Profit and loss balance analysis and electricity price sensitivity analysis method based on symbol regression

Abstract

The invention discloses a profit and loss balance analysis and electricity price sensitivity analysis method based on symbol regression, and relates to the technical field of profit and loss balance analysis and electricity price sensitivity analysis, and the method comprises the steps: obtaining three kinds of change rate data of a first object; establishing a target function according to the three kinds of change rate data; and carrying out profit and loss balance analysis and electricity price sensitivity analysis. According to the method, through a symbol regression method, a more complex nonlinear relation can be captured, the model adaptability and the prediction precision are improved, through substituting a function relation obtained through symbol regression and calculating a profit and loss balance point, a clear operation target is provided for an enterprise, the scientificity of operation strategy making is improved, and through electricity price sensitivity analysis, the accuracy of the model is improved. According to the method, the sensitivity of the electricity price change to the enterprise profit is evaluated, decision support is provided for the enterprise to cope with the market electricity price fluctuation, the market adaptability and the anti-risk capability are improved, and better effects are achieved in the aspects of effectiveness, reliability and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of break-even analysis and electricity price sensitivity analysis, and in particular to a break-even analysis and electricity price sensitivity analysis method based on symbolic regression. Background Art

[0002] As a research method for the balance of project costs and benefits under market, production capacity and production management conditions, break-even analysis has important application value for typical industry products in the power market. Existing break-even analysis methods are often based on a series of simplified assumptions when evaluating project uncertainties, such as the positive proportional relationship between variable costs and output, the invariance of fixed costs, the uniformity of sales prices, and the linear relationship between sales revenue and sales volume. However, these assumptions are not always valid in the actual power market, especially when electricity prices fluctuate frequently and violently, the limitations of these assumptions are particularly obvious.

[0003] For electricity users, changes in electricity prices not only directly affect electricity costs, but also cause changes in electricity consumption and product production, further affecting raw material and labor costs. This complex interaction causes changes in electricity prices to have a nonlinear impact on the variable costs and revenues of typical industry products. The simplified processing methods in existing technologies often cannot accurately capture these nonlinear relationships, resulting in deviations in the results of break-even analysis, reducing the effectiveness and practicality of the analysis. In addition, existing technologies lack in-depth analysis of electricity price sensitivity and cannot provide power grid companies with specific data on the impact of electricity price changes on profits, thereby affecting the formulation of electricity price policies and risk management in the electricity market.

[0004] In this context, this application conducts an in-depth analysis of revenue and cost, studies the relationship between the rate of change of revenue, variable cost and electricity price, and takes it into account in the break-even relationship, thereby improving the reliability of the break-even analysis point and the effectiveness of the electricity price sensitivity analysis. Summary of the invention

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

[0006] Therefore, the technical problem solved by the present invention is: the existing break-even analysis method has low effectiveness, poor practicality, and cannot capture nonlinear relationships, as well as the problem of how to establish a symbolic regression model and apply it to break-even analysis and electricity price sensitivity analysis.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a method for break-even analysis and electricity price sensitivity analysis based on symbolic regression, comprising obtaining three types of change rate data of a first object; establishing an objective function according to the three types of change rate data; and performing break-even analysis and electricity price sensitivity analysis.

[0008] As a preferred solution of the break-even analysis and electricity price sensitivity analysis method based on symbolic regression described in the present invention, wherein: the acquisition of three types of change rate data of the first object includes calculating the three types of change rate data based on the historical profit and loss data of the first object.

[0009] As a preferred solution of the break-even analysis and electricity price sensitivity analysis method based on symbolic regression described in the present invention, the obtaining of three types of change rate data of the first object also includes calculating n three types of change rate data from the historical profit and loss data of the past n+1 periods.

[0010] As a preferred scheme of the break-even analysis and electricity price sensitivity analysis method based on symbolic regression described in the present invention, wherein: the establishment of the objective function based on the three change rate data includes establishing the objective function with the first change rate as the independent variable and the second change rate and the third change rate as the dependent variables.

