Oil field microgrid double-layer optimization scheduling method based on improved adaptive genetic algorithm

Abstract

The invention provides an oil field micro-grid double-layer optimization scheduling method based on an improved self-adaptive genetic algorithm. The oil field micro-grid double-layer optimization scheduling method based on the improved self-adaptive genetic algorithm comprises the steps of 1, building an oil field micro-grid system model; step 2, establishing an oil field micro-grid double-layer optimization scheduling model; 3, solving the model by adopting an improved adaptive genetic algorithm, and formulating a scheduling strategy of the micro-source in the micro-grid; 4, performing simulation calculation to obtain an optimal scheduling plan and an operation strategy of each micro-source of the oil field micro-grid; and 5, establishing an evaluation index to evaluate the advantages and disadvantages of the scheduling strategy formulated by the micro-grid. According to the oil field microgrid double-layer optimization scheduling method based on the improved adaptive genetic algorithm, the economic benefit of the microgrid is improved, the light abandoning rate is reduced, the physical significance is clear, and the method has the advantages of being scientific and reasonable, high in applicability and reasonable and effective in scheduling strategy and algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of oilfield microgrids, and in particular to a double-layer optimization scheduling method of oilfield microgrids based on an improved adaptive genetic algorithm. Background Art

[0002] Oilfield microgrids achieve source-grid-load power balance by relying on distributed energy generation and energy storage equipment. However, due to the randomness and volatility of renewable energy output, and considering the working characteristics of the pumping unit, its downstroke process is no-load or even in a reverse power generation state, all of which will affect the power balance of the system.

[0003] The optimized dispatching of oilfield microgrid is based on ensuring the power balance of the whole network and striving for economic rationality. The commonly used time resolution is 5 minutes to 1 hour. The prediction curve of renewable energy output and pumping unit load is used to optimize the operation strategy of each equipment for the next day.

[0004] The existing oilfield microgrid brings together renewable energy power generation, energy storage, inverters and rectifiers, etc., and the compatibility between sub-modules is not strong: with the increase in the application of renewable energy, the system cannot adapt to the management needs of renewable energy microgrids; the strong waveform of renewable energy power generation and pumping unit characteristic load leads to serious dynamic power imbalance among sources, networks and loads, and the utilization rate of renewable energy is low; therefore, based on the above problems, the existing optimization methods are difficult to achieve reasonable and effective scheduling.

[0005] In the Chinese patent application with application number: CN201310006694.5, a power optimization control method for an offshore oilfield power grid is involved. It establishes a large-scale, multi-constraint, nonlinear power optimization mathematical model, takes power generation fuel costs, active network losses, reactive power balance, and voltage residual as optimization targets, and realizes a multi-target comprehensive control mode through user control; with flow constraints, voltage constraints, branch transmission power constraints, etc. as constraint conditions, the safety of the system is guaranteed. The interior point method is used for programming on the IntelliJIDEA platform. The invention sets an optimization target suitable for offshore oilfield power grids, realizes coordinated control of active and reactive power of power grids, and realizes optimized automatic control of power grid power, which can reduce the fuel consumption of offshore oilfield power grids, improve their power generation efficiency, improve the safety and stability of power grids, and reduce fuel consumption and corresponding pollutant emissions.

[0006] In the Chinese patent application with application number: CN202110389022.1, a power coordination and optimization method for an offshore oilfield group based on shore-based power supply is involved. The power data of the platform equipment in the offshore oilfield platform is obtained, and the power data is sent to the power coordination platform. The power coordination platform receives the power data sent by the offshore oilfield platform, performs line loss analysis and power allocation on the power data, obtains the line loss analysis results and the power allocation results, and sends the results to the remote control platform. The remote control platform is used to obtain the results sent by the power coordination platform and display them for power monitoring personnel to view, and perform remote optimization and adjustment to improve the efficiency of power coordination and optimization of offshore oilfield groups.

[0007] In the Chinese patent application with application number: CN201610172802.X, a method for economic optimization operation and dispatching of microgrids based on an improved quantum genetic algorithm is involved. The microgrid is in a grid-connected mode operation state, including multiple micro sources and loads, the loads include electrical loads and thermal loads, and the micro sources include micro gas turbines, fans, photovoltaic cells, fuel cells, batteries and electric vehicles. The method includes the following steps: S1: obtaining the state information of each load and each micro source in the microgrid; S2: establishing a multi-objective economic dispatch model with the goal of minimizing the operating cost and the pollutant treatment cost; S3: using an improved quantum genetic algorithm to optimize and solve the multi-objective economic dispatch model to obtain the optimal active power of each micro source; S4: controlling the active power output of each micro source according to the optimal active power of each micro source. Compared with the prior art, the invention enables the microgrid composed of distributed power sources to operate in a more economical, flexible and environmentally friendly manner, and can give full play to the power generation advantages of distributed power sources.

