الگوریتم تکاملی چند هدفی مبتنی بر شبکه عصبی برای زمانبندی گردش کار پویا در محاسبات ابری
سال انتشار: 2020 - تعداد صفحات فایل pdf انگلیسی: 16 - تعداد صفحات فایل doc فارسی: 45
زمانبندی گردشکار یک موضوع پژوهشی است که به طور گسترده در محاسبات ابری مورد مطالعه قرار گرفته است و از منابع ابری برای کارهای گردش کار استفاده می¬شود و برای این منظور اهداف مشخص شده در QoS را لحاظ می¬کند. در این مقاله، مسئله زمانبندی گردش کار پویا را به عنوان یک مسئله بهینه سازی چند هدفه پویا (DMOP) مدل می¬کنیم که در آن منبع پویایی سازی بر اساس خرابی منابع و تعداد اهداف است که ممکن است با گذر زمان تغییر کنند. خطاهای نرم افزاری و یا نقص سخت افزاری ممکن است باعث ایجاد پویایی نوع اول شوند. از سوی دیگر مواجهه با سناریوهای زندگی واقعی در محاسبات ابری ممکن است تعداد اهداف را در طی اجرای گردش کار تغییر دهد. در این مطالعه یک الگوریتم تکاملی چند هدفه پویا مبتنی بر پیش بینی را به نام الگوریتم NN-DNSGA-II ارائه می¬دهیم و برای این منظور شبکه عصبی مصنوعی را با الگوریتم NGSA-II ترکیب می¬کنیم. علاوه بر این پنج الگوریتم پویای مبتنی بر غیرپیش بینی از ادبیات موضوعی برای مسئله زمانبندی گردش کار پویا ارائه می¬شوند. راه¬حل¬های زمانبندی با در نظر گرفتن شش هدف یافت می¬شوند: حداقل سازی هزینه ساخت، انرژی و درجه عدم تعادل و حداکثر سازی قابلیت اطمینان و کاربرد. مطالعات تجربی مبتنی بر کاربردهای دنیای واقعی از سیستم مدیریت گردش کار Pegasus نشان می¬دهد که الگوریتم NN-DNSGA-II ما به طور قابل توجهی از الگوریتم¬های جایگزین خود در بیشتر موارد بهتر کار می¬کند با توجه به معیارهایی که برای DMOP با مورد واقعی پارتو بهینه در نظر گرفته می¬شود از جمله تعداد راه¬حل¬های غیرغالب، فاصله¬گذاری Schott و شاخص Hypervolume.
|مقاله ترجمه شده|
Behavior of crossover operators in NSGA-III for large-scale optimization problems
رفتار اپراتورهای متقاطع در NSGA-III برای مسائل بهینه سازی در مقیاس بزرگ-2020
Traditional multi-objective optimization evolutionary algorithms (MOEAs) do not usu- ally meet the requirements for online data processing because of their high compu- tational costs. This drawback has resulted in difficulties in the deployment of MOEAs for multi-objective, large-scale optimization problems. Among different evolutionary algo- rithms, non-dominated sorting genetic algorithm-the third version (NSGA-III) is a fairly new method capable of solving large-scale optimization problems with acceptable com- putational requirements. In this paper, the performance of three crossover operators of the NSGA-III algorithm is benchmarked using a large-scale optimization problem based on human electroencephalogram (EEG) signal processing. The studied operators are simu- lated binary (SBX), uniform crossover (UC), and single point (SI) crossovers. Furthermore, enhanced versions of the NSGA-III algorithm are proposed through introducing the con- cept of Stud and designing several improved crossover operators of SBX, UC, and SI. The performance of the proposed NSGA-III variants is verified on six large-scale optimization problems. Experimental results indicate that the NSGA-III methods with UC and UC-Stud (UCS) outperform the other developed variants.
Keywords: Electroencephalography | Large-scale optimization | Big data optimization | Evolutionary multi-objective optimization | NSGA-III | Crossover operator | Performance analysis
Security-aware multi-objective optimization of distributed reconfigurable embedded systems
بهینه سازی چند هدفه امنیت آگاه سیستم های جاسازی شده قابل تنظیم مجدد توزیع شده-2019
Distributed embedded systems are increasingly prevalent in numerous applications, and with pervasive network access within these systems, security is also a critical design concern. We present a modeling and optimization framework for distributed embedded systems incorporating heterogeneous resources, including single core processor, asymmetric multicore processors, and FPGAs. A dataflow-based modeling framework for streaming applications integrates models for computational latency, cryptographic security levels, communication latency, and power consumption. We utilize a multi-objective genetic optimization algorithm to optimize security subject to constraints for energy consumption and minimum security level. The presented methodology is evaluated using a video-based object detection and tracking application considering several distributed heterogeneous embedded systems architectures.