[0011] As a preferred scheme of the break-even analysis and electricity price sensitivity analysis method based on symbolic regression described in the present invention, wherein: the establishment of the objective function based on the three change rate data also includes the functional relationship between the second change rate and the third change rate obtained by output fitting and the first change rate.

[0012] As a preferred scheme of the break-even analysis and electricity price sensitivity analysis method based on symbolic regression described in the present invention, wherein: the break-even analysis includes substituting the functional relationship between the second change rate and the third change rate with respect to the first change rate into the break-even analysis formula to calculate the break-even analysis point.

[0013] As a preferred scheme of the break-even analysis and electricity price sensitivity analysis method based on symbolic regression described in the present invention, wherein: the electricity price sensitivity analysis includes performing electricity price sensitivity analysis based on the break-even relationship, and calculating the change in profit when the electricity price changes by 1% according to the functional relationship between the second change rate and the first change rate.

[0014] Another object of the present invention is to provide a break-even analysis and electricity price sensitivity analysis system based on symbolic regression, which can output the fitted functional relationship of the second change rate and the third change rate with respect to the first change rate based on three types of change rate data, with the first change rate as the independent variable and the second change rate and the third change rate as the dependent variables through training, thereby solving the problem that the current break-even analysis method cannot capture nonlinear relationships.

[0015] As a preferred solution for the break-even analysis and electricity price sensitivity analysis based on symbolic regression described in the present invention, it includes: a data acquisition module, a model training module, and an analysis module; the data acquisition module is used to obtain historical profit and loss data from a database of a first object, and calculate three types of change rate data based on the historical profit and loss data; the model training module is used to output the functional relationship between the second change rate and the third change rate obtained by fitting and the first change rate through training based on the three types of change rate data, with the first change rate as an independent variable and the second change rate and the third change rate as dependent variables; the analysis module is used to substitute the functional relationship into the break-even analysis formula, calculate the break-even analysis point, perform electricity price sensitivity analysis based on the break-even relationship and the functional relationship between the second change rate and the first change rate, and calculate the change in profit when the electricity price changes by 1%.

[0016] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of a break-even analysis and electricity price sensitivity analysis method based on symbolic regression.

[0017] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a break-even analysis and electricity price sensitivity analysis method based on symbolic regression.

[0018] Beneficial effects of the present invention: The symbolic regression-based break-even analysis and electricity price sensitivity analysis method provided by the present invention provides quantitative decision support for enterprises by obtaining the electricity price change rate, revenue change rate and variable cost change rate, thereby improving data utilization and decision accuracy. The symbolic regression method can capture more complex nonlinear relationships, improve model adaptability and prediction accuracy, and calculate the break-even point by substituting the functional relationship obtained by symbolic regression, thereby providing enterprises with clear business goals and improving the scientific nature of business strategy formulation. Through electricity price sensitivity analysis, the sensitivity of electricity price changes to corporate profits is evaluated, providing decision support for enterprises to cope with market electricity price fluctuations, and improving market adaptability and risk resistance. The present invention achieves better results in terms of effectiveness, reliability and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0020] Figure 1An overall flow chart of a break-even analysis and electricity price sensitivity analysis method based on symbolic regression provided in the first embodiment of the present invention.

[0021] Figure 2 A module schematic diagram of a break-even analysis and electricity price sensitivity analysis system based on symbolic regression provided in the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0023] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a break-even analysis and electricity price sensitivity analysis method based on symbolic regression, comprising:

[0024] Three types of change rate data of the first object are obtained.

[0025] The objective function is established based on the three types of change rate data.

[0026] Conduct break-even analysis and electricity price sensitivity analysis.

[0027] Among them, the first object can be an electrolytic aluminum enterprise, a steel enterprise, a ferroalloy enterprise, a cement enterprise, etc.; the three change rate data include the first change rate being the electricity price change rate, the second change rate being the income change rate and the third change rate being the variable cost change rate.

