Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection

Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable attention.Various constrained multi-objective optimization evolutionary algorithms(CMOEAs)have been developed with the use of different algorithmic strategies,evolutionary operators,and constraint-handling techniques.The performance of CMOEAs may be heavily dependent on the operators used,however,it is usually difficult to select suitable operators for the problem at hand.Hence,improving operator selection is promising and necessary for CMOEAs.This work proposes an online operator selection framework assisted by Deep Reinforcement Learning.The dynamics of the population,including convergence,diversity,and feasibility,are regarded as the state;the candidate operators are considered as actions;and the improvement of the population state is treated as the reward.By using a Q-network to learn a policy to estimate the Q-values of all actions,the proposed approach can adaptively select an operator that maximizes the improvement of the population according to the current state and thereby improve the algorithmic performance.The framework is embedded into four popular CMOEAs and assessed on 42 benchmark problems.The experimental results reveal that the proposed Deep Reinforcement Learning-assisted operator selection significantly improves the performance of these CMOEAs and the resulting algorithm obtains better versatility compared to nine state-of-the-art CMOEAs.

A survey on joint-operation application for unmanned swarm formations under a complex confrontation environment

With the rapid development of informatization,autonomy and intelligence,unmanned swarm formation intelligent operations will become the main combat mode of future wars.Typical unmanned swarm formations such as ground-based directed energy weapon formations,space-based kinetic energy weapon formations,and sea-based carrier-based formations have become the trump card for winning future wars.In a complex confrontation environment,these sophisticated weapon formation systems can precisely strike mobile threat group targets,making them extreme deterrents in joint combat applications.Based on this,first,this paper provides a comprehensive summary of the outstanding advantages,strategic position and combat style of unmanned clusters in joint warfare to highlight their important position in future warfare.Second,a detailed analysis of the technological breakthroughs in four key areas,situational awareness,heterogeneous coordination,mixed combat,and intelligent assessment of typical unmanned aerial vehicle(UAV)swarms in joint warfare,is presented.An in-depth analysis of the UAV swarm communication networking operating mechanism during joint warfare is provided to lay the theoretical foundation for subsequent cooperative tracking and control.Then,an indepth analysis of the shut-in technology requirements of UAV clusters in joint warfare is provided to lay a theoretical foundation for subsequent cooperative tracking control.Finally,the technical requirements of UAV clusters in joint warfare are analysed in depth so the key technologies can form a closed-loop kill chain system and provide theoretical references for the study of intelligent command operations.

Study on the Characteristics of A New Hybrid Mooring System for DualPlatform Joint Operations

As the sustainable exploitation of marine resources develops,dual-platform joint operation has caught increasing attention.Dual-platform joint operation requires smaller relative motion between the two sub-platforms,which is normally difficult to be satisfied by the traditional mooring system.Therefore,a new hybrid mooring system is developed and studied in this article.To ensure safety during platform movements,both the number of anchor chains and the relative motion between the two sub-platforms are reduced in the new hybrid mooring system.By performing numerical simulations based on three-dimensional potential flow theory in AQWA and physical experiments,the performances of both the new hybrid and traditional mooring systems under two different wave conditions(i.e.,working wave and freak wave conditions) are systematically investigated.Regarding the new hybrid mooring system,the relative stability between the two sub-platforms of the new system is better,and the platforms can restore stability faster when affected by freak waves.

Multi-objective reservoir operation using particle swarm optimization with adaptive random inertia weights

Based on conventional particle swarm optimization(PSO),this paper presents an efficient and reliable heuristic approach using PSO with an adaptive random inertia weight(ARIW)strategy,referred to as the ARIW-PSO algorithm,to build a multi-objective optimization model for reservoir operation.Using the triangular probability density function,the inertia weight is randomly generated,and the probability density function is automatically adjusted to make the inertia weight generally greater in the initial stage of evolution,which is suitable for global searches.In the evolution process,the inertia weight gradually decreases,which is beneficial to local searches.The performance of the ARIWPSO algorithm was investigated with some classical test functions,and the results were compared with those of the genetic algorithm(GA),the conventional PSO,and other improved PSO methods.Then,the ARIW-PSO algorithm was applied to multi-objective optimal dispatch of the Panjiakou Reservoir and multi-objective flood control operation of a reservoir group on the Luanhe River in China,including the Panjiakou Reservoir,Daheiting Reservoir,and Taolinkou Reservoir.The validity of the multi-objective optimization model for multi-reservoir systems based on the ARIW-PSO algorithm was verified.

