CN111695718A - Power grid development aid decision-making method considering investment demand and planning target - Google Patents
Power grid development aid decision-making method considering investment demand and planning target Download PDFInfo
- Publication number
- CN111695718A CN111695718A CN202010299084.9A CN202010299084A CN111695718A CN 111695718 A CN111695718 A CN 111695718A CN 202010299084 A CN202010299084 A CN 202010299084A CN 111695718 A CN111695718 A CN 111695718A
- Authority
- CN
- China
- Prior art keywords
- investment
- project
- power grid
- power
- planning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011161 development Methods 0.000 title claims abstract description 31
- 238000005457 optimization Methods 0.000 claims abstract description 26
- 238000011156 evaluation Methods 0.000 claims abstract description 20
- 230000002068 genetic effect Effects 0.000 claims abstract description 12
- 238000012706 support-vector machine Methods 0.000 claims abstract description 9
- 238000010219 correlation analysis Methods 0.000 claims abstract description 4
- 241000282461 Canis lupus Species 0.000 claims description 18
- 238000009826 distribution Methods 0.000 claims description 16
- 230000005540 biological transmission Effects 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 230000009977 dual effect Effects 0.000 claims description 5
- 230000035772 mutation Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 238000013461 design Methods 0.000 description 10
- 238000010276 construction Methods 0.000 description 8
- 230000005611 electricity Effects 0.000 description 6
- 238000011084 recovery Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 101150084750 1 gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001308 synthesis method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Finance (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Technology Law (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a power grid development aid decision-making method considering investment demand and planning target, which is characterized in that an investment demand prediction model based on differential evolution-wolf optimization-support vector machine is established based on the first ten key factors which are screened out by a grey correlation analysis method and influence the investment demand of a power grid; considering a power grid planning target, constructing a project optimization ordering index system by combining various attributes of a project, and comprehensively evaluating the project based on an analytic hierarchy process and a linear weighting comprehensive method to enable the project to enter an early-stage project reserve library according to the sequence of comprehensive evaluation; and considering investment demand limitation and allocation proportion constraint of investment amount of different categories of projects, establishing a power grid project investment decision double-objective function seeking the maximum total score of the projects and the minimum total investment amount, and preferably selecting the project combination with the maximum comprehensive benefit score from the early-stage project reserve library based on an improved genetic algorithm.
Description
Technical Field
The invention belongs to the field of power grid enterprise investment aid decision making, and particularly relates to a power grid development aid decision making method considering investment requirements and planning targets.
Background
A new round of electricity changes and provides a reform direction of 'managing the middle and releasing two ends', a new electricity selling main body is allowed to enter an electricity selling side, multiple electricity selling companies are established on the basis of the existing power generation enterprises and power grid enterprises, market vitality of the electricity selling side is stimulated, the power grid enterprises face a more open market environment, and new opportunities and challenges are brought to the power grid enterprises in planning and investment work. Under the background of the advanced power system innovation, the accounting mode of the power grid enterprise is changed from 'price difference pricing' to 'permitted cost plus reasonable profit', and in addition, the general industrial and commercial power price is reduced in recent years, so that the profit margin of the power grid enterprise is greatly compressed. Therefore, in order to really know the construction and operation conditions of the power grid before the power grid planning work is implemented, strengthen the lean management of the power grid stock assets and incremental assets, and seek a reasonable and optimal investment strategy, a power grid enterprise needs to comprehensively consider the investment capacity restriction of the enterprise and the power grid planning target, and establish an effective power grid investment aid decision-making method.
The power grid enterprise also needs to ensure the economic benefit of the enterprise while fulfilling the power supply responsibility. Accurate and reasonable investment decision is an important premise for enterprises to improve the capital benefit, wherein the investment decision is a process for continuously optimizing the direction, scale and scheme of investment. The invention aims to enable the investment requirement and the investment target to be more clearly butted by considering various factors such as the investment capacity of a power grid, a power grid planning target and a fund distribution proportion, and provides an optimal investment decision so as to obtain the most accurate project group optimization combination and realize the maximum comprehensive benefit of investment fund.
Disclosure of Invention
Aiming at the problems, the invention provides a power grid development aid decision-making method considering investment requirements and planning targets, which comprises the following steps:
establishing an investment demand prediction model based on differential evolution, grayish optimization and a support vector machine based on the first ten key factors which are screened out by a gray correlation analysis method and influence the investment demand of the power grid;
considering a power grid planning target, constructing a project optimization ordering index system by combining various attributes of a project, and comprehensively evaluating the project based on an analytic hierarchy process and a linear weighting comprehensive method to enable the project to enter an early-stage project reserve library according to the sequence of comprehensive evaluation;
and considering investment demand limitation and allocation proportion constraint of investment amount of different categories of projects, establishing a power grid project investment decision double-objective function seeking the maximum total score of the projects and the minimum total investment amount, and preferably selecting the project combination with the maximum comprehensive benefit score from the early-stage project reserve library based on an improved genetic algorithm.
