the technical field of power system optimization, including: implementing the collection of power system data and preprocessing; extracting features from the preprocessed data, identifying problems in the power system, classifying them, and matching solutions; building a virtual model of the power system to verify the priority of the solution. The present invention analyzes data through the EMD algorithm, which can accurately identify problems in the power system and effectively classify them. It improves the efficiency of problem diagnosis and provides a reliable basis for selecting and matching the most appropriate solution. By constructing a digital twin model of the power system, the present invention enables the solution to be fully tested and verified before actual application. This step significantly improves the safety and reliability of decision-making and avoids potential risks and costs.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization, and specifically to a power optimization method and system based on intelligent data processing analysis and digital twins. Background Art

[0002] In the current technological context, the optimal management of power systems has always been a key research area, especially in the context of continued growth in global energy demand and the gradual integration of renewable energy resources into the power grid. Traditional power system management relies on empirical rules and simplified physical models for decision support, which has proven its effectiveness over the past few decades. However, as power systems become increasingly complex, including the integration of emerging technologies such as distributed generation, demand response, and electric vehicle charging networks, traditional approaches face huge challenges. To address these challenges, in recent years, intelligent data processing and analysis technologies, including machine learning, big data analysis, and artificial intelligence, have been introduced into the research and management of power systems. These technologies are capable of processing and analyzing large-scale, high-dimensional data sets, providing more accurate and dynamic decision support.

[0003] Despite this, the existing related technologies still have some shortcomings in power system optimization. First, most existing technologies focus on single-dimensional optimization, such as cost minimization, power generation efficiency improvement, or carbon emission reduction. Few methods can comprehensively consider multiple optimization objectives and constraints of the power system. Second, although intelligent data processing provides a new perspective for power system management, existing methods often ignore the physical nature and operational constraints of the power system, resulting in insufficient feasibility and safety of the optimization results in practical applications. In addition, as a typical dynamic system, the state of the power system changes over time. Existing technologies often lack effective dynamic optimization strategies and cannot adapt to real-time changes in the system state. Finally, although digital twin technology provides an innovative tool for simulating and predicting power systems, its application in power system optimization is still in its infancy and lacks systematic research and practical verification.

[0004] In view of the shortcomings of the above-mentioned existing technologies, our invention "Power optimization method and system based on intelligent data processing analysis and digital twin" proposes a comprehensive solution. This method not only uses intelligent data processing technology to conduct in-depth analysis of power system data to achieve accurate classification of problems and effective matching of solutions, but also builds a digital twin model of the power system to comprehensively consider the physical characteristics, operating constraints and dynamic changes of the system to achieve priority verification and dynamic optimization of solutions. The proposal of this method is expected to comprehensively improve the operating efficiency and safety of the power system, achieve multi-objective and dynamic system optimization, and provide more scientific, accurate and flexible decision-making support for power system management. By combining intelligent data processing and digital twin technology, our invention can not only overcome the limitations of existing technologies, but also provide an innovative optimization management strategy for the future development of power systems. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: how to overcome the problems in the prior art such as one-sided focus on a single optimization target, neglect of the physical nature and safety of the system, and lack of dynamic adaptability.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a power optimization method based on intelligent data processing analysis and digital twins, which comprises the following steps:

[0008] Implement the collection of power system data and pre-processing.

[0009] Feature extraction is performed on the preprocessed data to identify and classify problems in the power system and match solutions.

[0010] Build virtual models of power systems to validate solution priorities.

[0011] As a preferred solution of the power optimization method based on intelligent data processing analysis and digital twins described in the present invention, wherein: the power system data includes power generation data, power transmission data, power distribution and consumption data, and equipment status data;

[0012] The preprocessing is to remove invalid, abnormal and duplicate data records from the collected power system data, standardize the data, and appropriately resample or divide the time window for time-sensitive data.

[0013] As a preferred solution of the power optimization method based on intelligent data processing analysis and digital twins described in the present invention, the feature extraction of the preprocessed data is to model the power system into a graph model, the nodes represent various entities in the power system, the edges represent power connections or flows, and construct a feature extraction function, the expression is:

[0014]

[0015]

[0016] Among them, X i is the feature vector of node i extracted by integrating time series data and its rate of change. α, β, and γ are coefficients for adjusting the contribution of time series data, first-order derivatives, and custom nonlinear function Ψ. Θ represents the parameter of nonlinear function Ψ. S i (t) is the power data sequence of node i at time t, IMF n (S i (t)) is the nth eigenmode function.