Initiative Optimization Operation Strategy and Multi-objective Energy Management Method for Combined Cooling Heating and Power

This paper proposed an initiative optimization operation strategy and multi-objective energy management method for combined cooling heating and power(CCHP) with storage systems.Initially,the initiative optimization operation strategy of CCHP system in the cooling season,the heating season and the transition season was formulated.The energy management of CCHP system was optimized by the multi-objective optimization model with maximum daily energy efficiency,minimum daily carbon emissions and minimum daily operation cost based on the proposed initiative optimization operation strategy.Furthermore,the pareto optimal solution set was solved by using the niche particle swarm multi-objective optimization algorithm.Ultimately,the most satisfactory energy management scheme was obtained by using the technique for order preference by similarity to ideal solution(TOPSIS) method.A case study of CCHP system used in a hospital in the north of China validated the effectiveness of this method.The results showed that the satisfactory energy management scheme of CCHP system was obtained based on this initiative optimization operation strategy and multi-objective energy management method.The CCHP system has achieved better energy efficiency,environmental protection and economic benefits.

Multi-objective optimization of operation loop recommendation for kill web

In order to improve our military ’s level of intelligent accusation decision-making in future intelligent joint warfare, this paper studies operation loop recommendation methods for kill web based on the fundamental combat form of the future, i.e.,“web-based kill,” and the operation loop theory. Firstly, we pioneer the operation loop recommendation problem with operation ring quality as the objective and closed-loop time as the constraint, and construct the corresponding planning model.Secondly, considering the case where there are multiple decision objectives for the combat ring recommendation problem,we propose for the first time a multi-objective optimization algorithm, the multi-objective ant colony evolutionary algorithm based on decomposition(MOACEA/D), which integrates the multi-objective evolutionary algorithm based on decomposition(MOEA/D) with the ant colony algorithm. The MOACEA/D can converge the optimal solutions of multiple single objectives nondominated solution set for the multi-objective problem. Finally,compared with other classical multi-objective optimization algorithms, the MOACEA/D is superior to other algorithms superior in terms of the hyper volume(HV), which verifies the effectiveness of the method and greatly improves the quality and efficiency of commanders’ decision-making.

Study on Optimization of Urban Rail Train Operation Control Curve Based on Improved Multi-Objective Genetic Algorithm

A multi-objective improved genetic algorithm is constructed to solve the train operation simulation model of urban rail train and find the optimal operation curve.In the train control system,the conversion point of operating mode is the basic of gene encoding and the chromosome composed of multiple genes represents a control scheme,and the initial population can be formed by the way.The fitness function can be designed by the design requirements of the train control stop error,time error and energy consumption.the effectiveness of new individual can be ensured by checking the validity of the original individual when its in the process of selection,crossover and mutation,and the optimal algorithm will be joined all the operators to make the new group not eliminate on the best individual of the last generation.The simulation result shows that the proposed genetic algorithm comparing with the optimized multi-particle simulation model can reduce more than 10%energy consumption,it can provide a large amount of sub-optimal solution and has obvious optimization effect.

Optimal Location and Sizing of Distributed Generator via Improved Multi-Objective Particle Swarm Optimization in Active Distribution Network Considering Multi-Resource

In the framework of vigorous promotion of low-carbon power system growth as well as economic globalization,multi-resource penetration in active distribution networks has been advancing fiercely.In particular,distributed generation(DG)based on renewable energy is critical for active distribution network operation enhancement.To comprehensively analyze the accessing impact of DG in distribution networks from various parts,this paper establishes an optimal DG location and sizing planning model based on active power losses,voltage profile,pollution emissions,and the economics of DG costs as well as meteorological conditions.Subsequently,multiobjective particle swarm optimization(MOPSO)is applied to obtain the optimal Pareto front.Besides,for the sake of avoiding the influence of the subjective setting of the weight coefficient,the decisionmethod based on amodified ideal point is applied to execute a Pareto front decision.Finally,simulation tests based on IEEE33 and IEEE69 nodes are designed.The experimental results show thatMOPSO can achieve wider and more uniformPareto front distribution.In the IEEE33 node test system,power loss,and voltage deviation decreased by 52.23%,and 38.89%,respectively,while taking the economy into account.In the IEEE69 test system,the three indexes decreased by 19.67%,and 58.96%,respectively.