[0028] Furthermore, obtaining three types of change rate data of the first object includes obtaining the historical profit and loss data of a typical industry, and calculating the electricity price change rate, revenue change rate and variable cost change rate at different stages based on the historical profit and loss data. The historical profit and loss data include historical electricity prices, revenue, and variable cost data. The historical profit and loss data can be divided according to different time intervals, such as by month, by quarter, and by year.

[0029] It should be noted that the objective function established based on the three types of change rate data includes taking the electricity price change rate as the independent variable, the income change rate and the variable cost change rate as the dependent variables, and fitting the functional relationship between income and variable cost on electricity price respectively through the symbolic regression method. Symbolic regression is a supervised machine learning method used to discover a hidden mathematical expression or function to best fit a given data set. Unlike traditional regression methods, symbolic regression is not only about finding the parameters of a mathematical model, but also about automatically constructing a mathematical expression by searching and combining basic mathematical operators and functions. Compared with linear regression, which can only express linear relationships, symbolic regression can output more complex nonlinear relationships. Through training, the best-adapted mathematical expression is output, and the output income change rate y and variable cost change rate z are expressed as:

[0030] y=F1(x)

[0031] z=F2(x)

[0032] Among them, F1(x) is the rate of change of income caused by changes in electricity prices, and F2(x) is the rate of change of variable costs caused by changes in electricity prices.

[0033] Example 2, reference Figure 1 , which is an embodiment of the present invention, provides a break-even analysis and electricity price sensitivity analysis method based on symbolic regression, comprising:

[0034] S1: Acquire three types of change rate data of the first object.

[0035] Furthermore, obtaining three types of change rate data of the first object includes calculating the three types of change rate data according to historical profit and loss data of the first object.

[0036] It should be noted that obtaining the three types of change rate data of the first object also includes calculating n three types of change rate data from the historical profit and loss data of the past n+1 periods.

[0037] It should also be noted that the calculation of the three types of change rate data includes: the electricity price data of the first object at intervals is p1, p2, ... p n+1 , income data is I1,I2,…I n+1 , the variable cost data is VC1, VC2, ...VC n+1 , where n+1 represents the data recorded in the past n+1 periods, and the rate of change of electricity price, rate of change of income and rate of change of variable cost are calculated as follows:

[0038]

[0039] Among them, x i is the rate of change of electricity price from the i-th period to the i+1-th period, y iis the rate of change of income from the i-th period to the i+1-th period, z i is the rate of change of variable cost from the i-th period to the i+1-th period, i=1,2…n.

[0040] S2: Establish the objective function based on the three types of change rate data.

[0041] Furthermore, establishing the objective function based on the three change rate data includes establishing the objective function with the first change rate as the independent variable and the second change rate and the third change rate as the dependent variables.

[0042] It should be noted that establishing the objective function based on the three change rate data also includes outputting the functional relationship between the second change rate and the third change rate obtained by fitting and the first change rate.

[0043] It should also be noted that, through symbolic regression training, the functional relationship between the second change rate and the third change rate obtained by fitting and the first change rate is outputted, and the specific steps include:

[0044] a) Define the problem: Determine the objectives and problems to be solved, as well as the input and output data. The input is the rate of change of electricity price (x), and the output is the rate of change of revenue (y) and the rate of change of variable cost (z) caused by the price change.

[0045] b) Generate initial population: Create an initial random population in which each individual is a mathematical expression.

[0046] c) Evaluate fitness: Use the fitness function to evaluate the fitness of each individual and compare it with the target data. The fitness function of the individual f(x) is the inverse of the mean square error function (MSE), expressed as:

[0047]

[0048] d) Selection operation: According to the result of the fitness function, some individuals with larger evaluated fitness are selected as the parents of the next generation.

[0049] e) Mutation and crossover operations: Perform mutation and crossover operations on the selected parents to generate new individuals.

