Photovoltaic power generation project EPC whole process intelligent consultation service system

Abstract

The invention relates to a photovoltaic power generation project EPC whole process intelligent consultation service system, and the system comprises the steps: building a multivariate statistical model between consultation related data and project benefit indexes through collecting the consultation related data and project benefit indexes of a photovoltaic power generation project in a historical period, so as to predict the benefits of a photovoltaic power generation project to be consulted; and adjusting the consultation related data according to a prediction result to achieve an expected benefit index. The problem that project consultation service evaluation is inaccurate due to the fact that the prior art depends on human experience and does not consider the unique situation of each photovoltaic power generation project is solved. And key consultation related data having significant influence on project benefit indexes are screened and identified through the redundancy analysis model, so that the efficiency and accuracy of subsequent modeling are improved. The benefit of the to-be-consulted project is evaluated through the multiple linear regression model, and the problem that human experience lacks consistency and comparability is solved.

Description

Technical Field

[0001] The invention belongs to the technical field of project consulting, and relates to an EPC full-process intelligent consulting service system for a photovoltaic power generation project. Background Art

[0002] As the global demand for clean energy continues to grow, photovoltaic power generation is developing rapidly as a sustainable energy solution. Against this background, the scale and number of photovoltaic power generation projects are increasing, and its EPC (engineering, procurement and construction) model is widely used due to its advantages such as efficient resource integration and shortened construction period. The entire EPC process of photovoltaic power generation projects involves many complex links, from project data evaluation, EPC bidding to contract terms review, etc. Each link is closely linked and affects each other, which places extremely high demands on the accuracy and efficiency of project management.

[0003] At present, most project consulting services assess feasibility and risk by assigning weights to different aspects of the project. However, experience-based weight assignment is often difficult to accurately adapt to the unique situation of each photovoltaic power generation project EPC. Due to the huge differences in factors such as the geographical location, scale, technical requirements and market environment of each project, the universal experience weight cannot fully and meticulously reflect the true importance and risk level of each link of a specific project. This experience-based weight assignment is highly subjective, and different evaluators have different experiences and cognitions, and the weights assigned may be very different, making the evaluation results lack consistency and comparability. Summary of the invention

[0004] The present invention provides an intelligent consulting service system for the entire EPC process of photovoltaic power generation projects, which aims to collect historical photovoltaic power generation project data and the final benefit indicators of the projects, and use multivariate statistical models to quantify the relationship between consulting-related data at each stage of the project and the project benefit indicators instead of assigning weights, so as to solve the problem of inaccurate evaluation of project consulting services in the prior art.

[0005] The purpose of the present invention can be achieved through the following technical solutions: The present application provides an intelligent consulting service system for the entire EPC process of a photovoltaic power generation project, including a process management module, a project evaluation module and a project adjustment module, wherein the process management module, the project evaluation module and the project adjustment module are communicatively connected, wherein: The process management module is used to obtain consulting related information of the photovoltaic power generation project to be consulted, and the consulting related information includes survey information, bidding information, project cost information and contract terms review information; The project evaluation module is used to collect consulting-related data and project benefit indicators of photovoltaic power generation projects in historical periods, and to establish a multivariate statistical model between the consulting-related data and the project benefit indicators to predict the benefits of the photovoltaic power generation projects to be consulted; The project adjustment module is used to adjust the consultation related data according to the predicted benefits of the photovoltaic power generation project to be consulted, so as to achieve the expected benefit indicators.

[0006] Furthermore, the multivariate statistical model includes a redundancy analysis model and a multivariate linear regression model. The redundancy analysis model is used to identify key consulting-related data that have a significant impact on project benefit indicators; the multivariate linear regression model is used to obtain the conversion relationship between key consulting-related data and project benefit indicators.

[0007] Furthermore, the survey data include topographic data, geological condition reports and meteorological data; the bidding materials include project technical requirements, project duration requirements, project technical plans and historical performance of bidding companies; the engineering cost data include equipment procurement costs, construction costs and operation and maintenance cost budgets; the contract terms review materials include price terms, duration and progress terms, quality and acceptance terms, operation and maintenance and after-sales service terms, and breach of contract liability and dispute resolution terms.

[0008] Furthermore, the project benefit indicators include energy supply indicators, environmental benefit indicators and social benefit indicators.