Do Search and Selection Operators Play Important Roles in Multi-Objective Evolutionary Algorithms:A Case Study

Multi-objective Evolutionary Algorithm (MOEA) is becoming a hot research area and quite a few aspects of MOEAs have been studied and discussed. However there are still few literatures discussing the roles of search and selection operators in MOEAs. This paper studied their roles by solving a case of discrete Multi-objective Optimization Problem (MOP): Multi-objective TSP with a new MOEA. In the new MOEA, We adopt an efficient search operator, which has the properties of both crossover and mutation, to generate the new individuals and chose two selection operators: Family Competition and Population Competition with probabilities to realize selection. The simulation experiments showed that this new MOEA could get good uniform solutions representing the Pareto Front and outperformed SPEA in almost every simulation run on this problem. Furthermore, we analyzed its convergence property using finite Markov chain and proved that it could converge to Pareto Front with probability 1. We also find that the convergence property of MOEAs has much relationship with search and selection operators.

ADC-GERT network parameter estimation model for mission effectiveness of joint operation system

Effectiveness evaluation of the joint operation system is an important basis for the demonstration and development of weapon equipment.With the consideration that existing models of system effectiveness evaluation seldom describe the structural relationship among equipment clearly as well as reflect the dynamic,the analog-to-digital converter-graphical evaluation and review technique(ADC-GERT)network parameter estimation model is proposed based on the ADC model and the joint operation system structure.Firstly,analysis of the joint operation system structure and operation process is conducted to build the GERT network,where equipment subsystems are nodes and activities are directed arches.Then the mission effectiveness of equipment subsystems is calculated by the ADC model.The probability transfer parameters are modified by the mission effectiveness of equipment subsystems based on the Bayesian theorem,with the ADC-GERT network parameter estimation model constructed.Finally,a case study is used to validate the efficiency and dynamic of the ADC-GERT network parameter estimation model.

Hemocoagulase Injection blood anesthesia in joint operation

Objective:To investigate the role of Hemocoagulase Injection used in the joint operation and the effect on the blood coagulable function.Methods:A total of 60 patients who undergoing joint operation in our hospital were randomly divided into two groups.Experiment group(Group A,n=30)was injected with 2 U Hemocoagulase Injection in 5 min before anesthesia induction.The contrast group(Group B,n=30)was treated with 0.9%normal saline in 5 min before anesthesia induction.Then common anesthesia was given to the two groups of patients.The venous blood was withdrawn for blood routine examination,thrombelastography and coagulable function at the time of pre-inducement, end of operation,and in 6 and 12 h after operation.The change of thrombelastograph and coagulable state were monitored during the whole surgery.And the volume of transfusion and hemorrhage between two groups was contrasted. Results:After the use of Hemocoagulase Injection,the operative time was shortened obviously(P<0.05).The volumes hemorrhage and transfusion was obviously smaller in Group A than in Group B(P<0.01).Hemocoagulase Injection did not influence fibrinogen and thrombelastograph of Group A(P>0.05).Conclusion:Hemocoagulase Injection can reduce the volumes of hemorrhage and transfusion and not influence the coagulable function.It is worth using in the joint operation.

Superconducting joints using reacted multifilament MgB_(2)wires:A technology toward cryogen-free MRI magnets

The development of superconducting joining technology for reacted magnesium diboride(MgB_(2))conductors remains a critical challenge for the advancement of cryogen-free MgB_(2)-based magnets for magnetic resonance imaging(MRI).Herein,the fabrication of superconducting joints using reacted carbon-doped multifilament MgB_(2)wires for MRI magnets is reported.To achieve successful superconducting joints,the powder-in-mold method was employed,which involved tuning the filament protection mechanism,the powder compaction pressure,and the heat treatment condition.The fabricated joints demonstrated clear superconducting-to-normal transitions in self-field,with effective magnetic field screening up to 0.5 T at 20 K.To evaluate the interface between one of the MgB_(2)filaments and the MgB_(2)bulk within the joint,serial sectioning was conducted for the first time in this type of superconducting joint.The serial sectioning revealed space formation at the interface,potentially caused by the volume shrinkage associated with the MgB_(2)formation or the combined effect of the volume shrinkage and the different thermal expansion coefficients of the MgB_(2)bulk,the filament,the mold,and the sealing material.These findings are expected to be pivotal in developing MgB_(2)superconducting joining technology for MRI magnet applications through interface engineering.