The first ten key factors comprise fixed asset investment, capacity increment of 220kV and above power transformation equipment, capacity increment of GDP, 110kV and below power transformation equipment, highest power load, power consumption of the whole society, length increment of 220kV and above power transmission lines, capacity-load ratio, length increment of 110kV and below power transmission lines and contact rate of distribution lines.
The differential evolution-wolf optimization-support vector machine model prediction steps are as follows:
step 1: setting related parameters and initializing a population;
step 2: calculating the fitness value of the individual gray wolfs, and sequencing the fitness values to determine the positions of the first three gray wolf individuals with the optimal fitness values, wherein the positions are marked as Xα，XβAnd X；
And step 3: calculating other wolf individuals and X in populationα，XβAnd XUpdating the wolf pack position and GWO algorithm-related parameters;
and 4, step 4: carrying out mutation and cross operation to generate a new filial generation population;
and 5: selecting operation is carried out, and the position of the wolf pack is updated;
step 6: judging whether the maximum iteration times is reached, if so, outputting the current optimal solution (c, g), otherwise, skipping to the step 2 to continue parameter optimization;
and 7: and assigning the optimized parameter values to the SVM, and establishing a prediction model.
The project optimization sequencing index system comprises a primary index and a secondary index. The first-level indexes comprise power grid safety reliability, power grid development coordination, project economic rationality and social development serviceability.
And comparing the indexes of all dimensions pairwise by using an analytic hierarchy process, establishing a judgment matrix with importance degree, calculating the weight of the judgment matrix by using a geometric mean method or a standard column mean method, and carrying out consistency check to finally obtain the weight of the optimized item sorting indexes.
The dual objective function is:
wherein f is1、f2Respectively representing a project scoring function and a total investment function; siA score representing the ith item; n is a radical ofiRepresenting the investment amount of the ith project; x is the number ofiIndicating an item selection status value (1 indicates that the ith item is selected, and 0 indicates that the ith item is not selected).
The constraints of the dual objective function include a capital constraint and an investment allocation proportion constraint. The capital constraint is that the total investment amount after optimizing investment should not exceed the investment capacity of the power grid enterprise, namely:
wherein N isiThe investment amount of the ith project is shown, and N shows the investment capacity of the power grid enterprise.
The investment distribution proportion is restricted to be equal to the ratio of the contribution degree of the safety and reliability index improvement of the power grid, and the calculation mode is as follows:
T1:T2:…:Tj＝D1:D2:…:Dj
Tjrepresents the investment allocation of the j-th category of items; djAnd the contribution degree of the grid safety reliability index representing the j-th category item is improved.
The invention has the beneficial effects that: according to the method, the investment projects of the power grid are sorted and screened according to a project optimization sorting model based on comprehensive evaluation, and a project optimization sorting table is obtained. The investment demand prediction of the power grid is carried out by establishing an investment demand prediction model based on a differencing-gray wolf optimization-support vector machine (DE-GWO-SVM). And comparing the investment demand with the investment capacity, calculating a project investment decision optimization model based on an improved genetic algorithm, and finally obtaining an optimal investment project combination by combining project optimization sequencing, so that the investment fund is fully used, and the comprehensive benefit of the project is maximized.
Drawings
FIG. 1 is a flow chart of a power grid development aid decision method considering investment requirements and planning targets according to the present invention;
FIG. 2 is a flow chart of DE-GWO-SVM model prediction;
FIG. 3 is a preferred flow chart of the improved genetic algorithm.
Detailed Description
The embodiments are described in detail below with reference to the accompanying drawings.
The invention provides a power grid development aid decision-making method considering investment requirements and planning targets, and a flow chart of the method is shown in figure 1. Firstly, screening key influence factors of investment demand, and establishing a power grid investment demand prediction model; secondly, considering a power grid planning target, combining various attributes of the project, constructing a project optimization ordering index system, and comprehensively evaluating the project based on an analytic hierarchy process and a linear weighting comprehensive method to enable the project to enter a preliminary project storage library according to the sequence of comprehensive evaluation; and finally, considering investment demand limitation and allocation proportion constraint of investment amount of different categories of projects, constructing a project investment decision optimization model, and preferably selecting a project combination with the maximum comprehensive benefit score from the early-stage project reserve library based on an improved genetic algorithm.
Screening key influence factors of the investment demand and establishing a power grid investment demand prediction model.
Based on grey correlation analysis, the first ten key factors influencing the power grid investment requirement are screened out, and the key factors are as follows: fixed asset investment, capacity increment of 220kV and above power transformation equipment, capacity increment of GDP, 110kV and below power transformation equipment, highest power load, power consumption of the whole society, length increment of 220kV and above power transmission lines, capacity-load ratio, length increment of 110kV and below power transmission lines and contact rate of power distribution lines. And (4) taking the index data of the ten factors as model input to predict the investment requirement of the power grid.
