Energy demand quantity analysis method and system

Abstract

The invention relates to the technical field of data mining, and provides an energy demand quantity analysis method and system. The method comprises the following steps: screening and grouping initial indexes of a predetermined target energy demand quantity to generate a plurality of index groups of the target energy demand quantity; performing frequency mixing operation on data with different frequencies in pre-acquired target energy demand data, and extracting common factors of a plurality of demand evaluation indexes in each index group in frequency mixing data generated by the frequency mixing operation in each quarter based on a frequency mixing dynamic factor model of a Markov switching mechanism, meanwhile, determining an energy demand attribute corresponding to the common factor of each quarter in each index group; and finally, according to a pre-constructed Markov chain-based synthesis index model, and according to the frequency mixing data, the common factors of each quarter of the plurality of demand evaluation indexes in each index group and the corresponding energy demand attributes, calculating the demand index of each quarter of the target energy.

Description

Technical Field

[0001] The present application relates to the field of data mining technology, and in particular to an energy demand analysis method and system. Background Art

[0002] Energy has a profound impact on economic and social development and stability. With the global energy transformation, traditional energy is facing unprecedented challenges and pressures.

[0003] Existing demand analysis models that reflect changes in energy demand primarily include the Dynamic Factor Model (DFM), the Diffusion Index Model (DI), and the Composite Index Model (CI). The Dynamic Factor Model is capable of processing diverse indicator data, extracting common factors from multiple energy indicators to depict synchronized fluctuations in energy demand. However, the Dynamic Factor Model has limitations in capturing and reflecting the asymmetry and dynamic changes in energy demand, particularly in terms of accuracy and timeliness when dynamically adjusting indicator weights to accommodate different time periods.

[0004] Composite index models and diffusion index models are widely used to assess the overall state of energy demand. The composite index model combines multiple energy indicators to generate a comprehensive index that reflects the overall state of energy demand. Its core concept is to weight different energy indicators according to certain weights to obtain a comprehensive score to measure and compare energy demand. The diffusion index model is mainly used to measure the degree of diffusion of energy indicators and reflect the overall state of energy demand. Its core concept is to construct an index reflecting energy demand by calculating the proportion of diffusion states (contraction or diffusion) in energy indicators. Summary of the Invention

[0005] The purpose of this application is to provide an energy demand analysis method and system to solve or alleviate the problems existing in the above-mentioned prior art.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] The present application provides an energy demand analysis method, comprising: step S101, screening and grouping initial indicators of a predetermined target energy demand to generate multiple indicator groups of the target energy demand; wherein each indicator group includes multiple demand evaluation indicators;

[0008] Step S102: performing a mixing operation on data of different frequencies in the pre-acquired target energy demand data, and extracting the common factors of each quarter for the plurality of demand evaluation indicators in each indicator group from the mixed data generated by the mixing operation based on a mixing dynamic factor model of a Markov switching mechanism, and determining the energy demand attributes corresponding to the common factors of each quarter in each indicator group;

[0009] Step S103 , calculating the demand index of the target energy in each quarter according to the pre-built Markov chain-based composite index model, the mixed data, the common factors of the multiple demand evaluation indicators in each indicator group in each quarter, and their corresponding energy demand attributes.

[0010] Preferably, in step S101, based on the time difference correlation coefficient analysis method, multiple initial indicators of the predetermined target energy demand are screened and grouped to generate a leading indicator group, a consistency indicator group and a lagging indicator group of the target energy demand.

[0011] Preferably, in step S102, the mixing dynamic factor model includes: a single factor observation equation, a factor dynamic equation and a state space equation;

[0012] The single factor observation equation is:

[0013]

[0014] Where Y m,t,1 is the mixed frequency data of monthly frequency in the tth quarter, Y q,t,2 is the mixed frequency data of quarterly frequency in the tth quarter; α is the intercept term, and β is the factor loading coefficient; is the common factor of multiple demand evaluation indicators of the j-th indicator group in the t-th quarter; is the data error of the mixed frequency data in the t-th quarter time period of the j-th indicator group; t and j are both positive integers, and t>1;

[0015] The factor dynamic equation is:

[0016]

[0017] Where, φ f is a lag operator, representing the common factor of multiple demand evaluation indicators of the jth indicator group in the t-1th quarter The common factor of multiple demand evaluation indicators of the jth indicator group in the tth quarter The hysteresis effect of S t is the Markov state variable of the multiple demand evaluation indicators of the j-th indicator group in the t-th quarter, representing the demand transfer probability of the target energy in the j-th indicator group from the demand in the t-1-th quarter to the demand in the t-th quarter; ν t is the random error of the mixed frequency data of the jth indicator group in the tth quarter, with a mean of 0 and a variance of ∈ v Normal distribution;

[0018] The state space equation is:

[0019]

[0020] Where Y t is the mixed frequency data in the tth quarter, including the mixed frequency data Y of the monthly frequency in the tth quarter m,t,1 and the mixed frequency data Y of quarterly frequency in quarter t q,t,2 ; A is the constant term vector, H is the load matrix, X t is the state variable matrix of the jth indicator group in the tth quarter, t is the intercept vector; is the state variable matrix X of the jth indicator group in the t-1th quarter t-1 The state variable matrix X of the jth indicator group in the tth quarter t The coefficient matrix of the lag effect; V t is the error matrix of the mixed data of the jth indicator group in the tth quarter.

[0021] Preferably, step S103 includes: calculating the symmetrical change rate C of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t), to determine the normalization factor A of the i-th demand evaluation indicator in the j-th indicator group within n quarters ij , and according to the symmetrical change rate C ij (t) and the normalization factor A ij , determine the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t); where t, i, j, and n are all positive integers, and t>1;

[0022] According to the standardized change rate S ij (t) Calculate the kth index in the jth index group j The average change rate R of the demand evaluation indicators in the t quarter j (t), to determine the normalization factor F of the jth indicator group in the nth quarter j ; where k j is a positive integer;

[0023] Based on the normalization factor F j , the average rate of change R j (t) is modified to obtain the kth index in the jth index group. j The first standardized average change rate V of the demand evaluation index in the t quarter j (t,S t );

[0024] The average growth rate r′ of the initial composite index of the predetermined plurality of indicator groups j and the target demand trend of the predetermined target energy G r , for the first standardized average rate of change V j (t,S t ) to adjust the trend and obtain the kth indicator group j The second standardized change rate V′ of the demand evaluation index in the t quarter j (t,S t );

[0025] According to the second normalized change rate V′ j (t,S t ) Calculate the trend-adjusted composite index I′ of the jth indicator group in the tth quarter j (t), and is based on the trend-adjusted average composite index of the jth group of indicators over n quarters and the predetermined benchmark index I′ of the jth index group j (1) Calculate the demand index CI of the target energy corresponding to the jth indicator group in the tth quarter j (t).