[0009] Furthermore, the redundancy analysis model includes the following analysis steps: S1. Standardize the data of consulting related materials and project benefit indicators; S2, using consulting related data as explanatory variables and project benefit indicators as response variables, a redundancy analysis model was constructed; S3. Determine the rationality of the model by checking the significance of the full model and the first major axis; S4. Use the variance decomposition method to analyze the contribution rate of each consulting-related data to the model; S5. Select consulting-related information with a contribution rate greater than a% as key consulting-related information.

[0010] Furthermore, the multivariate linear regression model includes the following analysis steps: T1. Using a single key consulting-related data as the explanatory variable and the project benefit index as the response variable, a single factor linear regression model was established; T2. Detect the significance and explanation rate of all monomial linear regression models and sort them from large to small according to the explanation rate; T3. Eliminate the single factors that do not meet the significance standard, and add the remaining single factors into the model in the order of explanation rate to form a multivariate linear regression model; T4. When adding single factors one by one, use the AIC criterion to check whether the model fit is improved. If the AIC value does not decrease after adding a single factor, remove the single factor.

[0011] Furthermore, the single factor linear regression model also includes interaction factors consisting of all two different key consultation-related data.

[0012] Furthermore, the multivariate linear regression model is expressed as follows: , In the formula, Y represents the project benefit index; a 0 represents the intercept; x 1 , x 2 , …, x n Key consulting data indicating that the single factor linear regression model is significant, a 1 , a 2 , …, a n is the corresponding regression coefficient.

[0013] Furthermore, the adjustment of the consultation-related materials according to the predicted benefits of the photovoltaic power generation project to be consulted includes the following steps: E1. Set the first expected value of the project benefit index of the photovoltaic power generation project to be consulted; E2. When the predicted project benefit index is lower than the first expected value, all key consulting related data are compared with historical data to identify outlier key consulting related data; E3. Adjust the outlier key consulting related data according to the order of the regression coefficients in the multivariate linear regression model until the project benefit index of the project to be consulted is not lower than the first expected value.

[0014] Furthermore, in step E2, when the predicted project benefit index is lower than a second expected value, it is prompted that the project to be consulted is unqualified, and the second expected value is less than the first expected value.

[0015] Beneficial effects of the present invention: (1) By collecting consulting-related data and project benefit indicators of photovoltaic power generation projects in historical periods, a multivariate statistical model between consulting-related data and project benefit indicators is established to predict the benefits of the photovoltaic power generation projects to be consulted; according to the predicted benefits of the photovoltaic power generation projects to be consulted, the consulting-related data are adjusted to achieve the expected benefit indicators. The present invention solves the problem that the prior art relies on human experience and does not consider the unique situation of each photovoltaic power generation project, resulting in inaccurate evaluation of project consulting services.

[0016] (2) Through the redundancy analysis model, key consulting-related information that has a significant impact on project benefit indicators can be screened and identified, thereby improving the efficiency and accuracy of subsequent modeling.

[0017] (3) The conversion relationship between key consulting-related data and project benefit indicators is quantified through a multivariate linear regression model. In the process, regression coefficients are used instead of weights to obtain a model that can evaluate the benefits of the consulting project, thus solving the problem of lack of consistency and comparability of human experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0019] Figure 1 This is a structural diagram of an EPC full-process intelligent consulting service system for photovoltaic power generation projects in the present invention.

[0020] Figure 2 The flowchart of constructing a redundancy analysis model in one embodiment of the present invention.

[0021] Figure 3 The flowchart of constructing a multivariate linear regression model in one embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0023] See also Figure 1-Figure 3 The present application provides a photovoltaic power generation project EPC full-process intelligent consulting service system, including a process management module, a project evaluation module and a project adjustment module, wherein the process management module, the project evaluation module and the project adjustment module are communicatively connected, wherein: The process management module is used to obtain consulting related information of the photovoltaic power generation project to be consulted, and the consulting related information includes survey information, bidding information, project cost information and contract terms review information; Furthermore, the survey data include topographic data, geological condition reports and meteorological data; the bidding materials include project technical requirements, project duration requirements, project technical plans and historical performance of bidding companies; the engineering cost data include equipment procurement costs, construction costs and operation and maintenance cost budgets; the contract terms review materials include price terms, duration and progress terms, quality and acceptance terms, operation and maintenance and after-sales service terms, and breach of contract liability and dispute resolution terms.

