Hybrid Multi-objective Optimization Approach in Water Flooding

2021 ◽  
pp. 1-22
Author(s):  
Mohammed Al-Aghbari ◽  
Ashish M. Gujarathi ◽  
Majid Al-Wadhahi ◽  
Nirupam Chakraborti
Keyword(s):  
Neural Network ◽  
Water Injection ◽  
Optimal Solution ◽  
Pareto Optimal Solution ◽  
Data Driven ◽  
Water Flooding ◽  
Real Field ◽  
Pareto Optimal ◽  
Nsga Ii ◽  
Evolutionary Neural Network

Abstract Non-dominated Sorting Genetic Algorithm, second version (NSGA-II) is used as a stochastic optimization technique successfully in different engineering applications. In this study, a data-driven optimization strategy based upon evolutionary neural network algorithm (EvoNN) is developed for providing input into NSGA-II optimization. Evolutionary neural-network data-driven model is built and trained using initial solutions generated by NSGA-II optimization coupled with the reservoir simulation model. Evolutionary optimization incorporated in the EvoNN strategy is applied in the trained data-driven model to generate the Pareto optimal solution, which is then used as a guiding input into NSGA-II optimization. The described method is applied in two case studies (i.e. Brugge field model & water injection pattern model). The Pareto optimal solutions obtained with data-driven model guided NSGA-II in both models show improvement in convergence and diversity of the solution. The convergence to the Pareto optimal solution has improved by 9% for case-1 (i.e. Brugge field) and by 43% for case-2 (i.e. water injection pattern model). In addition, the Pareto optimal solution obtained by the proposed hybridization has shown improvement in the water oil ratio (WOR) up to 6% in the Brugge field and up to 97% in the water injection pattern model. This improvement can lead to wide applications in using evolutionary optimizations in real field simulation models at acceptable computation time.

scholarly journals Sea Surface Current Velocity Retrieving from TanDAM-X Satellite Data

2021 ◽  
pp. 1-10
Author(s):  
M. Marghany ◽  
J.L. Genderen
Keyword(s):  
Neural Network ◽  
Coastal Waters ◽  
Optimal Solution ◽  
Surface Current ◽  
Hopfield Neural Network ◽  
Pareto Optimal Solution ◽  
Sea Surface ◽  
Pareto Optimal ◽  
Network Algorithm ◽  
Neural Network Algorithm

This is the first investigation for the use of TanDEM-X data, satellite for the Malaysian coastal waters. This aims at utilizing an optimization of the Hopfield neural network to retrieve variation of sea surface current along Malaysian coastal waters. In doing so, a multi-objective evolutionary algorithm based on the Pareto front is used to minimize the error produced due to non-linearity between TanDEM-X data and sea surface movements. This work aimed at retrieving sea surface current from TanDEM-X data along the coastal waters of Malaysia. Two approaches have been implemented, the Hopfield neural network algorithm and Pareto optimal solution. The study shows that the Pareto optimal solution has a higher performance than the Hopfield neural network algorithm with a lower RMSE of ±0.009. Furthermore, a Pareto optimal solution can determine the sea surface current pattern variation along the coastal water from TanDEM-X data. In conclusion, TanDEM-X data shows an excellent promise for retrieving sea surface currents.

Simulation Optimization of Multi-Objective Flexible Job Shop Scheduling

2013 ◽  
Vol 365-366 ◽  
pp. 602-605
Author(s):  
Gui Cong Wang ◽  
Chuan Peng Li ◽  
Huan Yong Cui
Keyword(s):  
Simulation Model ◽  
Job Shop ◽  
Simulation Optimization ◽  
Optimal Solution ◽  
Pareto Optimal Solution ◽  
Pareto Optimal ◽  
Flexible Job Shop ◽  
Final Solution ◽  
Nsga Ii ◽  
Multi Objective

Current scheduling approach for multiple objective flexible job shop problem (FJSP) cannot construct a precise scheduling model and obtain a satisfactory scheduling result at the same time. To deal with this problem, a simulation optimization scheduling approach was presented which was composed of two basic modules: the Fast non-dominated Sorting Genetic Algorithm (NSGA-II) module and Witness simulation module. Firstly, a multi-objective mathematical model was found for FJSP and NSGA-II was applied to solve. Then, a set of Pareto optimal solution was obtained by NSGA-II module. In order to select the final solution from the Pareto optimal solution for FJSP, the simulation model was set up by Witness, every Pareto solution was as input for simulation model. Finally, the final solution can be selected according other performance indicators.

Multi-Objective Optimization Algorithm Design and Implementation of Mobile Base Station Site Selection

2010 ◽  
Vol 29-32 ◽  
pp. 2496-2502
Author(s):  
Min Wang ◽  
Jun Tang
Keyword(s):  
Site Selection ◽  
Engineering Application ◽  
Optimal Solution ◽  
Base Station ◽  
Pareto Optimal Solution ◽  
Antibody Concentration ◽  
Pareto Optimal ◽  
Memory Cells ◽  
Multi Objective Optimization ◽  
Multi Objective

The number of base station location impact the network quality of service. A new method is proposed based on immune genetic algorithm for site selection. The mathematical model of multi-objective optimization problem for base station selection and the realization of the process were given. The use of antibody concentration selection ensures the diversity of the antibody and avoiding the premature convergence, and the use of memory cells to store Pareto optimal solution of each generation. A exclusion algorithm of neighboring memory cells on the updating and deleting to ensure that the Pareto optimal solution set of the distribution. The experiments results show that the algorithm can effectively find a number of possible base station and provide a solution for the practical engineering application.

Optimized parallel architecture of evolutionary neural network for mass spectrometry data processing

2017 ◽  
Vol 08 (01) ◽  
pp. 1750016 ◽  
Author(s):  
Amin Jarrah ◽  
Bashar Haddad ◽  
Mohammad A. Al-Jarrah ◽  
Muhammad Bassam Obeidat
Keyword(s):  
Neural Network ◽  
Mass Spectrometry ◽  
Parallel Processing ◽  
Optimal Solution ◽  
Optimization Techniques ◽  
Function Optimization ◽  
Mass Spectrometry Data ◽  
Adaptive Optimization ◽  
Graphic Processing Units ◽  
Evolutionary Neural Network

Evolutionary neural network (ENN) shows high performance in function optimization and in finding approximately global optima from searching large and complex spaces. It is one of the most efficient and adaptive optimization techniques used widely to provide candidate solutions that lead to the fitness of the problem. ENN has the extraordinary ability to search the global and learning the approximate optimal solution regardless of the gradient information of the error functions. However, ENN requires high computation and processing which requires parallel processing platforms such as field programmable gate arrays (FPGAs) and graphic processing units (GPUs) to achieve a good performance. This work involves different new implementations of ENN by exploring and adopting different techniques and opportunities for parallel processing. Different versions of ENN algorithm have also been implemented and parallelized on FPGAs platform for low latency by exploiting the parallelism and pipelining approaches. Real data form mass spectrometry data (MSD) application was tested to examine and verify our implementations. This is a very important and extensive computation application which needs to search and find the optimal features (peaks) in MSD in order to distinguish cancer patients from control patients. ENN algorithm is also implemented and parallelized on single core and GPU platforms for comparison purposes. The computation time of our optimized algorithm on FPGA and GPU has been improved by a factor of 6.75 and 6, respectively.

Sign in / Sign up

Export Citation Format

Share Document