CN117775224A - Marine hybrid power energy management method and system based on MOEAD algorithm - Google Patents
Marine hybrid power energy management method and system based on MOEAD algorithm Download PDFInfo
- Publication number
- CN117775224A CN117775224A CN202311584002.5A CN202311584002A CN117775224A CN 117775224 A CN117775224 A CN 117775224A CN 202311584002 A CN202311584002 A CN 202311584002A CN 117775224 A CN117775224 A CN 117775224A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- population
- moead
- vector
- energy management
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 66
- 238000007726 management method Methods 0.000 title claims abstract description 45
- 238000005457 optimization Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 29
- 239000000446 fuel Substances 0.000 claims abstract description 18
- 239000013598 vector Substances 0.000 claims description 103
- 230000006870 function Effects 0.000 claims description 27
- 230000035772 mutation Effects 0.000 claims description 27
- 238000013461 design Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims description 3
- 238000010521 absorption reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 229910052744 lithium Inorganic materials 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000009826 distribution Methods 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 3
- 239000005431 greenhouse gas Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 description 2
- 239000001569 carbon dioxide Substances 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 244000005700 microbiome Species 0.000 description 2
- 239000003921 oil Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000010729 system oil Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention discloses a marine hybrid power energy management method and system based on MOEAD algorithm, comprising the following steps: building a ship diesel-electric hybrid power system model; determining decision variables for hybrid power system optimization; the MOEAD algorithm is used to achieve multi-objective optimization of fuel consumption and emissions of the hybrid powertrain system. The invention optimizes the energy management of the marine diesel-electric hybrid power system by adopting the MOEAD algorithm, thereby realizing remarkable beneficial effects. Effectively reduces oil consumption and emission, and has positive influence on environmental protection. Compared with the traditional strategy based on the logic threshold value, the method improves the accuracy and efficiency of energy management, reduces the dependence on experience, and enables the energy distribution to be more optimized. The running performance and economy of the ship are improved, and a more intelligent and efficient solution is provided for energy management of the ship hybrid power system.
Description
Technical Field
The invention relates to the technical field of ship hybrid power energy management, in particular to a ship hybrid power energy management method and system based on a MOEAD algorithm.
Background
In the field of energy management of marine hybrid systems, conventional approaches typically employ energy management strategies based on logic threshold values. The core of this strategy is to control the operating mode of the vessel by setting a series of predefined threshold values, such as when to use the diesel engine, when to switch to the electric motor, and when to use both simultaneously. These threshold values are typically based on specific operating parameters such as speed, load or battery status. Since the method is based on simple logic judgment, the calculation amount of the method is relatively small, and the method is suitable for a scene requiring quick response. There is a clear margin between the different modes of operation, making it easier to predict and control the behavior of the system in different states. The setting of the logic threshold values is largely dependent on the experience of the designer and understanding of the particular ship operating environment. This may result in that these threshold values are no longer applicable in different vessels or under different operating conditions. This approach is generally less effective than more complex optimization algorithms in terms of global energy consumption optimization and emission reduction due to the lack of comprehensive systematic considerations.
In response to these limitations of the conventional approach, the present invention proposes a new energy management strategy that utilizes a decomposition-based multi-objective optimization algorithm (MOEAD) to optimize energy usage of the hybrid system. Compared with a method based on a logic threshold value, the method can provide a finer and comprehensive energy management solution, so that the dependence on experience is reduced, and better performance is shown in the aspects of reducing oil consumption and emission. The introduction of the method marks the transition of the energy management strategy of the ship hybrid power system to more intelligent and efficient.
Disclosure of Invention
The present invention has been made in view of the above-described problems.
Therefore, the technical problems solved by the invention are as follows: the energy management strategy based on the logic threshold value is widely applied to hybrid power ship energy management, and most of optimization targets are ship power system oil consumption and greenhouse gas emission, but setting of the logic threshold value is excessively dependent on experience, so that the overall optimization effect is poor. The method combines the traditional method based on the logic threshold value with the MOEAD algorithm, provides the marine hybrid power energy management method based on the MOEAD algorithm, and improves the optimization effect aiming at the specific optimization target.