[0008] In the Chinese patent application with application number: CN201210516497.3, a short-term power generation prediction method applied to photovoltaic power generation system is involved, which is characterized by comprising two stages: 1. Empirical mode decomposition of the original power generation signal; 2. Constructing a BP neural network prediction model based on genetic algorithm for each decomposition component. The advantages of the present invention are mainly manifested in: accurate photovoltaic power generation prediction in advance can determine the current flow direction of the traditional power grid and the photovoltaic power generation microgrid, formulate the dispatch plan of the power system and reduce the operating cost of the power system; at the same time, energy reserve planning can be formulated in advance to reduce the uncontrollability and intermittency of photovoltaic power generation. The adverse effects on the large power grid, enhance the market competitiveness of photovoltaic power generation. At the same time, the system is also a precedent for applying computer technologies such as artificial neural networks and genetic algorithms to photovoltaic power generation prediction, which has great novelty and practicality.

[0009] The above existing technologies are significantly different from the present invention and fail to solve the technical problem we want to solve. Therefore, we have invented a new two-layer optimization scheduling method for oilfield microgrids based on an improved adaptive genetic algorithm. Summary of the invention

[0010] The purpose of the present invention is to provide a two-layer optimization scheduling method for oilfield microgrids based on an improved adaptive genetic algorithm, which has clear physical meaning, takes into account the problems of reverse power generation energy feedback between microgrid well groups, uncertainty of renewable energy output, etc., and has scientific and reasonable methods, strong applicability, and effective scheduling strategies.

[0011] The object of the present invention can be achieved by the following technical measures: a two-layer optimization scheduling method for oilfield microgrid based on an improved adaptive genetic algorithm, the two-layer optimization scheduling method for oilfield microgrid based on an improved adaptive genetic algorithm comprises:

[0012] Step 1: Build an oilfield microgrid system model;

[0013] Step 2, establish a two-layer optimization scheduling model for oilfield microgrid;

[0014] Step 3, using an improved adaptive genetic algorithm to solve the model and formulate a dispatching strategy for micro-sources in the microgrid;

[0015] Step 4, perform simulation calculations to obtain the optimal scheduling plan and operation strategy for each micro-source of the oilfield microgrid;

[0016] Step 5: Establish evaluation indicators to evaluate the quality of the dispatching strategy formulated by the microgrid.

[0017] The purpose of the present invention can also be achieved by the following technical measures:

[0018] In step 1, the oilfield microgrid model includes three parts: micro-source side, load side and energy storage side. It is integrated by distributed power supply, energy storage and pumping unit load. The oilfield microgrid adopts a centralized control structure. The central controller of the oilfield microgrid is responsible for formulating the next-day scheduling plan for each unit, collecting decision-making information, taking into account the economy and rationality of the scheduling strategy, and formulating an effective scheduling strategy on the basis of ensuring the safe and stable operation of the microgrid.

[0019] In step 1, decision information includes:

[0020] a) Power forecast curves of renewable energy and oil pumping unit loads for the next day;

[0021] b) The capacity, maximum and minimum power, ramp rate and unit dispatch cost of distributed generation;

[0022] c) Capacity, charging and discharging power and efficiency of the energy storage unit.

[0023] In step 2, a two-layer optimization scheduling model is established to take into account both the smoothing of multi-pump load power fluctuations and the economy of oilfield microgrid operation. The upper model adopts the time-sharing scheduling strategy of the well group with the same flushing frequency to optimize the multi-pump load power, and the lower model establishes an economic scheduling model to reduce oil production cost investment.

[0024] In step 2, the upper model uses the fluctuation of the total output power curve of the well group as the criterion for measuring the well group optimization scheduling control strategy, and constructs the well group time-sharing scheduling control strategy. The mathematical model can be expressed as:

[0025]

[0026] Where: Q is the variance index of the total output power curve of the well group; P all (t) is the total output power of the well group; is the average value of the total output power of the well group; N is the number of scheduling optimization periods.