[0024] In this embodiment, the process management module is responsible for obtaining relevant information on each key link of the photovoltaic power generation project to be consulted. These data are the basis for subsequent project evaluation and adjustment, and provide comprehensive and necessary data support for the analysis and decision-making of the entire project. Among them: Topographic data: The topographic features of the project site, such as undulating terrain, slope size, whether it is flat and open, etc., have a profound impact on the planning and implementation of photovoltaic power generation projects. Flat terrain is conducive to the neat arrangement and large-scale laying of photovoltaic modules, which can reduce the difficulty of construction and reduce construction costs. Complex terrain, such as mountains and hills, may require special design and construction methods, which will not only increase construction costs, but also affect the lighting angle of photovoltaic modules, and thus affect the average annual power generation.

[0025] Geological conditions report: Geological conditions are related to the stability and cost of the project's infrastructure. Information such as soil type, bearing capacity, and groundwater level determine the design and construction methods of the photovoltaic power station foundation. For example, soil with weak bearing capacity may require deeper and more solid infrastructure, thereby increasing construction costs. If the geological conditions are not good, during the project operation, the stability of the equipment may be affected due to problems such as foundation settlement, and even equipment damage may occur, affecting power generation and operation and maintenance costs.

[0026] Meteorological data: Meteorological data has a direct and critical impact on the benefits of photovoltaic power generation projects. Among them, light resource data, such as the average annual sunshine hours, solar radiation intensity and its distribution, are the core factors that determine the average annual power generation. Adequate light resources mean higher power generation potential, which is directly related to the economic benefits of the project. In addition, meteorological factors such as temperature, precipitation, and wind speed cannot be ignored. Too high or too low temperature will affect the power generation efficiency of photovoltaic modules; excessive precipitation may cause dirt to accumulate on the surface of the modules, affecting lighting, requiring more frequent cleaning and maintenance, and increasing operation and maintenance costs; strong winds may place higher requirements on the structural strength of photovoltaic brackets, affecting equipment procurement costs and safety.

[0027] Project technical requirements: This is a clear regulation of the technology and equipment specifications used in photovoltaic power generation projects, such as the conversion efficiency of photovoltaic modules, the performance indicators of inverters, etc. Higher technical requirements usually mean higher power generation efficiency and better equipment performance, but also lead to higher equipment procurement costs. However, in the long run, efficient equipment may bring higher annual power generation, thereby improving the economic and environmental benefits of the project.

[0028] Project duration requirements: The time limits for each stage of the project from start to finish are clearly defined. Shorter duration requirements may prompt the construction party to increase manpower and material resources to ensure timely completion, which will undoubtedly increase construction costs. On the other hand, if the project can be connected to the grid and generate electricity ahead of schedule, it can obtain benefits in advance. However, if the duration requirements are unreasonable, the construction party may ignore the quality of the project in order to catch up with the progress, which will affect the service life of the equipment and the average annual power generation, bringing long-term negative impacts to the project.

[0029] Project technical plan: including the overall layout design of the photovoltaic power station, electrical system design, etc. Reasonable layout design can make full use of land resources, optimize the lighting angle of photovoltaic modules, improve power generation efficiency, and increase annual power generation. Advanced electrical system design can reduce power loss during transmission and further improve the economic benefits of the project.

[0030] Bidding company's historical performance: reflects the performance and ability of the bidding company in previous photovoltaic power generation projects. Rich experience in successful projects shows that the company has the ability to deal with various complex situations and can better ensure the quality and progress of the project. A company with a good historical performance is more likely to avoid common problems and reduce project risks during project implementation, thus having a positive impact on the overall benefits of the project.

[0031] Equipment procurement costs: involves the purchase costs of major equipment such as photovoltaic modules, inverters, and brackets. The quality and price of equipment are usually positively correlated. Although high-quality equipment has a higher procurement cost, it has higher power generation efficiency and longer service life. For example, efficient photovoltaic modules can generate more electricity under the same lighting conditions, increasing the average annual power generation; while low-priced equipment with poor quality may frequently malfunction, requiring more repairs and replacements, increasing operation and maintenance costs, and may also lead to reduced power generation, ultimately affecting the economic benefits of the project.

[0032] Construction cost: covers the costs of a series of construction processes, from site leveling, infrastructure construction to equipment installation and commissioning. Factors such as the choice of construction technology, the qualifications and experience of the construction team will affect the construction cost and quality. Reasonable control of construction costs can improve the economic benefits of the project while ensuring the quality of the project. However, if an inadequately qualified construction team is selected or unreasonable construction technology is adopted in order to reduce costs, it may lead to project quality problems, increase the subsequent operation and maintenance costs and power generation losses.

