Machine Learning Enabled Design Automation and Multi-Objective Optimization for Electric Transportation Power Systems

2021 ◽  
pp. 1-1
Author(s):  
Derek Jackson ◽  
Syrine Belakaria ◽  
Yue Cao ◽  
Janardhan Rao Doppa ◽  
Xiaonan Lu
Keyword(s):  
Machine Learning ◽  
Power Systems ◽  
Design Automation ◽  
Multi Objective Optimization ◽  
Multi Objective

scholarly journals Multi-Objective Optimization of Autonomous Microgrids with Reliability Consideration

Energies ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4466
Author(s):  
Maël Riou ◽  
Florian Dupriez-Robin ◽  
Dominique Grondin ◽  
Christophe Le Loup ◽  
Michel Benne ◽  
...  
Keyword(s):  
Power Systems ◽  
Rural Areas ◽  
Energy System ◽  
Design Stage ◽  
Multi Objective Optimization ◽  
Renewable Energy Resources ◽  
Nsga Ii ◽  
Renewable Integration ◽  
Multi Objective ◽  
Trade Offs

Microgrids operating on renewable energy resources have potential for powering rural areas located far from existing grid infrastructures. These small power systems typically host a hybrid energy system of diverse architecture and size. An effective integration of renewable energies resources requires careful design. Sizing methodologies often lack the consideration for reliability and this aspect is limited to power adequacy. There exists an inherent trade-off between renewable integration, cost, and reliability. To bridge this gap, a sizing methodology has been developed to perform multi-objective optimization, considering the three design objectives mentioned above. This method is based on the non-dominated sorting genetic algorithm (NSGA-II) that returns the set of optimal solutions under all objectives. This method aims to identify the trade-offs between renewable integration, reliability, and cost allowing to choose the adequate architecture and sizing accordingly. As a case study, we consider an autonomous microgrid, currently being installed in a rural area in Mali. The results show that increasing system reliability can be done at the least cost if carried out in the initial design stage.

scholarly journals Multi-Objective Bee Swarm Optimization Algorithm with Minimum Manhattan Distance for Passive Power Filter Optimization Problems

Mathematics ◽  
2022 ◽  
Vol 10 (1) ◽  
pp. 133
Author(s):  
Nien-Che Yang ◽  
Danish Mehmood
Keyword(s):  
Power Systems ◽  
Optimization Problems ◽  
Filter Design ◽  
Manhattan Distance ◽  
Multi Objective Optimization ◽  
Optimal Method ◽  
Pareto Solution ◽  
Swarm Optimization ◽  
Multi Objective ◽  
Passive Power

Harmonic distortion in power systems is a significant problem, and it is thus necessary to mitigate critical harmonics. This study proposes an optimal method for designing passive power filters (PPFs) to suppress these harmonics. The design of a PPF involves multi-objective optimization. A multi-objective bee swarm optimization (MOBSO) with Pareto optimality is implemented, and an external archive is used to store the non-dominated solutions obtained. The minimum Manhattan distance strategy was used to select the most balanced solution in the Pareto solution set. A series of case studies are presented to demonstrate the efficiency and superiority of the proposed method. Therefore, the proposed method has a very promising future not only in filter design but also in solving other multi-objective optimization problems.

Synthesis of LC-Oscillators Using Rival Multi-Objective Multi-Constraint Optimization Kernels

2015 ◽  
pp. 1-27 ◽  
Author(s):  
Ricardo Póvoa ◽  
Ricardo Lourenço ◽  
Nuno Lourenço ◽  
António Canelas ◽  
Ricardo Martins ◽  
...  
Keyword(s):  
Design Automation ◽  
State Of The Art ◽  
Voltage Controlled Oscillator ◽  
Multi Objective Optimization ◽  
Nsga Ii ◽  
Multi Objective ◽  
Lc Oscillator ◽  
Lc Oscillators ◽  
Statistical Results ◽  
Multiple Synthesis

This chapter presents a state-of-the-art multi-objective/multi-constraint design automation approach applied to the design of an LC-Voltage Controlled Oscillator and an LC-Oscillator for a 130 nm technology node and leading to sets of design solutions showing figures-of-merit around -192 dBc/Hz and -186 dBc/Hz, respectively. The proposed approach, implemented in AIDA-C, guarantees accuracy by using commercial circuit simulators (HSPICE® and ELDO®) to evaluate the performance of the tentative circuit solutions, where the number of time-consuming circuit simulations is efficiently pruned by the optimization kernel. Three multi-objective optimization algorithms, the NSGA-II, the MOPSO, and the MOSA, are experimented with in the synthesis of the quoted oscillators and compared in terms of performance using statistical results obtained from multiple synthesis runs for each one of the oscillators. The performance of the optimized oscillators is then compared to other state-of-the-art results, showing the benefits of the presented multi-objective design approach.

scholarly journals Comparison of synchronous and asynchronous parallelization of extreme surrogate-assisted multi-objective evolutionary algorithm

2020 ◽  
Author(s):  
Tomohiro Harada ◽  
Misaki Kaidan ◽  
Ruck Thawonmas
Keyword(s):  
Machine Learning ◽  
Evolutionary Algorithm ◽  
Optimization Problems ◽  
Computing Time ◽  
The Other ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Evaluation Time ◽  
Surrogate Function

Abstract This paper investigates the integration of a surrogate-assisted multi-objective evolutionary algorithm (MOEA) and a parallel computation scheme to reduce the computing time until obtaining the optimal solutions in evolutionary algorithms (EAs). A surrogate-assisted MOEA solves multi-objective optimization problems while estimating the evaluation of solutions with a surrogate function. A surrogate function is produced by a machine learning model. This paper uses an extreme learning surrogate-assisted MOEA/D (ELMOEA/D), which utilizes one of the well-known MOEA algorithms, MOEA/D, and a machine learning technique, extreme learning machine (ELM). A parallelization of MOEA, on the other hand, evaluates solutions in parallel on multiple computing nodes to accelerate the optimization process. We consider a synchronous and an asynchronous parallel MOEA as a master-slave parallelization scheme for ELMOEA/D. We carry out an experiment with multi-objective optimization problems to compare the synchronous parallel ELMOEA/D with the asynchronous parallel ELMOEA/D. In the experiment, we simulate two settings of the evaluation time of solutions. One determines the evaluation time of solutions by the normal distribution with different variances. On the other hand, another evaluation time correlates to the objective function value. We compare the quality of solutions obtained by the parallel ELMOEA/D variants within a particular computing time. The experimental results show that the parallelization of ELMOEA/D significantly reduces the computational time. In addition, the integration of ELMOEA/D with the asynchronous parallelization scheme obtains higher quality of solutions quicker than the synchronous parallel ELMOEA/D.

Sign in / Sign up

Export Citation Format

Share Document