[0026] Preferably, in step S103, according to the mixed data, according to the formula:

[0027]

[0028] Calculate the symmetrical change rate C of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t); where Y ij (t) is the data matrix of the mixed frequency data of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter; ij (t-1) is the data matrix of the mixed data of the i-th demand evaluation indicator in the j-th indicator group in the t-1 quarter; λ is the common factor of multiple demand evaluation indicators in the j-th indicator group in the t-1 quarter Adjustment parameters; t, i, j are all positive integers, and t>1;

[0029] According to the formula:

[0030]

[0031] Determine the normalization factor A of the i-th demand evaluation indicator in the j-th indicator group within n quarters ij ; Wherein, n is a positive integer;

[0032] According to the formula:

[0033]

[0034] Determine the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t).

[0035] Preferably, in step S103, according to the formula:

[0036]

[0037] Determine the kth indicator group j The average change rate R of the demand evaluation indicators in the t quarter j (t); where w ij is the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t) weight; where t, i, j, k j are all positive integers, and t>1;

[0038] According to the formula:

[0039]

[0040] Determine the normalization factor F of the jth indicator group in n quarters j Where, S is the data error of the mixed frequency data of the jth indicator group in the tth quarter; t is the Markov state variable of multiple demand evaluation indicators of the jth indicator group in the tth quarter, representing the demand transfer probability of the target energy in the jth indicator group from the demand in the t-1th quarter to the demand in the tth quarter; R2(t) is the kth indicator group in the second indicator group j The average change rate of the demand evaluation indicators in the tth quarter; wherein the second indicator group is the consistency indicator group; n is a positive integer;

[0041] According to the formula:

[0042]

[0043] For the kth index group j The average change rate R of the demand evaluation indicators in the t quarter j (t) is modified to obtain the kth index in the jth index group. j The first standardized average change rate V of the demand evaluation index in the t quarter j (t,S t ).

[0044] Preferably, the indicator group includes: a leading indicator group, a consistency indicator group and a lagging indicator group;

[0045] The average growth rate of each indicator sequence in the consistency indicator group is calculated by the compound interest formula to determine the target demand trend G of the target energy. r ;

[0046] Based on the index synthesis method, after determining the initial synthetic indexes of the leading indicator group, the consistency indicator group and the lagging indicator group respectively, the average growth rate r' of the initial synthetic indexes of the leading indicator group, the consistency indicator group and the lagging indicator group is calculated by the compound interest formula j ;

[0047] According to the formula:

[0048]

[0049] Determine the Markov state variable S of the tth quarter based on the multiple demand evaluation indicators in the jth indicator group t The adjusted initial composite index I of the jth indicator group in the tth quarter j (t); where I j (t-1) is the Markov state variable S in the t-1 quarter based on the multiple demand evaluation indicators in the j-th indicator group t-1 The initial composite index of the adjusted j-th indicator group in the t-1 quarter; V j (t,S t ) is the kth indicator group j The first standardized average change rate V of the demand evaluation index in the t quarter j (t,S t ); t, j, k j are all positive integers, and t>1.

[0050] Preferably, in step S103, according to the formula:

[0051] V′ j (t,S t )=V j (t,S t )+(G r -r′ j )

[0052] For the kth index group j The first standardized average change rate V of the demand evaluation index in the tth quarter j (t,S t ) to perform trend adjustment and obtain the second standardized rate of change V′ j (t,St );where G r is the target demand trend of the predetermined target energy, r′ j is the average growth rate of the initial composite index of the plurality of indicator groups;

[0053] According to the formula:

[0054]

[0055] Calculate the demand index CI of the target energy corresponding to the jth indicator group in the tth quarter j (t); where I′ j (t) is the composite index of the jth indicator group in the tth quarter after trend adjustment; I′ j (t-1) is the trend-adjusted composite index of the jth indicator group in the t-1th quarter; I′ is the average composite index of the jth indicator group after trend adjustment in n quarters; j (1) is the pre-determined benchmark index of the jth indicator group; where t, j, k j are all positive integers, and t>1.

[0056] Preferably, the method further includes: determining the demand index dynamics of the target energy in each quarter based on the demand index of the target energy in each quarter and a preset index dynamic range, so as to generate a demand transfer probability matrix of the target energy in n quarters;

[0057] Determine the target energy demand dynamics transfer vector for the current quarter based on the target energy demand index dynamics for the current quarter;

[0058] According to the demand transfer probability matrix and the demand dynamic transfer vector of the target energy in the current quarter, the demand transfer probability vector of the target energy in the next quarter is calculated, and the exponential dynamic interval of the maximum element value in the demand transfer probability vector is selected as the demand exponential dynamics of the target energy in the next quarter.

[0059] The present application also provides an energy demand analysis system, comprising: an indicator screening and grouping unit, configured to screen and group predetermined initial indicators of target energy demand to generate a plurality of indicator groups of target energy demand; wherein each indicator group includes a plurality of demand evaluation indicators;

[0060] a factor extraction and attribute determination unit configured to perform a mixing operation on data of different frequencies in the pre-acquired target energy demand data, and extract the common factors of each quarter of the plurality of demand evaluation indicators in each indicator group from the mixed data generated by the mixing operation based on a mixing dynamic factor model of a Markov switching mechanism, and simultaneously determine the energy demand attributes corresponding to the common factors of each quarter in each indicator group;

[0061] The demand index determination unit is configured to calculate the demand index of the target energy in each quarter according to a pre-constructed Markov chain-based synthetic index model, the mixed data and the common factors of each quarter of the multiple demand evaluation indicators in each indicator group and the corresponding energy demand attributes.

[0062] Beneficial effects:

[0063] In the energy demand analysis method provided in this specification, the initial indicators of the predetermined target energy demand are screened and grouped to generate multiple indicator groups of the target energy demand, and each indicator group contains multiple demand evaluation indicators; at the same time, a mixing operation is performed on the data of different frequencies in the pre-acquired target energy demand data, and based on the mixing dynamic factor model of the Markov switching mechanism, the common factors of each quarter of the multiple demand evaluation indicators in each indicator group in the mixed data generated by the mixing operation are extracted separately, and the energy demand attributes corresponding to the common factors of each quarter in each indicator group are determined; finally, according to the pre-constructed Markov chain-based synthetic index model, the target energy demand index for each quarter is calculated according to the mixed data and the common factors of each quarter of the multiple demand evaluation indicators in each indicator group and their corresponding energy demand attributes.