[0017] Using EMD algorithm to solve IMF n (S i (t)), including the preset power system time series data S i (t) Using extreme value detection, through difference and smoothing methods, all local maximum and minimum points are identified, and the upper envelope and lower envelope are obtained by adaptive interpolation method. The envelope mean is further calculated and the mean is calculated by introducing a method based on the local energy and frequency characteristics of the signal. i (t) minus the envelope mean, introduce a dynamic filtering mechanism based on data characteristics to output the signal level, and determine whether the detail d(t) meets the IMF condition.

[0018] When the number of maximum and minimum points is not equal and the difference is greater than 1, the current signal volatility is asymmetric, and the difference and smoothing methods are further adjusted to decompose the signal.

[0019] When the number of maximum and minimum points is equal or the difference is equal to 1, it is further determined whether the mean of the upper envelope and the lower envelope of the detail d(t) at any point is 0. If it is not 0, it is determined to be an unbalanced fluctuation and cannot be represented as a complete IMF. The original data or detail d(t) is further analyzed. If the mean of the upper envelope and the lower envelope of the detail d(t) at any point is 0, it is determined to be a complete IMF. It is further extracted from the original signal and the extracted IMFS is subtracted from the original data. i (t) = S i (t)-IMF n (S i(t)), repeat the EMD algorithm until no new IMF can be extracted from the remaining data.

[0020] The difference and smoothing method is expressed as:

[0021] D(t)=S i (t+1)-S i (t)

[0022]

[0023] Among them, S i (t) is the time series data of the i-th node in the power system at time t, D(t) is the first-order difference of the original time series data, k is the size of the smoothing window, and D′(t) is the difference sequence after smoothing.

[0024] The extreme points are determined by checking the sign change of the smoothed difference sequence. If D′(t-1)<0 and D′(t+1)>0, then S i (t) is the local minimum point. If D′(t-1)>0 and D′(t+1)<0, then S i (t) is the local maximum point.

[0025] The adjustment difference and smoothing processing method decomposes the signal by increasing or decreasing the smoothing window size k of the difference sequence. When the original sequence noise is higher than a threshold, k is increased to output a smoother difference sequence. When the signal change speed is greater than a threshold, k is reduced.

[0026] As a preferred solution of the power optimization method based on intelligent data processing analysis and digital twins described in the present invention, the identification and classification of problems in the power system is to construct a classification function based on the result output by the feature extraction function, which is expressed as:

[0027] Y i =C(X i ,W)

[0028]

[0029]

[0030]

[0031] Among them, W is the weight matrix in the classification function C, are the adjacent node sets of nodes i and j respectively, are the normalized degrees of nodes i and j respectively.

[0032] As a preferred solution of the power optimization method based on intelligent data processing analysis and digital twins described in the present invention, the matching solution is to build a matching model, which is expressed as follows:

[0033] S i =M(Y i )

[0034] Among them, Y i represents the state category of node i after classification based on the feature vector, S i is the set of solution strategies that match the problem of node i, and M is a rule mapping.

[0035] Determine the state category Y of node i according to the probability distribution i , select the category with the highest probability as the final state of node i, and determine the corresponding solution strategy set S through rule mapping M i .

[0036] As a preferred solution of the power optimization method based on intelligent data processing analysis and digital twins described in the present invention, the virtual model of the power system includes a load forecasting model, a power system cost model, a stability assessment model, and a safety and reliability assessment model.

[0037] The load forecasting model is expressed as:

[0038]

[0039] in, represents the predicted load at time t, L t-1 ,L t-2 ,…,L t-n represents historical load data, Θ represents model parameters.

[0040] The power system cost model is expressed as:

[0041]

[0042] Among them, c i is the unit cost of the ith generating unit, P g,i is the power generation, λ is the penalty coefficient for load forecast error, L j and are the actual and predicted loads, respectively.

[0043] The stability evaluation model is expressed as:

[0044]

[0045] Where S is the stability index, Δω(t) is the system frequency deviation, ωmax is the maximum allowable frequency deviation, α is the attenuation coefficient, and T is the evaluation time.