[0050] f) Update the population: add newly generated individuals to the population and replace some of the poorer individuals.

[0051] g) Termination condition: Determine whether to terminate the algorithm based on the preset termination condition (such as reaching the maximum number of iterations or reaching a certain fitness threshold).

[0052] h) Output results: Select the individual with the best fitness as the final mathematical expression for prediction or modeling.

[0053] Through the above steps, training is performed and the best adaptable mathematical expression is output, where the income change rate is y=F1(x) and the variable cost change rate is z=F2(x).

[0054] S3: Conduct break-even analysis and electricity price sensitivity analysis.

[0055] Furthermore, the break-even analysis includes substituting the functional relationship between the second change rate and the third change rate with respect to the first change rate into the break-even analysis formula to calculate the break-even analysis point.

[0056] It should be noted that the electricity price sensitivity analysis includes performing electricity price sensitivity analysis based on a break-even relationship, and calculating the change in profit when the electricity price changes by 1% according to a functional relationship between the second change rate and the first change rate.

[0057] It should also be noted that calculating the break-even analysis point involves substituting current revenue and variable costs into the break-even analysis equation, which is expressed as:

[0058] Income (I) = Fixed Cost (FC) + Variable Cost (VC)

[0059] Among them, fixed costs include rental fees for factories or office space, depreciation of fixed assets such as production equipment, machinery and buildings, etc., and variable costs include electricity costs, material costs and labor costs, etc.

[0060] The functional relationship between the income change rate, variable cost change rate and electricity price change rate caused by the change in electricity price is output through symbolic regression training, and is substituted into the break-even analysis to output the break-even analysis formula when the current electricity price changes, which is expressed as:

[0061] (1+F1(x))I'=FC'+(1+F2(x))VC'

[0062] Among them, I' is the current income adjusted based on the income change rate, FC' is the adjusted current fixed cost, and VC' is the current variable cost adjusted based on the variable cost change rate.

[0063] Substitute the calculated current income, fixed costs and variable costs into the break-even analysis formula, and use Newton's method to solve the rate of change x of the electricity price, and then obtain the electricity price at the break-even analysis point as (1+x)p', where p' is the current electricity price.

[0064] It should also be noted that the electricity price sensitivity analysis includes calculating the change in profit when the electricity price changes by 1%, based on the break-even analysis formula when the current electricity price changes, expressed as:

[0065] Q=(1+F1(1%))I'-FC'-(1+F2(1%))VC'

[0066] Among them, Q is the sensitivity of electricity price.

[0067] Example 3 is an embodiment of the present invention, which provides a break-even analysis and electricity price sensitivity analysis method based on symbolic regression. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0068] Firstly, the electricity price, revenue and variable cost data of each month from January to mid-May 2020 of an electrolytic aluminum enterprise were collected. According to the historical data, the monthly electricity price change rate, revenue change rate and variable cost change rate were calculated. The symbolic regression method was used to fit the functional relationship between the revenue change rate and the variable cost change rate and the electricity price change rate. The functional relationship was substituted into the break-even analysis formula to calculate the break-even point. Based on the break-even relationship, the change in profit when the electricity price changed by 1% was calculated. The break-even analysis and electricity price sensitivity analysis results based on the symbolic regression method were compared with the traditional break-even analysis method to evaluate the accuracy and reliability of the two methods.

[0069] Refer to Table 1 for a comparative analysis of the experimental data.

[0070] Table 1 Experimental data comparison table

[0071]

[0072]

[0073] By comparing the data in the table, it can be seen that under the condition of the same electricity price change rate, the income change rate and variable cost change rate calculated by the method of the present invention are different from those of the prior art method. The result of the method of the present invention is more accurate because the present invention can better capture the nonlinear changes in income and cost. The calculation results of the break-even electricity price show that the method of the present invention is more accurate in predicting the impact of electricity price changes on the break-even point, indicating that the method of the present invention has advantages in dealing with complex nonlinear relationships. The electricity price sensitivity analysis shows that the method of the present invention is more sensitive in assessing the impact of electricity price changes on profits, providing more detailed insights, and helping enterprises make more effective decisions when electricity prices fluctuate.