[0033] Operation and maintenance cost budget: used to plan the expenses required for the project during the operation and maintenance phase, including regular equipment maintenance, fault repair, parts replacement, and personnel training. A scientific and reasonable operation and maintenance cost budget can ensure the long-term stable operation of the project and guarantee the average annual power generation. If the operation and maintenance cost budget is too high, it will reduce the profit margin of the project and affect the economic benefits; while a budget that is too low may lead to inadequate operation and maintenance work, accelerated equipment aging, shortened equipment service life, and reduced power generation.

[0034] Price clauses: including the photovoltaic power sales price and equipment and material purchase price adjustment clauses. The photovoltaic power sales price directly determines the source of revenue for the project. Higher electricity prices can significantly improve the economic benefits of the project when the power generation is stable. At the same time, it is also crucial to pay attention to the price adjustment mechanism and subsidy period, as they will affect the stability and sustainability of project revenue. The equipment and material purchase price adjustment clause can cope with the risks brought by market price fluctuations. Reasonable adjustment clauses can not only guarantee the reasonable profits of suppliers, but also avoid excessive impact on project costs due to large price fluctuations, thereby maintaining the economic benefits of the project.

[0035] Construction period and progress clauses: clarify the time nodes and delivery requirements for each stage of the project. On-time completion is crucial to the economic benefits of the project. Only when the power generation is connected to the grid on time can the project obtain benefits as planned. If the construction period is delayed, it may result in liquidated damages, increase project costs, and extend the project's investment recovery period, affecting economic benefits. In addition, the progress clause stipulates that the extension of the construction period due to force majeure and other factors can reasonably share risks and protect the interests of all parties in the project.

[0036] Quality and acceptance clauses: Detailed provisions on the quality standards that each part of the project should meet and the specific procedures for acceptance. Strict quality standards help ensure that the project maintains stable performance during long-term operation, increases annual power generation, and improves the economic and environmental benefits of the project. Clear acceptance clauses can avoid disputes due to quality issues after project delivery and reduce additional costs.

[0037] Operation and maintenance and after-sales service terms: stipulate the responsibilities and obligations of suppliers during the operation and maintenance phase of the project, such as the warranty period of the equipment, maintenance response time, etc. Good operation and maintenance and after-sales service terms can ensure the normal operation of the equipment during the warranty period, solve equipment problems in a timely manner, reduce operation and maintenance costs, extend the service life of the equipment, and have a positive impact on the long-term benefits of the project.

[0038] Breach of contract liability and dispute resolution clauses: clarify the responsibilities and compensation methods that both parties to the contract should bear in the event of a breach of contract. Reasonable breach of contract liability clauses can constrain both parties to strictly perform their contractual obligations and reduce project risks. Clear dispute resolution clauses provide a solution to disputes that may arise during the implementation of the project, ensuring that the project can proceed smoothly and avoiding project stagnation due to improper dispute handling, thereby ensuring the overall benefits of the project.

[0039] The project evaluation module is used to collect consulting-related data and project benefit indicators of photovoltaic power generation projects in historical periods, and to establish a multivariate statistical model between the consulting-related data and the project benefit indicators to predict the benefits of the photovoltaic power generation projects to be consulted; Furthermore, the multivariate statistical model includes a redundancy analysis model and a multivariate linear regression model. The redundancy analysis model is used to identify key consulting-related data that have a significant impact on project benefit indicators; the multivariate linear regression model is used to obtain the conversion relationship between key consulting-related data and project benefit indicators.

[0040] In this embodiment, the project evaluation module is the core analysis unit of the entire intelligent consulting service system. It collects various consulting-related materials (such as survey, bidding, project cost, contract terms review materials) of photovoltaic power generation projects in historical periods and corresponding project benefit indicators (such as annual average power generation, investment return rate, environmental benefits, etc.), and uses complex mathematical statistical methods to establish the internal connection between the two, so as to predict the benefits of the photovoltaic power generation projects currently to be consulted. This process provides a scientific basis based on data and models for project decision-making, which helps the project team understand the potential benefits of the project in advance so as to make more reasonable planning and decisions.