[0046] The safety and reliability evaluation model is expressed as:

[0047]

[0048] Among them, R is the system reliability index, p f,i is the probability of failure of the ith component, n k is the number of components involved in the kth failure mode, σ k is the proportion of system performance loss caused by the kth failure mode.

[0049] As a preferred solution of the power optimization method based on intelligent data processing analysis and digital twins described in the present invention, the priority of the verification solution is to build a comprehensive scoring model and determine the priority of the solution according to the score. The expression is:

[0050] E k =ω a A k +ω b B k +ω c C k +ω d D k

[0051]

[0052]

[0053]

[0054]

[0055] Among them, L j is the actual load, is the solution k The predicted load, M is the total number of time points in the evaluation period, P g,i,k is the solution k The power generation of the i-th power generation unit, c i The unit cost of the i-th generating unit, λ is the penalty coefficient for load forecast error, Δω k (t) is the solution S k The resulting system frequency deviation, ω max Maximum permissible frequency deviation, n k is the number of components involved in the kth failure mode, p f,i The probability of failure of the ith component, A k, B k , C k , D k are the load forecast accuracy score, cost optimization efficiency score, stability score, safety and reliability score of solution Sk, respectively. k For the comprehensive rating.

[0056] Another object of the present invention is to provide a power optimization method system based on intelligent data processing analysis and digital twins, which can achieve accurate load forecasting and problem classification by deeply integrating and analyzing power system data, and simulate and verify the solution in an all-round way with the digital twin model. Through this method, the present invention solves the problems of the prior art in multi-objective optimization, dynamic adaptation and safety verification of power systems.

[0057] To solve the above technical problems, the present invention provides the following technical solutions: an electric power optimization method system based on intelligent data processing analysis and digital twins, comprising: a data collection and preprocessing module, a feature extraction and classification module, a solution matching and priority assessment module, a virtual model construction and verification module, and a comprehensive scoring module.

[0058] The data collection and preprocessing module collects data from the power system for data preprocessing, removes invalid, abnormal and duplicate data records, performs standardization processing, and performs appropriate resampling or time window division on time-sensitive data.

[0059] The feature extraction and classification module uses a feature extraction function to extract key features from preprocessed data, and classifies problems in the power system through a classification function.

[0060] The solution matching and priority assessment module is to construct a matching model, match appropriate solutions to various problems identified in the power system, and assess the priority of each solution through a comprehensive scoring model.

[0061] The virtual model construction and verification module is used to construct a virtual model of the power system, including load forecasting, cost model, stability and security assessment model, and verify the effects of different solutions without interfering with the actual power system operation through the virtual model.

[0062] The comprehensive scoring module comprehensively considers load forecasting accuracy, cost optimization efficiency, stability score and safety score, calculates a comprehensive score for each solution, and determines the basis for the priority of the final solution through scoring the comprehensive solution.

[0063] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the power optimization method based on intelligent data processing analysis and digital twins as described above are implemented.

[0064] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the power optimization method based on intelligent data processing analysis and digital twins as described above are implemented.

[0065] Beneficial effects of the present invention: The present invention analyzes data through the EMD algorithm, which can accurately identify problems in the power system and effectively classify them. This not only improves the efficiency of problem diagnosis, but also provides a reliable basis for selecting and matching the most appropriate solution. By constructing a digital twin model of the power system, the present invention enables the solution to be fully tested and verified before actual application. This step significantly improves the safety and reliability of decision-making and avoids potential risks and costs. The comprehensive scoring model provides a quantitative evaluation for the selection of different solutions, making the decision-making process more scientific and reasonable. This step ensures that the solution finally implemented can comprehensively meet the various optimization needs of the power system and achieve the best overall effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0067] Figure 1 An overall flow chart of a power optimization method based on intelligent data processing analysis and digital twins provided for the first embodiment of the present invention;

[0068] Figure 2 A structural diagram of an electric power optimization system based on intelligent data processing analysis and digital twins provided for the second embodiment of the present invention. DETAILED DESCRIPTION

[0069] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0070] Example 1

[0071] Reference Figure 1 As an embodiment of the present invention, a power optimization method based on intelligent data processing analysis and digital twin is provided, which is characterized by:

[0072] Implement the collection of power system data and pre-processing.

