scholarly journals Surrogate assisted interactive multiobjective optimization in energy system design of buildings

2021 ◽  
Author(s):  
Pouya Aghaei Pour ◽  
Tobias Rodemann ◽  
Jussi Hakanen ◽  
Kaisa Miettinen
Keyword(s):  
Decision Maker ◽  
Management Strategy ◽  
Computation Time ◽  
Energy System ◽  
Surrogate Models ◽  
Model Management ◽  
Interactive Methods ◽  
Objective Functions ◽  
Interactive Method ◽  
Computationally Expensive

AbstractIn this paper, we develop a novel evolutionary interactive method called interactive K-RVEA, which is suitable for computationally expensive problems. We use surrogate models to replace the original expensive objective functions to reduce the computation time. Typically, in interactive methods, a decision maker provides some preferences iteratively and the optimization algorithm narrows the search according to those preferences. However, working with surrogate models will introduce some inaccuracy to the preferences, and therefore, it would be desirable that the decision maker can work with the solutions that are evaluated with the original objective functions. Therefore, we propose a novel model management strategy to incorporate the decision maker’s preferences to select some of the solutions for both updating the surrogate models (to improve their accuracy) and to show them to the decision maker. Moreover, we solve a simulation-based computationally expensive optimization problem by finding an optimal configuration for an energy system of a heterogeneous business building complex. We demonstrate how a decision maker can interact with the method and how the most preferred solution is chosen. Finally, we compare our method with another interactive method, which does not have any model management strategy, and shows how our model management strategy can help the algorithm to follow the decision maker’s preferences.

scholarly journals A Visualization Technique for Accessing Solution Pool in Interactive Methods of Multiobjective Optimization

2015 ◽  
Vol 10 (4) ◽  
pp. 508 ◽  
Author(s):  
Ernestas Filatovas ◽  
Dmitry Podkopaev ◽  
Olga Kurasova
Keyword(s):  
Multiobjective Optimization ◽  
Dimensionality Reduction ◽  
Decision Maker ◽  
Optimization Problem ◽  
Interactive Methods ◽  
Optimal Solutions ◽  
Objective Functions ◽  
Visualization Technique ◽  
Preference Information ◽  
Optimal Set

<pre>Interactive methods of <span>multiobjective</span> optimization repetitively derive <span>Pareto</span> optimal solutions based on decision maker's preference information and present the obtained solutions for his/her consideration. Some interactive methods save the obtained solutions into a solution pool and, at each iteration, allow the decision maker considering any of solutions obtained earlier. This feature contributes to the flexibility of exploring the <span>Pareto</span> optimal set and learning about the optimization problem. However, in the case of many objective functions, the accumulation of derived solutions makes accessing the solution pool cognitively difficult for the decision maker. We propose to enhance interactive methods with visualization of the set of solution outcomes using dimensionality reduction and interactive mechanisms for exploration of the solution pool. We describe a proposed visualization technique and demonstrate its usage with an example problem solved using the interactive method NIMBUS.</pre>

scholarly journals Assessing the Performance of Interactive Multiobjective Optimization Methods

2021 ◽  
Vol 54 (4) ◽  
pp. 1-27
Author(s):  
Bekir Afsar ◽  
Kaisa Miettinen ◽  
Francisco Ruiz
Keyword(s):  
Multiobjective Optimization ◽  
Decision Maker ◽  
Optimization Problems ◽  
Optimization Methods ◽  
Interactive Methods ◽  
Value Functions ◽  
Technical Aspects ◽  
Preference Information ◽  
Multiobjective Optimization Problems ◽  
Human Decision