[0041] Redundancy analysis model In the numerous consulting-related materials, not all factors have the same important impact on the project benefit indicators. Some factors may be redundant or have little impact. The main task of the redundancy analysis model is to use statistical principles to select the key factors that have a significant impact on the project benefit indicators from the massive consulting-related data factors. For example, among the many factors that affect the average annual power generation (energy supply index) of photovoltaic power generation projects, the influence of factors such as topography, light intensity, and equipment procurement costs may be more prominent, while some minor factors may have little impact on power generation. The redundancy analysis model can accurately identify these key factors and exclude those redundant factors that have little impact on the results, making subsequent analysis more focused and efficient. Determining key consulting-related materials through the redundancy analysis model can not only simplify the analysis process and reduce unnecessary data processing burdens, but also allow the project team to have a clearer understanding of the core factors that affect project benefits. This helps to focus key resources and attention on these key factors during project implementation, conduct more in-depth research and control, and improve the pertinence and effectiveness of project management.

[0042] After the redundancy analysis model identifies the key consulting-related information, the multiple linear regression model plays a further role. It constructs a quantitative conversion relationship between the key consulting-related information and the project benefit indicators through in-depth analysis of historical data. Taking the average annual power generation as an example, assuming that the key consulting-related information is the duration of sunshine, the conversion efficiency of photovoltaic modules, the equipment operation and maintenance cost, etc., the multiple linear regression model can fit a large amount of historical project data to derive a specific mathematical relationship such as how much the average annual power generation will increase accordingly under the conditions of specific photovoltaic module conversion efficiency and equipment operation and maintenance cost for every additional hour of sunshine. This quantitative conversion relationship provides an accurate tool for project benefit prediction. The project team can substitute the key consulting-related information data of the project to be consulted into the multiple linear regression model to accurately predict the project's benefit indicators, such as predicting the average annual power generation and estimating the return on investment. This enables the project to have a more accurate expectation of future benefits during the planning stage, which helps to formulate reasonable project goals, optimize project plans, and conduct effective risk assessments.

[0043] Furthermore, the project benefit indicators include energy supply indicators, environmental benefit indicators and social benefit indicators.

[0044] In this embodiment, the project benefit indicators cover multiple dimensions such as energy supply, environmental benefits and social benefits. The energy supply indicators are directly related to the project's contribution to the energy sector. The average annual power generation is the core, which intuitively shows the average total power generation of the project within one year. It is measured in megawatt hours or kilowatt hours and is the cornerstone of measuring the project's energy supply capacity. The power generation efficiency reflects the level at which the photovoltaic system converts solar energy into electrical energy. It is affected by factors such as component quality, lighting conditions, and system design. Efficient conversion can increase overall power generation. Power supply reliability cannot be ignored either. It is measured by the power supply reliability rate, that is, the ratio of effective power supply time to total power supply time, which reflects whether the project can provide continuous and stable power supply and ensure the stability of energy supply.

[0045] Environmental benefit indicators highlight the green value of photovoltaic power generation projects. Carbon dioxide emission reduction is the key. Compared with traditional fossil energy power generation, photovoltaic power generation can greatly reduce carbon dioxide emissions. By calculating the emission reduction of replacing traditional energy power generation, its contribution to mitigating global warming can be clearly measured. Pollutant emission reduction is equally important. Traditional power generation will emit a large amount of pollutants such as sulfur dioxide, nitrogen oxides and particulate matter, which harms the atmospheric environment and human health, while photovoltaic power generation can avoid these pollutants. In addition, ecological impact is also an evaluation point. Rationally constructed photovoltaic projects can promote the rational use of land, protect animal and plant habitats, maintain water resource balance, and have a positive impact on the surrounding ecosystem.

[0046] The social benefit indicators reflect the far-reaching significance of the project to social development. The creation of employment opportunities runs through the entire project. Construction positions in the construction phase and long-term positions such as operation and maintenance and management in the operation phase all provide job opportunities for local residents and promote social stability and economic development. In terms of energy structure optimization, photovoltaic power generation helps increase the proportion of renewable energy in the energy structure, reduce dependence on traditional fossil energy, improve the diversity and security of energy supply, and promote energy transformation. At the same time, the project can also drive local economic development. Upstream and downstream industries such as photovoltaic module manufacturing, installation and maintenance, and logistics and transportation will flourish due to the implementation of the project, increase local fiscal revenue, and promote regional economic prosperity.

[0047] Furthermore, the redundancy analysis model includes the following analysis steps: S1. Standardize the data of consulting related materials and project benefit indicators; S2, using consulting related data as explanatory variables and project benefit indicators as response variables, a redundancy analysis model was constructed; S3. Determine the rationality of the model by checking the significance of the full model and the first major axis; S4. Use the variance decomposition method to analyze the contribution rate of each consulting-related data to the model; S5. Select consulting-related information with a contribution rate greater than a% as key consulting-related information.

