Power grid project screening and state tracking method, device, equipment, medium and product

Abstract

The invention discloses a power grid project screening and state tracking method and device, equipment, a medium and a product, and relates to the technical field of power grid project management, and the method comprises the steps: obtaining the project data of a plurality of power grid projects; the project data of each power grid project comprises a construction progress report, field monitoring data and a production income report; based on the preprocessed project data of each power grid project, taking technical stability and equipment supply supportability as optimization targets, adopting an NSGA-II multi-target optimization algorithm to carry out power grid project screening to calculate a Pareto optimal solution set, and taking the power grid project in the Pareto optimal solution set as the screened power grid project; determining a to-be-tracked power grid project from the screened power grid projects; for each to-be-tracked power grid project, state stage tracking is carried out based on a hidden Markov model; the full life cycle of each to-be-tracked power grid project comprises a plurality of state stages. The monitoring efficiency of the power grid project can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of power grid project management, and in particular to a method, device, equipment, medium and product for screening and status tracking of power grid projects. Background Art

[0002] As the power system continues to evolve, power grid companies face numerous challenges in investment planning and project management. With the growth of renewable energy installed capacity and the large-scale integration of intermittent energy sources such as wind power and photovoltaics, grid stability and scheduling complexity have increased significantly. Existing grid project screening methods are often based on static planning and empirical decision-making, relying on fixed evaluation criteria and historical experience. They lack comprehensive consideration of renewable energy development trends and power load fluctuations. Existing project management models struggle to adapt to the dynamic development needs of the power grid, easily leading to a disconnect between project investment directions and actual needs, thereby impacting the overall operational efficiency and resource utilization of the power grid.

[0003] Currently, the selection and status management of power grid projects primarily relies on manual decision-making, using fixed-cycle planning to select projects for the reserve pool. This lacks a scientific optimization mechanism, resulting in some projects failing to maximize their returns. Furthermore, existing power grid project management models lack real-time monitoring tools, making it impossible to effectively track project status and construction progress. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment, medium and product for screening and status tracking of power grid projects, which can improve the monitoring efficiency of power grid projects.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for screening and tracking the status of power grid projects, comprising:

[0007] Obtain project data for multiple power grid projects; each power grid project's project data includes construction progress reports, on-site monitoring data, and commissioning benefit reports;

[0008] Preprocess the data of each project;

[0009] Based on the pre-processed project data of each power grid project, with technical stability and equipment supply security as the optimization goals, the NSGA-II multi-objective optimization algorithm is used to screen power grid projects, calculate the Pareto optimal solution set, and select the power grid projects in the Pareto optimal solution set as the screened power grid projects;

[0010] Determine the power grid projects to be tracked from the screened power grid projects;

[0011] For each power grid project to be tracked, state stage tracking is performed based on the hidden Markov model; the full life cycle of each power grid project to be tracked includes multiple state stages.

[0012] Optionally, taking technology stability and equipment supply security as optimization goals, specifically including: taking minimization of technology historical failure rate and maximization of equipment supply security as optimization goals;

[0013] The objective function for minimizing the technology historical failure rate is expressed as:

[0014] The objective function of maximizing equipment supply security is expressed as:

[0015] Among them, S is the technical historical maintenance rate; N f is the number of technical failures in history; N tu is the number of historical applications of the technology; f is the equipment supply security, T C is the number of devices with existing supply chain guarantees, T t The total number of equipment required to ensure supply chain security for power grid projects.

[0016] Optionally, for each power grid project to be tracked, state stage tracking is performed based on a hidden Markov model; the full life cycle of each power grid project to be tracked includes multiple state stages, specifically including:

[0017] For each power grid project to be tracked, a state transition matrix and an observation probability matrix are constructed; the state stages include a reserve stage, a planning stage, a construction stage, and an operation stage;

[0018] Based on the state transition matrix and observation probability matrix, the state stage prediction is performed.

[0019] Optionally, the state transition matrix is expressed as:

[0020] Among them, A represents the state transfer matrix, S i Indicates the i-th state stage, S j Indicates the jth state stage, P ij Indicates that from S i Transfer to S j The probability of

[0021] The observation probability matrix is expressed as:

[0022] Among them, B represents the observation probability matrix, O nj It represents the probability of the nth observation value appearing in the jth state stage, where the observation value is the data in the construction progress report, on-site monitoring data, or production income report.