Study on joint optimization operation scheme forPangduo reservoir and Zhikong reservoir

The cascade hydropower system composed of Pangduo reservoir and Zhikong reservoir are formed on the middlereach of the main Lasahe river. For giving full play of joint compensation effect of the two reservoirs, the paper studied the joint operationscheme for Pangduo reservoir and Zhikong reservoir. Based on the respective operation scheme, a reservoir group joint operationmodel is built, the model is solved by the simulation- optimization method, and then the practical and operational scheme isachieved. The scheme could give full play of the joint regulation and storage effect of the reservoir group and improve effectivelythe utilization factor of hydropower resources.

Autonomous process collaboration framework for C4ISR system interoperation

Interoperability plays an important role in the joint command, control, communication, computer, intelligence, surveillance, reconnaissance(C4 ISR) operations. Coordinating and integrating operational processes to fulfill a common mission are challenged by the ever-changing battlefield and hence requires a cross-organizational process management that produces an autonomous, flexible and adaptable architecture for collaborative process evolution. The traditional business process collaboration pattern is based on the predefined "public-view" perspective and cannot meet the requirement of the joint task operations. This paper proposes a flexible visibility control mechanism and a dynamic collaboration framework for modeling and generating collaborative processes. The mechanism allows collaborators to define a set of visibility rules to generate different views of the private processes for different collaborations, which gives a great flexibility for the collaboration initiator to decide on an appropriate collaboration pattern. The framework supports collaborators to dynamically and recursively add a new process or even a new organization to an existing collaboration. Moreover, a formal representation of the processes and a set of generation algorithms are provided to consolidate the proposed theory.

Multi-objective Optimization of Geothermal Extraction from the Enhanced Geothermal System in Qiabuqia Geothermal Field, Gonghe Basin

A geothermal demonstration exploitation area will be established in the Enhanced Geothermal System of the Qiabuqia field, Gonghe Basin, Qinghai–Xizang Plateau in China. Selection of operational parameters for geothermal field extraction is thus of great significance to realize the best production performance. A novel integrated method of finite element and multi-objective optimization has been employed to obtain the optimal scheme for thermal extraction from the Gonghe Basin. A thermal-hydraulic-mechanical coupling model(THM) is established to analyze the thermal performance. From this it has been found that there exists a contraction among different heat extraction indexes. Parametric study indicates that injection mass rate(Q_(in)) is the most sensitive parameter to the heat extraction, followed by well spacing(WS) and injection temperature(T_(in)). The least sensitive parameter is production pressure(p_(out)). The optimal combination of operational parameters acquired is such that(T_(in), p_(out), Q_(in), WS) equals(72.72°C, 30.56 MPa, 18.32 kg/s, 327.82 m). Results indicate that the maximum electrical power is 1.41 MW for the optimal case over 20 years. The thermal break has been relieved and the pressure difference reduced by 8 MPa compared with the base case. The optimal case would extract 50% more energy than that of a previous case and the outcome will provide a remarkable reference for the construction of Gonghe project.

A Multi-Objective Optimal Evolutionary Algorithm Based on Tree-Ranking

Multi-objective optimal evolutionary algorithms (MOEAs) are a kind of new effective algorithms to solve Multi-objective optimal problem (MOP). Because ranking, a method which is used by most MOEAs to solve MOP, has some shortcoming s, in this paper, we proposed a new method using tree structure to express the relationship of solutions. Experiments prove that the method can reach the Pare-to front, retain the diversity of the population, and use less time.