[0048] In the S1 data standardization process, since the original data of consulting related materials and project benefit indicators often have different dimensions and value ranges, this will seriously interfere with the accuracy and reliability of subsequent analysis. Through standardization, all data are unified to a specific scale, dimension differences are eliminated, and each variable can be compared and analyzed under the same benchmark, ensuring the scientific nature of subsequent model construction.

[0049] Entering the S2 stage of building a redundant analysis model, consulting-related data are used as explanatory variables. They are like "causes" and try to explain the "result" of project benefit indicators as response variables. For example, consulting-related data such as topographic data and equipment procurement costs are associated with project benefit indicators such as annual average power generation and carbon dioxide emission reduction, and the basic framework of the model is built to lay the foundation for exploring the internal connection between the two.

[0050] After completing the model construction, S3 verifies the rationality of the model by checking the significance of the full model and the first major axis. The significance check of the full model can determine whether the entire model is valid and whether there is really a correlation between the explanatory variables and the response variables. The significance of the first major axis focuses on the most important direction of change in the model to confirm whether it is significant. If both are significant, it means that the model is meaningful and can effectively reflect the relationship between variables; otherwise, the model construction needs to be re-examined.

[0051] S4 uses the variation decomposition method to further analyze the contribution rate of each consulting-related data to the model. This method breaks down the total variation of the project benefit indicators and clarifies the proportion of each explanatory variable (consulting-related data). For example, it can clearly know the contribution of light resource data to the variation of the project benefit indicator of annual average power generation, as well as the impact of equipment procurement costs on the return on investment.

[0052] Finally, in S5, based on the variation decomposition results, consulting-related data with a contribution rate greater than a% are selected as key consulting-related data. This a is a threshold set based on project characteristics and analysis requirements. Data above this threshold have the most critical impact on project benefit indicators. Screening out these key data can help the project team focus resources and energy on core influencing factors, accurately control project benefits, provide strong support for subsequent decision-making and project optimization, and promote the efficient and scientific development of photovoltaic power generation projects.

[0053] Furthermore, the multivariate linear regression model includes the following analysis steps: T1. Using a single key consulting-related data as the explanatory variable and the project benefit index as the response variable, a single factor linear regression model was established; T2. Detect the significance and explanation rate of all monomial linear regression models and sort them from large to small according to the explanation rate; T3. Eliminate the single factors that do not meet the significance standard, and add the remaining single factors into the model in the order of explanation rate to form a multivariate linear regression model; T4. When adding single factors one by one, use the AIC criterion to check whether the model fit is improved. If the AIC value does not decrease after adding a single factor, remove the single factor.

[0054] In step T1, a single factor linear regression model is established with a single key consulting-related data as the explanatory variable and a project benefit index as the response variable. For example, a model is constructed by combining the key consulting-related data of sunshine duration with the project benefit index of average annual power generation to explore the simple linear relationship between the two, and based on this, a preliminary analysis is made on the impact of each key factor on the project benefit.

[0055] In step T2, all established single-factor linear regression models are tested for significance and explanation rate. The significance test determines whether the model is statistically significant, and the explanation rate measures the extent to which the single factor can explain the changes in the project benefit indicators. After the test is completed, the explanation rate is sorted from large to small, clearly showing the order of the influence of each single factor on the project benefit indicators.

[0056] In step T3, single factors that do not meet the significance criteria are eliminated because their impact on the project benefit indicators is not statistically significant and cannot effectively explain the relationship between variables. The remaining single factors that meet the significance criteria are added to the model in order of explanation rate, gradually forming a multivariate linear regression model. This gradual addition method can ensure that each factor in the model plays an important role in explaining the project benefit indicators and that the model structure is reasonable.

[0057] In step T4, each time a single factor is added, the AIC criterion (Akaike Information Criterion) is used to check whether the model fit is improved. The AIC criterion comprehensively considers the complexity of the model and the degree of fit to the data. The smaller the value, the better the model. When the AIC value does not decrease after adding a single factor, it means that although the single factor has a certain significance, it may make the model too complex after adding it, but it does not significantly improve the fit. At this time, the single factor is eliminated. In this way, the multivariate linear regression model is continuously optimized so that it can not only accurately reflect the relationship between key consulting-related information and project benefit indicators, but also maintain the simplicity and effectiveness of the model, providing a reliable tool for the prediction and analysis of the benefits of photovoltaic power generation projects.