[0027] In step 2, the lower model takes the minimum daily operating cost of the oilfield microgrid as the optimization goal, which mainly includes the fuel and operation and maintenance cost of distributed power generation, energy storage cost, abandoned light cost and load shedding cost. Its objective function is

[0028] minF=C1+C2+C3+C4+C5 (11)

[0029] In the formula, C1 is the photovoltaic operation and maintenance cost, C2 is the gas turbine fuel and operation and maintenance cost, C3 is the energy storage operation and maintenance cost, C4 is the load shedding penalty cost, and C5 is the renewable energy curtailment cost.

[0030] In step 2, the constraints of the upper model and the lower model mainly include power balance constraints and operation constraints of each device in the microgrid.

[0031] In step 2, the constraints are as follows:

[0032] a) Photovoltaic output constraints:

[0033]

[0034] Where: and is the actual absorption value and predicted value of the photovoltaic unit;

[0035] b) Energy storage related constraints:

[0036]

[0037]

[0038] Where: is the state of charge of the energy storage; Δt is the scheduling time interval; The charging and discharging power of the energy storage; They are the charging and discharging signs of energy storage, respectively. When the value is 1, it indicates energy storage action, and when the value is 0, it indicates energy storage static. and are the upper and lower limits of energy storage charging and discharging power, respectively, η chr , η dis are the charging and discharging efficiency of energy storage respectively; are the maximum and minimum values ​​of the energy storage charge state, respectively;

[0039] At the same time, it is necessary to ensure that the charging and discharging of energy storage cannot be carried out at the same time, and considering the service life of energy storage, its charging and discharging frequency is restricted, that is,

[0040]

[0041]

[0042] In actual operation, energy storage must also meet the following charging and discharging ramp constraints:

[0043]

[0044] Where: and are the upper and lower limits of the energy storage charging and discharging ramp rate; γ is the upper limit of the total number of energy storage charging and discharging in a whole scheduling cycle;

[0045]

[0046]

[0047] Where: is the electrical power output by MT in period t, They are the upper and lower limits of MT climbing rate respectively; They are the upper and lower limits of the MT’s output power respectively;

[0048] c) Electric power balance constraints

[0049]

[0050] Where P i (t) is the output power of the i-th pumping unit in period t.

[0051] In step 3, the optimization process of the improved adaptive genetic algorithm includes gene encoding, decoding, crossover, mutation, selection and iteration.

[0052] In step 3, gene coding refers to using an ordered array to represent the independent variable in the optimization problem. In order to conveniently represent genetic variation in the optimization algorithm, the gene of the independent variable is single-stranded. According to the different encoding bases, it can be divided into binary coding and decimal coding. In order to facilitate observation and simplify the calculation process, decimal coding is used.

[0053] In step 3, decoding means converting the gene sequence generated during the calculation process into the actual value represented by the gene through the decoder. For the decoder, the selection is as follows:

[0054]

[0055] In the formula, [a, b] is the variable interval; n is the encoding dimension; m is the number of variables.

[0056] In step 3, crossover refers to exchanging population genes with a certain probability, changing the original gene sequence, and generating new genes. The specific crossover process is as follows:

[0057] The initial population genes are as follows:

[0058]

[0059] cross:

[0060]

[0061] In the formula, is the gene of individual i in the population;

[0062] Adaptive genetic algorithm is used to assign crossover probability to individuals with different fitness. The specific method is as follows:

[0063]

[0064] Where P c is the individual adaptive crossover rate, generally the fitness is less than the mean direct crossover, that is, k2 is 1; k1 is the crossover coefficient; f max is the maximum fitness of individuals in the population; is the mean fitness value, the initial value is 0.5, and it can be adjusted according to the optimization results.

[0065] In step 3, mutation is the process of making a certain number of individual genes or the crossover process of individuals change randomly with a certain probability during the crossover process. Mutation greatly affects the evolution of the population. If the mutation rate is too small, the population diversity will be rapidly reduced and effective genes will be lost. If the mutation rate is too large, the population diversity will increase and the population structure will be destroyed. Therefore, the adaptive genetic algorithm changes the traditional fixed probability mutation and determines the mutation rate according to the fitness of the individual population to increase the effectiveness of the algorithm. The specific method is as follows:

[0066]

[0067] Where P m is the individual adaptive mutation rate; individuals with fitness less than the mean are allowed to mutate directly, that is, k4 = 1; k3 is the coefficient of variation; f max is the maximum fitness of individuals in the population; The initial value of the fitness mean is 0.5, which can be adjusted according to the optimization results.

[0068] In step 3, selection and iteration refers to selecting individuals with high fitness in each optimization result as the initial population for the next optimization, repeating the process of crossover, mutation, and selection to complete the optimization.