[0064] Therefore, the mixed data is processed by a mixed dynamic factor model based on the Markov switching mechanism, which effectively avoids the data inconsistency and information loss problems of the traditional composite index method when facing data of different frequencies; the introduction of the Markov switching mechanism enables the model to automatically identify the different stages of energy demand and flexibly adjust the indicator weights according to the stage changes of energy demand, effectively avoiding the subjective human intervention in the traditional method, ensuring that the weight distribution is more scientific and reasonable, and improving the objectivity and adaptability of the model; at the same time, combining the Markov switching mechanism and the dynamic factor model, dynamically identifying and capturing the asymmetric changes in energy demand, and adjusting the weights according to the changes in demand, accurately reflecting the asymmetric characteristics of energy demand, improving the adaptability and accuracy of the demand index to changes in energy demand, enhancing the real-time monitoring and prediction capabilities of the demand index, providing more accurate and timely demand trend analysis, and improving the adaptability and foresight of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1A schematic flow chart of an energy demand analysis method according to some embodiments of the present application;

[0066] Figure 2 A logical diagram of an energy demand analysis method according to some embodiments of the present application;

[0067] Figure 3 A hardware schematic diagram of an energy demand analysis method according to some embodiments of the present application;

[0068] Figure 4 This is a structural schematic diagram of an energy demand analysis system provided according to some embodiments of the present application. DETAILED DESCRIPTION

[0069] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. Each example is provided by way of explanation of the present application and does not limit the present application. In fact, it will be clear to those skilled in the art that modifications and variations can be made in the present application without departing from the scope or spirit of the present application. For example, a feature shown or described as part of one embodiment can be used in another embodiment to produce yet another embodiment. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention should fall within the scope of protection of the embodiments of the present invention.

[0070] Among the existing demand analysis models that reflect energy demand changes, whether the dynamic factor model (DFM), the diffusion index (DI) model, or the composite index model (CI), there are significant problems in identifying and predicting energy demand changes, mainly manifested as follows:

[0071] First, data processing issues: (1) Insufficient integration of heterogeneous frequency data processing - Existing demand analysis models are usually based on data of the same frequency, such as quarterly or monthly data, and it is difficult to flexibly process monthly and quarterly frequency data that are simultaneously included in energy-related indicator data. This leads to insufficient data utilization and insufficient real-time and accurate reflection of energy demand; (2) Low system automation and data processing efficiency - Existing models rely on manual calculation and judgment when calculating and predicting energy demand indexes, involving a large amount of manual data processing and calculation work, which is not only cumbersome and inefficient, but also easily leads to poor accuracy of data processing and increases the risk of human error.

[0072] Second, the subjectivity of indicator selection and weighting: Existing demand analysis models generally rely on the selection and weighting of a set of energy indicators, a process that is highly subjective. Different studies may choose different indicators and weighting schemes based on their own preferences, resulting in differences in demand index results, lack of consistency and objectivity.

[0073] Third, there's the issue of energy demand identification: insufficient sensitivity to asymmetric energy demand. Existing composite index models typically assume symmetry in energy demand, meaning that artificial expansion and contraction periods are similar in length and magnitude. However, actual energy demand often exhibits asymmetric characteristics, with expansion periods often being longer than recessionary periods. Existing models are unable to effectively capture this asymmetry, limiting the accuracy and timeliness of demand indices.

[0074] Fourth, the limitations of dynamism and real-time performance: Traditional demand analysis models rely on fixed weights and historical data, making it difficult to promptly reflect the impact of rapidly changing emergencies. This characteristic makes the demand index slow to respond to changes in demand, affecting its real-time monitoring and forecasting capabilities and reducing its applicability to dynamic changes in demand.

[0075] Fifth, issues of complexity and transparency: Although the composite index model can provide a comprehensive indicator, the model calculation process is quite complex, making it difficult to fully evaluate its logic and effectiveness, which in turn affects the model's transparency and the public's trust in it.

[0076] Sixth, insufficient trend forecasting capabilities: Existing composite index models typically rely on leading indices for trend forecasting. However, traditional leading index methods often assume that future demand trends are closely related to current leading indicators, and do not fully consider complex nonlinear relationships and long-term trends in demand changes. Therefore, when dealing with complex cyclical fluctuations in energy demand, the forecast results may be inaccurate or delayed.

[0077] Seventh, the limitations of manual measurement: Energy demand forecasting often relies on manual calculations and judgment, which involves extensive manual data processing and computation. This manual method has numerous drawbacks. Firstly, it is time-consuming and labor-intensive, and is susceptible to human influence, leading to inconsistent results and reduced accuracy. Secondly, the data processing steps involved in manual calculations are complex, prone to omissions and errors. Especially when dealing with large-scale, complex data, manual calculations lack efficiency, reliability, and transparency.

[0078] Based on this, this specification proposes a mixed-frequency Markov dynamic factor demand analysis model based on synthetic index (MF-MS-DFM-CI). By introducing the mixed-frequency dynamic factor model (MF-DFM), the Markov switching mechanism (MS), and the synthetic index method (CI), it not only systematically solves the significant limitations of the existing dynamic factor model (DFM), synthetic index model (CI), and diffusion index model (DI) in processing heterogeneous frequency data, capturing energy demand asymmetry, dynamically adjusting indicator weights, and improving real-time and predictive capabilities, but also achieves a high degree of automation and systematization of demand forecasting by developing an automation system based on Python, Tkinter, and MySQL, thereby greatly improving computing efficiency, accuracy, and user experience.

[0079] like Figures 1 to 3 As shown, the energy demand analysis method includes:

[0080] Step S101 : Screening and grouping the predetermined initial indicators of target energy demand to generate a plurality of indicator groups of target energy demand.

[0081] In this instruction manual, initial indicators that can reflect the target energy demand are collected, such as the target total energy consumption, energy utilization efficiency, the average level of industrial automation (the proportion of automated equipment), energy conservation and emission reduction rate, target energy output, pollutant emission concentration (smoke, sulfur dioxide, nitrogen oxides, etc.), target energy unit energy consumption, unit energy consumption, target energy intensity, carbon emission intensity, energy renewable penetration rate (the proportion of renewable energy in total energy consumption), the proportion of clean energy, energy efficiency of energy-consuming equipment, etc.

[0082] Then, based on the time-difference correlation coefficient analysis method and the statistical properties of the indicators, the multiple initial indicators of the determined target energy demand were screened and grouped. The selected target energy demand demand evaluation indicators were divided into multiple indicator groups, each containing multiple demand evaluation indicators. Thus, the leading indicator group, consistency indicator group, and lagging indicator group of the target energy demand were generated through indicator grouping.

[0083] Specifically, before performing indicator screening, a baseline indicator that reflects energy demand is first determined. In this specification, the target total energy consumption, which is highly consistent with the energy demand fluctuation trend, is used as the baseline indicator. After determining the baseline indicator, the time-difference correlation coefficient between multiple initial indicators of target energy demand and the baseline indicator is calculated using a time-difference correlation coefficient analysis method. Indicator screening is performed based on the time-difference correlation coefficient to select multiple demand evaluation indicators. These indicators are then divided into a leading indicator group, a consistency indicator group, and a lagging indicator group.