An intelligent algorithm-based power grid investment demand prediction model, namely an investment demand prediction model based on differential evolution-grey wolf optimization-support vector machine (DE-GWO-SVM), is adopted. The model takes a support vector machine as a basic prediction algorithm, combines a differential evolution algorithm and a wolf optimization algorithm, performs hybrid optimization on parameters of the support vector machine, can better process a complex nonlinear relation between influencing factors and power grid investment requirements, and achieves great improvement of the precision of the prediction model. The DE-GWO-SVM model prediction flow chart is shown in FIG. 2.
Step 1: setting related parameters and initializing a population;
step 2: calculating the fitness value of the individual gray wolfs, and sequencing the fitness values to determine the positions of the first three gray wolf individuals with the optimal fitness values, wherein the positions are marked as Xα，XβAnd X；
And step 3: calculating other wolf individuals and X in populationα，XβAnd XUpdating the wolf pack position and GWO algorithm-related parameters;
and 4, step 4: carrying out mutation and cross operation to generate a new filial generation population;
and 5: selecting operation is carried out, and the position of the wolf pack is updated;
step 6: judging whether the maximum iteration times is reached, if so, outputting the current optimal solution (c, g), otherwise, skipping to the step 2 to continue parameter optimization;
and 7: and assigning the optimized parameter values to the SVM, and establishing a prediction model.
And (4) considering a power grid planning target, combining various attributes of the project, constructing a project optimization sequencing index system, and comprehensively evaluating the project based on an analytic hierarchy process and a linear weighting synthesis method so that the project enters an early-stage project reserve library according to the sequence of comprehensive evaluation.
According to a power grid planning target, project management requirements of power grid enterprises, related power grid project exploitable report evaluation indexes and the like, a project optimization sequencing index system is established, and is shown in table 1.
TABLE 1 project optimization ordering index system
(1) Index definition
The number of the first-level indexes is four, and the first-level indexes are respectively power grid safety reliability, power grid development coordination, project economic rationality and social development serviceability.
1) Safety and reliability of power grid
Item power supply capacity: the project power supply capacity refers to the final design scale approved by relevant departments when the project can be researched and reviewed.
Target maximum load moment power factor: power factor refers to the ratio of the average power to the apparent power of an ac circuit. The power factor represents the proportion of active power in the total power and it is clear that in any case it is not possible to have a power factor greater than 1.
Comprehensive power supply voltage qualification rate: the ratio of the accumulated running time of the actual running voltage of the power supply in the allowable voltage deviation range to the corresponding total running statistical time is used for reflecting the power quality condition. And in the evaluation, the target value of the comprehensive power supply voltage qualified rate reached by the project design is taken.
Target power supply reliability: the power supply reliability is the ratio of the total effective power supply time of the user in the statistical period to the corresponding total power supply statistical time, and reflects the continuous power supply capacity of the power supply system to the user. In the evaluation, a target value of the power supply reliability reached by the project design is taken.
Target grid N-1 pass rate: the N-1 passing rate of the power grid refers to the proportion of the number of elements meeting the N-1 check in the power grid to the number of the elements at the end of the statistical period.
Calculating the formula: the passing rate (%) of the power grid N-1 is the original number meeting the rule of the specification N-1 at the end of the statistical period ÷ the total original number at the end of the statistical period multiplied by 100%
And during evaluation, the target value of the grid N-1 passing rate reached by the project design is taken.
The failure outage rate of the target transmission line is as follows: the failure outage rate of the power transmission line refers to the failure outage times of the power transmission line per hundred kilometers per year in a statistical period. After the line is tripped, reclosing is not successful or is not started, so that the line outage is calculated as 1 failure outage.
Calculating the formula: transmission line fault outage rate (times/hundred kilometers per year) — (transmission line fault outage times ÷ (operation and maintenance transmission line length ÷ 100))/(statistics period days ÷ total days of the year) × 100%
And during evaluation, the target value of the failure outage rate of the transmission line, which is reached by the project design, is taken.
Failure outage rate of the target transformer: the failure outage rate of the transformer refers to the failure outage frequency of the transformer which is averagely generated every hundred of transformers per year in a statistical period.
Calculating the formula: the failure outage rate of the transformer (times/hundred station/year) — (failure outage times of the transformer ÷ (number of stations of operation and maintenance transformer ÷ 100))/(number of days in statistical period ÷ total days in the year) × 100%
And in the evaluation, a target value of the failure outage of the transformer, which is reached by the project design, is taken.
Whether the circuit has a 'neck clamp' problem: the index is 0-1 index, if the line has a 'neck clamp' problem before the project construction, the index value is 1, otherwise, the index value is 0.