[0073] Feature extraction is performed on the preprocessed data to identify and classify problems in the power system and match solutions.

[0074] Create virtual models of power systems to verify the effectiveness and safety of solutions.

[0075] Based on the results of the simulation test, the solution is iteratively optimized.

[0076] The power system data includes power generation data, power transmission data, power distribution and consumption data, and equipment status data.

[0077] The preprocessing is to remove invalid, abnormal and duplicate data records from the collected power system data, standardize the data, and appropriately resample or divide the time window for time-sensitive data.

[0078] Further explanation is:

[0079] Power generation data includes the power generation, power generation efficiency, and operating status of various power stations such as hydropower, thermal power, wind power, and solar power.

[0080] Transmission data includes transmission line load, line loss rate, real-time grid load, etc.

[0081] Power distribution and consumption data involve end-user electricity consumption, peak and valley periods, and power quality (such as frequency and voltage).

[0082] Environmental data include temperature, wind speed, sunshine, etc. These environmental factors have a direct impact on renewable energy generation.

[0083] Equipment status data includes the operating status, maintenance records, fault history, etc. of key equipment.

[0084] For power systems, invalid data may include data generated when equipment fails, blank values ​​or illegal values ​​(such as negative power generation or consumption) during data collection. These data are useless for analysis and need to be identified and removed first. Outliers in power systems may be caused by equipment failures, emergencies (such as power outages, short circuits), or data transmission errors. Statistical methods (such as IQR, Z-score) or machine learning methods (such as isolation forests) can be used to identify and process outliers.

[0085] During the data collection process of the power system, duplicate records may be generated due to system failures or human errors. Identify and remove duplicate data to ensure the uniqueness and accuracy of the data.

[0086] Further explanation is:

[0087] Different power devices and sensors may report data in different units or dimensions (e.g., power may be reported in kW or MW). In order to unify the analysis, all data needs to be converted to consistent units and dimensions. In addition, for data with large range differences (such as power generation and ambient temperature), normalization or standardization is performed so that all variables are treated fairly in the model.

[0088] Power system data usually has the characteristics of time series, and different data may be collected at different frequencies (e.g., power generation may be recorded once an hour, while grid load may be recorded once a minute). Depending on the analysis requirements, it may be necessary to resample all data to a unified time frequency, such as every 15 minutes or every hour.

[0089] Time window partitioning: For problems such as analyzing power system load forecasting or consumption patterns, sliding window or fixed window methods can be used to partition time series data to capture periodic changes and trends.

[0090] The detailed preprocessing steps above not only improve the accuracy and reliability of power system data analysis, but also ensure that subsequent models better understand the characteristics and patterns of the data. This targeted preprocessing method provides a solid data foundation for solving power system-specific problems.

[0091] Feature extraction of preprocessed data is to transform the power system model into a graph model, where nodes represent various entities in the power system, edges represent power connections or flows, and construct a feature extraction function, which is expressed as:

[0092]

[0093]

[0094] Among them, X i is the feature vector of node i extracted by integrating time series data and its rate of change. α, β, and γ are coefficients for adjusting the contribution of time series data, first-order derivatives, and custom nonlinear function Ψ. Θ represents the parameter of nonlinear function Ψ. S i (t) is the power data sequence of node i at time t, IMF n (S i (t)) is the nth eigenmode function.

[0095] Using EMD algorithm to solve IMF n(S i (t)):

[0096] S1. Identify all maximum and minimum values: For a given power system time series data S i (t), first identify all local maximum and minimum points using the improved extreme value detection method. This step can be optimized by considering the local change rate of the data and adding noise tolerance to reduce misjudgment caused by data fluctuations.

[0097] S2. Interpolation to obtain envelope: Adaptive interpolation method is used for all maximum points (interpolation algorithm is selected based on local characteristics, such as cubic spline interpolation or Gaussian process regression based on the same part volatility) to obtain the upper envelope; the same method is used to obtain the lower envelope. This adaptive interpolation method can better reflect the nonlinear characteristics of power data.

[0098] S3. Calculate the mean: Calculate the mean m(t) of the upper envelope and the lower envelope, and introduce a method based on the dynamic adjustment of the local energy and frequency characteristics of the signal to calculate the mean, so as to more accurately capture the transient and long-term trends of the power system.