In order to solve the technical problems, the invention provides the following technical scheme: a marine hybrid power energy management method based on a MOEAD algorithm, comprising: building a ship diesel-electric hybrid power system model;
determining decision variables for hybrid power system optimization;
the MOEAD algorithm is used to achieve multi-objective optimization of fuel consumption and emissions of the hybrid powertrain system.
As a preferable scheme of the marine hybrid power energy management method based on the MOEAD algorithm, the invention comprises the following steps: the ship diesel-electric hybrid power system model building method comprises the step of modeling according to the operation mechanism of a model object by adopting a steady-state model method, wherein the modeling comprises a diesel engine model, a motor model, a lithium battery model, a parallel operation gear box model, a diesel generator model and a ship model.
As a preferable scheme of the marine hybrid power energy management method based on the MOEAD algorithm, the invention comprises the following steps: the decision variables for determining the optimization of the hybrid system comprise the design working power P of the diesel generator 1 gen1opt The diesel generator 2 is designed with working power P gen2opt Upper and lower section SOC of battery SOC up And SOC (System on chip) down Diesel engine design working torque T eopt And motor design operating torque T m_opt_max 。
As a preferable scheme of the marine hybrid power energy management method based on the MOEAD algorithm, the invention comprises the following steps: the MOEAD algorithm comprises the steps of distributing weight vectors to sub-problems, determining adjacent weight vectors of each weight vector, initializing a population and a target vector value, initializing a reference point, performing intersection and mutation by using a self-adaptive differential evolution algorithm, selecting and absorbing boundaries, updating the reference point and the population, and updating an output population.
As a preferable scheme of the marine hybrid power energy management method based on the MOEAD algorithm, the invention comprises the following steps: the assignment of weight vectors to the sub-problems includes assigning a population of individuals to each sub-problem, each population of individuals also having a corresponding weight vector, for each weight vector, the elements in the vector need to satisfy 0 or more and sum to 1, for the multi-objective optimization problem of two objectives, the weight vector of the ith population of individualsExpressed as:
wherein,the j-th element of the weight vector representing the i-th sub-problem, i=1, …, P size ；P size Representing the population number;
the determining of the neighboring weight vectors for each weight vector includes determining, by euclidean distance between the weight vectors, expressed as,
representing a weight vector lambda i And a weight vector lambda j Euclidean distance d of (2) ij ；
The initialization population and the target vector value comprise setting the lower bound of decision variables asLet the upper bound of decision variable be +.>The size of the jth decision variable in the ith initial population of individuals is expressed as:
wherein rand [0,1] represents a uniform random number of 0 to 1; k represents the number of decision variables;
after the initial population is obtained, assuming that the number of decision variables is M, for inputting the decision variable value of each individual into the multi-objective optimization problem, obtaining an objective function vector, which is expressed as:
V i ＝OF(x i )
wherein x is i A real value parameter vector representing the individual dimension value M of the ith population; OF represents a multi-objective function; v (V) i Representing the target vector value for the ith population of individuals.