[0023] Optionally, state stage prediction is performed based on the state transition matrix and the observation probability matrix, specifically including:

[0024] The forward-backward algorithm is used to calculate the probability that the power grid project to be tracked is in the kth state stage at time t. The calculation formula is expressed as:

[0025]

[0026] Among them, P(S k |O1,O2,...,O t ) represents the probability that the power grid project to be tracked is in the kth state stage at time t, S k is the kth state stage, O t is the observation data at time t, the observation data is the geometry of the observation value, t≥1, P(O t |S k ) indicates that the observation data at time t in the kth state stage is O t The probability of P(O t |S j ) indicates that the observed data at time t in the jth state stage is O t The probability, P(S k |O1,...,O t-1 ) represents the probability that the power grid project to be tracked is in the kth state stage at time t-1, P(S j |O1,...,O t-1 ) represents the probability that the power grid project to be tracked is in the jth state stage at time t-1.

[0027] Optionally, the power grid project screening and status tracking method further includes: when P(S k |O1,O2,...,O t ) is less than the corresponding preset probability value, a project progress warning is issued.

[0028] In a second aspect, the present application provides a power grid project screening and status tracking device, the power grid project screening and status tracking device comprising:

[0029] The project data acquisition module is used to obtain project data of multiple power grid projects; the project data of each power grid project includes construction progress reports, on-site monitoring data and production income reports;

[0030] Preprocessing module, used to preprocess the data of each project;

[0031] The power grid project screening module is used to screen power grid projects based on the pre-processed project data of each power grid project, with technical stability and equipment supply security as optimization goals, using the NSGA-II multi-objective optimization algorithm to calculate the Pareto optimal solution set, and select the power grid projects in the Pareto optimal solution set as the screened power grid projects;

[0032] A module for determining power grid projects to be tracked is used to determine power grid projects to be tracked from the screened power grid projects;

[0033] The status stage tracking module is used to track the status stage of each power grid project to be tracked based on the hidden Markov model; the full life cycle of each power grid project to be tracked includes multiple status stages.

[0034] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned methods for screening and tracking power grid projects and for tracking status.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned methods for screening and tracking the status of power grid projects.

[0036] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned methods for screening and tracking the status of power grid projects.

[0037] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0038] The present application provides a method, apparatus, equipment, medium and product for screening and status tracking of power grid projects. Based on the pre-processed project data of each power grid project, with technical stability and equipment supply security as optimization goals, the NSGA-II multi-objective optimization algorithm is used to screen power grid projects, and the power grid projects to be tracked are determined from the screened power grid projects. The screened power grid projects are power grid projects with reliable technical stability and equipment supply security, thereby realizing the screening of high-quality power grid projects and realizing the monitoring of high-quality power grid projects. For each power grid project to be tracked, status stage tracking is performed based on a hidden Markov model; the full life cycle of each power grid project to be tracked includes multiple status stages, thereby realizing dynamic monitoring of the full life cycle of the power grid project to be tracked, and improving the monitoring efficiency of the power grid project. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flowchart of a method for screening and tracking power grid projects according to an embodiment of the present application is provided;

[0041] Figure 2 A schematic diagram of a data preprocessing process according to an embodiment of the present application;

[0042] Figure 3 A schematic diagram of the NSGA-II optimization process provided in one embodiment of the present application;

[0043] Figure 4 A schematic diagram of a Hidden Markov Model (HMM) state transition provided in one embodiment of the present application;

[0044] Figure 5 A schematic diagram of the structure of a power grid project screening and status tracking device provided in one embodiment of the present application;

[0045] Figure 6 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0047] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0048] This application provides a method for screening and tracking the status of power grid projects, such as Figure 1 As shown, the power grid project screening and status tracking method includes steps 101 to 105.

[0049] Step 101: Acquire project data of multiple power grid projects; the project data of each power grid project includes a construction progress report, on-site monitoring data, and a production income report.

[0050] Step 102: Pre-process the data of each project.

[0051] Step 103: Based on the pre-processed project data of each power grid project, with technical stability and equipment supply security as optimization goals, the NSGA-II multi-objective optimization algorithm is used to screen the power grid projects, calculate the Pareto optimal solution set, and use the power grid projects in the Pareto optimal solution set as the screened power grid projects.

[0052] Step 104: Determine the power grid projects to be tracked from the screened power grid projects.

[0053] Step 105: For each power grid project to be tracked, perform state stage tracking based on the hidden Markov model; the full life cycle of each power grid project to be tracked includes multiple state stages.

[0054] Wherein, step 101 specifically includes: obtaining project data in the project reserve library of the target power grid company.