[0084] In a specific example, define As the benchmark index, X={x1,x2,…,x n} are other indicators to be selected (i.e. initial indicators), r l is the time difference correlation coefficient, according to the formula:

[0085]

[0086] Calculate the time difference correlation coefficient r between the tlth initial index value and the tth benchmark index value l Where l is the leading or lagging period (negative values ​​are leading indicators, positive values ​​are lagging indicators, and zero is a coincidence indicator), l = {0, ±1, ±2…, ±L}, L is a positive integer; n l is the number of benchmark index values, that is, the number of elements in the benchmark index, y t is the tth benchmark index value, x t-l is the data of the previous period of other indicators to be selected, that is, the initial indicator value of the tlth, is the average value of other selected indicators, that is, the average value of n (n is a positive integer) initial indicator values, n l (n l is a positive integer) the average value of the benchmark indicator values.

[0087] By calculating the correlation coefficient of each candidate indicator with the benchmark indicator at different delay periods, the indicator with the largest time difference correlation coefficient is selected, and its leading or lagging period relative to the benchmark indicator is determined to divide the indicator groups. In this specification, the indicators with a time difference correlation coefficient exceeding 0.5 are screened, and the initial indicators with a time difference correlation coefficient exceeding 0.5 are divided into a leading indicator group, a consistency indicator group, and a lagging indicator group based on a time difference of at least 1 quarter. Here, the indicators in the leading indicator group are defined as leading indicators, the indicators in the consistency indicator group are defined as consistent indicators, and the indicators in the lagging indicator group are defined as lagging indicators.

[0088] Step S102: Perform a mixing operation on data of different frequencies in the pre-acquired target energy demand data, and based on the mixing dynamic factor model of the Markov switching mechanism, extract the common factors of each quarter of multiple demand evaluation indicators in each indicator group in the mixed data generated by the mixing operation, and determine the energy demand attributes corresponding to the common factors of each quarter in each indicator group.

[0089] In this application, the mixed-frequency dynamic factor model based on the Markov switching mechanism effectively integrates the high-frequency data (monthly data) and low-frequency data (quarterly data) in the obtained target energy demand data, and uses linear interpolation and nearest neighbor interpolation methods to fill in the missing values in the monthly and quarterly data, ensuring the integrity and timeliness of the data; the X-13ARIMA-SEATS method is used to perform seasonal adjustment and smoothing on the monthly data, further ensuring the consistency and comparability of the data at different time granularities.

[0090] The mixed-frequency dynamic factor model based on the Markov switching mechanism performs mixed-frequency operations on data of different frequencies, effectively avoiding the inconsistency of traditional composite index methods when facing data of different frequencies, and capturing the asymmetric changes in energy demand more accurately. Here, among the obtained target energy demand data, the mixed-frequency data at the monthly frequency within the t-th quarter is defined as Y m,t,1 , and the mixed-frequency data at the quarterly frequency within the t-th quarter is defined as Y q,t,2 , for {Y m,t,1 , -∞ < t < +∞} and {Y q,t,2 , -∞ < t < +∞}, a single-factor observation equation is established, specifically:

[0091]

[0092] In the formula, α is the intercept term, and β is the factor loading coefficient; <​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​Subject to the mean of 0 and variance of ∈ v Normal distribution.

[0096] S t is the Markov state variable of multiple demand evaluation indicators of the jth indicator group in the tth quarter, S t Obeying a first-order Markov process, with a certain state transition probability P(S t |S t-1 ), which represents the state transition probability of the target energy in the jth indicator group from the energy demand in the t-1th quarter to the energy demand in the tth quarter. Based on this, the intercept term α and the factor loading coefficient β can be dynamically adjusted to adapt to the dynamic changes in the target energy demand and reflect the expansion or contraction of the target energy demand.

[0097] In order to better adapt to the cyclical characteristics of target energy demand data, this specification uses a mixed dynamic factor model based on the Markov switching mechanism to capture the asymmetric fluctuation relationship between high-frequency data (monthly data) and low-frequency data (quarterly data). Specifically, the state space equation of the mixed dynamic factor model based on the Markov switching mechanism is established as follows:

[0098]

[0099] Where Y t is the mixed frequency data in the tth quarter, including the mixed frequency data of monthly frequency in the tth quarter m,t,1 and the mixed frequency data Y of quarterly frequency in quarter t q,t,2 ;X t is the state variable matrix of the jth indicator group in the tth quarter, representing the state probability of energy demand corresponding to the jth indicator group in the tth quarter in the mixed frequency data. t =A+HX t ) describes the observed variable Y t With the unobservable state variable X t The interdependence between them, A is the constant term vector; H is the load matrix, which describes the observed variable Y t With the unobservable state variable X t The relationship between the mixed data Y is obtained by nonlinear fitting method. t and the state variable matrix X t Perform nonlinear fitting to determine.

[0100] In the state space equation, the state equation (i.e. ) describes the state variable X t The dynamic path of Ξ is controlled by the Markov mechanism to effectively capture the asymmetric changes in energy demand. In the state space equation,t is the intercept vector, that is, the vector expression of the intercept term α; is the state variable matrix X of the jth indicator group in the t-1th quarter t-1 The state variable matrix X for the jth indicator group in the tth quarter t The coefficient matrix of the lag effect; V t is the error matrix of the mixed frequency data of the jth indicator group in the tth quarter, that is, the random error υ t Vector expression of .

[0101] In this manual, the mixed dynamic factor model is used to integrate the high-frequency (monthly) and low-frequency (quarterly) data of the target energy demand data to extract the common factors. Describes the synchronization of energy demands; common factors It follows a first-order autoregressive AR(1) process, and the Markov mechanism has two states, namely S t =0 or S t =1, S t =0 corresponds to energy demand μ1, S t =1 corresponds to energy demand μ2, μ1<0, represents the contraction of target energy demand; μ2>0, represents the expansion of target energy demand. The mixed dynamic factor model based on Markov switching mechanism is used to extract common factors from the high-frequency and low-frequency data of target energy demand data. Make the common factor It changes dynamically with the changes in Markov state variables, captures the asymmetric changes in energy demand, effectively ensures the dynamic adjustment of weight distribution in different time periods, and effectively enhances the adaptability to dynamic changes in energy demand.

[0102] Step S103 : Calculate the demand index of the target energy in each quarter according to the pre-built composite index model, the mixed data, the common factors of the multiple demand evaluation indicators in each indicator group in each quarter, and their corresponding energy demand attributes.