As a preferable scheme of the marine hybrid power energy management method based on the MOEAD algorithm, the invention comprises the following steps: the initialization reference point comprises using a reference point vector z composed of the minimum values of the solution objective functions of the initialization population to replace the theoretical reference point vector z * Z can be calculated from the following formula:
z＝(z 1 ,..,z M ) T
the crossover and mutation by using the adaptive differential evolution algorithm comprises the following steps of neighbor Nh i ＝{i 1 ,i 2 ,...,i T Three population individuals with different superscripts are arbitrarily selected for differential evolution operation, and the generated variation vector is obtained by the following formula according to the principle of a differential evolution algorithm:
wherein eta i Gen+1 Representing the progeny vector resulting from the variation; i.e a ,i b ,i c Representing the slave neighborhood Nh i Wherein a, b, c and weight vector sequence number i are different from each other; f represents a mutation operator;
the size of a particular mutation operator is expressed as:
F'＝F 0 ×2 λ
wherein F is 0 Representing an initial mutation operator; gen (Gen) max Representing a maximum number of iterations; f', an adaptive mutation operator;
in addition to the mutation operation, in order to increase the diversity of the population, a crossover operation is also required, and specific steps are expressed as follows:
ζ i Gen+1 ＝(ζ i 1,Gen+1 ,..,ζ i k,Gen+1 )
wherein ζ i Gen+1 Representing the weight vector obtained after the crossing; k represents the number of decision variables; CR represents a crossover operator; randb (j) represents the jth random number of the 0 to 1 random number generator; rnbr (j) represents the jth random number of the random integer generator from 0 to M;
the selection and boundary absorption process comprises that the weight vector after mutation and crossover process needs to be compared with the weight vector of the current population, the weight vector with the minimum objective function value becomes the new individual of the population, in order to ensure the weight vector ζ i Is located in the feasible domain of the multi-objective problem, all parameter values outside the feasible domain are set as adjacent upper or lower boundariesBoundary value, corrected ζ is obtained i '。
As a preferable scheme of the marine hybrid power energy management method based on the MOEAD algorithm, the invention comprises the following steps: the updating of the reference point Z and the population comprises the correction of ζ i ' bring into the objective function, if equation (1) holds, then the reference point z is updated according to equation (2):
z j ＝f j (ζ i' ) (2)
for any i εnh i ＝{i 1 ,i 2 ,...,i T If equation (3) holds, then population individuals and objective function vectors are updated according to equations (4) and (5):
g te (ζ i' ∣λ i ,z)≤g te (x i ∣λ i ,z) (3)
x i ＝ζ i' (4)
V i ＝OF(ζ i' ) (5)
wherein g te Representing a chebyshev formula;
the updating the output population includes removing the driven OF (ζ i' ) If the dominant objective function vector does not exist in the output solution set, dominant OF (ζ i' ) OF (ζ) i' ) The target function vector is the optimal solution, and after the iteration termination condition is met, the output result is the Pareto optimal solution.
A marine hybrid power energy management system based on MOEAD algorithm, characterized in that: the method comprises the following steps of: building a ship diesel-electric hybrid power system model;
decision variable determining module: determining decision variables for hybrid power system optimization;
MOEAD algorithm module: the MOEAD algorithm is used to achieve multi-objective optimization of fuel consumption and emissions of the hybrid powertrain system.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method as described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the method as described above.
The invention has the beneficial effects that: the invention realizes remarkable beneficial effects by adopting a decomposition-based multi-objective optimization algorithm (MOEAD) to optimize the energy management of the diesel-electric hybrid power system of the ship. Effectively reduces oil consumption and emission, and has positive influence on environmental protection. Compared with the traditional strategy based on the logic threshold value, the method improves the accuracy and efficiency of energy management, reduces the dependence on experience, and enables the energy distribution to be more optimized. The running performance and economy of the ship are improved, and a more intelligent and efficient solution is provided for energy management of the ship hybrid power system.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is an overall flow chart of a marine hybrid power energy management method based on MOEAD algorithm according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram showing a marine hybrid power energy management method based on MOEAD algorithm according to a first embodiment of the present invention, showing a marine diesel-electric hybrid power system structure and a system energy flow diagram under different operation modes;
FIG. 3 is a flow chart of MOEAD algorithm of a marine hybrid power energy management method based on MOEAD algorithm according to a first embodiment of the present invention;
fig. 4 is a graph of fuel consumption and emission under Pareto optimal solution of a marine hybrid power energy management method based on a MOEAD algorithm according to a second embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Referring to fig. 1 to 3, for one embodiment of the present invention, there is provided a marine hybrid power energy management method based on a MOEAD algorithm, including:
s1: and building a ship diesel-electric hybrid power system model.