[0069] In step 3, the specific steps of improving the adaptive genetic algorithm are as follows:

[0070] Step 1: Input parameters, encode independent variables, and randomly generate the initial population;

[0071] Step 2: Calculate the individual fitness value and measure the individual's quality based on the evaluation results of the objective function and constraints;

[0072] Step 3: Perform crossover and mutation operations and recalculate individual fitness values;

[0073] Step 4: Check whether the termination conditions are met, such as reaching the maximum number of iterations or the convergence of the objective function value; if the conditions are met, stop the algorithm; otherwise, return to step 2 and continue iterating;

[0074] Step 5: Output the best individual as the solution to the problem, that is, the individual with the best fitness value.

[0075] In step 4, based on the predicted data of photovoltaic power generation and multi-pumping unit load; distributed power supply capacity, maximum and minimum output, climbing rate and unit power generation cost coefficient; energy storage equipment capacity, charging and discharging power, efficiency and unit power generation cost; a two-layer optimization scheduling method is used to obtain the optimal scheduling plan and operation strategy for each micro-source in the oilfield microgrid.

[0076] In step 5, the power fluctuation evaluation index and the photovoltaic absorption rate index are

[0077]

[0078]

[0079] Where S is the power fluctuation variance; is the variance function; K is the photovoltaic absorption rate; is the actual photovoltaic power; Predicting performance for photovoltaics.

[0080] The oilfield microgrid double-layer optimization scheduling method based on improved adaptive genetic algorithm in the present invention comprises establishing a mathematical model of oilfield microgrid equipment, constructing a double-layer optimization scheduling model of oilfield microgrid and proposing an improved adaptive genetic algorithm suitable for solving the double-layer optimization model. Compared with the existing single-layer economic scheduling research, the present invention achieves energy mutual feedback of each pumping unit by formulating an operation strategy of the well group pumping units and simultaneously schedules controllable micro-sources to achieve power balance of source, grid and load, which not only improves the economic benefits of the microgrid but also reduces the abandonment rate of light. The method has clear physical meaning, scientific and reasonable methods, strong applicability, and reasonable and effective scheduling strategies and algorithms. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a schematic diagram of the oilfield microgrid structure in a specific embodiment of the present invention;

[0082] Figure 2 A schematic diagram of a distributed photovoltaic power generation array in a specific embodiment of the present invention;

[0083] Figure 3 It is a flow chart of an improved adaptive genetic algorithm in a specific embodiment of the present invention;

[0084] Figure 4 It is a schematic diagram of the measured power curves of four oil pumping units in a specific embodiment of the present invention;

[0085] Figure 5 A comparison diagram of power curves of simultaneous synchronous operation and time-sharing staggered operation of oil pumping units in a specific embodiment of the present invention;

[0086] Figure 6 This is a diagram of oilfield microgrid scheduling results under a double-layer optimization strategy in a specific embodiment of the present invention;

[0087] Figure 7 It is a diagram of oilfield microgrid scheduling results under a single-layer optimization strategy in a specific embodiment of the present invention;

[0088] Figure 8 It is a comparison diagram of the experimental results of SGA, AGA and improved AGA in a specific embodiment of the present invention;

[0089] Fig. 9 The present invention is a flowchart of a specific embodiment of the oilfield microgrid double-layer optimization scheduling method based on the improved adaptive genetic algorithm. DETAILED DESCRIPTION

[0090] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0091] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations and / or combinations thereof.

[0092] like Fig. 9 As shown, Fig. 9 The flowchart of the oilfield microgrid dual-layer optimization scheduling method based on the improved adaptive genetic algorithm of the present invention. The oilfield microgrid dual-layer optimization scheduling method based on the improved adaptive genetic algorithm includes:

[0093] 101) Build an oilfield microgrid system model

[0094] Figure 2 This is a schematic diagram of a distributed photovoltaic power generation array. Photovoltaic panels absorb light energy and convert it into electrical energy, which is then converted and boosted by a photovoltaic inverter to supply power to the load. Excess electrical energy is stored in the energy storage. Figure 1 This is a schematic diagram of the oilfield microgrid structure, which includes distributed power sources such as photovoltaics and gas turbines, controllable and uncontrollable pumping unit loads, energy storage devices, etc. Each part needs to be controlled by a central controller to formulate a scheduling plan for the micro-source, where the power flow represents the power flow direction of the source load, and the information flow indicates that the central controller collects source load information and transmits control instructions. The decision information required is mainly:

[0095] a) Power forecast curves of renewable energy and oil pumping unit loads for the next day;

[0096] b) The capacity, maximum and minimum power, ramp rate and unit dispatch cost of distributed generation;

[0097] c) Capacity, charging and discharging power and efficiency of the energy storage unit.