[0099] S4. Extract details: From the original data S i Subtract the mean m(t) from S(t) to get the detail d(t) = S i (t)-m(t). In order to better reflect the specific phenomena in the power system, a dynamic filtering mechanism based on data characteristics can be added in this step, such as dynamically adjusting the extraction process according to predefined power system state characteristics.

[0100] S5. Check IMF conditions: Check whether the detail d(t) meets the IMF conditions. At the same time, an adaptive IMF condition checking mechanism based on signal characteristics is introduced to adjust the strictness of the IMF conditions according to the local characteristics of the signal (such as the significance of the transient response and the noise level) to ensure that the extracted IMFs are more representative.

[0101] S6. Iterative process: subtracting the extracted IMFS from the original data i (t) = S i (t)-IMF n (S i (t)), and then repeat steps 1 to 5 until no new IMFs can be extracted from the remaining data. Instead of simply iterating until no new IMFs can be extracted, an intelligent stopping condition based on signal interpretation capability and analysis objectives is introduced to automatically determine the optimal stopping point of the iteration according to the power system analysis requirements.

[0102] Through this optimized EMD process, we not only improve the accuracy and applicability of feature extraction, but also increase the flexibility and pertinence of the process, making it more suitable for processing complex and non-stationary signals in power systems. This method provides a more reliable data basis for problem identification, classification and solution matching in power systems.

[0103] The difference and smoothing method is expressed as:

[0104] D(t)=S i (t+1)-S i (t)

[0105]

[0106] Among them, S i (t) is the time series data of the i-th node in the power system at time t, D(t) is the first-order difference of the original time series data, k is the size of the smoothing window, and D′(t) is the difference sequence after smoothing;

[0107] The extreme points are determined by checking the sign change of the smoothed difference sequence. If D′(t-1)<0 and D′(t+1)>0, then S i (t) is the local minimum point. If D′(t-1)>0 and D′(t+1)<0, then S i (t) is the local maximum point.

[0108] Adjusting the difference and smoothing method to decompose the signal is to increase or decrease the smoothing window size k of the difference sequence. When the noise of the original sequence is higher than the threshold, increase k to output a smoother difference sequence. When the signal change speed is greater than the threshold, reduce k.

[0109] The detail d(t)) refers to the step from the original signal S i (t) The purpose of EMD is to gradually extract the fluctuation components of various frequencies from the signal. Each step of the extracted components can be regarded as a "level of detail" of the original signal. This level of detail represents an intrinsic mode function IMF of the signal, which contains the specific frequency information of the signal.

[0110] Identifying and classifying problems in the power system is to construct a classification function based on the output of the feature extraction function, which is expressed as:

[0111] Y i =C(X i ,W)

[0112]

[0113]

[0114]

[0115] Among them, W is the weight matrix in the classification function C, are the adjacent node sets of nodes i and j respectively, are the normalized degrees of nodes i and j respectively.

[0116] The matching solution is to build a matching model, which is expressed as:

[0117] S i =M(Y i )

[0118] Among them, Y i represents the state category of node i after classification based on the feature vector, S i is the set of solution strategies that match the problem of node i, and M is a rule mapping.

[0119] Determine the state category Y of node i according to the probability distribution i , select the category with the highest probability as the final state of node i, and determine the corresponding solution strategy set S through rule mapping M i .

[0120] Constructing virtual models of power systems including load forecasting models, power system cost models, stability assessment models, and safety and reliability assessment models;

[0121] The load forecasting model is expressed as:

[0122]

[0123] in, represents the predicted load at time t, L t-1 ,L t-2 ,…,L t-n represents historical load data, Θ represents model parameters;

[0124] The power system cost model is expressed as:

[0125]

[0126] Among them, c i is the unit cost of the ith generating unit, P g,i is the power generation, λ is the penalty coefficient for load forecast error, L j and are the actual and predicted loads, respectively;

[0127] The stability evaluation model is expressed as:

[0128]

[0129] Where S is the stability index, Δω(t) is the system frequency deviation, ω max is the maximum allowable frequency deviation, α is the attenuation coefficient, and T is the evaluation duration;

[0130] The safety and reliability evaluation model is expressed as:

[0131]

[0132] Among them, R is the system reliability index, p f,i is the probability of failure of the ith component, n k is the number of components involved in the kth failure mode, σ k is the proportion of system performance loss caused by the kth failure mode.