In order to study the hybrid power system of the ship, a proper system model needs to be established. Modeling is carried out according to the operation mechanism of the model object by adopting a steady-state model method, and the modeling process ignores transient behaviors of the model object, wherein the transient behaviors comprise a diesel engine model, a motor model, a lithium battery model, a parallel operation gear box model, a diesel generator model and a ship model. The energy flow between the models can be seen with reference to fig. 2.
S2: decision variables for hybrid powertrain optimization are determined.
The decision variables of the current series-parallel hybrid power system optimization problem are 6, and the diesel generator 1 designs the working power P gen1opt The diesel generator 2 is designed with working power P gen2opt Upper and lower section SOC of battery SOC up And SOC (System on chip) down Diesel engine design working torque T eopt And motor design operating torque T m_opt_max 。
S3: the MOEAD algorithm is used to achieve multi-objective optimization of fuel consumption and emissions of the hybrid powertrain system.
(1) The sub-problem assigns a weight vector: each sub-problem is assignedA population of individuals, the individuals also having corresponding weight vectors. For each weight vector, the elements in the vector need to satisfy 0 or more and sum to 1. For the multi-objective optimization problem of two objectives, the weight vector of the ith population individualCan be expressed as:
wherein,the j-th element of the weight vector representing the i-th sub-problem, i=1, …, P size ；P size Representing the population number.
(2) Determining an adjacent weight vector for each weight vector: the decomposition-based multi-objective optimization algorithm is characterized in that adjacent weight vectors of the weight vectors need to be found to perform differential evolution operation, wherein the adjacent weight vectors can be defined by Euclidean distance between the weight vectors, and the following formula represents the weight vector lambda i And a weight vector lambda j Euclidean distance d of (2) ij . The number of adjacent weight vectors is artificially defined as a setting parameter of the MOEAD algorithm, assuming that T adjacent weight vectors need to be foundThen the neighborhood of each weight vector is the set of the sequence numbers of the T weight vectors nearest to that vector, defined as Nh i ＝{i 1 ,i 2 ,...,i T }；
(3) Initializing population and target vector values: the simplest method for initializing the population is to randomly value decision variables in a feasible domain according to the number of individuals of the population, and presumeThere is a random initialisation population that meets a uniform probability distribution. Let the lower bound of the decision variable beLet the upper bound of decision variable be +.>The size of the jth decision variable in the ith initial population of individuals can be expressed as:
wherein rand [0,1] represents a uniform random number of 0 to 1; k represents the number of decision variables.
After the initial population is obtained, assuming that the number of decision variables is M, for inputting the decision variable value of each individual into the multi-objective optimization problem, obtaining an objective function vector, which is expressed as:
V i ＝OF(x i )
wherein x is i A real value parameter vector representing the individual dimension value M of the ith population; OF represents a multi-objective function; v (V) i Representing the target vector value for the ith population of individuals.
(4) Initializing a reference point: updating neighbor solutions using an aggregation function requires information about reference points, theoretical reference point vector z * Is composed of the minimum values of all solution objective functions in the solution set, is difficult to obtain in practice, and can be replaced by a reference point vector z composed of the minimum values of the solution objective functions of the initialized population * Z can be calculated from the following formula:
z＝(z 1 ,..,z M ) T
(5) And (3) performing crossover and mutation by using an adaptive differential evolution algorithm: from neighborhood Nh i ＝{i 1 ,i 2 ,...,i T And 3, randomly selecting three population individuals with different superscripts to perform differential evolution operation. According to the principle of the differential evolution algorithm, the generated variance vector can be obtained by the following formula:
wherein eta i Gen+1 Representing the progeny vector resulting from the variation; i.e a ,i b ,i c Representing the slave neighborhood Nh i Wherein a, b, c and weight vector sequence number i are different from each other; f represents the mutation operator.