2) Coordination of power grid development
Target capacity-to-load ratio: the capacity-load ratio refers to a ratio of the total capacity of the public transformation equipment of a certain power supply area and the power grid with the same voltage class to the corresponding total load (grid supply load) in a statistical period. During calculation, the capacity of the booster transformer and the direct supply load of the regional power plant, and the capacity of the transformer substation special for the user and the supplied load thereof are deducted.
Calculating the formula: the capacity-to-load ratio (kilovolt-ampere/kilowatt) of a certain voltage class is the sum of the main variable capacities of the transformer stations in the whole network or the power supply area of the voltage class and the annual maximum load of the whole network or the power supply area of the voltage class
And in the evaluation, a target value of the failure outage of the transformer, which is reached by the project design, is taken.
Target integrated line loss rate: the comprehensive line loss rate is the ratio of the electric quantity consumed and lost in the power supply production process of the power grid operation enterprise to the power supply quantity in the statistical period, and reflects the power grid planning design, production operation and operation management level.
Calculating the formula: comprehensive line loss rate (%) — line loss electric quantity ÷ power supply quantity × 100%
In the evaluation, a target value of the comprehensive line loss rate reached by the project design is taken.
Contact rate of the target distribution line: the distribution line contact rate refers to the proportion of the number of lines meeting the interconnection structure in the 10(20) kilovolt power distribution network line in the statistics period end to the total number of the lines.
Calculating the formula: the contact rate (%) of the distribution line is equal to the number of lines of the distribution network at the end of the period, which meets the requirements of the interconnection structure, the number of lines of the distribution network at the end of the period, which is multiplied by 100%
And in the evaluation, a target value of the distribution line contact rate reached by the project design is taken.
Whether to solve the distributed energy problem: the index is 0-1 index, if the project can solve the distributed energy problem, the index value is 1, otherwise, the index value is 0.
Whether solve equipment heavy load, overload problem: the index is 0-1 index, if the project can solve the problems of heavy load and overload of equipment, the index value is 1, otherwise, the index value is 0.
Whether the power supply requirement of the newly added load is met: the index is an index of 0-1, if the project can meet the power supply requirement of a newly added load, the index value is 1, otherwise, the index value is 0.
3) The economic rationality of the project is as follows:
dynamic investment recovery period: the return on investment period is the time required to recover all investment with the net benefit of the project from the date the project was built. The investment recovery period is expressed by years, and generally, the expression is as follows from the beginning year of construction:
in the formula, CItIndicating a cash-in for the t year; CO represents cash out for year t; t represents the static payback period.
The investment recovery period of the electric power engineering is longer, so that the examination is more reasonable by using the dynamic investment recovery period.
The dynamic payback period expression is as follows:
in the formula, TtRepresenting a reference discount rate; i.e. i0Representing a dynamic payback period.
Net present value: the net present value index is a present value accumulated value for converting the net cash flow of each year in the project calculation period to the initial construction period according to the set reference discount rate. The expression is as follows:
in the formula, NPV represents the net present value; n represents the project life time limit.
If the net present value is positive, the return rate of the investment scheme is higher than the expected return rate and the investment scheme is accepted; otherwise, the project should be deeply demonstrated.
Internal rate of return: the internal yield is simply the discount rate when the net present value is zero. Specifically, the internal rate of return means that the investment is never returned by interest rate (i ═ IRR) over the life of the project, and is just completely returned at the end of life. The internal rate of return is generally considered to be the profitability of the project investment, reflecting the efficiency of the investment usage, and is expressed as follows:
the internal rate of return IRR can be found by solving the above equation.
Investment per unit volume: the unit capacity investment amount is calculated by dividing the investment amount of the project after being examined and approved by the power supply amount of the project, and reflects the cost and the economy of project construction.
Calculating the formula: investment per unit capacity is equal to total investment per project and power supply capacity per project
4) Economic social development serviceability
Whether the project is a rural power grid project: the index is 0-1 index, if the project is a rural power grid project, the index value is 0.8, otherwise, the index value is 0.
Whether the power grid project is a matched power grid project for changing coal into electricity is judged: the index is 0-1 index, if the project is a coal-to-electricity matching power grid project, the index value is 0.8, otherwise, the index value is 0.
Whether the power grid project is matched with the regional government project or not: the index is 0-1 index, if the project is a regional government project matched construction power grid project, the index value is 1, otherwise, the index value is 0.
Whether there is special policy support: the index is 0-1 index, if the project has special policy support, the index value is 1, otherwise the index value is 0.
(2) Index data processing
Due to different dimensions and magnitudes of index properties and quantity indexes, inconvenience is brought to comparison of comprehensive evaluation results, so that index data needs to be subjected to consistency and dimensionless processing to ensure scientific reasonability of the comprehensive evaluation results.
Firstly, unifying the extremely small index and the interval index into a maximum index by adopting an index consistency processing method; then, values of data of other indexes except the 0-1 index are unified into a [0,1] interval according to a non-dimensionalization processing method.
