scholarly journals Technical note: the caRamel R package for Automatic Calibration by Evolutionary Multi Objective Algorithm

2019 ◽  
Author(s):  
Céline Monteil ◽  
Fabrice Zaoui ◽  
Nicolas Le Moine ◽  
Frédéric Hendrickx
Keyword(s):  
Stable Solution ◽  
R Package ◽  
Technical Note ◽  
Main Function ◽  
Nsga Ii ◽  
Multiple Criteria Optimization ◽  
Multi Objective ◽  
Study Case ◽  
Nondominated Sorting

Abstract. Environmental modelling is complex, and models often require the calibration of several parameters that are not directly evaluable from a physical quantity or a field measurement. The R package caRamel has been designed to easily implement a multi-objective optimizer in the R environment to calibrate these parameters. A multiobjective calibration allows to find a compromise between different goals by defining a set of optimal parameters. The algorithm is a hybrid of the Multiobjective Evolutionary Annealing Simplex method (MEAS) and the Nondominated Sorting Genetic Algorithm II (ε-NSGA-II algorithm). The optimizer was initially developed for the calibration of hydrological models but can be used for any environmental model. The main function of the package, caRamel(), requires to define a multi-objective calibration function as well as bounds on the variation of the underlying parameters to optimize. CaRamel is well adapted to complex modelling. As an example, caRamel converges quickly and has a stable solution after 5,000 model evaluations with robust results for a real study case of a hydrological problem with 8 parameters and 3 objectives of calibration. The comparison with another well-known optimizer (i.e. MCO, for Multiple Criteria Optimization) confirms the quality of the algorithm.

scholarly journals Multi-objective calibration by combination of stochastic and gradient-like parameter generation rules – the caRamel algorithm

2020 ◽  
Vol 24 (6) ◽  
pp. 3189-3209
Author(s):  
Céline Monteil ◽  
Fabrice Zaoui ◽  
Nicolas Le Moine ◽  
Frédéric Hendrickx
Keyword(s):  
R Package ◽  
Calibration Procedure ◽  
Automatic Calibration ◽  
Hydrological Models ◽  
Environmental Modelling ◽  
Nsga Ii ◽  
Multi Objective ◽  
Constrained Problem ◽  
Stochastic Rules

Abstract. Environmental modelling is complex, and models often require the calibration of several parameters that are not able to be directly evaluated from a physical quantity or field measurement. Multi-objective calibration has many advantages such as adding constraints in a poorly constrained problem or finding a compromise between different objectives by defining a set of optimal parameters. The caRamel optimizer has been developed to meet the requirement for an automatic calibration procedure that delivers not just one but a family of parameter sets that are optimal with regard to a multi-objective target. The idea behind caRamel is to rely on stochastic rules while also allowing more “local” mechanisms, such as the extrapolation along vectors in the parameter space. The caRamel algorithm is a hybrid of the multi-objective evolutionary annealing simplex (MEAS) method and the non-dominated sorting genetic algorithm II (ε-NSGA-II). It was initially developed for calibrating hydrological models but can be used for any environmental model. The caRamel algorithm is well adapted to complex modelling. The comparison with other optimizers in hydrological case studies (i.e. NSGA-II and MEAS) confirms the quality of the algorithm. An R package, caRamel, has been designed to easily implement this multi-objective algorithm optimizer in the R environment.

A Multi-Criteria Approach to Rank the Municipalities of the States of Mexico by its Marginalization Level: The Case of Jalisco

2017 ◽  
Vol 16 (02) ◽  
pp. 473-513 ◽  
Author(s):  
Juan Carlos Leyva Lopez ◽  
Jesus Jaime Solano Noriega ◽  
Diego Alonso Gastelum Chavira
Keyword(s):  
Fuzzy Theory ◽  
Optimization Methods ◽  
Business Leaders ◽  
Multi Objective Optimization ◽  
Nsga Ii ◽  
Demographic Situation ◽  
Multi Objective ◽  
Mexican Government ◽  
Nondominated Sorting

Marginalization studies of a population are tools that enable the Mexican government to understand and compare the socio-demographic situation of different regions of the country. The goal is to implement effectively various programs of social or economic development whose aims are to fight against the population’s lag, which has affected the quality of life of Mexican citizens. In this paper, a multi-criteria approach for ranking the municipalities of the states of Mexico by their levels of marginalization is proposed, and the case of Jalisco, Mexico, is presented. The approach uses the ELECTRE III method to construct a medium-sized valued outranking relation and then employs a new multi-objective evolutionary algorithm (MOEA) based on the nondominated sorting genetic algorithm (NSGA) II to exploit the relation to obtain a recommendation. The results of this application can be useful for policymakers, planners, academics, investors, and business leaders. This study also contributes to an important, yet relatively new, body of application-based literature that investigates multi-criteria approaches to decision-making that use fuzzy theory and evolutionary multi-objective optimization methods. A comparison of the ranking obtained with the proposed methodology and the stratification created by the National Population Council of Mexico shows that the methodology presented is consistent and yields reliable results for this problem.