[0098] Based on the above information, the central controller of the oilfield microgrid needs to take into account the economy and rationality of the dispatching strategy and formulate an effective dispatching strategy on the basis of ensuring the safe and stable operation of the microgrid.

[0099] 102) Establishment of a two-layer optimization scheduling model for oilfield microgrids

[0100] In order to balance the fluctuation of load power of multiple pumping units and the economy of oilfield microgrid operation, a two-layer optimization scheduling model is established. The upper model adopts the time-sharing scheduling strategy of well group with the same flushing frequency to optimize the load power of multiple pumping units, and the lower model establishes an economic scheduling model to reduce the investment in oil production costs.

[0101] Upper model: The fluctuation of the total output power curve of the well group is used as the criterion for measuring the optimization scheduling control strategy of the well group, and the time-sharing scheduling control strategy of the well group is constructed. The mathematical model can be expressed as

[0102]

[0103] Where: Q is the variance index of the total output power curve of the well group; P all (t) is the total output power of the well group; is the average value of the total output power of the well group; N is the number of scheduling optimization periods.

[0104] Lower model: The optimization goal is to minimize the daily operating cost of the oilfield microgrid, which mainly includes the fuel and operation and maintenance costs of distributed power sources, energy storage costs, abandoned light costs and load shedding costs. Its objective function is:

[0105] minF=C1+C2+C3+C4+C5 (2)

[0106] In the formula, C1 is the photovoltaic operation and maintenance cost, C2 is the gas turbine fuel and operation and maintenance cost, C3 is the energy storage operation and maintenance cost, C4 is the load shedding penalty cost, and C5 is the renewable energy curtailment cost.

[0107] The constraints mainly include power balance constraints and operation constraints of various equipment in the microgrid.

[0108] 103) Improved adaptive genetic algorithm

[0109] The optimization process of the improved adaptive genetic algorithm (AGA) is basically the same as that of the traditional genetic algorithm, which mainly includes gene encoding, decoding, crossover, mutation, selection and iteration.

[0110] Coding refers to using an ordered array to represent the independent variable in the optimization problem, which is similar to the gene sequence of an organism, except that the genes of organisms in nature are multi-chain or double-chain, while in the optimization algorithm, in order to conveniently represent genetic variation, the genes of the independent variable are single-chain. According to the different bases of the coding, it can be divided into binary coding and decimal coding. In order to facilitate observation and simplify the calculation process, decimal coding is used.

[0111] Decoding refers to converting the gene sequence generated during the calculation process into the actual value represented by the gene through a decoder. For the decoder, this method selects the following:

[0112]

[0113] In the formula, [a, b] is the variable interval; n is the encoding dimension; m is the number of variables.

[0114] Crossover refers to exchanging population genes with a certain probability, changing the original gene sequence and generating new genes. The specific crossover process is as follows:

[0115] The initial population genes are as follows:

[0116]

[0117] cross:

[0118]

[0119] In the formula, is the gene of individual i in the population.

[0120] Crossover is one of the most important features that distinguish genetic algorithms from other algorithms. The crossover effect directly affects the effectiveness and computational efficiency of the algorithm. If the crossover probability is too small, the population will evolve slowly and converge slowly; if the crossover probability is too large, the population structure will change and excellent individuals will be lost. According to experience, the range of crossover probability is [0.4, 0.99], but a fixed crossover probability cannot be applied to all individuals with different fitness functions. Individuals with high fitness should be retained with a higher probability; individuals with low fitness should be reused to screen out those with computational value. The adaptive genetic algorithm is based on this idea and assigns crossover probabilities to individuals with different fitness. The specific method is as follows:

[0121]

[0122] Where P c is the individual adaptive crossover rate, generally the fitness is less than the mean direct crossover, that is, k2 is 1; k1 is the crossover coefficient; f max is the maximum fitness of individuals in the population; is the mean fitness value, the initial value is 0.5, and it can be adjusted according to the optimization results.