[0055] Project data is a multi-dimensional data set, specifically including technical stability data and equipment supply security data. Technical stability data includes the project's historical technical maintenance rate, historical technical failure times, mean time between failures, etc., and is used for technical stability.

[0056] Among them, such as Figure 2 As shown, step 102 specifically includes: performing preprocessing on each project data including data cleaning, outlier detection and standardization to ensure data quality and consistency.

[0057] Data cleaning specifically includes: removing low-quality data, such as redundant or incomplete data, for example: project data with missing fields, and ensuring the integrity of input data during optimization calculations.

[0058] Standardization specifically includes: converting construction progress reports and benefit evaluation reports from different sources into a unified data structure to achieve format standardization to adapt to optimized calculations and status tracking analysis.

[0059] Standardization can be performed using different methods depending on the characteristics of the data. For example, the Min-Max normalization method can be used to normalize numerical data so that the data range is normalized to [0, 1]. The formula is as follows:

[0060]

[0061] Where x is the original eigenvalue, min(x) and max(x) are the minimum and maximum values of the feature, respectively, and x″ is the normalized eigenvalue.

[0062] Data preprocessing also includes time series alignment. For construction progress data and fund allocation data, data at different time nodes are adjusted to consistent time steps to improve the state prediction accuracy of the HMM model.

[0063] The objective function construction process of the NSGA-II optimization algorithm includes: quantifying technical stability data. Based on existing project technical stability data and combined with financial models, the technical historical failure rate or technical mean time between failures of each project is calculated and used for optimization screening; and calculating the equipment supply security score based on the number of key equipment required for the project that is obtained on time.

[0064] Construction feasibility can also be used as a goal of the NSGA-II optimization algorithm, which comprehensively analyzes factors such as construction period, equipment supply chain stability, and construction area restrictions to calculate the construction feasibility score.

[0065] Among them, the optimization goals are technical stability and equipment supply security, specifically including: minimizing the historical technical failure rate and maximizing the equipment supply security as the optimization goals.

[0066] The objective function for minimizing the technology historical failure rate is expressed as:

[0067] The objective function of maximizing equipment supply security is expressed as:

[0068] Among them, S is the technical historical maintenance rate; N f is the number of technical failures in history; N tu is the number of historical applications of the technology; f is the equipment supply security, T C is the number of devices with existing supply chain guarantees, T t The total number of equipment required to ensure supply chain security for power grid projects.

[0069] Solve the Pareto optimal solution: Figure 3 As shown in the figure, NSGA-II is used for multi-objective optimization, and the Pareto optimal solution set is obtained through non-dominated sorting. The solutions are then screened and sorted according to the project priorities to select the optimal investment projects, i.e., the power grid projects to be tracked.

[0070] Step 104 specifically includes: prioritizing the selected power grid projects, and selecting the top N power grid projects as the power grid projects to be tracked, where N is a preset integer.

[0071] The hidden Markov model relies on the data of the state stage before the current moment to infer the current state stage of the power grid project to be tracked and predict its possible state transition in the future.

[0072] Among them, step 105 specifically includes: for each power grid project to be tracked, constructing a state transition matrix and an observation probability matrix; the state stages include the reserve stage, the planning stage, the construction stage and the commissioning stage, and the transition of each state stage is as follows: Figure 4 As shown; based on the state transfer matrix and observation probability matrix, the state stage prediction is performed.

[0073] The state transfer matrix is expressed as:

[0074] Among them, A represents the state transfer matrix, S i Indicates the i-th state stage, S j Indicates the jth state stage, P ij Indicates that from S i Transfer to S j The state transition matrix is determined based on historical project data.

[0075] Assume that the project status is affected by the following observation variables: project approval documents (affecting the reserve stage → planning stage); construction progress report (affecting the planning stage → construction stage); on-site monitoring data (affecting the construction stage → commissioning stage); and commissioning income report (to evaluate the stability of the commissioning stage).

[0076] The observation probability matrix is expressed as:

[0077] Among them, B represents the observation probability matrix, O nj It represents the probability of the nth observation value appearing in the jth state stage, where the observation value is the data in the construction progress report, on-site monitoring data, or production income report.

[0078] The observation data in the reserve stage mainly come from feasibility study reports and market analysis. The observation values in the reserve stage include land resource feasibility (% of land that complies with planned use), capital availability rate (% of funds received / % of planned funds), expected power supply contribution rate (% of power supply in the budget period after the project is put into production / % of power supply in the previous period) and expected loss reduction contribution rate.

[0079] Land resource feasibility = area that meets planned land use requirements / total planned land area.