[0133] The priority of the verification solution is to build a comprehensive scoring model and determine the priority of the solution based on the score. The expression is:

[0134] E k =ω a A k +ω b B k +ω c C k +ω d D k

[0135]

[0136]

[0137]

[0138]

[0139] Among them, L j is the actual load, is the solution k The predicted load, M is the total number of time points in the evaluation period, P g,i,k is the solution k The power generation of the i-th power generation unit, c i The unit cost of the i-th generating unit, λ is the penalty coefficient for load forecast error, Δω k (t) is the solution S k The resulting system frequency deviation, ω max Maximum permissible frequency deviation, n k is the number of components involved in the kth failure mode, p f,i The probability of failure of the ith component, Ak , B k , C k , D k are the load forecast accuracy score, cost optimization efficiency score, stability score, safety and reliability score of solution Sk, respectively. k For the comprehensive rating.

[0140] Example 2

[0141] Reference Figure 2 , which is an embodiment of the present invention, provides a system for a power optimization method based on intelligent data processing analysis and digital twins, which is characterized by: including a data collection and preprocessing module, a feature extraction and classification module, a solution matching and priority assessment module, a virtual model construction and verification module, and a comprehensive scoring module.

[0142] The data collection and preprocessing module collects data from the power system for data preprocessing, removes invalid, abnormal and duplicate data records, performs standardization, and performs appropriate resampling or time window division for time-sensitive data.

[0143] The feature extraction and classification module uses feature extraction functions to extract key features from preprocessed data and classifies problems in the power system through classification functions.

[0144] The solution matching and priority assessment module builds a matching model to match appropriate solutions to various problems identified in the power system and assesses the priority of each solution through a comprehensive scoring model.

[0145] The virtual model construction and verification module builds a virtual model of the power system, including load forecasting, cost model, stability and security assessment model. The virtual model is used to verify the effects of different solutions without interfering with the actual operation of the power system.

[0146] The comprehensive scoring module comprehensively considers load forecast accuracy, cost optimization efficiency, stability score and safety score, calculates a comprehensive score for each solution, and determines the basis for the priority of the final solution through scoring the comprehensive solution.

[0147] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0148] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0149] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0150] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0151] Example 3

[0152] In this embodiment, in order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments. This embodiment experiments the existing traditional method and the method of this embodiment respectively.

[0153] In this embodiment, an experiment is designed to verify the effectiveness of the "electricity optimization method and system based on intelligent data processing analysis and digital twin". The experiment aims to compare the performance of the present invention with the prior art in terms of power system load forecasting accuracy, cost optimization efficiency, system stability and security.

[0154] The test preparation phase includes collecting two months of power system operation data, which covers power generation, transmission, distribution and consumption data as well as status data of various equipment. The authenticity and accuracy of the collected data are ensured by cooperating with the power company. Then, the data preprocessing method proposed in this invention is used to denoise, standardize and divide the collected data into time windows in preparation for subsequent analysis and model building.

[0155] Construct feature extraction functions and classification models to model the power system into a graph model, where nodes represent various entities in the power system and edges represent power connections or flows. Through intelligent data processing and analysis technology, especially machine learning algorithms, features are extracted from preprocessed data and problems in the power system are effectively classified.

[0156] Next, a digital twin of the power system was created and several pre-selected solutions were validated in this virtual environment. Solutions included generation scheduling optimization, transmission line improvement options, and demand response strategies for the distribution network. Each solution was simulated in the digital twin based on its expected impact.

[0157] In order to evaluate and compare the effects of different solutions, this embodiment designs a comprehensive scoring model, which combines scores of multiple aspects such as load forecasting accuracy, cost optimization efficiency, stability and security, and calculates the comprehensive score of each solution to determine its priority.

[0158] Table 1 Data comparison table

[0159]

[0160] By analyzing the data in the above table, it can be clearly seen that the content of the present invention has significantly improved load forecasting accuracy, cost optimization efficiency, stability index and safety score compared with the prior art. Inventive solution C has improved load forecasting accuracy by 8% over the prior art, cost optimization efficiency by 15%, and stability index and safety score by 13% and 12% respectively. This improvement directly reflects that the present invention can more accurately understand the dynamic changes of the power system and effectively predict and respond to various problems in the system through the application of intelligent data processing and digital twin technology.