Keywords: Distributed embedded systems | Security | Co-design modeling | Dynamic optimization | Design space exploration | Penalty functions
A big-data oriented recommendation method based on multi-objective optimization
یک روش توصیه داده های بزرگ گرا برای بهینه سازی چند هدفی-2019
Due to its successful application in recommender systems, collaborative filtering (CF) has become a hot research topic in data mining. For traditional CF-based recommender systems, the accuracy of recommendation results can be guaranteed while the diversity will be lost. An ideal recommender system should be built with both accurate and diverse performance. Faced with accuracy–diversity dilemma, we propose a novel recommendation method based on MapReduce framework. In MapReduce framework, a block computational technique is used to shorten the operational time. And an improved collaborative filtering model is refined with a novel similarity computational process which considers many factors. By translating the procedure of generating personalized recommendation results into a multi-objective optimization problem, the multiple conflicts between accuracy and diversity are well handled. The experimental results demonstrate that our method outperforms other state-of-the-art methods.
Keywords: Recommender systems | Multi-objective optimization | MapReduce | Accuracy | Diversity
Building facade multi-objective optimization for daylight and aesthetical perception
ساختمان بهینه سازی چند هدفه برای نور روز و درک زیبایی شناختی-2019
In recent years, especially in a building envelope, parametric design provides a method of continuous deformation of façade patterns until the architect finds interesting patterns or shapes that satisfy the desired aesthetics. However, these new design methods pose a question regarding the reasoning behind them, and sometimes the aesthetic interest dominates the true function of the envelope system and contrasts it. In opposite, too much engineering in the envelope system creates a problem with the identity of the façade. The purpose of this paper is to propose a method to integrate two different performances, quality and quantity, into one measurable goal. Using an existing buildings facade as a case study, the buildings facade was analyzed to understand the architects logic behind its design. Then the found logic was programmed into the tool that allowed for the morphing of the façade into a different configuration, which can be evaluated by both quality and quantity performance to find the better solution to satisfy both goals. For the purpose of this paper, multi-objective evolutionary algorithms were considered to find solutions. For a quantitative objective, the indoor daylight availability was used as a measurement to allow for the best daylighting performance envelope system. For a qualitative objective, a matrix was developed to find the users design preference and used it to evaluate and find a quantitative performance goal. The proposed method provides building facades that satisfy daylighting performance, and most importantly, it allows users to match their aesthetic sensibilities with the design preference.
Keywords: Multi-objective optimization (MOO) | Expert system | Aesthetical perception | Daylight | Building performance | Parametric design
Combining Principal Component Analysis, Discrete Wavelet Transform and XGBoost to trade in the financial markets
ترکیب تجزیه و تحلیل مؤلفه های اصلی ، تبدیل موجک گسسته و XGBoost برای تجارت در بازارهای مالی-2019
When investing in financial markets it is crucial to determine a trading signal that can provide the in- vestor with the best entry and exit points of the financial market, however this is a difficult task and has become a very popular research topic in the financial area. This paper presents an expert system in the financial area that combines Principal Component Analysis (PCA), Discrete Wavelet Transform (DWT), Extreme Gradient Boosting (XGBoost) and a Multi-Objective Optimization Genetic Algorithm (MOO-GA) in order to achieve high returns with a low level of risk. PCA is used to reduce the dimensionality of the financial input data set and the DWT is used to perform a noise reduction to every feature. The re- sultant data set is then fed to an XGBoost binary classifier that has its hyperparameters optimized by a MOO-GA. The importance of the PCA is analyzed and the results obtained show that it greatly improves the performance of the system. In order to improve even more the results obtained in the system using PCA, the PCA and the DWT are then applied together in one system and the results obtained show that this system is capable of outperforming the Buy and Hold (B&H) strategy in three of the five analyzed financial markets, achieving an average rate of return of 49.26% in the portfolio, while the B&H achieves on average 32.41%.