[0080] Estimated loss reduction contribution rate = budgeted power supply after project commissioning × (previous period line loss rate - expected line loss rate) / (previous period power supply × previous period line loss rate)%.

[0081] The observation data of the technical stage mainly come from approval documents, bidding announcements, construction plans, etc. The observation data of the technical stage include project approval progress (number of approved items / total number of items requiring approval%), construction plans including the funding availability rate in the planning stage (funds received / planned funds%) and major equipment procurement completion rate (equipment purchased / planned equipment purchase%).

[0082] Observational data during the construction phase comes from construction site monitoring, scheduling systems, and financial systems. These include the construction progress deviation rate (actual days - planned days / planned days %), construction quality failure rate (number of failures / total number of inspection items %), machinery cost deviation rate (actual machinery cost - planned machinery cost / planned machinery cost %), labor cost deviation rate (actual labor cost - planned labor cost / planned labor cost %), material cost deviation rate (actual material cost - planned material cost / planned material cost %), and equipment stable operation rate (equipment in stable operation / total number of equipment %).

[0083] The observation data during the commissioning phase comes from the power grid dispatching center, operation and maintenance system, financial system, etc. The observation data during the commissioning phase include the commissioning time deviation rate, actual power supply contribution rate and actual loss reduction contribution rate.

[0084] Production time deviation rate = actual production time - expected production time / expected production time (%).

[0085] Actual power supply contribution rate = power supply after project commissioning / power supply in the previous period (%).

[0086] Actual loss reduction contribution rate = power supply after project commissioning × (line loss rate in the previous period - line loss rate after commissioning) / (power supply in the previous period × line loss rate in the previous period)%).

[0087] Among them, the state stage prediction is performed based on the state transition matrix and the observation probability matrix, specifically including: using the forward-backward algorithm to calculate the probability that the power grid project to be tracked is in the kth state stage at time t. The calculation formula is expressed as:

[0088]

[0089] Among them, P(S k |O1,O2,...,O t ) represents the probability that the power grid project to be tracked is in the kth state stage at time t, S k is the kth state stage, O t is the observation data at time t, the observation data is the geometry of the observation value, t≥1, P(O t |S k ) indicates that the observation data at time t in the kth state stage is O t The probability of P(O t |Sj ) indicates that the observed data at time t in the jth state stage is O t The probability, P(S k |O1,...,O t-1 ) represents the probability that the power grid project to be tracked is in the kth state stage at time t-1, P(S j |O1,...,O t-1 ) represents the probability that the power grid project to be tracked is in the jth state stage at time t-1.

[0090] This application uses a forward-backward algorithm to predict project status change trends and provide progress warnings.

[0091] The power grid project screening and status tracking method further includes: when P(S k |O1,O2,...,O t ) is less than the corresponding preset probability value, a project progress warning is issued.

[0092] By combining the NSGA-II multi-objective optimization algorithm with the HMM state prediction model, this application achieves the following: intelligent project screening: selecting the optimal power grid project based on Pareto optimization to improve the scientific nature of project screening; accurate state tracking: using HMM to calculate project progress and predict the probability of construction phase transitions; dynamic adjustment strategy: combining the forward-backward algorithm to identify progress deviations and generate early warning signals.

[0093] When predicting the status of power grid projects, the Hidden Markov Model uses construction progress reports, fund allocation and equipment procurement data, field monitoring data, and commissioning benefit reports as inputs.

[0094] Construction progress reports are used to calculate the probability of a project moving from the "Planning" phase to the "Construction" phase and predict the risk of construction delays.

[0095] Fund allocation and equipment procurement data, as reference variables for construction progress, affect the probability of state transition from the "construction" to the "commissioning" stage.

[0096] On-site monitoring data is used to identify the actual construction status of the project to correct the state prediction of the HMM model and improve the prediction accuracy.

[0097] The commissioning benefit report is used to determine whether the project has achieved the expected benefits and to identify any adjustments or optimization needs that may arise during the "commissioning" phase.

[0098] The NSGA-II optimization algorithm of this application adopts a dynamic adjustment strategy, which includes adaptive weight adjustment, environmental constraint correction and multi-objective evolutionary adjustment. That is, the NSGA-II optimization algorithm of this application updates the screening of power grid projects according to the update of project data.

[0099] Adaptive weight adjustment: Dynamically adjust the weights of policy adaptability, technical stability, and rationality of construction conditions based on the grid company's annual investment priorities.