[0103] In this specification, a mixed dynamic factor model based on Markov switching mechanism can extract common factors from multiple demand evaluation indicators. The energy demand is described synchronously; at the same time, a Markov switching mechanism is introduced to dynamically adjust the weights of each demand index through state transfer to ensure that it can be adaptively adjusted according to different time periods (demand expansion or demand contraction).

[0104] Furthermore, in order to calculate the target energy demand index more accurately, the extracted common factors By integrating the traditional composite index model and introducing the Markov switching mechanism, the traditional composite index model is improved to achieve dynamic weight allocation. It not only makes full use of the implicit information in the data, but also makes the demand index more sensitive to the cyclical fluctuations of energy demand through state-dependent weight adjustment. Compared with the traditional composite index method, it effectively enhances the sensitivity and accuracy of the demand index to better reflect the dynamic changes in energy demand.

[0105] First, calculate the symmetrical change rate C of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t), to determine the standardized factor A of the i-th demand evaluation indicator in the j-th indicator group within n quarters ij ; Wherein, t, i, j, n are all positive integers, and t>1. Here, the symmetric change rate C ij In the calculation of (t), a dynamic common factor is introduced Characterize the common changes of multiple demand evaluation indicators. Specifically, based on the mixed frequency data, according to the formula:

[0106]

[0107] Calculate the symmetrical change rate C of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t). Where, Y ij (t) is the data matrix of the mixed frequency data of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter; Y ij (t-1) is the data matrix of the mixed data of the i-th demand evaluation indicator in the j-th indicator group in the t-1 quarter; λ is the common factor of multiple demand evaluation indicators in the j-th indicator group in the t-1 quarter Adjustment parameters for controlling common factors Impact on symmetric rate of change calculations.

[0108] The symmetrical change rate C of the i-th demand evaluation index in the j-th index group in the t-th quarter is obtained. ij (t), according to the formula:

[0109]

[0110] Determine the normalization factor A of the i-th demand evaluation indicator in the j-th indicator group within n quarters ij . Then, according to the symmetric change rate C ij (t) and normalization factor A ij , determine the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t). Specifically, according to the formula:

[0111]

[0112] Determine the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t). Thus, by standardizing the symmetrical rate of change, the impact of a single high-volatility indicator on the composite index can be effectively reduced.

[0113] The average change rate of multiple demand evaluation indicators in each indicator group directly reflects the overall change of each indicator group. In this specification, the Markov state variable S t The introduction of the average change rate enables dynamic adaptation to the dynamic changes in energy demand. ij (t) Calculate the kth index group j The average change rate R of the demand evaluation index in the t quarter j (t); Specifically, according to the formula:

[0114]

[0115] Determine the kth indicator group j The average change rate R of the demand evaluation index in the t quarter j (t); where w ij is the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij Here, the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter can be determined by the correlation coefficient method, factor analysis method, entropy weight method, etc. ij The weight w of (t) ij , to effectively ensure that the importance of each indicator in the composite index is reasonably reflected.

[0116] Different Markov states have different energy requirements, and different energy requirements correspond to different average change rate adjustment factors. j The average change rate R of the demand evaluation index in the t quarter j (t) Calculate the corresponding Markov state variable S t The normalization factor under . Specifically, according to the formula:

[0117]

[0118] Determine the normalization factor F for the jth indicator group in quarter n j Where, is the data error of the mixed frequency data of the jth indicator group in the tth quarter; S tis the Markov state variable of multiple demand evaluation indicators of the jth indicator group in the tth quarter, representing the state transition probability of the target energy in the jth indicator group from the energy demand in the t-1th quarter to the energy demand in the tth quarter; R2(t) is the kth indicator group in the second indicator group (i.e., consistency indicator group). j The average change rate of a demand evaluation indicator in quarter t.

[0119] Then, according to the current Markov state variable S t Adjust the standardized average rate of change, that is, based on the standardization factor F j , for the average rate of change R j (t) is modified to obtain the kth index group j The revised standardized average change rate of the demand evaluation index in the tth quarter, that is, the first standardized average change rate V j (t,S t ). Specifically, according to the formula:

[0120]

[0121] For the kth index group j The average change rate R of the demand evaluation index in the t quarter j (t) is modified to obtain the kth index group j The first standardized average change rate V of the demand evaluation index in quarter t j (t,S t ).

[0122] After determining the jth indicator group k j After the standardized average change rate of the demand evaluation indicators in the tth quarter is corrected, the average change rate of the indicator group is adjusted in trend by combining the initial composite index determined by the index composite method. In the calculation of the initial composite index, the average growth rate of each indicator sequence in the consistency indicator group is calculated by the compound interest formula to determine the target trend G of the target energy. r Specifically, first calculate the average growth rate r of each indicator sequence in the consistency indicator group using the compound interest formula i , that is, according to the formula:

[0123]

[0124] Calculate the average growth rate r of each indicator sequence in the consistency indicator group i ; In the formula sa, are the average values ​​of the first cycle and the last cycle of the i-th requirement evaluation indicator in the consistency indicator group, are the first cycle number and the last cycle number of the u-th demand evaluation indicator in the consistency indicator group; m i Y is the number of periods from the first cycle center to the last cycle center of the i-th demand evaluation indicator in the consistency indicator group; i = 2, 3, ..., k2, k2 is the number of demand evaluation indicators in the consistency indicator group. i (t) is the i-th demand evaluation indicator in the t-th quarter in the consistency indicator group.

[0125] Then, according to the average growth rate r of each indicator sequence in the consistency indicator group i Calculate the average growth rate of the consistency indicator group, that is, the target trend G r Specifically, according to the formula:

[0126]

[0127] Determine the average growth rate of the consistency indicator group, that is, the target trend G r .

[0128] At the same time, based on the index synthesis method, the initial synthesis indexes of the leading indicator group, consistency indicator group and lagging indicator group are determined respectively. Specifically, according to the formula:

[0129]

[0130] Determine the Markov state variable S in the tth quarter based on multiple demand evaluation indicators in the jth indicator group t The initial composite index I of the adjusted j-th indicator group in the t-th quarter j (t); where I j (t-1) is the Markov state variable S in the t-1 quarter based on multiple demand evaluation indicators in the j-th indicator group t-1 The initial composite index of the adjusted j-th indicator group in the t-1 quarter; V j (t,S t ) is the kth index group j The first standardized average change rate V of the demand evaluation index in quarter t j (t,S t ).