When the mutation operator takes a fixed value, the mutation operator is oversized, the algorithm searching efficiency is poor, and the obtained global optimal solution has lower precision; the mutation operator is too small, so that the diversity of the population is poor, and the population is easy to fall into local optimum. Therefore, the mutation operator needs to be capable of changing correspondingly along with the iterative times of the algorithm, a larger value is kept in the initial stage, and the diversity of the population is improved; gradually reducing the efficiency of a lifting algorithm in the middle and later stages, improving the overall optimal solution precision, and expressing the size of a specific mutation operator as follows:
F'＝F 0 ×2 λ
wherein F is 0 Representing an initial mutation operator; gen (Gen) max Representing a maximum number of iterations; f', an adaptive mutation operator.
In addition to the mutation operation, in order to increase the diversity of the population, a crossover operation is also required, and specific steps are expressed as follows:
ζ i Gen+1 ＝(ζ i 1,Gen+1 ,..,ζ i k,Gen+1 )
wherein ζ i Gen+1 Representing the weight vector obtained after the crossing; k represents the number of decision variables; CR represents a crossover operator; randb (j) represents the jth random number of the 0 to 1 random number generator; rnbr (j) represents the jth random number of the random integer generator from 0 to M.
It should be noted that, in addition to using a single differential evolution algorithm to generate new individuals, gaussian variation can also be combined to improve the local search capability of the algorithm.
(6) Selection and boundary absorption treatment: the weight vector after mutation and cross treatment needs to be compared with the weight vector of the current population, so that the weight vector with the minimum objective function value becomes a new individual of the population. To ensure the weight vector ζ i The elements of (2) are located in the feasible domain of the multi-objective problem, all parameter values outside the feasible domain are set as adjacent upper boundary or lower boundary values, and modified zeta is obtained i' 。
(7) Updating the reference point z and the population: zeta after correction i' If equation (1) holds, the reference point z is updated according to equation (2).
z j ＝f j (ζ i' ) (2)
For any i εnh i ＝{i 1 ,i 2 ,...,i T If equation (3) holds, then population individuals and objective function vectors are updated according to equations (4) and (5).
g te (ζ i' ∣λ i ,z)≤g te (x i ∣λ i ,z) (3)
x i ＝ζ i' (4)
V i ＝OF(ζ i' ) (5)
Wherein g te Representing the chebyshev formula.
(8) Updating the output population: removing the quilt OF (ζ) from the optimal solution set i' ) Dominant objective function vector, if the output solution set does not have dominant OF (ζ i' ) OF (ζ) i' ) Is the objective function vector of the optimal solution. After the iteration termination condition is met, the output result is the Pareto optimal solution.
Note that fuel consumption can be obtained by integrating the instantaneous fuel consumption rate with respect to time, expressed as:
wherein g gen_de1_ins Represents the instantaneous fuel consumption rate (g/s) of the diesel generator 1; g gen_de2_ins Represents the instantaneous fuel consumption rate (g/s) of the diesel generator 2; g e_ins Representing the instantaneous fuel consumption rate (g/s) of the diesel engine; g represents total fuel consumption (kg).
The greenhouse gas emissions can be calculated from the following formula:
EM＝(E gen_de1 +E gen_de2 +E e )EM fuel +E b EM ele
wherein EM represents total greenhouse gas emissions (kg); e (E) gen_de1 Represents the energy (kw·h) consumed by the diesel generator 1; e (E) gen_de2 Represents the energy (kw·h) consumed by the diesel generator 2; EM (effective microorganisms) fuel Represents the carbon dioxide emission (kg/(kW.h)) produced by a diesel engine with fuel per kilowatt-hour; e (E) b Energy (kw.h) representing battery consumption; e (E) e Represents the energy consumed by the diesel engine (kW.h); EM (effective microorganisms) ele The carbon dioxide emission amount per kilowatt-hour shore power generation (kg/(kw·h)) is indicated.