[0161] The comprehensive score further demonstrates the superiority of the present invention. By considering multiple key performance indicators to evaluate the solution, it is ensured that the selected solution can meet the optimization needs of the power system in many aspects. The comprehensive score of the invention solution C is the highest, showing its comprehensive advantages in improving prediction accuracy, reducing costs, enhancing system stability and improving safety.

[0162] These data support the innovative and novel effects of the present invention, and prove that the present invention can provide a more effective power system optimization solution compared with the prior art. Through intelligent data analysis and the application of digital twin models, the present invention improves the operating efficiency and safety of the power system.

[0163] Table 2 Data comparison table

[0164]

[0165] From the table data, it can be seen that the present invention shortens the system response time from 60 seconds to 15 seconds through optimization algorithms and efficient data processing processes. This rapid response capability is crucial for real-time monitoring of the power system and rapid response in emergency situations. The efficient data processing architecture of the new technology of the present invention increases the daily data processing volume from 5TB to 20TB, greatly enhancing the power system's data processing and analysis capabilities, and providing richer and more accurate data support for power optimization and decision-making.

[0166] The present invention introduces more flexible data analysis and optimization algorithms, which increases the number of adaptive adjustments that the system can make from 2 to 8 times per month, effectively improving the adaptability and flexibility of the power system to environmental changes. By optimizing power distribution and utilization efficiency, the energy saving and consumption reduction rate is increased from 5% to 20%, which not only significantly reduces operating costs, but also reduces the impact on the environment, helping to achieve sustainable development goals.

[0167] It should be noted that 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A power optimization method based on intelligent data processing analysis and digital twins, characterized in that: include: Implement the collection of power system data and pre-processing; Extract features from preprocessed data, identify and classify problems in the power system, and match solutions; Build a virtual model of the power system to verify the priority of the solution; The feature extraction of the preprocessed data is to model the power system into a graph model, where nodes represent various entities in the power system, edges represent power connections or flows, and construct a feature extraction function, which is expressed as: Among them, X i is the feature vector of node i extracted by integrating time series data and its rate of change. α, β, and γ are coefficients for adjusting the contribution of time series data, first-order derivatives, and custom nonlinear function Ψ. Θ represents the parameter of nonlinear function Ψ. S i (t) is the power data sequence of node i at time t, IMF n (S i (t)) is the nth intrinsic mode function, and the EMD algorithm is used to solve the IMF n (S i (t)); The identification and classification of problems in the power system is to construct a classification function based on the output of the feature extraction function, which is expressed as: Y i =C(X i ,W) Among them, W is the weight matrix in the classification function C, are the adjacent node sets of nodes i and j respectively, are the normalized degrees of nodes i and j respectively; The matching solution is to construct a matching model, which is expressed as: S i =M(Y i ) Among them, Y i represents the state category of node i after classification based on the feature vector, S i is the set of solution strategies matched to the problem of node i, and M is a rule mapping; Determine the state category Y of node i according to the probability distribution i , select the category with the highest probability as the final state of node i, and determine the corresponding solution strategy set S through rule mapping M i ; The virtual model of the power system includes a load forecasting model, a power system cost model, a stability assessment model, and a safety and reliability assessment model; The load forecasting model is expressed as: in, represents the predicted load at time t, L t-1 ,L t-2 ,…,L t-n represents historical load data, Θ represents model parameters; The power system cost model is expressed as: Among them, c i is the unit cost of the ith generating unit, P g,i is the power generation, λ is the penalty coefficient for load forecast error, L j and are the actual and predicted loads, respectively; The stability evaluation model is expressed as: Where S is the stability index, Δω(t) is the system frequency deviation, ω max is the maximum allowable frequency deviation, α is the attenuation coefficient, and T is the evaluation duration; The safety and reliability evaluation model is expressed as: Among them, R is the system reliability index, p f,i is the probability of failure of the ith component, n k is the number of components involved in the kth failure mode, σ k is the proportion of system performance loss caused by the kth failure mode; The priority of the verification solution is to build a comprehensive scoring model and determine the priority of the solution according to the score. The expression is: E k =ω a A k +oh b B k +oh c C k +oh d D k Among them, L j is the actual load, is the solution k The predicted load, M is the total number of time points in the evaluation period, P g,i,k is the solution k The power generation of the i-th power generation unit, c i The unit cost of the i-th generating unit, λ is the penalty coefficient for load forecast error, Δω k (t) is the solution S k The resulting system frequency deviation, ω max Maximum permissible frequency deviation, n k is the number of components involved in the kth failure mode, p f,i The probability of failure of the ith component, A k , B k , C k , D k The solutions S are k The load forecast accuracy score, cost optimization efficiency score, stability score, safety and reliability score, E k For the comprehensive rating.