New operation strategy and multi-objective optimization of hybrid solar-fuel CCHP system with fuel thermochemical conversion and source-loads matching

Multi-energy hybrid energy systems are a promising option to mitigate fluctuations in the renewable energy supply and are crucial in achieving carbon neutrality.Solar-fuel thermochemical hybrid utilization upgrades solar energy to fuel chemical energy,thereby achieving the efficient utilization of solar energy,reducing CO_(2)emission,and improving operation stability.For hybrid solar-fuel thermochemical CCHP systems,conventional integration optimization methods and operation modes do not account for the instability of solar energy,thermochemical conversion,and solar fuel storage.To improve the utilization efficiency of solar energy and fuel and achieve favorable economic and environmental performance,a new operation strategy and the optimization of a mid-and-low temperature solar-fuel thermochemical hybrid CCHP system are proposed herein.The system operation modes for various supply-demand scenarios of solar energy input and thermal-power outputs are analyzed,and a new operation strategy that accounts for the effect of solar energy is proposed,which is superior to conventional CCHP system strategies that primarily focus on the balance between system outputs and user loads.To alleviate the challenges of source-load fluctuations and supply-demand mismatches,a multi-objective optimization model is established to optimize the system integration configurations,with objective functions of system energy ratio,cost savings ratio,and CO_(2)emission savings ratio,as well as decision variables of power unit capacity,solar collector area,and syngas storage capacity.The optimization design of the system configuration and the operation strategy improve the performance of the hybrid system.The results show that the system annual energy ratio,cost saving ratio,and CO_(2)emission saving ratio are 52.72%,11.61%,and 36.27%,respectively,whereas the monthly CO_(2)emission reduction rate is 27.3%–47.6%compared with those of reference systems.These promising results will provide useful guidance for the integrated design and operational regulation of hybrid solar-fuel thermochemical systems.

Simulation-optimization model of reservoir operation based on target storage curves

This paper proposes a new storage allocation rule based on target storage curves. Joint operating rules are also proposed to solve the operation problems of a multi-reservoir system with joint demands and water transfer-supply projects. The joint operating rules include a water diversion rule to determine the amount of diverted water in a period, a hedging rule based on an aggregated reservoir to determine the total release from the system, and a storage allocation rule to specify the release from each reservoir. A simulation-optimization model was established to optimize the key points of the water diversion curves, the hedging rule curves, and the target storage curves using the improved particle swarm optimization （IPSO） algorithm. The multi-reservoir water supply system located in Liaoning Province, China, including a water transfer-supply project, was employed as a case study to verify the effectiveness of the proposed join operating rules and target storage curves. The results indicate that the proposed operating rules are suitable for the complex system. The storage allocation rule based on target storage curves shows an improved performance with regard to system storage distribution.

Optimization on Water Resource System Operation Policy during Drought

The mixed linear programming model is commonly recognized to be an effective means for searching optimal reservoir operation policy in water resources system. In this paper a multi-objective mixed integer linear programming model is set up to obtain the optimal operation policy of multi-reservoir water supply system during drought, which is able to consider the operation rule of reservoir-group system within longer-term successive drought periods, according to the basic connotation of indexes expressing the water-supply risk of reservoir during drought, that is, reliability, resilience and vulnerability of reservoir water supply, and mathematical programming principles. The model-solving procedures, particularly, the decomposition-adjustment algorithm, are proposed based on characteristics of the model structure. The principle of model-solving technique is to decompose the complex system into several smaller sub-systems on which some ease-solving mathematical models may be established. The objective of this optimization model aims at maximizing the reliability of water supply and minimizing the maximum water-shortage of single time-period within water- supply system during drought. The multi-objective mixed integer linear programming model and proposed solving procedures are applied to a case study of reservoir-group water-supply system in Huanghe-Huaihe River Basin, China. The desired water-shortage distribution within the system operation term and the maximum shortage of single time-period are achieved. The results of case study verifies that the lighter water-shortage distributed evenly among several time-periods can avoid the calamities resulted from severe water shortage concentrated on a few time-periods during drought.

Improved Fuzzification Method for Multi-Objective Decision-Making and Its Application in Evaluation of Highway Planning

A new fuzzification method for multi-objective decision-making and selective sorting is proposed on the basis of the fuzzy consistent relation, and the specific algorithm is presented. The method is applied to the evaluation of highway planning of Zhanjiang city. To decrease the subjectivity in the process of decision-making, the LOWA operator is introduced, and a discussion on how to select appropriate weights involved in multi-objective sorting is made. It is concluded that it is feasible to apply the fuzzy consistent relation to multi-objective decision-making analysis, and the improved fuzzication method is workable.