[0131] Then, the compound interest formula is used again to calculate the average growth rate r' of the initial composite index of the leading indicator group, consistency indicator group and lagging indicator group respectively j Specifically, according to the formula:

[0132]

[0133] Calculate the average growth rate r' of the initial composite index of the leading indicator group, consistency indicator group and lagging indicator groupj Where, are the average values ​​of the first cycle and the last cycle of the jth demand evaluation indicator in the indicator group, are the first cycle number and the last cycle number of the j-th demand evaluation indicator in the indicator group respectively; m is the number of cycles from the first cycle center to the last cycle center of the j-th demand evaluation indicator in the indicator group.

[0134] Then, according to the average growth rate r′ of the initial composite index of the determined multiple indicator groups j and target trend of target energy G r , for the first standardized average rate of change V j (t,S t ) to adjust the trend and get the kth indicator group j The adjusted and modified standardized average change rate of the demand evaluation index in the tth quarter, that is, the second standardized change rate V′ j (t,S t ). Specifically, according to the formula:

[0135]

[0136] For the kth index group j The revised standardized average change rate V of the demand evaluation index in the tth quarter j (t,S t ) to perform trend adjustment and obtain the second standardized rate of change V′ j (t,S t );where G r is the target trend of the predetermined target energy, r′ j is the average growth rate of the initial composite index of multiple indicator groups.

[0137] In this specification, the target trend G of the consistency indicator group is r As the target trend of target energy, the trend of the leading indicator group and the lagging indicator group are adjusted respectively to effectively ensure that the composite index of all indicator groups remains consistent in the long-term trend. Then, according to the adjusted modified standardized average change rate (i.e., the second standardized change rate) V′ j (t,S t ) Calculate the trend-adjusted composite index I′ for the jth indicator group in the tth quarter j (t). Specifically, according to the formula:

[0138]

[0139] Calculate the trend-adjusted composite index I′ for the jth indicator group in the tth quarter j (t); where I′j (t-1) is the composite index of the jth indicator group after trend adjustment in the t-1th quarter.

[0140] Finally, the trend-adjusted average composite index of the jth indicator group over n quarters is And the benchmark index I′ of the jth indicator group determined j (1) Calculate the demand index CI corresponding to the target energy index group j in the tth quarter j (t). Specifically, according to the formula:

[0141]

[0142] Determine the demand index CI corresponding to the jth indicator group of target energy in the tth quarter j (t). Where, I′ is the average composite index of the jth indicator group after trend adjustment in n quarters; j (1) is the pre-determined benchmark index of the hth indicator group.

[0143] This specification combines a mixed-frequency dynamic factor model with a Markov mechanism to improve upon the traditional composite index model. This improved composite index model can adjust in real time based on data updates. The Markov mechanism dynamically adjusts the weights of indicators according to the different stages of energy demand. The mixed-frequency dynamic factor model reflects changes in data at different frequencies in real time, and dynamic factors are used to adjust weights and capture changes in energy demand. Furthermore, the model's automated adjustments and transparent calculation process reduce subjective human interference, effectively improving the transparency and interpretability of energy forecasts.

[0144] Furthermore, after obtaining the demand index of the target energy in each quarter, the demand index of the target energy in the future quarter can be predicted by using the Markov chain model or the long short-term memory neural network. First, based on the demand index of the target energy in each quarter, the demand index state of the target energy in each quarter is determined based on the preset state interval. Specifically, based on the average demand index of the target energy in all quarters, and standard deviation σ, divide the energy demand index state interval, and define the interval The demand index state is "overcooled", define the interval The demand index state is "cold", define the interval The demand index status is "normal", define the interval The demand index state is "hot", define the interval The demand index status is "overheated".

[0145] In the "normal" state, energy demand is relatively stable; in the "slightly cold" state, energy demand is relatively shrinking; in the "overcooled" state, energy demand drops significantly; in the "slightly hot" state, energy demand rises relatively slowly; in the "overheated" state, energy demand over-expands. In this manual, 1, 2, 3, 4, and 5 are used to represent the five states of the target energy: "overcooled," "slightly cold," "normal," "slightly hot," and "overheated," and according to the formula:

[0146]

[0147] For the target energy state S i The number of occurrences r i Perform statistics; where n is the total number of quarters, t and n are both positive integers, and x t CI is the target energy demand index in quarter t j (t); I(x t ∈S i ) is a linear function, when the condition I(x t ∈S i )=1, otherwise I(x t ∈S i )=0.

[0148] At the same time, according to the formula:

[0149]

[0150] For the target energy in the tth quarter, the i-th state S i Transfer to the jth state S in the t+1th quarter j The number of occurrences z ij Perform statistics; where i, j∈n, i, j, n are all positive integers. I(x t ∈S i ;x t+1 ∈S j ) is a linear function. When the condition is met, I(x t ∈S i ;x t+1 ∈S j )=1, otherwise I(x t ∈S i ;x t+1 ∈S j )=0.

[0151] According to the target energy state S i The number of occurrences r i and the target energy state S in the tth quarter i Transfer to the jth state S in the t+1th quarter j The number of occurrences zij , generate the state transition probability matrix of the target energy in n quarters. Specifically, according to the formula:

[0152]

[0153] Calculate the target energy in the i-th state S in the t-th quarter i Transfer to the jth state S in the t+1th quarter j The state transition probability P ij , and then establish the state transition probability matrix P of the target energy in n quarters = (P ij ) 5×5 .

[0154] At the same time, according to the demand index state of the target energy in the current quarter, the state transition vector of the target energy in the current quarter is determined. Specifically, according to the formula:

[0155] v T ={P 11 ,…,P 1i ,…,P 1n}

[0156] Determine the state transition vector v of the target energy in the current quarter T ; Where n = 5. For the status S of the current quarter i , then the corresponding state transition vector P 1i =1, and the rest of the elements are 0.

[0157] Finally, according to the state transition probability matrix P and the state transition vector v of the target energy in the current quarter T , calculate the state transition probability vector of the target energy in the next quarter, and select the state interval with the maximum element value in the state transition probability vector as the demand index state of the target energy in the next quarter. Specifically, according to the formula:

[0158]

[0159] Determine the demand index state of the target energy in the next quarter, that is, select the state corresponding to the maximum state transition probability.

[0160] In a specific example, the demand index state corresponding to each quarter is determined according to the demand index of the target energy in each quarter, and the i-th state S of the target energy in the t-th quarter is calculated. i Transfer to the jth state S in the t+1th quarter j The number of occurrences z ij The statistics are shown in Table 1:

[0161] Table 1 Statistics of state transition times

[0162]

[0163] Then, according to the formula:

[0164]

[0165] Calculate the target energy in the i-th state S in the t-th quarter i Transfer to the jth state S in the t+1th quarter j The state transition probability P ij , establish the state transition probability matrix P of the target energy within n quarters, specifically:

[0166]

[0167] It can be seen that the state transition probability is:

[0168]

[0169] Therefore, the probability that the energy demand index in this embodiment is in a normal state is predicted to be 90.14%.