[0123] Mutation is similar to the gene mutation of organisms, that is, in the process of individual crossover, a certain number of individual genes or the crossover process of individuals will change randomly with a certain probability. Mutation greatly affects the evolution of the population. If the mutation rate is too small, the population diversity will be rapidly reduced and effective genes will be lost; if the mutation rate is too large, the population diversity will increase and the population structure will be destroyed. Therefore, the adaptive genetic algorithm changes the traditional fixed probability mutation, determines the mutation rate according to the fitness of the individual population, and increases the effectiveness of the algorithm. The specific method is as follows:

[0124]

[0125] Where P m is the individual adaptive mutation rate; generally, individuals with fitness less than the mean are allowed to mutate directly, that is, k4 = 1; k3 is the coefficient of variation; f maxis the maximum fitness of individuals in the population; The initial value of the fitness mean is 0.5, which can be adjusted according to the optimization results.

[0126] Selection and iteration refers to selecting individuals with high fitness in each optimization result as the initial population for the next optimization, repeating the process of crossover, mutation, and selection to complete the optimization. The specific process of improving the adaptive genetic algorithm is as follows: Figure 3 As shown, the specific steps are as follows:

[0127] Step 1: Input parameters, encode independent variables, and randomly generate the initial population;

[0128] Step 2: Calculate the individual fitness value and measure the individual's quality based on the evaluation results of the objective function and constraints;

[0129] Step 3: Perform crossover and mutation operations and recalculate individual fitness values;

[0130] Step 4: Check whether the termination conditions are met, such as reaching the maximum number of iterations or the objective function value convergence. If the conditions are met, stop the algorithm; otherwise, return to step 2 and continue iterating;

[0131] Step 5: Output the best individual as the solution to the problem, that is, the individual with the best fitness value.

[0132] 104) Simulation calculation

[0133] Simulation input: predicted data of photovoltaic power generation and multi-pumping unit load; distributed power supply capacity, maximum and minimum output, climbing rate and unit power generation cost coefficient; energy storage equipment capacity, charging and discharging power, efficiency and unit power generation cost, etc.; based on the proposed two-layer optimization scheduling method, the optimal scheduling plan and operation strategy for each micro-source of the oilfield microgrid are obtained.

[0134] 105) Evaluation indicators

[0135] The microgrid evaluation index is used to evaluate the quality of the dispatching strategy formulated by the microgrid. To this end, the present invention defines the power fluctuation variance and the renewable energy consumption rate to evaluate the dispatching strategy of the microgrid.

[0136] The power fluctuation evaluation index and photovoltaic consumption rate index are

[0137]

[0138]

[0139] Where S is the power fluctuation variance; is the variance function; K is the photovoltaic absorption rate; is the actual photovoltaic power; Predicting performance for photovoltaics.

[0140] The following are several specific embodiments of the present invention.

[0141] Example 1

[0142] In a specific embodiment 1 of the present invention, the present invention adopts a double-layer optimization scheduling strategy for each pumping unit in the well group. The measured power curves of the four pumping units are as follows: Figure 4 The scheduling result is as shown in Figures 5 to 8 The evaluation indicators are shown in Table 1. Compared with the single-layer microgrid, the two-layer optimization strategy reduces the operating cost by 7.46% and increases the photovoltaic consumption rate by 36.57%, which verifies the effectiveness of the constructed two-layer dispatching strategy.

[0143] Table 1 Comparison of single-layer and double-layer optimization strategy results

[0144]

[0145] The comparison of experimental results of different algorithms is shown in Table 2. It can be found that the improved AGA shows good adaptability in the above optimization problem, optimizes quickly and is not easy to fall into the local optimal solution. Its convergence speed is greater than that of AGA and SGA, which verifies the effectiveness of the proposed algorithm.

[0146] Table 2 Comparison of experimental results of SGA, AGA and improved AGA

[0147]

[0148] Example 2

[0149] In the specific embodiment 2 of the application of the present invention, two strategies are set up for comparison and verification of the effectiveness of the present invention. Strategy 1: adopting the two-level programming method proposed by the present invention; Strategy 2: adopting the multi-objective programming method and taking the objective functions of the upper and lower layer models as the two sub-objectives of the multi-objective model.

[0150] The comparison of the results of strategy 1 and strategy 2 is shown in Table 3. The multi-objective planning method needs to comprehensively consider the weights of the two sub-objectives during the optimization process. Compared with the two-layer optimization method, it cannot achieve deep optimization. Therefore, the economic cost of strategy 2 is higher than that of strategy 1, while the photovoltaic consumption rate is low, which verifies the effectiveness of the proposed two-layer optimization method.

[0151] Table 3 Comparison of results between strategy 1 and strategy 2

[0152]

[0153] Example 3

[0154] In the specific embodiment 3 of the application of the present invention, three optimization algorithms are set to compare and verify the effectiveness of the present invention. Algorithm 1: adopts the improved adaptive genetic algorithm proposed by the present invention; Algorithm 2: adopts the particle swarm optimization algorithm; Algorithm 3: adopts the improved particle swarm optimization algorithm.