(3) Determining index weights using analytic hierarchy process
Analytic Hierarchy Process (Analytic Hierarchy Process) decomposes a complex problem into multiple levels of indicators and data. And comparing the indexes of all dimensions pairwise to establish a judgment matrix with importance degree. Generally, a geometric average method or a normalized column average method is adopted to calculate the weight of the judgment matrix, consistency check is carried out, and finally the weight of the optimized ranking index of the project is obtained.
And (4) considering investment demand limitation and allocation proportion constraint of investment amount of different categories of projects, constructing a project investment decision optimization model, and preferably selecting a project combination with the maximum comprehensive benefit score from the early-stage project reserve library based on an improved genetic algorithm.
And the decision flow is to establish a power grid project investment decision double-objective function with the largest sought project total score and the smallest total investment amount, solve the problem by using an improved genetic algorithm, and preferably select a project set with the largest comprehensive benefit score from a project reserve library in the early period for investment.
(1) Objective function
The invention establishes a power grid project investment decision objective function expression as follows:
wherein f is1、f2Respectively representing a project scoring function and a total investment function; siA score representing the ith item; n is a radical ofiRepresenting the investment amount of the ith project; x is the number ofiIndicating an item selection status value (1 indicates that the ith item is selected, and 0 indicates that the ith item is not selected).
(2) Model constraint conditions
1) Capital constraints
The total investment amount after optimizing investment should not exceed the investment capacity of the power grid enterprise, i.e. there are the following constraints.
Wherein N represents the investment capacity of the power grid enterprise.
2) The investment distribution proportion is restricted: analyzing the relation between various operation indexes and investment according to the historical development condition of a regional power grid; secondly, determining a target value by combining the current situation and the expectation; determining the contribution degree of the project to the power grid development according to the corresponding relation between the projects of different categories and the power grid development indexes, and increasing the investment intensity of the project categories with great significance to the power grid development according to the investment distribution proportion of the project categories, namely, the calculation mode of the ratio of the investment distribution proportion equal to the improvement contribution degree of the power grid safe reliability indexes is as follows:
T1:T2:…:Tj＝D1:D2:…:Dj(7)
wherein, TjRepresents the investment allocation of the j-th category of items; djAnd the contribution degree of the grid safety reliability index representing the j-th category item is improved.
In summary, the constraints of the model are:
(2) model solution
Genetic algorithms are used for preference. And comprehensively considering capital constraint conditions of the investment portfolio, and evaluating each investment portfolio scheme by using an objective function. And coding all decision variables of the investment portfolio scheme of the power grid construction project, and setting the variation rate and the crossing rate. Each portfolio scenario X corresponds to 1 chromosome in the genetic algorithm. Using integer coding, each item to be selected xiCorresponding to 1 gene, if the item appears in this scheme, its gene value is 1, otherwise it is 0, and the flow chart is shown in FIG. 3.
The method of the present invention will be described below with reference to a specific embodiment. And selecting a part of power grid planning project of the power grid of a certain area in a certain year as shown in table 2.
TABLE 2 partial investment situation table in a certain region
First, the project is comprehensively evaluated.
According to the project optimization ordering model based on comprehensive evaluation, firstly, according to an index system and a grading standard, grading is carried out on each power grid planning project. Here, the item a is taken as an example and the specific scoring results are shown in table 3.
Table 3 item a scoring table
Firstly, a judgment matrix is constructed according to the scoring value, then the consistency test is carried out on the judgment matrix through a Matlab program, the matrix which does not meet the consistency test is reasonably adjusted, the weight of each level of index is calculated for the judgment matrix which meets the consistency test, and the comprehensive weight of the second level of index can be obtained through further calculation, as shown in Table 4.
TABLE 4 index weight table
From the index weight calculation results, the factors which should be considered in the power grid planning project during investment decision are firstly safety and reliability, secondly coordination of power grid development is promoted, secondly economic rationality of the project is realized, and finally the situation of project service social development is realized.
The score of the item a is calculated to be 0.628 points based on a linear composite weighting method. Taking this as an example, scores of other grid projects are calculated and ranked, and the result is shown in table 5.
TABLE 5 ranking table for item scoring
| Item numbering | Evaluation score | Item numbering | Evaluation score |
| O | 0.8756 | M | 0.6912 |
| P | 0.8652 | L | 0.689 |
| R | 0.8527 | I | 0.6736 |
| S | 0.8472 | Q | 0.6721 |
| G | 0.8196 | A | 0.628 |
| N | 0.798 | H | 0.6052 |
| E | 0.7892 | C | 0.5912 |
| K | 0.7653 | B | 0.5688 |
| T | 0.732 | J | 0.542 |
| D | 0.7235 | F | 0.4863 |
And then, forecasting the investment requirement and measuring and calculating the investment capacity.
According to the power grid investment demand prediction model, the investment demand of the power grid in the region in the year can be predicted to be 678.95 billion yuan, the investment capacity measured and calculated by a company is 628.45 billion yuan based on financial data, the investment capacity cannot meet the investment demand, and the investment project optimization decision needs to be made in consideration of capital constraint conditions.