[0170] In this specification, predicting the most likely state of the energy demand index in the next quarter through the Markov chain model is a quantitative analysis, and predicting the trend of changes in the energy demand index based on the trend of changes in the leading index is a qualitative analysis. By combining quantitative analysis with qualitative analysis, the subjectivity of the prediction is effectively reduced, making the prediction results more objective and scientific.

[0171] In another specific example, when forecasting the demand index of a target energy source for future quarters, a long-short-term memory (LSTM) neural network model was introduced to effectively capture the long-term and short-term dependencies in time series data. By learning from the historical quarterly demand index data of the target energy source, future changes in the energy demand index were predicted. Unlike traditional methods, the LSTM neural network model continuously updates model weights, iterates training, and automatically extracts effective features from the data, reducing reliance on manual intervention. Furthermore, the LSTM neural network effectively captures long-term trends and complex fluctuations, better addressing nonlinear relationships and sudden changes in the target energy source's cyclical changes.

[0172] In addition, this manual also uses the Python programming language, Tkinter interface development and MySQL database technology to build a highly systematic and automated demand forecasting platform. Specifically, (1) Data processing automation: Use the data processing library in Python (such as Pandas, NumPy, etc.) to clean, interpolate and preprocess the target energy demand data of different frequencies. The automated data processing process not only improves work efficiency, but also effectively avoids human omissions and calculation errors. (2) Graphical user interface (GUI) design: Use Tkinter to build an interactive graphical user interface, allowing users to input data, control the calculation process and display results through a visual interface, thereby lowering the usage threshold and improving the convenience of operation. (3) Database management: Through the MySQL database management system, various energy indicator data, calculation results and historical records are stored and managed. The MySQL database ensures long-term data preservation, data consistency and query efficiency, and supports the needs of large-scale data processing and multiple queries. (4) Automated execution of the model: The system can automatically calculate the demand index based on the MF-MS-DFM-CI model, update the index results, and perform trend forecasting using the long-short-term memory neural network model. All calculation processes are automatically completed by the system, improving efficiency and accuracy. Therefore, the mixed-frequency Markov dynamic factor demand analysis model based on the composite index (MF-MS-DFM-CI) not only solves the key problems in the existing technology, but also significantly improves the prediction ability of energy demand through innovative model design and automated system implementation.

[0173] like Figure 4 As shown, this specification also provides an energy demand analysis system, including:

[0174] The indicator screening and grouping unit 401 is configured to screen and group the predetermined initial indicators of the target energy demand to generate multiple indicator groups of the target energy demand; wherein each indicator group includes multiple demand evaluation indicators;

[0175] The factor extraction and attribute determination unit 402 is configured to perform a mixing operation on data of different frequencies in the pre-acquired target energy demand data, and extract the common factors of each quarter for multiple demand evaluation indicators in each indicator group in the mixed data generated by the mixing operation based on a mixing dynamic factor model of a Markov switching mechanism, and determine the energy demand attributes corresponding to the common factors in each quarter for each indicator group;

[0176] The demand index determination unit 403 is configured to calculate the demand index of the target energy in each quarter according to a pre-constructed Markov chain-based composite index model, based on the mixed data and the common factors of the multiple demand evaluation indicators in each indicator group in each quarter and the corresponding energy demand attributes.

[0177] The energy demand analysis system provided in this specification can implement the steps and processes of the energy demand analysis method of any of the above embodiments and achieve the same technical effects, which will not be described in detail here.

[0178] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0179] In the present invention, the terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0180] The foregoing description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are readily apparent to those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for analyzing energy demand, characterized in that: include: Step S101: screening and grouping the predetermined initial indicators of target energy demand to generate multiple indicator groups of target energy demand; wherein each indicator group includes multiple demand evaluation indicators; Step S102: performing a mixing operation on data of different frequencies in the pre-acquired target energy demand data, and extracting the common factors of each quarter for the plurality of demand evaluation indicators in each indicator group from the mixed data generated by the mixing operation based on a mixing dynamic factor model of a Markov switching mechanism, and determining the energy demand attributes corresponding to the common factors of each quarter in each indicator group; Step S103 , calculating the demand index of the target energy in each quarter according to the pre-built Markov chain-based composite index model, the mixed data, the common factors of the multiple demand evaluation indicators in each indicator group in each quarter, and their corresponding energy demand attributes.

2. The energy demand analysis method according to claim 1, characterized in that: In step S101, Based on the time-difference correlation coefficient analysis method, multiple initial indicators of the predetermined target energy demand are screened and grouped to generate the leading indicator group, consistency indicator group and lagging indicator group of the target energy demand.

3. The energy demand analysis method according to claim 1, characterized in that: In step S102, the mixing dynamic factor model includes: a single factor observation equation, a factor dynamic equation and a state space equation; The single factor observation equation is: Where Y m,t,1 is the mixed frequency data of monthly frequency in the tth quarter, Y q,t,2 is the mixed frequency data of quarterly frequency in the tth quarter; α is the intercept term, β is the factor loading coefficient; f t j is the common factor of multiple demand evaluation indicators of the j-th indicator group in the t-th quarter; is the data error of the mixed frequency data in the t-th quarter time period of the j-th indicator group; t and j are both positive integers, and t>1; The factor dynamic equation is: Where, φ f is a lag operator, representing the common factor of multiple demand evaluation indicators of the jth indicator group in the t-1th quarter The common factor f of multiple demand evaluation indicators of the jth indicator group in the tth quarter t j The hysteresis effect of S t is the Markov state variable of the multiple demand evaluation indicators of the j-th indicator group in the t-th quarter, representing the demand transfer probability of the target energy in the j-th indicator group from the demand in the t-1-th quarter to the demand in the t-th quarter; υ t is the random error of the mixed frequency data of the jth indicator group in the tth quarter, with a mean of 0 and a variance of ∈ v Normal distribution; The state space equation is: Where Y t is the mixed frequency data in the tth quarter, including the mixed frequency data Y of the monthly frequency in the tth quarter m,t,1 and the mixed frequency data Y of quarterly frequency in quarter t q,t,2 ; A is the constant term vector, H is the load matrix, X t is the state variable matrix of the jth indicator group in the tth quarter, t is the intercept vector; is the state variable matrix X of the jth indicator group in the t-1th quarter t-1 The state variable matrix X of the jth indicator group in the tth quarter t The coefficient matrix of the lag effect; V t is the error matrix of the mixed data of the jth indicator group in the tth quarter.