[0155] The above three algorithms are used to solve the model respectively, and 50 tests are performed to take the average fitness value. The experimental results are shown in Table 4. It can be seen that the fitness function value of the proposed improved adaptive genetic algorithm is the smallest. When the number of iterations is 20, the global optimal solution has been found. Compared with the particle swarm optimization algorithm and the improved particle swarm optimization algorithm, it has better convergence and faster calculation speed, which verifies the effectiveness of the proposed algorithm.

[0156] Table 4 Comparison of experimental results of different algorithms

[0157]

[0158] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein with equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0159] Except for the technical features described in the specification, all other technical features are known technologies to those skilled in the art.

Claims

1. A two-layer optimization scheduling method for oilfield microgrid based on improved adaptive genetic algorithm, characterized in that: The oilfield microgrid two-layer optimization scheduling method based on the improved adaptive genetic algorithm includes: Step 1: Build an oilfield microgrid system model; Step 2, establish a two-layer optimization scheduling model for oilfield microgrid; Step 3, using an improved adaptive genetic algorithm to solve the model and formulate a dispatching strategy for micro-sources in the microgrid; Step 4, perform simulation calculations to obtain the optimal scheduling plan and operation strategy for each micro-source of the oilfield microgrid; Step 5: Establish evaluation indicators to evaluate the quality of the dispatching strategy formulated by the microgrid.

2. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 1 is characterized in that: In step 1, the oilfield microgrid model includes three parts: micro-source side, load side and energy storage side. It is integrated by distributed power supply, energy storage and pumping unit load. The oilfield microgrid adopts a centralized control structure. The central controller of the oilfield microgrid is responsible for formulating the next-day scheduling plan for each unit, collecting decision-making information, taking into account the economy and rationality of the scheduling strategy, and formulating an effective scheduling strategy on the basis of ensuring the safe and stable operation of the microgrid.

3. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 2 is characterized in that: In step 1, decision information includes: a) Power forecast curves of renewable energy and oil pumping unit loads for the next day; b) The capacity, maximum and minimum power, ramp rate and unit dispatch cost of distributed generation; c) Capacity, charging and discharging power and efficiency of the energy storage unit.

4. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 1 is characterized in that: In step 2, a two-layer optimization scheduling model is established to take into account both the smoothing of multi-pump load power fluctuations and the economy of oilfield microgrid operation. The upper model adopts the time-sharing scheduling strategy of the well group with the same flushing frequency to optimize the multi-pump load power, and the lower model establishes an economic scheduling model to reduce oil production cost investment.

5. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 4 is characterized in that: In step 2, the upper model uses the fluctuation of the total output power curve of the well group as the criterion for measuring the well group optimization scheduling control strategy, and constructs the well group time-sharing scheduling control strategy. The mathematical model can be expressed as: Where: Q is the variance index of the total output power curve of the well group; P all (t) is the total output power of the well group; is the average value of the total output power of the well group; N is the number of scheduling optimization periods.

6. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 5 is characterized in that: In step 2, the lower model takes the minimum daily operating cost of the oilfield microgrid as the optimization goal, which mainly includes the fuel and operation and maintenance cost of distributed power generation, energy storage cost, abandoned light cost and load shedding cost. Its objective function is min F=C1+C2+C3+C4+C5 (11) In the formula, C1 is the photovoltaic operation and maintenance cost, C2 is the gas turbine fuel and operation and maintenance cost, C3 is the energy storage operation and maintenance cost, C4 is the load shedding penalty cost, and C5 is the renewable energy curtailment cost.

7. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 6 is characterized in that: In step 2, the constraints of the upper model and the lower model mainly include power balance constraints and operation constraints of each device in the microgrid.

8. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 7 is characterized in that: In step 2, the constraints are as follows: a) Photovoltaic output constraints: Where: and is the actual absorption value and predicted value of the photovoltaic unit; b) Energy storage related constraints: Where: is the state of charge of the energy storage; Δt is the scheduling time interval; The charging and discharging power of the energy storage; They are the charging and discharging signs of energy storage, respectively. When the value is 1, it indicates energy storage action, and when the value is 0, it indicates energy storage static. and are the upper and lower limits of energy storage charging and discharging power, respectively, η chr , η dis are the charging and discharging efficiency of energy storage respectively; are the maximum and minimum values ​​of the energy storage charge state, respectively; At the same time, it is necessary to ensure that the charging and discharging of energy storage cannot be carried out at the same time, and considering the service life of energy storage, its charging and discharging frequency is restricted, that is, In actual operation, energy storage must also meet the following charging and discharging ramp constraints: Where: and are the upper and lower limits of the energy storage charging and discharging ramp rate; γ is the upper limit of the total number of energy storage charging and discharging in a whole scheduling cycle; Where: is the electrical power output by MT in period t, They are the upper and lower limits of MT climbing rate respectively; They are the upper and lower limits of the MT’s output power respectively; c) Electric power balance constraints Where P i (t) is the output power of the i-th pumping unit in period t.

9. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 1 is characterized in that: In step 3, the optimization process of the improved adaptive genetic algorithm includes gene encoding, decoding, crossover, mutation, selection and iteration.

10. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 9, characterized in that: In step 3, gene coding refers to using an ordered array to represent the independent variable in the optimization problem. In order to conveniently represent genetic variation in the optimization algorithm, the gene of the independent variable is single-stranded. According to the different encoding bases, it can be divided into binary coding and decimal coding. In order to facilitate observation and simplify the calculation process, decimal coding is used.

11. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 9, characterized in that: In step 3, decoding means converting the gene sequence generated during the calculation process into the actual value represented by the gene through the decoder. For the decoder, the selection is as follows: In the formula, [a, b] is the variable interval; n is the encoding dimension; m is the number of variables.

12. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 9, characterized in that: In step 3, crossover refers to exchanging population genes with a certain probability, changing the original gene sequence, and generating new genes. The specific crossover process is as follows: The initial population genes are as follows: cross: In the formula, is the gene of individual i in the population; Adaptive genetic algorithm is used to assign crossover probability to individuals with different fitness. The specific method is as follows: Where P c is the individual adaptive crossover rate, generally the fitness is less than the mean direct crossover, that is, k2 is 1; k1 is the crossover coefficient; f max is the maximum fitness of individuals in the population; is the mean fitness value, the initial value is 0.5, and it can be adjusted according to the optimization results.

13. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 9 is characterized in that: In step 3, mutation is the process of making a certain number of individual genes or the crossover process of individuals change randomly with a certain probability during the crossover process. Mutation greatly affects the evolution of the population. If the mutation rate is too small, the population diversity will be rapidly reduced and effective genes will be lost. If the mutation rate is too large, the population diversity will increase and the population structure will be destroyed. Therefore, the adaptive genetic algorithm changes the traditional fixed probability mutation and determines the mutation rate according to the fitness of the individual population to increase the effectiveness of the algorithm. The specific method is as follows: Where P m is the individual adaptive mutation rate; individuals with fitness less than the mean are allowed to mutate directly, that is, k4 = 1; k3 is the coefficient of variation; f max is the maximum fitness of the individuals in the population; f is the mean fitness, the initial value is 0.5, and it can be adjusted according to the optimization results.

14. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 9, characterized in that: In step 3, selection and iteration refers to selecting individuals with high fitness in each optimization result as the initial population for the next optimization, repeating the process of crossover, mutation, and selection to complete the optimization.

15. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 14, characterized in that: In step 3, the specific steps of improving the adaptive genetic algorithm are as follows: Step 1: Input parameters, encode independent variables, and randomly generate the initial population; Step 2: Calculate the individual fitness value and measure the individual's quality based on the evaluation results of the objective function and constraints; Step 3: Perform crossover and mutation operations and recalculate individual fitness values; Step 4: Check whether the termination conditions are met, such as reaching the maximum number of iterations or the convergence of the objective function value; if the conditions are met, stop the algorithm; otherwise, return to step 2 and continue iterating; Step 5: Output the best individual as the solution to the problem, that is, the individual with the best fitness value.

16. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 1, characterized in that: In step 4, based on the predicted data of photovoltaic power generation and multi-pumping unit load; distributed power supply capacity, maximum and minimum output, climbing rate and unit power generation cost coefficient; energy storage equipment capacity, charging and discharging power, efficiency and unit power generation cost; a two-layer optimization scheduling method is used to obtain the optimal scheduling plan and operation strategy for each micro-source in the oilfield microgrid.

17. The oilfield microgrid dual-layer optimization scheduling method based on improved adaptive genetic algorithm according to claim 1, characterized in that: In step 5, the power fluctuation evaluation index and the photovoltaic absorption rate index are Where S is the power fluctuation variance; is the variance function; K is the photovoltaic absorption rate; is the actual photovoltaic power; Predicting performance for photovoltaics.

Images