Keywords: Financial markets | Principal Component Analysis (PCA) | Discrete Wavelet Transform (DWT) | Extreme Gradient Boosting (XGBoost) | Multi-Objective Optimization Genetic | Algorithm (MOO-GA)
Application of multi-objective optimization to blind source separation
استفاده از بهینه سازی چند هدفه برای جداسازی منبع کور-2019
Several problems in signal processing are addressed by expert systems which take into account a set of priors on the sought signals and systems. For instance, blind source separation is often tackled by means of a mono-objective formulation which relies on a separation criterion associated with a given property of the sought signals (sources). However, in many practical situations, there are more than one property to be exploited and, as a consequence, a set of separation criteria may be used to recover the original signals. In this context, this paper addresses the separation problem by means of an approach based on multi-objective optimization. Differently from the existing methods, which provide only one estimate for the original signals, our proposal leads to a set of solutions that can be utilized by the system user to take his/her decision. Results obtained through numerical experiments over a set of biomedical signals highlight the viability of the proposed approach, which provides estimations closer to the mean squared error solutions compared to the ones achieved via a mono-objective formulation. Moreover, since our proposal is quite general, this work also contributes to encourage future researches to develop expert systems that exploit the multi-objective formulation in different source separation problems.
Keywords: Blind source separation | Multi-objective optimization | Evolutionary algorithms
Scheduling workflows with privacy protection constraints for big data applications on cloud
جریان های برنامه ریزی شده با محدودیت های حفاظت از حریم خصوصی برای برنامه های داده بزرگ در ابر-2018
Nowadays, business or scientific processes with massive big data in Cyber-Physical-Social environments are springing up in cloud. Cloud customers’ private information stored in cloud may be easily exposed and lead to serious privacy leakage issues in Cyber-Physical-Social environments. To avoid such issues, cloud customers’ privacy or sensitive data may be restricted to being processed by some specific trusted cloud data centers. Therefore, a new problem is how to schedule workflow with such data privacy protection constraints, while minimizing both execution time and monetary cost for big data applications on cloud. In this paper, we model such problem as a multi-objective optimization problem and propose a Multi Objective Privacy-Aware workflow scheduling algorithm, named MOPA. It can provide cloud customers with a set of Pareto tradeoff solutions. The problem-specific encoding and population initialization are proposed in this algorithm. The experimental results show that our algorithm can obtain higher quality solutions when compared with other ones.
Keywords: Privacy protection ، Workflow scheduling ، Cloud ، Big data ، Multi-objective optimization
Impact of shelf life on the trade-off between economic and environmental objectives: A dairy case
تاثیر عمر طاقچه ای روی سبک و سنگین کردن بین اهداف اقتصادی و محیطی: یک مورد لبنیاتی-2018
Food manufacturers introduce more environmentally friendly processes to account for increasing sustainability concerns. However, these processes often go along with a reduction of product shelf life, limiting the delay of sales to future periods with higher prices. We develop a framework to analyze the impact of shelf life on the trade-off between economic and environmental performance of two types of dairy products. Since the differences in shelf life have their key impact at the tactical planning level, we develop an optimization model for this aggregation level. Its objectives reflect profit and relevant environmental indicators. A rolling horizon scheme is used to deal with price uncertainty, using Eurex futures as price predictors. Our framework uses these tactical planning results for strategic decisions on product and process selection. A real-life case study contrasts traditional milk powders against novel milk concentrates. Concentrates require less energy in processing, but have a shorter shelf life. Results show that powders offer a potential profit benefit of up to 34.5%. However, this economic value of shelf life is subject to a priori perfect price knowledge. If futures are used as price predictors, the value of shelf life is reduced to only 1.1%. The economic value of shelf life is therefore not a strong argument against the substitution of powders with more environmentally friendly concentrates. We also show that two objectives, profit and eutrophication potential, are sufficient to capture trade-offs in the case. Several product mixes are determined that omit powders and perform well with regard to profit and environment.
keywords: Perishability |Sustainability |Multi-objective optimization |Objective reduction |Dairy industry
A multi-objective evolutionary approach for mining frequent and high utility itemsets
یک روش تکاملی چند هدفه برای استخراج مجموعه اقلام مکرر و سودمند-2018
Mining interesting itemsets with both high support and utility values from transactional database is an important task in data mining. In this paper, we consider the two measures support and utility in a unified framework from a multi-objective view. Specifically, the task of mining frequent and high utility itemsets is modeled as a multi-objective problem. Then, a multi-objective itemset mining algorithm is proposed for solving the transformed problem, which can provide multiple itemsets recommendation for decision makers in only one run. One key advantage of the proposed multi-objective algorithm is that it does not need to specify the prior parameters such as minimal support threshold min sup and minimal utility threshold min uti, which brings much convenience to users. The experimental results on several real datasets demonstrate the effectiveness of the proposed algorithm. In addition, comparison results show that the proposed algorithm can provide more diverse yet frequent and high utility itemsets in only one run.
Keywords: Frequent itemset mining ، High utility itemset mining ، Data mining ، Multi-objective optimization ، Evolutionary algorithms