On the basis of the above, project investment decisions are made that take into account capital constraints.
Classifying 20 power grid planning projects given by the cases according to the voltage grades, wherein the specific classification result of the projects is shown as 6:
TABLE 6 Power grid item Classification
The investment decision objective function is a dual objective function that seeks the maximum total score and the minimum total investment of the project, as shown in equation (9).
And (4) establishing constraint conditions by considering the total investment capacity of the power grid project and the limit of the investment allocation proportion of various projects.
(1) Investment constraints
The planned investment capital of a power grid construction project of a certain area power grid in a certain year is known to be not more than 628.45 billion yuan, namely:
(2) investment allocation ratio constraint
According to the plan of investment estimation of power grid classification projects in the thirteen-five stage of the region, the investment distribution proportion of different project categories is assumed to be I: II: III: IV: 4:2:3: 1.
(3) Model solution results
The preferred results of the project obtained by using MATLAB program calculation and solving according to the improved genetic algorithm in consideration of the conditions of the investment constraints and the investment allocation proportions are shown in Table 7.
TABLE 7 genetic Algorithm solution results
| Item categories | Optimizing decision results | Gross investment of project (Yi Yuan) |
| I | G,E,D,A,H,C | 259.21 |
| II | K,L,I | 126.39 |
| III | O,P,N,M,Q | 182.82 |
| IV | S | 56.95 |
As can be seen from the above table, the total investment of all the preferred projects is 625.37 billion, and the investment ratio of each category project is approximately 4.55:2.22:3.21:1, which is basically consistent with the investment ratio of the four categories project in the sample area of 4:2:3: 1. The method of the invention ensures that the investment fund is fully used under the condition of ensuring the maximum decision value, and ensures the maximization of the comprehensive benefit of the project.
The present invention is not limited to the above embodiments, and any changes or substitutions that can be easily made by those skilled in the art within the technical scope of the present invention are also within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A power grid development aid decision-making method considering investment demand and planning target is characterized by comprising the following steps:
establishing an investment demand prediction model based on differential evolution, grayish optimization and a support vector machine based on the first ten key factors which are screened out by a gray correlation analysis method and influence the investment demand of the power grid;
considering a power grid planning target, constructing a project optimization ordering index system by combining various attributes of a project, and comprehensively evaluating the project based on an analytic hierarchy process and a linear weighting comprehensive method to enable the project to enter an early-stage project reserve library according to the sequence of comprehensive evaluation;
and considering investment demand limitation and allocation proportion constraint of investment amount of different categories of projects, establishing a power grid project investment decision double-objective function seeking the maximum total score of the projects and the minimum total investment amount, and preferably selecting the project combination with the maximum comprehensive benefit score from the early-stage project reserve library based on an improved genetic algorithm.
2. The power grid development aid decision-making method considering investment demand and planning targets as claimed in claim 1, wherein the first ten key factors include fixed asset investment, capacity increment of 220kV and above power transformation equipment, GDP, capacity increment of 110kV and below power transformation equipment, highest power load, power consumption of the whole society, length increment of 220kV and above power transmission line, capacity-to-load ratio, length increment of 110kV and below power transmission line, and contact rate of power distribution line.
3. The power grid development aid decision-making method considering investment demand and planning objective according to claim 1, wherein the differential evolution-sirius optimization-support vector machine model prediction step is as follows:
step 1: setting related parameters and initializing a population;
step 2: calculating the fitness value of the individual gray wolfs, and sequencing the fitness values to determine the positions of the first three gray wolf individuals with the optimal fitness values, wherein the positions are marked as Xα，XβAnd X；
And step 3: calculating other wolf individuals and X in populationα，XβAnd XUpdating the wolf pack position and GWO algorithm-related parameters;
and 4, step 4: carrying out mutation and cross operation to generate a new filial generation population;
and 5: selecting operation is carried out, and the position of the wolf pack is updated;
step 6: judging whether the maximum iteration times is reached, if so, outputting the current optimal solution (c, g), otherwise, skipping to the step 2 to continue parameter optimization;
and 7: and assigning the optimized parameter values to the SVM, and establishing a prediction model.
4. The power grid development aid decision-making method taking investment demand and planning objective into consideration as claimed in claim 1, wherein the project optimization ranking index system comprises a primary index and a secondary index.
5. The power grid development aid decision method considering investment demand and planning objectives according to claim 4, wherein the primary indexes include power grid safety reliability, power grid development coordination, project economic rationality, and social development serviceability.
6. The power grid development aid decision method considering investment requirements and planning targets according to claim 1, characterized in that indexes of each dimension are pairwise compared by an analytic hierarchy process, a judgment matrix with importance degree is established, a geometric mean method or a canonical column mean method is adopted to calculate weights of the judgment matrix, consistency inspection is performed, and finally, project optimization ranking index weights are obtained.