In the above embodiment, the marine hybrid power energy management system based on the MOEAD algorithm is further included, specifically:
and a model building module: building a ship diesel-electric hybrid power system model;
decision variable determining module: determining decision variables for hybrid power system optimization;
MOEAD algorithm module: the MOEAD algorithm is used to achieve multi-objective optimization of fuel consumption and emissions of the hybrid powertrain system.
The computer device may be a server. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing data cluster data of the power monitoring system. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a marine hybrid energy management method based on the MOEAD algorithm.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile memory may include Read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high density embedded nonvolatile memory, resistive random access memory (ReRAM), magnetic random access memory (MagnetoresistiveRandomAccessMemory, MRAM), ferroelectric memory (FerroelectricRandomAccessMemory, FRAM), phase change memory (PhaseChangeMemory, PCM), graphene memory, and the like. Volatile memory may include random access memory (RandomAccessMemory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can take many forms, such as static random access memory (StaticRandomAccessMemory, SRAM) or dynamic random access memory (DynamicRandomAccessMemory, DRAM), among others. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
Example 2
Referring to fig. 3, for one embodiment of the present invention, a marine hybrid power energy management method based on the MOEAD algorithm is provided, and in order to verify the beneficial effects of the present invention, scientific demonstration is performed through economic benefit calculation and simulation/comparison experiments.
The decision variables of the current series-parallel hybrid power system optimization problem are 6, and the diesel generator 1 designs the working power P gen1opt The diesel generator 2 is designed with working power P gen2opt Upper and lower section SOC of battery SOC up And SOC (System on chip) down Diesel engine design working torque T eopt And motor design operating torque T m_opt_max . Table 1 is the MOEAD algorithm parameter setting case, where the number of iterations is 60, the number of populations is set to 20, and the number of neighbor weight vectors is 4.
Table 1 genetic algorithm parameter set table
| Parameters (parameters) | Size and dimensions of |
| Number of iterations | 60 |
| Number of objective functions | 2 |
| Population number | 20 |
| Decision variables | 6 |
| Number of neighbor weight vectors | 6 |
Referring to fig. 3, the size of the objective function under 20 Pareto optimal solutions obtained through the operation is shown.
Reference may also be made to table 2:
table 2 size reference table of decision variables under Pareto optimal solution
It can be seen that the use of the MOEAD algorithm can reduce fuel consumption and emissions by 2.23% and 0.92% respectively, compared to non-optimized systems, for a series-parallel hybrid system based on a logic threshold energy management strategy.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. A marine hybrid power energy management method based on a MOEAD algorithm, comprising:
building a ship diesel-electric hybrid power system model;
determining decision variables for hybrid power system optimization;
the MOEAD algorithm is used to achieve multi-objective optimization of fuel consumption and emissions of the hybrid powertrain system.
2. The marine hybrid energy management method based on the MOEAD algorithm of claim 1, wherein: the ship diesel-electric hybrid power system model building method comprises the step of modeling according to the operation mechanism of a model object by adopting a steady-state model method, wherein the modeling comprises a diesel engine model, a motor model, a lithium battery model, a parallel operation gear box model, a diesel generator model and a ship model.
3. The marine hybrid energy management method based on the MOEAD algorithm of claim 2, wherein: the decision variables for determining the optimization of the hybrid system comprise the design working power P of the diesel generator 1 gen1opt The diesel generator 2 is designed with working power P gen2opt Upper and lower section SOC of battery SOC up And SOC (System on chip) down Diesel engine design working torque T eopt And motor design operating torque T m_opt_max 。
4. The marine hybrid energy management method based on the MOEAD algorithm of claim 3, wherein: the MOEAD algorithm comprises the steps of distributing weight vectors to sub-problems, determining adjacent weight vectors of each weight vector, initializing a population and a target vector value, initializing a reference point, performing intersection and mutation by using a self-adaptive differential evolution algorithm, selecting and absorbing boundaries, updating the reference point and the population, and updating an output population.