[0074] In summary, the method of the present invention has obvious advantages over the prior art in processing complex nonlinear relationships, and can provide enterprises with more accurate break-even analysis and electricity price sensitivity analysis. Therefore, our invention is creative.

[0075] Example 4, reference Figure 2, is an embodiment of the present invention, and provides a computing platform load balancing system based on a particle swarm genetic algorithm, including a data acquisition module, a model training module, and an analysis module.

[0076] The data acquisition module is used to obtain historical profit and loss data from the database of the first object, and calculate three types of change rate data based on the historical profit and loss data; the model training module is used to output the fitted functional relationship between the second change rate and the third change rate and the first change rate based on the three types of change rate data, with the first change rate as the independent variable and the second change rate and the third change rate as the dependent variables through training; the analysis module is used to substitute the functional relationship into the break-even analysis formula, calculate the break-even analysis point, perform electricity price sensitivity analysis based on the break-even relationship and the functional relationship between the second change rate and the first change rate, and calculate the change in profit when the electricity price changes by 1%.

[0077] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0078] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0079] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0080] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0081] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for break-even analysis and electricity price sensitivity analysis, characterized in that: include: Acquire three types of change rate data of the first object; Establish the objective function based on the three types of change rate data; Conduct break-even analysis and electricity price sensitivity analysis.

2. The method for breakeven analysis and electricity price sensitivity analysis according to claim 1, characterized in that: The obtaining of three types of change rate data of the first object includes calculating the three types of change rate data according to the historical profit and loss data of the first object.

3. The method for breakeven analysis and electricity price sensitivity analysis according to claim 2, characterized in that: The obtaining of three types of change rate data of the first object further includes calculating n three types of change rate data from historical profit and loss data of the past n+1 periods.

4. The method for breakeven analysis and electricity price sensitivity analysis according to claim 3, characterized in that: The method of establishing the objective function based on the three change rate data includes establishing the objective function with the first change rate as the independent variable and the second change rate and the third change rate as the dependent variables.

5. The method for breakeven analysis and electricity price sensitivity analysis according to claim 4, characterized in that: The method of establishing the target function based on the three types of change rate data also includes outputting a functional relationship between the second change rate and the third change rate obtained by fitting and the first change rate.

6. The method for breakeven analysis and electricity price sensitivity analysis according to claim 5, characterized in that: The break-even analysis includes substituting the functional relationship between the second change rate and the third change rate with respect to the first change rate into the break-even analysis formula to calculate the break-even analysis point.

7. The method for breakeven analysis and electricity price sensitivity analysis according to claim 6, characterized in that: The electricity price sensitivity analysis includes performing an electricity price sensitivity analysis based on a break-even relationship, and calculating a change in profit when the electricity price changes by 1% according to a functional relationship between the second change rate and the first change rate.

8. A system using the break-even analysis and electricity price sensitivity analysis method according to any one of claims 1 to 7, characterized in that: Including data acquisition module, model training module, and analysis module; The data acquisition module is used to acquire historical profit and loss data from the database of the first object, and calculate three types of change rate data based on the historical profit and loss data; The model training module is used to output the functional relationship between the second change rate and the third change rate and the first change rate obtained by fitting through training based on three types of change rate data, with the first change rate as the independent variable and the second change rate and the third change rate as the dependent variables; The analysis module is used to substitute the functional relationship into the break-even analysis formula, calculate the break-even analysis point, perform electricity price sensitivity analysis based on the break-even relationship and the functional relationship of the second change rate with respect to the first change rate, and calculate the change in profit when the electricity price changes by 1%.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the break-even analysis and electricity price sensitivity analysis method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the break-even analysis and electricity price sensitivity analysis method according to any one of claims 1 to 7 are implemented.

Images