4. The energy demand analysis method according to claim 1, characterized in that: Step S103 includes: Calculate the symmetrical change rate C of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t), to determine the normalization factor A of the i-th demand evaluation indicator in the j-th indicator group within n quarters ij , and according to the symmetrical change rate C ij (t) and the normalization factor A ij , determine the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t); where t, i, j, and n are all positive integers, and t>1; According to the standardized change rate S ij (t) Calculate the kth index in the jth index group j The average change rate R of the demand evaluation indicators in the t quarter j (t), to determine the normalization factor F of the jth indicator group in the nth quarter j ; where k j is a positive integer; Based on the normalization factor F j , the average rate of change R j (t) is modified to obtain the kth index in the jth index group. j The first standardized average change rate V of the demand evaluation index in the t quarter j (t,S t ); According to the average growth rate r of the initial composite index of the plurality of predetermined indicator groups ′ j and the target demand trend of the predetermined target energy G r , for the first standardized average rate of change V j (t,S t ) to adjust the trend and obtain the kth indicator group j The second standardized change rate V of the demand evaluation index in the t quarter ′ j (t,S t ); According to the second normalized change rate V ′ j (t,S t ) Calculate the composite index I after trend adjustment for the jth indicator group in the tth quarter ′ j (t), and is based on the trend-adjusted average composite index of the jth group of indicators over n quarters and the predetermined benchmark index I′ of the jth index group j (1) Calculate the demand index CI of the target energy corresponding to the jth indicator group in the tth quarter j (t).

5. The energy demand analysis method according to claim 4, characterized in that: In step S103, according to the mixed data, the formula: Calculate the symmetrical change rate C of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t); where Y ij (t) is the data matrix of the mixed frequency data of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter; ij (t-1) is the data matrix of the mixed frequency data of the i-th demand evaluation indicator in the j-th indicator group in the t-1 quarter; λ is the common factor f of multiple demand evaluation indicators in the j-th indicator group in the t-1 quarter t j Adjustment parameters; t, i, j are all positive integers, and t>1; According to the formula: Determine the normalization factor A of the i-th demand evaluation indicator in the j-th indicator group within n quarters ij ; Wherein, n is a positive integer; According to the formula: Determine the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t).

6. The energy demand analysis method according to claim 4, characterized in that: In step S103, according to the formula: Determine the jth indicator group j The average change rate R of the demand evaluation indicators in the t quarter j (t); where w ij is the standardized change rate S of the i-th demand evaluation indicator in the j-th indicator group in the t-th quarter ij (t) weight; where t, i, j, k j are all positive integers, and t>1; According to the formula: Determine the normalization factor F of the jth indicator group in n quarters j Where, S is the data error of the mixed frequency data of the jth indicator group in the tth quarter; t is the Markov state variable of multiple demand evaluation indicators of the jth indicator group in the tth quarter, representing the demand transfer probability of the target energy in the jth indicator group from the demand in the t-1th quarter to the demand in the tth quarter; R2(t) is the kth indicator group in the second indicator group j The average change rate of the demand evaluation indicators in the tth quarter; wherein the second indicator group is the consistency indicator group; n is a positive integer; According to the formula: For the kth index group j The average change rate R of the demand evaluation indicators in the t quarter j (t) is modified to obtain the kth index in the jth index group. j The first standardized average change rate V of the demand evaluation index in the t quarter j (t,S t ).

7. The energy demand analysis method according to claim 4, characterized in that: The indicator groups include: a leading indicator group, a consistency indicator group and a lagging indicator group; The average growth rate of each indicator sequence in the consistency indicator group is calculated by the compound interest formula to determine the target demand trend G of the target energy. r ; Based on the index synthesis method, after determining the initial synthetic indexes of the leading indicator group, the consistency indicator group and the lagging indicator group respectively, the average growth rate r of the initial synthetic indexes of the leading indicator group, the consistency indicator group and the lagging indicator group is calculated by the compound interest formula. ′ j ; According to the formula: Determine the Markov state variable S of the tth quarter based on the multiple demand evaluation indicators in the jth indicator group t The adjusted initial composite index I of the jth indicator group in the tth quarter j (t); where I j (t-1) is the Markov state variable S in the t-1 quarter based on the multiple demand evaluation indicators in the j-th indicator group t-1 The initial composite index of the adjusted j-th indicator group in the t-1 quarter; V j (t,S t ) is the kth indicator group j The first standardized average change rate V of the demand evaluation index in the t quarter j (t,S t ); t, j, k j are all positive integers, and t>1.

8. The energy demand analysis method according to claim 4, characterized in that: In step S103, according to the formula: V ′ j (t,S t )=V j (t,S t )+(G r -r ′ j ) For the kth index group j The first standardized average change rate V of the demand evaluation index in the tth quarter j (t,S t ) to perform trend adjustment and obtain the second standardized rate of change V ′ j (t,S t );where G r The target demand trend for the predetermined target energy, r ′ j is the average growth rate of the initial composite index of the plurality of indicator groups; According to the formula: Calculate the demand index CI of the target energy corresponding to the jth indicator group in the tth quarter j (t); where I′ j (t) is the composite index of the jth indicator group in the tth quarter after trend adjustment; I ′ j (t-1) is the trend-adjusted composite index of the jth indicator group in the t-1th quarter; I is the average composite index of the jth indicator group after trend adjustment in n quarters; ′ j (1) is the pre-determined benchmark index of the jth indicator group; where t, j, k j are all positive integers, and t>1.

9. The energy demand analysis method according to claim 1, characterized in that: Also includes: According to the demand index of the target energy in each quarter, based on the preset index dynamic range, the demand index dynamics of the target energy in each quarter is determined to generate the demand transfer probability matrix of the target energy in n quarters; Determine the target energy demand dynamics transfer vector for the current quarter based on the target energy demand index dynamics for the current quarter; According to the demand transfer probability matrix and the demand dynamic transfer vector of the target energy in the current quarter, the demand transfer probability vector of the target energy in the next quarter is calculated, and the exponential dynamic interval of the maximum element value in the demand transfer probability vector is selected as the demand exponential dynamics of the target energy in the next quarter.

10. An energy demand analysis system, characterized in that: include: An indicator screening and grouping unit is configured to screen and group the predetermined initial indicators of the target energy demand to generate a plurality of indicator groups of the target energy demand; wherein each indicator group includes a plurality of demand evaluation indicators; a factor extraction and attribute determination unit configured to perform a mixing operation on data of different frequencies in the pre-acquired target energy demand data, and extract the common factors of each quarter of the plurality of demand evaluation indicators in each indicator group from the mixed data generated by the mixing operation based on a mixing dynamic factor model of a Markov switching mechanism, and simultaneously determine the energy demand attributes corresponding to the common factors of each quarter in each indicator group; The demand index determination unit is configured to calculate the demand index of the target energy in each quarter according to a pre-constructed Markov chain-based synthetic index model, the mixed data and the common factors of each quarter of the multiple demand evaluation indicators in each indicator group and the corresponding energy demand attributes.

Images