7. The grid development aid decision-making method considering investment requirements and planning objectives according to claim 1, wherein the dual objective function is:
wherein f is1、f2Respectively representing a project scoring function and a total investment function; siA score representing the ith item; n is a radical ofiRepresenting the investment amount of the ith project; x is the number ofiIndicating an item selection status value (1 indicates that the ith item is selected, and 0 indicates that the ith item is not selected).
8. The grid development aid decision making method considering investment demand and planning objective as claimed in claim 7, wherein the constraint conditions of the dual objective function include capital constraint and investment allocation proportion constraint.
9. The grid development aid decision-making method considering investment demand and planning objective as claimed in claim 8, wherein the capital constraints are that the total investment amount after optimizing investment should not exceed the investment capacity of the grid enterprise, that is:
wherein N isiThe investment amount of the ith project is shown, and N shows the investment capacity of the power grid enterprise.
10. The power grid development aid decision-making method considering investment demand and planning objective according to claim 8, wherein the investment allocation proportion constraint is that the investment allocation proportion is equal to the ratio of the contribution degree of the power grid safe reliability index improvement, and the calculation method is as follows:
T1:T2:…:Tj＝D1:D2:…:Dj
Tjrepresents the investment allocation of the j-th category of items; djAnd the contribution degree of the grid safety reliability index representing the j-th category item is improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010299084.9A CN111695718A (en) | 2020-04-16 | 2020-04-16 | Power grid development aid decision-making method considering investment demand and planning target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010299084.9A CN111695718A (en) | 2020-04-16 | 2020-04-16 | Power grid development aid decision-making method considering investment demand and planning target |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111695718A true CN111695718A (en) | 2020-09-22 |
Family
ID=72476403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010299084.9A Pending CN111695718A (en) | 2020-04-16 | 2020-04-16 | Power grid development aid decision-making method considering investment demand and planning target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695718A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112435131A (en) * | 2020-10-19 | 2021-03-02 | 嘉兴恒创电力设计研究院有限公司 | Accurate investment index theory and calculation method based on high-elasticity power grid |
| CN113537847A (en) * | 2021-09-17 | 2021-10-22 | 广州粤芯半导体技术有限公司 | Productivity planning method and readable storage medium |
| CN114638393A (en) * | 2021-11-18 | 2022-06-17 | 国网天津市电力公司 | Neural network-based power grid investment decision evaluation method and device |
| CN114757549A (en) * | 2022-04-24 | 2022-07-15 | 中交第二航务工程勘察设计院有限公司 | Inland river main stream channel overwater service area function and scale decision-making method |
| CN115994459A (en) * | 2023-03-24 | 2023-04-21 | 国网湖北省电力有限公司经济技术研究院 | Method, system and equipment for optimizing construction time sequence of mass power grid infrastructure projects |
| CN117252707A (en) * | 2023-11-14 | 2023-12-19 | 国网吉林省电力有限公司经济技术研究院 | Power grid project investment optimization method and device |
| CN117764306A (en) * | 2023-11-20 | 2024-03-26 | 国电南瑞南京控制系统有限公司 | Project management method and system for power distribution network |
| CN117913800A (en) * | 2023-12-29 | 2024-04-19 | 国网宁夏电力有限公司经济技术研究院 | Power distribution network construction planning method and system |
| CN118037072A (en) * | 2024-02-20 | 2024-05-14 | 国网江苏省电力有限公司泰州供电分公司 | Method for evaluating problem severity of current distribution network and optimizing and delivering project |
| CN118195132A (en) * | 2024-02-22 | 2024-06-14 | 国网宁夏电力有限公司电力科学研究院 | Multi-parameter evaluation decision-making method and system for enterprise |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214449A (en) * | 2018-08-28 | 2019-01-15 | 华北电力大学 | A kind of electric grid investment needing forecasting method |
| CN110738345A (en) * | 2019-08-08 | 2020-01-31 | 国网江苏省电力有限公司泰州供电分公司 | Unit distribution power grid planning project optimization method based on accurate investment strategy |
| CN110909985A (en) * | 2019-11-01 | 2020-03-24 | 国网经济技术研究院有限公司 | Multi-region power grid reserve project screening method considering power grid benefits |
-
2020
- 2020-04-16 CN CN202010299084.9A patent/CN111695718A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214449A (en) * | 2018-08-28 | 2019-01-15 | 华北电力大学 | A kind of electric grid investment needing forecasting method |
| CN110738345A (en) * | 2019-08-08 | 2020-01-31 | 国网江苏省电力有限公司泰州供电分公司 | Unit distribution power grid planning project optimization method based on accurate investment strategy |