[0100] Environmental constraint correction: Consider the environmental impact of the construction area (such as climate and geographical restrictions) and dynamically adjust the construction feasibility goals.

[0101] Multi-objective evolutionary adjustment: Based on historical investment data of power grid projects, the NSGA-II optimization strategy is automatically revised to improve the long-term priority of screened projects.

[0102] The state prediction process of the hidden Markov model of the present application adopts an error correction mechanism, including model training based on historical data, anomaly detection mechanism and dynamic feedback adjustment.

[0103] Model training based on historical data: Utilize the construction progress and funding allocation data of past projects to optimize the state transition matrix of the hidden Markov model.

[0104] Anomaly detection mechanism: If the state transition probability predicted by the hidden Markov model deviates from the actual monitoring data, it automatically triggers model retraining to improve prediction accuracy.

[0105] Dynamic feedback adjustment: Combined with the latest construction monitoring data, the state transition probability of the current project is corrected to ensure that the state prediction results are consistent with the actual progress, and realize the dynamic adaptability of project planning.

[0106] The project progress warning for this application includes construction delay warning and financial risk warning.

[0107] Construction Delay Warning: If the Hidden Markov Model predicts that the project will not be able to move from the "Construction" phase to the "Commissioning" phase as planned, a management warning will be automatically triggered.

[0108] Funding risk warning: When the funding disbursement progress lags behind the construction progress, the system automatically calculates the delay risk and provides adjustment suggestions.

[0109] This application tracks project status based on the hidden Markov model, combines the forward-backward algorithm to calculate the probability of project progress, predict possible status change trends, and identify abnormal project status or potential construction delays, thereby achieving early identification of risks that may affect project operation and investment, and ensuring the accuracy and controllability of power grid investment planning.

[0110] Optimize power grid project management based on status tracking results, combine with dynamic adjustment strategies to improve the accuracy of power grid project management, resource allocation, and provide intelligent decision-making support.

[0111] This application solves the problems existing in the current power grid project investment planning and status management process, such as single screening criteria, lagging status monitoring, and low resource allocation efficiency. It uses a forward-backward algorithm to calculate the probability of project progress, predict possible status change trends, and form an intelligent management plan; finally, it combines dynamic adjustment strategies to optimize power grid project management, improve technical stability and construction progress prediction capabilities; improve the scientific nature of power grid project screening and the intelligent level of management, optimize resource allocation, and improve the accuracy and controllability of power grid investment planning, thereby promoting the high-quality development of power grid projects.

[0112] In an exemplary embodiment, the present application defines the key elements of the hidden Markov model: state space (reserve stage, planning stage, construction stage, commissioning stage), observation values (key data based on reserves, planning, construction, and commissioning), state transition probability matrix A, observation probability matrix B, and initial state probability π.

[0113] Calculate forward probability (Forward Algorithm): Calculate the possible state probability of a to-be-tracked power grid project a of a power grid company's power grid infrastructure at the future time step t.

[0114] Calculate the backward probability (BackwardAlgorithm): Calculate the impact of future time step t on the current state.

[0115] Calculate P(S) using the forward-backward algorithm k |O), that is, given the observation data O, item a is in a certain state S k probability.

[0116] The state transition probability matrix A (constructed based on the historical data of the power grid company) represents the probability that project a may transition from the current state to other states:

[0117] The state transition probability matrix A is expressed in the company's historical project data:

[0118] 70% of the power grid projects remain in the reserve stage, and 30% of the power grid projects enter the planning stage.

[0119] 60% of the grid projects in the planning stage continued, 30% of the projects entered the construction stage, and 10% of the grid projects returned to the reserve stage.

[0120] During the construction phase, 60% of the grid projects continued, 20% of the grid projects entered the operation phase, and 20% of the grid projects returned to the planning phase.

[0121] During the commissioning phase, 90% of the power grid projects maintained operation, and only 10% of the power grid projects experienced regression.

[0122] The observation data of each stage of the power grid project a were obtained through data collection, as shown in Table 1.

[0123] Table 1 Observation data of each stage of power grid project a

[0124]

[0125]

[0126] Establish the observation probability matrix B based on the observation data:

[0127] Because project a is in the reserve stage, the initial probability vector π is: π = [1.0 0.0 0.0 0.0].

[0128] Then perform the forward probability calculation: N is the number of state stages.

[0129] Among them, α t (j) represents the probability that time step t is in the jth state stage.

[0130] P(S j |S i ) represents the probability of transitioning from the i-th state stage to the j-th state stage.

[0131] P(O t |S j ) indicates that the observed data is O when it is in the jth state stage t probability.