Interactive methods are useful decision-making tools for multiobjective optimization problems, because they allow a decision-maker to provide her/his preference information iteratively in a comfortable way at the same time as (s)he learns about all different aspects of the problem. A wide variety of interactive methods is nowadays available, and they differ from each other in both technical aspects and type of preference information employed. Therefore, assessing the performance of interactive methods can help users to choose the most appropriate one for a given problem. This is a challenging task, which has been tackled from different perspectives in the published literature. We present a bibliographic survey of papers where interactive multiobjective optimization methods have been assessed (either individually or compared to other methods). Besides other features, we collect information about the type of decision-maker involved (utility or value functions, artificial or human decision-maker), the type of preference information provided, and aspects of interactive methods that were somehow measured. Based on the survey and on our own experiences, we identify a series of desirable properties of interactive methods that we believe should be assessed.

scholarly journals Effect of the Foresight Horizon on Computation Time and Results Using a Regional Energy Systems Optimization Model

Energies ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 495
Author(s):  
Jessica Thomsen ◽  
Noha Saad Hussein ◽  
Arnold Dolderer ◽  
Christoph Kost
Keyword(s):  
Computation Time ◽  
Energy Systems ◽  
Energy System ◽  
Variable Cost ◽  
Optimization Approach ◽  
Or Efficiency ◽  
Electricity Grid ◽  
Regional Energy ◽  
Long Run ◽  
Regional Energy Systems

Due to the high complexity of detailed sector-coupling models, a perfect foresight optimization approach reaches complexity levels that either requires a reduction of covered time-steps or very long run-times. To mitigate these issues, a myopic approach with limited foresight can be used. This paper examines the influence of the foresight horizon on local energy systems using the model DISTRICT. DISTRICT is characterized by its intersectoral approach to a regionally bound energy system with a connection to the superior electricity grid level. It is shown that with the advantage of a significantly reduced run-time, a limited foresight yields fairly similar results when the input parameters show a stable development. With unexpected, shock-like events, limited foresight shows more realistic results since it cannot foresee the sudden parameter changes. In general, the limited foresight approach tends to invest into generation technologies with low variable cost and avoids investing into demand reduction or efficiency with high upfront costs as it cannot compute the benefits over the time span necessary for full cost recovery. These aspects should be considered when choosing the foresight horizon.

scholarly journals Multiple infill criterion-assisted hybrid evolutionary optimization for medium-dimensional computationally expensive problems

2021 ◽  
Author(s):  
Shufen Qin ◽  
Chan Li ◽  
Chaoli Sun ◽  
Guochen Zhang ◽  
Xiaobo Li
Keyword(s):  
Evolutionary Algorithms ◽  
Optimization Problems ◽  
Optimal Solution ◽  
Global Search ◽  
Model Management ◽  
The Other ◽  
Local Searches ◽  
Fitness Value ◽  
Expensive Problems ◽  
Computationally Expensive

AbstractSurrogate-assisted evolutionary algorithms have been paid more and more attention to solve computationally expensive problems. However, model management still plays a significant importance in searching for the optimal solution. In this paper, a new method is proposed to measure the approximation uncertainty, in which the differences between the solution and its neighbour samples in the decision space, and the ruggedness of the objective space in its neighborhood are both considered. The proposed approximation uncertainty will be utilized in the surrogate-assisted global search to find a solution for exact objective evaluation to improve the exploration capability of the global search. On the other hand, the approximated fitness value is adopted as the infill criterion for the surrogate-assisted local search, which is utilized to improve the exploitation capability to find a solution close to the real optimal solution as much as possible. The surrogate-assisted global and local searches are conducted in sequence at each generation to balance the exploration and exploitation capabilities of the method. The performance of the proposed method is evaluated on seven benchmark problems with 10, 20, 30 and 50 dimensions, and one real-world application with 30 and 50 dimensions. The experimental results show that the proposed method is efficient for solving the low- and medium-dimensional expensive optimization problems by compared to the other six state-of-the-art surrogate-assisted evolutionary algorithms.

scholarly journals Comparing interactive evolutionary multiobjective optimization methods with an artificial decision maker

2021 ◽  
Author(s):  
Bekir Afsar ◽  
Ana B. Ruiz ◽  
Kaisa Miettinen
Keyword(s):  
Multiobjective Optimization ◽  
Decision Maker ◽  
Optimization Problems ◽  
Optimization Methods ◽  
Decision Makers ◽  
Interactive Methods ◽  
Preference Information ◽  
Evolutionary Methods ◽  
Solution Processes ◽  
Trade Offs