[0058] Furthermore, the single factor linear regression model also includes interaction factors consisting of all two different key consultation-related data.

[0059] In this embodiment, when constructing a single factor linear regression model, incorporating all interaction factors consisting of two different key consulting-related data is of great significance to improving the model performance.

[0060] In photovoltaic power generation projects, each key consulting-related information does not affect the project benefit indicators in isolation. For example, light intensity and the orientation of photovoltaic modules. In general, the greater the light intensity, the higher the power generation, and the modules facing due south can receive the most light. But in fact, there is an interaction between the two. Under different light intensities, the influence of the module orientation on power generation varies. In strong light, the power generation of the south orientation is significantly improved; in weak light, other fine-tuning orientations may better capture limited light. If the model only considers a single factor, this synergistic relationship will be ignored.

[0061] Including interaction factors allows the model to fully capture these complex relationships and greatly improves the ability to explain project benefit indicators. However, this also increases the complexity of the model. On the one hand, more data is needed to support the estimation of model parameters to ensure the reliability of the results; on the other hand, the amount of calculation increases, which places higher demands on computing resources and time. However, as long as the amount of data is sufficient and the key interactions can be clearly identified, the model can more accurately fit the actual situation and provide a more solid basis for project benefit prediction and analysis. In the project decision-making stage, it can help decision makers comprehensively consider the comprehensive impact of various factors, formulate more scientific and reasonable strategies, and promote the efficient and stable development of photovoltaic power generation projects.

[0062] Furthermore, the multivariate linear regression model is expressed as follows: , In the formula, Y represents the project benefit index; a 0 represents the intercept; x 1 , x 2 , …, x n Key consulting data indicating that the single factor linear regression model is significant, a 1 , a 2 , …, a n is the corresponding regression coefficient.

[0063] The project adjustment module is used to adjust the consultation related data according to the predicted benefits of the photovoltaic power generation project to be consulted, so as to achieve the expected benefit indicators.

[0064] Furthermore, the adjustment of the consultation-related materials according to the predicted benefits of the photovoltaic power generation project to be consulted includes the following steps: E1. Set the first expected value of the project benefit index of the photovoltaic power generation project to be consulted; E2. When the predicted project benefit index is lower than the first expected value, all key consulting related data are compared with historical data to identify outlier key consulting related data; E3. Adjust the outlier key consulting related data according to the order of the regression coefficients in the multivariate linear regression model until the project benefit index of the project to be consulted is not lower than the first expected value.

[0065] Furthermore, in step E2, when the predicted project benefit index is lower than a second expected value, it is prompted that the project to be consulted is unqualified, and the second expected value is less than the first expected value.

[0066] In this embodiment, in the benefit optimization process of the photovoltaic power generation project, this series of adjustment steps are closely related to ensure that the project achieves the expected benefits.

[0067] In step E1, the first expected value of the project benefit index of the photovoltaic power generation project to be consulted is set, which is an important target value that the project hopes to achieve. For example, the first expected value of the average annual power generation is set to a specific value, or the expected return on investment is set in a specific range. This value is determined based on comprehensive factors such as the project's investment budget, market demand, and the company's strategic goals. It provides a clear direction and standard for subsequent project adjustments.

[0068] When the predicted project benefit index is lower than the first expected value, the E2 step is entered. This step requires traversing all key consulting-related materials and comparing them with historical data. In this way, outlier key consulting-related materials that deviate from the normal range and perform abnormally can be identified. For example, during the comparison process, it is found that the equipment procurement cost of a certain project to be consulted is much higher than the average level of similar historical projects. This may be an outlier key consulting-related material. When the predicted project benefit index is lower than the lower second expected value, it is directly prompted that the project to be consulted is unqualified. The second expected value is set to give a timely warning when the project benefits deviate seriously from expectations, so as to avoid investing too much invalid costs in subsequent adjustments.

[0069] In step E3, the identified outlier key consulting-related data are adjusted in the order of the size of the regression coefficients in the multivariate linear regression model. The regression coefficient reflects the degree of influence of the key consulting-related data on the project benefit indicators. For example, if the regression coefficient of a key consulting-related data is large, it means that it has a more significant impact on the project benefit, so it should be adjusted first. The adjustment methods can be diverse, such as re-evaluating suppliers for excessively high equipment procurement costs and looking for more cost-effective products. Through continuous adjustment, until the project benefit indicators of the project to be consulted reach or exceed the first expected value, the project benefit is optimized, ensuring that the project achieves the expected goals in many aspects such as economy and energy supply.