[0132] Initial state probability: α0 = π·B.

[0133] That is: α0 = [1.0×0.85, 1.0×0.60, 1.0×0.75, 1.0×0.50] = [0.85, 0.60, 0.75, 0.50].

[0134] When t=1:

[0135] For the reserve phase:

[0136]

[0137] Similarly:

[0138] Planning stage (S2): α1(2) = 0.3474.

[0139] Construction stage (S3): α1(3) = 0.1224.

[0140] Commissioning stage (S4): α1(4) = 0.00.

[0141] We get α1 = [0.6526, 0.3474, 0.1224, 0.00].

[0142] When t=2:

[0143] Similarly:

[0144] Reserve stage (S1): α2(1)=0.5786.

[0145] Planning stage (S2): α2(2) = 0.2990.

[0146] Construction stage (S3): α2(3) = 0.1224.

[0147] Commissioning stage (S4): α2(4) = 0.00.

[0148] We get α2 = [0.5786, 0.2990, 0.1224, 0.00].

[0149] The results of the forward calculation are shown in Table 2.

[0150] Table 2 Forward calculation results

[0151] Time step t <![CDATA[Reserve stage (S1)]]> <![CDATA[Planning Phase (S2)]]> <![CDATA[Construction phase (S3)]]> <![CDATA[Commissioning phase (S4)]]> t＝0 85.00％ 60.00％ 75.00％ 50.00％ t＝1 65.26％ 34.74％ 12.24％ 0.00％ t＝2 57.86％ 29.90％ 12.24％ 0.00％

[0152] t=0 (current): Project a is in the reserve stage (85%), because the initial state is set to 100% reserve and is adjusted after being affected by the observed data.

[0153] At t = 1 (next step): The probability of the reserve phase drops to 65.26%, indicating that the project is likely to advance to the planning stage. The probability of the planning phase rises to 34.74%, indicating that approvals and funding are critical at this time step. The probability of the construction phase is lower, at only 12.24%, because approvals are not completed at this time step and construction will not proceed directly in the short term. The probability of the commissioning phase is 0.00%, indicating that this stage is unlikely to occur in the short term.

[0154] At t = 2 (two steps into the future), the probability of the project remaining in the reserve phase decreases further to 57.86%, indicating that the probability of the project remaining in the reserve phase has further decreased. The probability of the project remaining in the planning phase decreases to 29.90%, while the probability of the project remaining in the construction phase increases to 12.24%, indicating that the probability of the project completing approval and entering construction has increased. The probability of the project remaining in the operation phase remains at 0.00%, indicating that the project will not enter operation directly in the short term.

[0155] Then calculate the backward probability:

[0156] Among them, β t(i) is the time step t in the i-th state stage S i and the probability of transitioning to a future state.

[0157] P(S j ∣S i ) belongs to the state transition probability matrix A.

[0158] P(O t+1 ∣S j ) belongs to the observation probability matrix B.

[0159] P(O t+1 |S j ) indicates that the observed data is O when it is in the jth state stage t+1 probability.

[0160] When t=2, the final result of the project will definitely be commissioning, so set β2=1.

[0161] That is: β2 = [1,1,1,1].

[0162] When t=1:

[0163] For the reserve phase (S1), there are:

[0164]

[0165] Similarly, we can get:

[0166] Planning stage (S2): β1(2) = 0.745.

[0167] Construction stage (S3): β1(3) = 0.80.

[0168] Commissioning stage (S4): β1(4) = 0.89.

[0169] That is, β1 = [0.805, 0.745, 0.80, 0.89].

[0170] When t=0:

[0171] Similarly, we can get:

[0172] Reserve stage (S1): β0(1) = 0.633.

[0173] Planning stage (S2): β0(2) = 0.5736.

[0174] Construction stage (S3): β0(3) = 0.4883.

[0175] Operation stage (S4): β0(4) = 0.785

[0176] We get: β0 = [0.633, 0.5736, 0.4883, 0.785].

[0177] The results of the post-calculation are shown in Table 3.

[0178] Table 3. Results of front-back calculation

[0179] Time step t <![CDATA[Reserve stage (S1)]]> <![CDATA[Planning Phase (S2)]]> <![CDATA[Construction phase (S3)]]> <![CDATA[Commissioning stage (S4)]]> t＝0 51.40％ 54.04％ 62.76％ 71.60％ t＝1 61.50％ 70.50％ 80.00％ 80.50％ t＝2 100.00％ 100.00％ 100.00％ 100.00％

[0180] t = 0 (current): The operation phase has the highest influence (71.60%), indicating that the ultimate goal at the current time step is still to complete the operation. The construction phase has the highest influence (62.76%), indicating that the short-term goal at the current time step is construction preparation.