AbstractSolving multiobjective optimization problems with interactive methods enables a decision maker with domain expertise to direct the search for the most preferred trade-offs with preference information and learn about the problem. There are different interactive methods, and it is important to compare them and find the best-suited one for solving the problem in question. Comparisons with real decision makers are expensive, and artificial decision makers (ADMs) have been proposed to simulate humans in basic testing before involving real decision makers. Existing ADMs only consider one type of preference information. In this paper, we propose ADM-II, which is tailored to assess several interactive evolutionary methods and is able to handle different types of preference information. We consider two phases of interactive solution processes, i.e., learning and decision phases separately, so that the proposed ADM-II generates preference information in different ways in each of them to reflect the nature of the phases. We demonstrate how ADM-II can be applied with different methods and problems. We also propose an indicator to assess and compare the performance of interactive evolutionary methods.

SQUEAK AND RATTLE PREVENTION BY GEOMETRIC VARIATION MANAGEMENT USING A TWO-STAGE EVOLUTIONARY OPTIMISATION APPROACH

2021 ◽  
pp. 1-40
Author(s):  
Mohsen Bayani ◽  
Casper Wickman ◽  
Lars Lindkvist ◽  
Rikard Söderberg
Keyword(s):  
Lower Order ◽  
Uniform Space ◽  
Order Effect ◽  
Objective Functions ◽  
Two Stage ◽  
Second Stage ◽  
Evolutionary Optimisation ◽  
Space Filler ◽  
Computationally Expensive ◽  
Geometric Variation

Abstract Squeak and rattle are annoying sounds that are often regarded as the failure indicators by car users. Geometric variation is a key contributor to the generation of squeak and rattle sounds. Optimisation of the connection configuration in assemblies can be a provision to minimise this risk. However, the optimisation process for large assemblies can be computationally expensive. The focus of this work is to propose a two-stage evolutionary optimisation scheme to find the fittest connection configurations that minimise the risk for squeak and rattle. This was done by defining the objective functions as the measured variation and deviation in the rattle direction and the squeak plane. In the first stage, the location of the fasteners primarily contributing to the rattle direction measures are identified. In the second stage, fasteners primarily contributing to the squeak plane measures are added to the fittest configuration from phase one. It was assumed that the fasteners from the squeak group plane have a lower-order effect on the rattle direction measures, compared to the fasteners from the rattle direction group. This assumption was falsified for a set of simplified geometries. Also, a new uniform space filler algorithm was introduced to efficiently generate an inclusive and feasible starting population for the optimisation process by incorporating the problem constraints in the algorithm. For two industrial cases, it was shown that by using the proposed two-stage optimisation scheme the variation and deviation measures in critical interfaces for squeak and rattle improved compared to the baseline results.

scholarly journals Modularization as a system life cycle management strategy: Drivers, barriers, mechanisms and impacts

2019 ◽  
Vol 11 ◽  
pp. 184797901882504 ◽  
Author(s):  
Guido JL Micheli ◽  
Paolo Trucco ◽  
Yasmine Sabri ◽  
Mauro Mancini
Keyword(s):  
Decision Making ◽  
Life Cycle ◽  
Decision Maker ◽  
Paradigm Shift ◽  
Management Strategy ◽  
Strategic Choice ◽  
Life Cycle Management ◽  
Design Option ◽  
Comprehensive View ◽  
System Life

This literature-grounded research contributes to a deeper understanding of modularization as a system life cycle management strategy, by providing a comprehensive view of its key barriers, drivers, possible mechanisms of implementation and impact. This comprehensive view, arranged into a decision-making–driven ontology, enables a decision maker to systematically identify modularization implementation opportunities in different industrial and service domains. The proposed ontology transforms modularization into a fully operationalizable strategy and contributes to a paradigm shift in the understanding of modularization, from a pure design option (i.e. modularity) to a fully strategic choice that, by nature, impacts on many of the system’s life cycle phases and involves a number of stakeholders.