[0070] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent consulting service system for the entire EPC process of photovoltaic power generation projects, characterized by: It includes a process management module, a project evaluation module and a project adjustment module, which are communicatively connected to each other, wherein: The process management module is used to obtain consulting related information of the photovoltaic power generation project to be consulted, and the consulting related information includes survey information, bidding information, project cost information and contract terms review information; The project evaluation module is used to collect consulting-related data and project benefit indicators of photovoltaic power generation projects in historical periods, and establish a multivariate statistical model between the consulting-related data and the project benefit indicators to predict the benefits of the photovoltaic power generation projects to be consulted; the multivariate statistical model includes a redundancy analysis model and a multivariate linear regression model, the redundancy analysis model is used to identify key consulting-related data that have a significant impact on the project benefit indicators; the multivariate linear regression model is used to obtain the conversion relationship between the key consulting-related data and the project benefit indicators; The project adjustment module is used to adjust the consultation related data according to the predicted benefits of the photovoltaic power generation project to be consulted, so as to achieve the expected benefit indicators.

2. The photovoltaic power generation project EPC full-process intelligent consulting service system according to claim 1 is characterized by: The survey data include topographic data, geological condition reports and meteorological data; the bidding materials include project technical requirements, project duration requirements, project technical plans and historical performance of bidding companies; the engineering cost data include equipment procurement costs, construction costs and operation and maintenance cost budgets; the contract terms review materials include price terms, duration and progress terms, quality and acceptance terms, operation and maintenance and after-sales service terms, and breach of contract liability and dispute resolution terms.

3. The photovoltaic power generation project EPC full-process intelligent consulting service system according to claim 1 is characterized by: The project benefit indicators include energy supply indicators, environmental benefit indicators and social benefit indicators.

4. The photovoltaic power generation project EPC full-process intelligent consulting service system according to claim 1 is characterized by: The redundancy analysis model includes the following analysis steps: S1. Standardize the data of consulting related materials and project benefit indicators; S2, using consulting related data as explanatory variables and project benefit indicators as response variables, a redundancy analysis model was constructed; S3. Determine the rationality of the model by checking the significance of the full model and the first major axis; S4. Use the variance decomposition method to analyze the contribution rate of each consulting-related data to the model; S5. Select consulting-related information with a contribution rate greater than a% as key consulting-related information.

5. The photovoltaic power generation project EPC full-process intelligent consulting service system according to claim 1 is characterized by: The multivariate linear regression model includes the following analysis steps: T1. Using a single key consulting-related data as the explanatory variable and the project benefit index as the response variable, a single factor linear regression model was established; T2. Detect the significance and explanation rate of all monomial linear regression models and sort them from large to small according to the explanation rate; T3. Eliminate the single factors that do not meet the significance standard, and add the remaining single factors into the model in the order of explanation rate to form a multivariate linear regression model; T4. When adding single factors one by one, use the AIC criterion to check whether the model fit is improved. If the AIC value does not decrease after adding a single factor, remove the single factor.

6. The photovoltaic power generation project EPC full-process intelligent consulting service system according to claim 5 is characterized by: The single factor linear regression model also includes interaction factors consisting of all two different key consulting-related data.

7. The photovoltaic power generation project EPC full-process intelligent consulting service system according to claim 5 is characterized by: The multivariate linear regression model is expressed as follows: ， In the formula, Y represents the project benefit index; a0 represents the intercept; x1, x2, ..., x n Indicates that the single factor linear regression model is significant key consulting related data, a1, a2, ..., a n is the corresponding regression coefficient.

8. The photovoltaic power generation project EPC full-process intelligent consulting service system according to claim 1 is characterized by: The method of adjusting the consultation-related materials according to the predicted benefits of the photovoltaic power generation project to be consulted includes the following steps: E1. Set the first expected value of the project benefit index of the photovoltaic power generation project to be consulted; E2. When the predicted project benefit index is lower than the first expected value, all key consulting related data are compared with historical data to identify outlier key consulting related data; E3. Adjust the outlier key consulting related data according to the order of the regression coefficients in the multivariate linear regression model until the project benefit index of the project to be consulted is not lower than the first expected value.

9. The photovoltaic power generation project EPC full-process intelligent consulting service system according to claim 8 is characterized by: In step E2, when the predicted project benefit index is lower than the second expected value, it is prompted that the project to be consulted is unqualified, and the second expected value is less than the first expected value.

Images