[0181] t = 1 (next step): The influence of the planning stage rises to 70.50%, indicating that the importance of the approval progress of Project A increases at this time step. The influence of the construction stage rises to 80.00%, indicating that Project A is likely to enter the construction phase at this time step.

[0182] t=2 (2 steps into the future): The backward influence probability of all states is 100%, which is a characteristic of the backward algorithm and means that the final state will definitely occur.

[0183] Finally, calculate the final state probability: the final state probability represents the probability that item a is in different states at each time step t given the observation data O. The formula is:

[0184]

[0185] Among them, P(S k |O) is the state S given the observation data O k The probability of t (k) is the forward probability that item a is in state S at time t k probability.

[0186] β t (k) is the backward probability, that is, the impact of the future state on the current state.

[0187] The normalization factor is the sum of products of all states, ensuring that the probabilities sum to 1.

[0188] When t=0:

[0189] have to:

[0190]

[0191] Similarly:

[0192] When t=1: P(S1|O)=0.5395.

[0193] When t=2: P(S2|O)=0.5786.

[0194] The final calculation results are shown in Table 4.

[0195] Table 4 Final calculation results

[0196] Time step t <![CDATA[Reserve stage (S1)]]> <![CDATA[Planning Phase (S2)]]> <![CDATA[Construction phase (S3)]]> <![CDATA[Commissioning stage (S4)]]> t＝0 27.47％ 20.40％ 29.61％ 22.52％ t＝1 53.95％ 32.92％ 13.13％ 0.00％ t＝2 57.86％ 29.90％ 12.24％ 0.00％

[0197] At t = 0 (current): At the current time step, there is a 27.47% probability that the project is still in the reserve phase, indicating that funding or approvals are not yet in place. There is a 29.61% probability that the project will enter the construction phase, but this may be subject to construction conditions. There is a 22.52% probability that the project will eventually enter the operation phase, but will require further support.

[0198] t = 1 (next step): At the current time step, there is a 53.95% probability that the project is still in the reserve stage. To advance to the planning stage, the approval process must be accelerated. There is a 32.92% probability that the project will enter the planning stage, but construction difficulties may still exist.

[0199] t = 2 (two steps into the future): At the current time step, there is a 57.86% probability that the project is still in the reserve phase, indicating that the observed data for the project is very poor. There is a 29.90% probability that the project has entered the planning phase, indicating that the project has only a small probability of advancing to the next phase.

[0200] Based on the same inventive concept, embodiments of the present application further provide a power grid project screening and status tracking device for implementing the aforementioned power grid project screening and status tracking method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more power grid project screening and status tracking device embodiments provided below can be found in the aforementioned limitations of the power grid project screening and status tracking method, and will not be further elaborated here.

[0201] In an exemplary embodiment, Figure 5 As shown, the present application provides a power grid project screening and status tracking device including:

[0202] The project data acquisition module is used to obtain project data of multiple power grid projects; the project data of each power grid project includes construction progress reports, on-site monitoring data and production income reports.

[0203] The preprocessing module is used to preprocess the data of each project.

[0204] The power grid project screening module is used to screen power grid projects based on the pre-processed project data of each power grid project, with technical stability and equipment supply security as optimization goals, using the NSGA-II multi-objective optimization algorithm to calculate the Pareto optimal solution set, and select the power grid projects in the Pareto optimal solution set as the screened power grid projects.

[0205] The module for determining power grid projects to be tracked is used to determine power grid projects to be tracked from the screened power grid projects.

[0206] The status stage tracking module is used to track the status stage of each power grid project to be tracked based on the hidden Markov model; the full life cycle of each power grid project to be tracked includes multiple status stages.

[0207] Through the collaborative work of the above system modules, this application can effectively realize the screening and status tracking of power grid projects based on NSGA-II and hidden Markov model, improve the intelligence level of power grid investment planning, make investment decisions more scientific and reasonable, optimize power grid resource allocation, and improve the implementation efficiency and investment returns of power grid projects.

[0208] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store power grid project screening and status tracking data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a power grid project screening and status tracking method is implemented.

[0209] Those skilled in the art will understand that Figure 6The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method embodiments when executing the computer program.

[0210] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0211] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0212] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0213] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0214] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, data processing logic of programmable logic devices, and the like.