5. The marine hybrid power energy management method based on the MOEAD algorithm of claim 4, wherein: the assigning a weight vector to the sub-questions includes, for each sub-questionThe questions are distributed with a population individual, each population individual also has a corresponding weight vector, for each weight vector, the elements in the vector need to satisfy the sum of more than or equal to 0 and 1, and for the multi-objective optimization problem of two objectives, the weight vector lambda of the ith population individual i ＝(λ 1 i ,λ 2 i ) T Expressed as:
wherein,the j-th element of the weight vector representing the i-th sub-problem, i=1, …, P size ；P size Representing the population number;
the determining of the neighboring weight vectors for each weight vector includes determining, by euclidean distance between the weight vectors, expressed as,
representing a weight vector lambda i And a weight vector lambda j Euclidean distance d of (2) ij ；
The initialization population and the target vector value comprise setting the lower bound of decision variables asLet the upper bound of decision variable be +.>The size of the jth decision variable in the ith initial population of individuals is expressed as:
wherein rand [0,1] represents a uniform random number of 0 to 1; k represents the number of decision variables;
after the initial population is obtained, assuming that the number of decision variables is M, for inputting the decision variable value of each individual into the multi-objective optimization problem, obtaining an objective function vector, which is expressed as:
V i ＝OF(x i )
wherein x is i A real value parameter vector representing the individual dimension value M of the ith population; OF represents a multi-objective function; v (V) i Representing the target vector value for the ith population of individuals.
6. The marine hybrid energy management method based on the MOEAD algorithm of claim 5, wherein: the initialization reference point comprises using a reference point vector z composed of the minimum values of the solution objective functions of the initialization population to replace the theoretical reference point vector z * Z can be calculated from the following formula:
z＝(z 1 ,..,z M ) T
the crossover and mutation by using the adaptive differential evolution algorithm comprises the following steps of neighbor Nh i ＝{i 1 ,i 2 ,...,i T Three population individuals with different superscripts are arbitrarily selected for differential evolution operation, and the generated variation vector is obtained by the following formula according to the principle of a differential evolution algorithm:
wherein eta i Gen+1 Representing the progeny vector resulting from the variation; i.e a ,i b ,i c Representing the slave neighborhood Nh i Wherein a, b, c and weight vector sequence number i are not mutually different from 3 weight vector sequence numbers randomly selected in the tableSimultaneously; f represents a mutation operator;
the size of a particular mutation operator is expressed as:
F'＝F 0 ×2 λ
wherein F is 0 Representing an initial mutation operator; gen (Gen) max Representing a maximum number of iterations; f', an adaptive mutation operator;
in addition to the mutation operation, in order to increase the diversity of the population, a crossover operation is also required, and specific steps are expressed as follows:
ζ i Gen+1 ＝(ζ i 1,Gen+1 ,..,ζ i k,Gen+1 )
wherein ζ i Gen+1 Representing the weight vector obtained after the crossing; k represents the number of decision variables; CR represents a crossover operator; randb (j) represents the jth random number of the 0 to 1 random number generator; rnbr (j) represents the jth random number of the random integer generator from 0 to M;
the selection and boundary absorption process comprises that the weight vector after mutation and crossover process needs to be compared with the weight vector of the current population, the weight vector with the minimum objective function value becomes the new individual of the population, in order to ensure the weight vector ζ i The elements of (2) are located in the feasible domain of the multi-objective problem, all parameter values outside the feasible domain are set as adjacent upper boundary or lower boundary values, and modified zeta is obtained i '。
7. The marine hybrid energy management method based on the MOEAD algorithm of claim 6, wherein: the updating of the reference point Z and the population comprises the correction of ζ i ' into the objective function if equation (1) becomesIf so, the reference point z is updated according to equation (2):
z j ＝f j (ζ i' ) (2)
for any i εnh i ＝{i 1 ,i 2 ,...,i T If equation (3) holds, then population individuals and objective function vectors are updated according to equations (4) and (5):
g te (ζ i' ∣λ i ,z)≤g te (x i ∣λ i ,z) (3)
x i ＝ζ i' (4)
V i ＝OF(ζ i' ) (5)
wherein g te Representing a chebyshev formula;
the updating the output population includes removing the driven OF (ζ i' ) If the dominant objective function vector does not exist in the output solution set, dominant OF (ζ i' ) OF (ζ) i' ) The target function vector is the optimal solution, and after the iteration termination condition is met, the output result is the Pareto optimal solution.