Applying Evolutionary Many-Objective Optimization Algorithms to the Quality-Driven Web Service Composition Problem

2016 ◽  
pp. 170-194
Author(s):  
Arion de Campos Jr. ◽  
Aurora T. R. Pozo ◽  
Silvia R. Vergilio
Keyword(s):  
Web Services ◽  
Web Service ◽  
Service Composition ◽  
Optimization Algorithms ◽  
Web Service Composition ◽  
Nsga Ii ◽  
Preference Relations ◽  
Multi Objective ◽  
Composition Problem

The Web service composition refers to the aggregation of Web services to meet customers' needs in the construction of complex applications. The selection among a large number of Web services that provide the desired functionalities for the composition is generally driven by QoS (Quality of Service) attributes, and formulated as a constrained multi-objective optimization problem. However, many equally important QoS attributes exist and in this situation the performance of the multi-objective algorithms can be degraded. To deal properly with this problem we investigate in this chapter a solution based in many-objective optimization algorithms. We conduct an empirical analysis to measure the performance of the proposed solution with the following preference relations: Controlling the Dominance Area of Solutions, Maximum Ranking and Average Ranking. These preference relations are implemented with NSGA-II using five objectives. A set of performance measures is used to investigate how these techniques affect convergence and diversity of the search in the WSC context.

scholarly journals A Scatter Search Approach for Multiobjective Selective Disassembly Sequence Problem

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Xiwang Guo ◽  
Shixin Liu
Keyword(s):  
Multiobjective Optimization ◽  
Scatter Search ◽  
Nsga Ii ◽  
Disassembly Sequence ◽  
Selective Disassembly ◽  
Local Search Strategy ◽  
Search Approach ◽  
Nondominated Sorting ◽  
Disassembly Time

Disassembly sequence has received much attention in recent years. This work proposes a multiobjective optimization of model for selective disassembly sequences and maximizing disassembly profit and minimizing disassembly time. An improved scatter search (ISS) is adapted to solve proposed multiobjective optimization model, which embodies diversification generation of initial solutions, crossover combination operator, the local search strategy to improve the quality of new solutions, and reference set update method. To analyze the effect on the performance of ISS, simulation experiments are conducted on different products. The validity of ISS is verified by comparing the optimization effects of ISS and nondominated sorting genetic algorithm (NSGA-II).

The Multi-Objective Optimization Design of a Forklift Steering Mechanism

2014 ◽  
Vol 1049-1050 ◽  
pp. 884-887
Author(s):  
Qin Man Fan ◽  
Yong Hai Wu
Keyword(s):  
Hydraulic System ◽  
Optimization Design ◽  
Multi Objective Optimization ◽  
Nsga Ii ◽  
Multi Objective ◽  
Oil Pump ◽  
System Pressure ◽  
Steering Mechanism ◽  
Steering Torque

The design and quality of steering mechanism is directly related to forklift traction, mobility, steering stability and safe operation. A multi-objective optimization model of the forklift steering mechanism is established in this paper. The objective function is minimum oil cylinder stroke difference and the minimum power oil pump. Steering torque, geometrical angles, geometry size and the hydraulic system pressure are used as constraint conditions. We use non dominated sorting genetic algorithm (NSGA II) based on the Pareto optimal concept to optimize and calculate model and get the optimal design of steering mechanism.

scholarly journals Balance of Cost, Time, and Quality Related to Construction Projects Regarding the Reinforced Concrete of Underground Structures using a Meta-Heuristic Algorithm

2017 ◽  
Vol 63 (4) ◽  
pp. 103-121 ◽  
Author(s):  
S. A. Hosseini ◽  
A. Akbarpour ◽  
H. Ahmadi ◽  
B. Aminnejad
Keyword(s):  
Reinforced Concrete ◽  
Construction Projects ◽  
Minimum Cost ◽  
Business Environment ◽  
Underground Structures ◽  
Nsga Ii ◽  
Multi Objective ◽  
Objective Model ◽  
Best Execution