2. The power optimization method based on intelligent data processing analysis and digital twinning according to claim 1, characterized in that: The power system data includes power generation data, power transmission data, power distribution and consumption data, and equipment status data; The preprocessing is to remove invalid, abnormal and duplicate data records from the collected power system data, standardize the data, and appropriately resample or divide the time window for time-sensitive data; The EMD algorithm is used to solve the IMF n (S i (t)), including the preset power system time series data S i (t) Using extreme value detection, through difference and smoothing methods, all local maximum and minimum points are identified, and the upper envelope and lower envelope are obtained by adaptive interpolation method. The envelope mean is further calculated and the mean is calculated by introducing a method based on the local energy and frequency characteristics of the signal. i (t) minus the envelope mean, introduce a dynamic filtering mechanism based on data characteristics to output the signal level, and determine whether the detail d(t) meets the IMF condition; When the number of maximum and minimum points is not equal and the difference is greater than 1, the current signal volatility is asymmetric, and the difference and smoothing methods are further adjusted to decompose the signal; When the number of maximum and minimum points is equal or the difference is equal to 1, it is further determined whether the mean of the upper envelope and the lower envelope of the detail d(t) at any point is 0. If it is not 0, it is determined to be an unbalanced fluctuation and cannot be represented as a complete IMF. The original data or detail d(t) is further analyzed. If the mean of the upper envelope and the lower envelope of the detail d(t) at any point is 0, it is determined to be a complete IMF. It is further extracted from the original signal and the extracted IMFS is subtracted from the original data. i (t) = S i (t)-IMF n (S i (t)), repeat the EMD algorithm until no new IMF can be extracted from the remaining data; The difference and smoothing method is expressed as: D(t)=S i (t+1)-S i (t) Among them, S i (t) is the time series data of the i-th node in the power system at time t, D(t) is the first-order difference of the original time series data, k is the size of the smoothing window, and D′(t) is the difference sequence after smoothing; The extreme points are determined by checking the sign change of the smoothed difference sequence. If D′(t-1)<0 and D′(t+1)>0, then S i (t) is the local minimum point. If D′(t-1)>0 and D′(t+1)<0, then S i (t) is the local maximum point; The adjustment difference and smoothing processing method decomposes the signal by increasing or decreasing the smoothing window size k of the difference sequence. When the original sequence noise is higher than a threshold, k is increased to output a smoother difference sequence. When the signal change speed is greater than a threshold, k is reduced.

3. A system using the power optimization method based on intelligent data processing analysis and digital twin as described in any one of claims 1 to 2, characterized in that: It includes data collection and preprocessing module, feature extraction and classification module, solution matching and priority assessment module, virtual model building and verification module and comprehensive scoring module; The data collection and preprocessing module collects data from the power system for data preprocessing, removes invalid, abnormal and duplicate data records, performs standardization processing, and performs appropriate resampling or time window division on time-sensitive data; The feature extraction and classification module uses a feature extraction function to extract key features from the preprocessed data and classifies the problems in the power system through a classification function; The solution matching and priority assessment module is to build a matching model, match appropriate solutions to various problems identified in the power system, and assess the priority of each solution through a comprehensive scoring model; The virtual model construction and verification module is to construct a virtual model of the power system, including load forecasting, cost model, stability and security assessment model, and verify the effects of different solutions without interfering with the actual power system operation through the virtual model; The comprehensive scoring module comprehensively considers load forecasting accuracy, cost optimization efficiency, stability score and safety score, calculates a comprehensive score for each solution, and determines the basis for the priority of the final solution through scoring the comprehensive solution.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the power optimization method based on intelligent data processing analysis and digital twins described in any one of claims 1 to 2 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power optimization method based on intelligent data processing analysis and digital twins as described in any one of claims 1 to 2 are implemented.

Images