scholarly journals A Multi-objective Scheduling Optimization Model for Hybrid Energy System Connected with Wind-Photovoltaic-Conventional Gas Turbines, CHP Considering Heating Storage Mechanism

Energies ◽  
2019 ◽  
Vol 12 (3) ◽  
pp. 425 ◽  
Author(s):  
Yao Wang ◽  
Yan Lu ◽  
Liwei Ju ◽  
Ting Wang ◽  
Qingkun Tan ◽  
...  
Keyword(s):  
Demand Response ◽  
Gas Turbines ◽  
Energy System ◽  
Objective Functions ◽  
Distributed Energy ◽  
Operating Income ◽  
Hybrid Energy ◽  
Multi Objective ◽  
Load Demand ◽  
Load Fluctuation

In order to meet the user’s electricity demand and make full use of distributed energy, a hybrid energy system (HES) was proposed and designed, including wind turbines (WTs), photovoltaic (PV) power generation, conventional gas turbines (CGTs), incentive-based demand response (IBDR), combined heat and power (CHP) and regenerative electric (RE) boilers. Then, the collaborative operation problem of HES is discussed. First, the paper describes the HES’ basic structure and presents the output model of power sources and heating sources. Next, the maximum operating income and minimum load fluctuation are taken as the objective function, and a multi-objective model of HES scheduling is proposed. Then an algorithm for solving the model is proposed that comprises two steps: processing the objective functions and constraints into linear equations and determining the optimal weight of the objective functions. The selected simulation system is a microgrid located on an eastern island of China to comparatively analyze the influence of RE-heating storage (RE-HS) and price-based demand response (PBDR) on HES operation in relation to four cases. By analyzing the results, the following three conclusions are drawn: (1) HES can comprehensively utilize a variety of distributed energy sources to meet load demand. In particular, RE technology can convert the abandoned energy of WT and PV into heat during the valley load time, to meet the load demand combined with CHP; (2) The proposed multi-objective scheduling model of HES operation not only considers the maximum operating income but also considers the minimum load fluctuation, thus achieving the optimal balancing operation; (3) RE-HS and PBDR have a synergistic optimization effect, and when RE-HS and PBDR are both applied, an HES can achieve optimal operation results. Overall, the proposed decision method is highly effective and applicable, and decision makers could utilize this method to design an optimal HES operation strategy according to their own actual conditions.

Multilevel Thresholding for Image Segmentation Based on Cellular Metaheuristics

2018 ◽  
Vol 9 (4) ◽  
pp. 1-32 ◽  
Author(s):  
Mohamed Abdou Bouteldja ◽  
Mohamed Baadeche ◽  
Mohamed Batouche
Keyword(s):  
Genetic Algorithm ◽  
Image Segmentation ◽  
Multilevel Thresholding ◽  
Objective Functions ◽  
Swarm Optimization ◽  
Cellular Genetic Algorithm ◽  
Kapur’S Entropy ◽  
Computationally Expensive ◽  
Segmentation Problem ◽  
Nature Inspired Metaheuristics

This article describes how multilevel thresholding image segmentation is a process used to partition an image into well separated regions. It has various applications such as object recognition, edge detection, and particle counting, etc. However, it is computationally expensive and time consuming. To alleviate these limitations, nature inspired metaheuristics are widely used to reduce the computational complexity of such problem. In this article, three cellular metaheuristics namely cellular genetic algorithm (CGA), cellular particle swarm optimization (CPSO) and cellular differential evolution (CDE) are adapted to solve the multilevel thresholding image segmentation problem. Experiments are conducted on different test images to assess the performance of the cellular algorithms in terms of efficiency, quality and stability based on the between-class variance and Kapur's entropy as objective functions. The experimental results have shown that the proposed cellular algorithms compete with and even outperform existing methods for multilevel thresholding image segmentation.

Sign in / Sign up

Export Citation Format

Share Document