[0215] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0216] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for screening and tracking the status of power grid projects, characterized in that: The power grid project screening and status tracking method includes: Obtain project data for multiple power grid projects; each power grid project's project data includes construction progress reports, on-site monitoring data, and commissioning benefit reports; Preprocess the data of each project; Based on the pre-processed project data of each power grid project, with technical stability and equipment supply security as the optimization goals, the NSGA-II multi-objective optimization algorithm is used to screen power grid projects, calculate the Pareto optimal solution set, and select the power grid projects in the Pareto optimal solution set as the screened power grid projects; Determine the power grid projects to be tracked from the screened power grid projects; For each power grid project to be tracked, state stage tracking is performed based on the hidden Markov model; the full life cycle of each power grid project to be tracked includes multiple state stages.

2. The method for screening and tracking power grid projects according to claim 1, characterized in that: Taking technical stability and equipment supply security as optimization goals, specifically including: minimizing the historical technical failure rate and maximizing the equipment supply security as optimization goals; The objective function for minimizing the technology historical failure rate is expressed as: The objective function of maximizing equipment supply security is expressed as: Among them, S is the technical historical maintenance rate; N f is the number of technical failures in history; N tu is the number of historical applications of the technology; f is the equipment supply security, T C is the number of devices with existing supply chain guarantees, T t The total number of equipment required to ensure supply chain security for power grid projects.

3. The method for screening and tracking power grid projects according to claim 1, characterized in that: For each power grid project to be tracked, the state stage tracking is performed based on the Hidden Markov Model. The full life cycle of each power grid project to be tracked includes multiple state stages, including: For each power grid project to be tracked, a state transition matrix and an observation probability matrix are constructed; the state stages include a reserve stage, a planning stage, a construction stage, and an operation stage; Based on the state transition matrix and observation probability matrix, the state stage prediction is performed.

4. The method for screening and tracking power grid projects according to claim 3, characterized in that: The state transfer matrix is expressed as: Among them, A represents the state transfer matrix, S i Indicates the i-th state stage, S j Indicates the jth state stage, P ij Indicates that from S i Transfer to S j The probability of The observation probability matrix is expressed as: Among them, B represents the observation probability matrix, O nj It represents the probability of the nth observation value appearing in the jth state stage, where the observation value is the data in the construction progress report, on-site monitoring data, or production income report.

5. The method for screening and tracking power grid projects according to claim 3, characterized in that: According to the state transfer matrix and observation probability matrix, the state stage prediction is carried out, including: The forward-backward algorithm is used to calculate the probability that the power grid project to be tracked is in the kth state stage at time t. The calculation formula is expressed as: Among them, P(S k |O1,O2,...,O t ) represents the probability that the power grid project to be tracked is in the kth state stage at time t, S k is the kth state stage, O t is the observation data at time t, the observation data is the geometry of the observation value, t≥1, P(O t |S k ) indicates that the observation data at time t in the kth state stage is O t The probability of P(O t |S j ) indicates that the observed data at time t in the jth state stage is O t The probability, P(S k |O1,...,O t-1 ) represents the probability that the power grid project to be tracked is in the kth state stage at time t-1, P(S j |O1,...,O t-1 ) represents the probability that the power grid project to be tracked is in the jth state stage at time t-1.

6. The method for screening and tracking power grid projects according to claim 5, characterized in that: The power grid project screening and status tracking method further includes: when P(S k |O1,O2,...,O t ) is less than the corresponding preset probability value, a project progress warning is issued.

7. A power grid project screening and status tracking device, characterized in that: The power grid project screening and status tracking device includes: The project data acquisition module is used to obtain project data of multiple power grid projects; the project data of each power grid project includes construction progress reports, on-site monitoring data and production income reports; Preprocessing module, used to preprocess the data of each project; The power grid project screening module is used to screen power grid projects based on the pre-processed project data of each power grid project, with technical stability and equipment supply security as optimization goals, using the NSGA-II multi-objective optimization algorithm to calculate the Pareto optimal solution set, and select the power grid projects in the Pareto optimal solution set as the screened power grid projects; A module for determining power grid projects to be tracked is used to determine power grid projects to be tracked from the screened power grid projects; The status stage tracking module is used to track the status stage of each power grid project to be tracked based on the hidden Markov model; the full life cycle of each power grid project to be tracked includes multiple status stages.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the power grid project screening and status tracking method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for screening and tracking the status of power grid projects according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for screening and tracking the status of power grid projects according to any one of claims 1 to 6 is implemented.

Images