AbstractUnderground spaces having features such as stability, resistance, and being undetected can play a key role in reducing vulnerability by relocating infrastructures and manpower. In recent years, the competitive business environment and limited resources have mostly focused on the importance of project management in order to achieve its objectives. In this research, in order to find the best balance among cost, time, and quality related to construction projects using reinforced concrete in underground structures, a multi-objective mathematical model is proposed. Several executive approaches have been considered for project activities and these approaches are analyzed via several factors. It is assumed that cost, time, and quality of activities in every defined approach can vary between compact and normal values, and the goal is to find the best execution for activities, achieving minimum cost and the maximum quality for the project. To solve the proposed multi-objective model, the genetic algorithm NSGA-II is used.

Multi-objective Differential Evolution for Dynamic Economic Emission Dispatch

2014 ◽  
Vol 15 (2) ◽  
pp. 141-150 ◽  
Author(s):  
M. Basu
Keyword(s):  
Differential Evolution ◽  
Test System ◽  
Nsga Ii ◽  
Multi Objective ◽  
Optimization Task ◽  
Conflicting Objectives ◽  
Sample Test ◽  
Emission Dispatch ◽  
Nondominated Sorting ◽  
Economic Emission Dispatch

Abstract Dynamic economic emission dispatch is an important optimization task in fossil fuel–based power plant operation for allocating generation among the committed units with predicted load demands over a certain period of time such that fuel cost and emission level are optimized simultaneously. It is a highly constrained dynamic multi-objective optimization problem involving conflicting objectives. This paper proposes multi-objective differential evolution for dynamic economic emission dispatch problem. Numerical results for a sample test system have been presented to demonstrate the performance of the proposed algorithm. The results obtained from the proposed algorithm are compared with those obtained from nondominated sorting genetic algorithm-II (NSGA-II).

Multi-Objective Optimization for Parameters of Energy Management Strategy of HEV Based on Improved NSGA-II

2010 ◽  
Vol 29-32 ◽  
pp. 912-917
Author(s):  
Fei Hu ◽  
Zhi Guo Zhao
Keyword(s):  
Energy Management ◽  
Fuel Economy ◽  
Management Strategy ◽  
Hybrid Electric Vehicle ◽  
Pareto Optimum ◽  
Multi Objective Optimization ◽  
Energy Management Strategy ◽  
Nsga Ii ◽  
Multi Objective ◽  
Nondominated Sorting

Hybrid Electric Vehicle (HEV) provides fairly high fuel economy with lower emissions compared to conventional vehicles. To enhance HEV performance in terms of fuel economy and emissions, subject to the satisfaction of driving performance, multi-objective optimization for parameters of energy management strategy is inevitable. Considering the defect of the method which transfers multi-objective optimization problem into that of single-objective and the shortage of the Pareto-optimum based nondominated sorting genetic algorithm II (NSGA-II), the NSGA-II has been improved and then applied to the optimization in this paper. The simulation results show that each run of the algorithm can produce many Pareto-optimal solutions and the satisfactory solution can be selected by decision-maker according to the requirement. The results also demonstrate the effectiveness of the approach.

Fuzzy multi-objective location and routing problem

2020 ◽  
Vol 39 (3) ◽  
pp. 3259-3273
Author(s):  
Nasser Shahsavari-Pour ◽  
Najmeh Bahram-Pour ◽  
Mojde Kazemi
Keyword(s):  
Firefly Algorithm ◽  
High Reliability ◽  
Research Area ◽  
Nsga Ii ◽  
Location Routing Problem ◽  
Routing Problem ◽  
Location Allocation ◽  
Multi Objective ◽  
Location Routing ◽  
The Cost

The location-routing problem is a research area that simultaneously solves location-allocation and vehicle routing issues. It is critical to delivering emergency goods to customers with high reliability. In this paper, reliability in location and routing problems was considered as the probability of failure in depots, vehicles, and routs. The problem has two objectives, minimizing the cost and maximizing the reliability, the latter expressed by minimizing the expected cost of failure. First, a mathematical model of the problem was presented and due to its NP-hard nature, it was solved by a meta-heuristic approach using a NSGA-II algorithm and a discrete multi-objective firefly algorithm. The efficiency of these algorithms was studied through a complete set of examples and it was found that the multi-objective discrete firefly algorithm has a better Diversification Metric (DM) index; the Mean Ideal Distance (MID) and Spacing Metric (SM) indexes are only suitable for small to medium problems, losing their effectiveness for big problems.

Sign in / Sign up

Export Citation Format

Share Document