Wyniki wyszukiwania - BazTech

1

A hybrid optimized resource allocation modelfor multi-cloud environment using batand particle swarm optimization algorithms

Selvapandian D., Santhosh R.

Computer Assisted Methods in Engineering and Science

|

2022

|

Vol. 29, no. 1-2 spec.

87--103

EN

In cloud computing, scheduling and resource allocation are the major factors that definethe overall quality of services. An efficient resource allocation module is required in cloudcomputing since resource allocation in a single cloud environment is a complex process.Whereas resource allocation in a multi-cloud environment further increases the complexityof allocation procedures. Earlier, resources from the multi-cloud environment were allocated based on task requirements. However, it is essential to analyze the present resourceavailability status and resource capability before allocating to the requested tasks. So, inthis research work, a hybrid optimized resource allocation model is presented using bat optimization algorithm and particle swarm optimization algorithm to allocate the resourceconsidering the resource status, distance, bandwidth, and task requirements. Proposedmodel performance is evaluated through simulation and compared with conventional optimization algorithms. For a set of 500 tasks, the proposed approach allocates resourcesin 47 s, with a minimum energy consumption of 200 kWh. Compared to conventionalapproaches, the performance of the proposed model is much better in terms of deadlinemissed tasks, resource requirement, energy consumption, and allocation time.

2

Multitemporal meteorological drought forecasting using Bat-ELM

Gholizadeh Reza, Yılmaz Hasan, Danandeh Mehr Ali

Acta Geophysica

|

2022

|

Vol. 70, no 2

917--927

EN

The advancement of the machine learning (ML) models has demonstrated notable progress in geosciences. They can identify the underlying process or causality of natural hazards. This article introduces the development and verification procedures of a new hybrid ML model, namely Bat-ELM for predictive drought modelling. The multi-temporal standardized precipitation evapotranspiration index (SPEI-3 and SPEI-6) is computed as the meteorological drought index at two study regions (Beypazari and Nallihan), located in Ankara province, Turkey. The proposed hybrid model is obtained by integrating the Bat optimization algorithm as the parameter optimizer with an extreme learning machine (ELM) as the regressor engine. The efficiency of the intended model was evaluated against the classic artificial neural network (ANN) and standalone ELM models. The evaluation and assessment are conducted using statistical metrics and graphical diagrams. The forecasting results showed that the accuracy of the proposed model outperformed the benchmark models. In a quantitative assessment, the Bat-ELM model attained minimal root mean square error for the SPEI-3 and SPEI-6 (RMSE=0.58 and 0.43 at Beypazari station and RMSE=0.53 and 0.37 at Nallihan station) over the testing phase. This indicates the new model approximately 20 and 15% improves the forecasting accuracy of traditional ANN and classic ELM techniques, respectively.

3

Zastosowanie półautomatycznego algorytmu doboru optymalnej liczby i położenia odwiertów wydobywczych

Łętkowski P.

Nafta-Gaz

|

2018

|

R. 74, nr 8

598--605

PL

Artykuł poświęcono zastosowaniu tzw. algorytmu nietoperza do rozwiązania problemu określenia optymalnej liczby i położenia odwiertów wydobywczych. W procesie optymalizacji jako funkcję celu wykorzystano bieżącą wartość netto (ang. net present value – NPV). Testy zbudowanego algorytmu przeprowadzono na przykładzie modelu symulacyjnego złoża PUNQ-S3, dostępne- go na zasadach open source. Zastosowany algorytm został wyposażony w dodatkowe mechanizmy zwiększające jego efektywność: mechanizm próbkowania sześcianu łacińskiego (ang. Latin hypercube sampling – LHS) oraz mechanizm eliminowania położeń odwiertów poza modelem. Przeprowadzone testy wskazują na bardzo dobrą zbieżność zbudowanego algorytmu w procesie optymalizacji.

EN

The article is devoted to the application of the so-called bat algorithm to solve the problem of determining the optimum number and location of production wells. This algorithm was proposed by Yang in 2010, and since then has been successfully used in solving both theoretical and practical optimization problems. The method belongs to a group of swarm optimization methods and in searching for the best solution, the algorithm uses a mechanism of echolocation, similar to the one used by a herd of bats. The current net present value (NPV) was used as a target function in the optimization process. The algorithm was tested on the example of the simulation model of the PUNQ-S3 reservoir available on an OpenSource basis. The applied algorithm was equipped with additional mechanisms increasing its effectiveness: Latin Hypercube Sampling (LHS) algorithm and the mechanism eliminating the locations of wells outside the operational area of the model. The first of the applied improvements ensures a better starting point for the proper optimization process, which significantly improves the convergence of the whole algorithm. The latter mechanism solves a problem specific to the issue in question.

4

Zastosowanie metody wzorowanej na echolokacyjnym zachowaniu nietoperzy w optymalnym projektowaniu przetworników elektromagnetycznych

Knypiński Ł.

Poznan University of Technology Academic Journals. Electrical Engineering

|

2017

|

No. 91

365--374

PL

W artykule przedstawiono algorytm optymalizacji parametrów wzbudzenia silnika synchronicznego o rozruchu własnym. Na podstawie algorytmu opracowano oprogramowanie w środowisku programistycznym Borland Delphi. Oprogramowanie składa się z dwóch modułów: modułu optymalizacyjnego oraz modułu zawierającego model matematyczny silnika synchronicznego o rozruchu własnym. Obliczenia optymalizacyjne wykonano z wykorzystaniem algorytmu wzorowanego na echolokacyjnym zachowaniu nietoperzy. Model matematyczny silnika opracowano w oprogramowaniu ANSYS Maxwell. Przedstawiono i omówiono wybrane wyniki obliczeń symulacyjnych i optymalizacyjnych.

EN

The article presents an algorithm and computer software for the optimization of excitation system of permanent magnet synchronous motor. The software consists of two modules: the module containing mathematical model of permanent magnet machine and optimization solver. The mathematical model of the device has been elaborated in Ansys Maxwell environment. The Bat Algorithm (BA) has been applied in the optimization procedure. The optimization module has been elaborated in Borland Delphi environment. Selected results of optimization calculation are presented and discussed.