8. A marine hybrid energy management system based on MOEAD algorithm employing the method of any one of claims 1-7, characterized by: marine hybrid power energy management method based on MOEAD algorithm
And a model building module: building a ship diesel-electric hybrid power system model;
decision variable determining module: determining decision variables for hybrid power system optimization;
MOEAD algorithm module: the MOEAD algorithm is used to achieve multi-objective optimization of fuel consumption and emissions of the hybrid powertrain system.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311584002.5A CN117775224A (en) | 2023-11-24 | 2023-11-24 | Marine hybrid power energy management method and system based on MOEAD algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311584002.5A CN117775224A (en) | 2023-11-24 | 2023-11-24 | Marine hybrid power energy management method and system based on MOEAD algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117775224A true CN117775224A (en) | 2024-03-29 |
Family
ID=90400971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311584002.5A Pending CN117775224A (en) | 2023-11-24 | 2023-11-24 | Marine hybrid power energy management method and system based on MOEAD algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117775224A (en) |
-
2023
- 2023-11-24 CN CN202311584002.5A patent/CN117775224A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yuan et al. | A new methodology for optimal location and sizing of battery energy storage system in distribution networks for loss reduction | |
| WO2023216150A1 (en) | Thermal management method for fuel cell | |
| CN116207750A (en) | Power distribution network reactive power optimization method based on depth deterministic strategy gradient algorithm | |
| CN116500986A (en) | Method and system for generating priority scheduling rule of distributed job shop | |
| CN117595392A (en) | Power distribution network joint optimization method and system considering light Fu Xiaona and light storage and charge configuration | |
| Huo et al. | An improved soft actor-critic based energy management strategy of fuel cell hybrid electric vehicle | |
| Yu et al. | A chaotic local search-based LSHADE with enhanced memory storage mechanism for wind farm layout optimization | |
| CN111461284A (en) | Data discretization method, device, equipment and medium | |
| CN116451947A (en) | Optimal scheduling method for electric heating gas comprehensive energy system, terminal equipment and storage medium | |
| Yang et al. | Optimization of fuzzy controller based on genetic algorithm | |
| Koga et al. | Speeding-up reinforcement learning through abstraction and transfer learning | |
| CN117775224A (en) | Marine hybrid power energy management method and system based on MOEAD algorithm | |
| CN117002472A (en) | Energy management optimization method and system for hybrid electric vehicle | |
| CN115528750B (en) | Power grid safety and stability oriented data model hybrid drive unit combination method | |
| CN114580864B (en) | Multi-element energy storage distribution method, system and equipment for comprehensive energy system | |
| CN114329317B (en) | Output power scheduling method and device based on hybrid generator set and terminal | |
| Sadati et al. | Unit commitment using particle swarm-based-simulated annealing optimization approach | |
| Tan | Research on sustainable carrying capacity of urban tourism environment based on multi objective optimization algorithm | |
| CN114861995A (en) | Demand prediction method and device for power supplies and computer equipment | |
| Park et al. | An application of evolutionary computations to economic load dispatch with piecewise quadratic cost functions | |
| Samanta et al. | Energy management in hybrid electric vehicles using optimized radial basis function neural network | |
| CN114942895B (en) | Address mapping strategy design method based on reinforcement learning | |
| CN116882653B (en) | Scheduling method and system suitable for coal-fired power plant | |
| CN118226757B (en) | Energy management method and system for fuel cell aircraft | |
| CN115648973B (en) | Improved DDPG reinforcement learning hybrid energy management method based on local sensitive hash |
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 |