| CN110909985A (en) * | 2019-11-01 | 2020-03-24 | 国网经济技术研究院有限公司 | Multi-region power grid reserve project screening method considering power grid benefits |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112435131A (en) * | 2020-10-19 | 2021-03-02 | 嘉兴恒创电力设计研究院有限公司 | Accurate investment index theory and calculation method based on high-elasticity power grid |
| CN113537847A (en) * | 2021-09-17 | 2021-10-22 | 广州粤芯半导体技术有限公司 | Productivity planning method and readable storage medium |
| CN114638393A (en) * | 2021-11-18 | 2022-06-17 | 国网天津市电力公司 | Neural network-based power grid investment decision evaluation method and device |
| CN114757549A (en) * | 2022-04-24 | 2022-07-15 | 中交第二航务工程勘察设计院有限公司 | Inland river main stream channel overwater service area function and scale decision-making method |
| CN115994459A (en) * | 2023-03-24 | 2023-04-21 | 国网湖北省电力有限公司经济技术研究院 | Method, system and equipment for optimizing construction time sequence of mass power grid infrastructure projects |
| CN115994459B (en) * | 2023-03-24 | 2023-06-13 | 国网湖北省电力有限公司经济技术研究院 | Method, system and equipment for optimizing construction time sequence of mass power grid infrastructure projects |
| CN117252707A (en) * | 2023-11-14 | 2023-12-19 | 国网吉林省电力有限公司经济技术研究院 | Power grid project investment optimization method and device |
| CN117252707B (en) * | 2023-11-14 | 2024-02-09 | 国网吉林省电力有限公司经济技术研究院 | Power grid project investment optimization method and device |
| CN117764306A (en) * | 2023-11-20 | 2024-03-26 | 国电南瑞南京控制系统有限公司 | Project management method and system for power distribution network |
| CN117913800A (en) * | 2023-12-29 | 2024-04-19 | 国网宁夏电力有限公司经济技术研究院 | Power distribution network construction planning method and system |
| CN117913800B (en) * | 2023-12-29 | 2024-08-20 | 国网宁夏电力有限公司经济技术研究院 | Power distribution network construction planning method and system |
| CN118037072A (en) * | 2024-02-20 | 2024-05-14 | 国网江苏省电力有限公司泰州供电分公司 | Method for evaluating problem severity of current distribution network and optimizing and delivering project |
| CN118195132A (en) * | 2024-02-22 | 2024-06-14 | 国网宁夏电力有限公司电力科学研究院 | Multi-parameter evaluation decision-making method and system for enterprise |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695718A (en) | Power grid development aid decision-making method considering investment demand and planning target | |
| Hilorme et al. | Smart grid concept as a perspective for the development of Ukrainian energy platform | |
| CN108805443A (en) | Comprehensive evaluation method and system for power grid performance | |
| CN102930482A (en) | Investment effect evaluation method for county power distribution networks | |
| CN108985602B (en) | Power grid classification project input and output evaluation method and system considering risks | |
| CN104182835A (en) | Three-dimensional material goods classification model based on entire life-cycle management and type determination method | |
| CN110309945A (en) | Power distribution station project optimizing evaluation method based on G1- entropy assessment | |
| CN111460378A (en) | Power distribution network accurate investment project optimization method considering risk measure | |
| CN112785060A (en) | Lean operation and maintenance level optimization method for power distribution network | |
| CN115600934A (en) | Investment efficiency benefit evaluation method and device for power distribution network engineering | |
| CN116823008A (en) | Park energy utilization efficiency evaluation method, system, equipment and storage medium | |
| CN110796296A (en) | Multi-objective investment optimization model construction method and device and computing equipment | |
| CN112734274B (en) | Low-carbon power grid operation leading influence factor mining and comprehensive evaluation method | |
| CN114219225A (en) | Power grid investment benefit evaluation system and evaluation method based on multi-source data | |
| CN110298551A (en) | A kind of rating model for market-oriented garden energy synthetic operation degree of urgency | |
| CN111428938A (en) | Power transmission network scheme optimization method based on function difference and full life cycle | |
| CN115034618A (en) | Community comprehensive energy system benefit evaluation method based on fuzzy evaluation | |
| CN111553525A (en) | Power grid investment strategy optimization method considering power transmission and distribution price supervision | |
| CN111369083A (en) | Evaluation method and system for investment benefits of power grid project | |
| Wei et al. | Credit risk evaluation and analysis of power generation enterprises under the spot trading | |
| Huo et al. | Quantitative Measurement of Power Grid Operation Carrying Capacity Based on the Principle of Fuzzy Comprehensive Evaluation | |
| Wang et al. | Estimation of the risks of energy performance contract projects based on the unascertained measure model | |
| Zhou et al. | Research on the planning and allocation method of smart grid technological transformation investment scale considering operational uncertain factors | |
| Zhang et al. | Analysis of Assessment of Power Grid Corp Asset Management Based on Set Pair Analysis Model | |
| CN115345417A (en) | Method for improving efficiency of power distribution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200922 |
|
| RJ01 | Rejection of invention patent application after publication |