Search results for: optimizer

Authors: Asawari Alok Pawaskar

Abstract:

This study was aimed at investigating quality assurance (QA) done with IBA matrix, the discrepan­cies observed for helical tomotherapy plans. A selection of tomotherapy plans that initially failed the with Matrix process was chosen for this investigation. These plans failed the fluence analysis as assessed using gamma criteria (3%, 3 mm). Each of these plans was modified (keeping the planning constraints the same), beamlets rebatched and reoptimized. By increasing and decreasing the modula­tion factor, the fluence in a circumferential plane as measured with a diode array was assessed. A subset of these plans was investigated using varied pitch values. Factors for each plan that were examined were point doses, fluences, leaf opening times, planned leaf sinograms, and uniformity indices. In order to ensure that the treatment constraints remained the same, the dose-volume histograms (DVHs) of all the modulated plans were compared to the original plan. It was observed that a large increase in the modulation factor did not significantly improve DVH unifor­mity, but reduced the gamma analysis pass rate. This also increased the treatment delivery time by slowing down the gantry rotation speed which then increases the maximum to mean non-zero leaf open time ratio. Increasing and decreasing the pitch value did not substantially change treatment time, but the delivery accuracy was adversely affected. This may be due to many other factors, such as the complexity of the treatment plan and site. Patient sites included in this study were head and neck, breast, abdomen. The impact of leaf tim­ing inaccuracies on plans was greater with higher modulation factors. Point-dose measurements were seen to be less susceptible to changes in pitch and modulation factors. The initial modulation factor used by the optimizer, such that the TPS generated ‘actual’ modulation factor within the range of 1.4 to 2.5, resulted in an improved deliverable plan.

Keywords: dose volume histogram, modulation factor, IBA matrix, tomotherapy

Procedia PDF Downloads 147

Authors: Choonoh Lee, Seyeon Park, Dongyun Kang, Jaehyeong Choi, Soojee Kim, Younggeun Kim

Abstract:

Market Kurly is the first South Korean online grocery retailer that guarantees same-day, overnight shipping. More than 1.6 million customers place an average of 4.7 million orders and add 3 to 14 products into a cart per month. The company has sold almost 30,000 kinds of various products in the past 6 months, including food items, cosmetics, kitchenware, toys for kids/pets, and even flowers. The company is operating and expanding multiple dry, cold, and frozen fulfillment centers in order to store and ship these products. Due to the scale and complexity of the fulfillment, pick-pack-ship processes are planned and operated in batches, and thus, the planning that decides the batch of the customers’ orders is a critical factor in overall productivity. This paper introduces a metaheuristic optimization method that reduces the complexity of batch processing in a fulfillment center. The method is an iterative genetic algorithm with heuristic creation and evolution strategies; it aims to group similar orders into pick-pack-ship batches to minimize the total number of distinct products. With a well-designed approach to create initial genes, the method produces streamlined plans, up to 13.5% less complex than the actual plans carried out in the company’s fulfillment centers in the previous months. Furthermore, our digital-twin simulations show that the optimized plans can reduce 3% of operation time for packing, which is the most complex and time-consuming task in the process. The optimization method implements a multithreading design on the Spring framework to support the company’s warehouse management systems in near real-time, finding a solution for 4,000 orders within 5 to 7 seconds on an AWS c5.2xlarge instance.

Keywords: fulfillment planning, genetic algorithm, online grocery retail, optimization

Procedia PDF Downloads 53

Authors: Julius M. Ndambuki, Gislar E. Kifanyi, Samuel N. Odai, Charles Gyamfi

Abstract:

Conjunctive management of surface and groundwater resources is a challenging task due to the spatial and temporal variability nature of hydrology as well as hydrogeology of the water storage systems. Surface water-groundwater hydrogeology is highly uncertain; thus it is imperative that this uncertainty is explicitly accounted for, when managing water resources. Various methodologies have been developed and applied by researchers in an attempt to account for the uncertainty. For example, simulation-optimization models are often used for conjunctive water resources management. However, direct application of such an approach in which all realizations are considered at each iteration of the optimization process leads to a very expensive optimization in terms of computational time, particularly when the number of realizations is large. The aim of this paper, therefore, is to introduce and apply an efficient approach referred to as Retrospective Optimization Approximation (ROA) that can be used for optimizing conjunctive use of surface water and groundwater over a multiple hydrogeological model simulations. This work is based on stochastic simulation-optimization framework using a recently emerged technique of sample average approximation (SAA) which is a sampling based method implemented within the Retrospective Optimization Approximation (ROA) approach. The ROA approach solves and evaluates a sequence of generated optimization sub-problems in an increasing number of realizations (sample size). Response matrix technique was used for linking simulation model with optimization procedure. The k-means clustering sampling technique was used to map the realizations. The methodology is demonstrated through the application to a hypothetical example. In the example, the optimization sub-problems generated were solved and analysed using “Active-Set” core optimizer implemented under MATLAB 2014a environment. Through k-means clustering sampling technique, the ROA – Active Set procedure was able to arrive at a (nearly) converged maximum expected total optimal conjunctive water use withdrawal rate within a relatively few number of iterations (6 to 7 iterations). Results indicate that the ROA approach is a promising technique for optimizing conjunctive water use of surface water and groundwater withdrawal rates under hydrogeological uncertainty.

Keywords: conjunctive water management, retrospective optimization approximation approach, sample average approximation, uncertainty

Procedia PDF Downloads 203

Authors: Mayowa Saheed Sanusi A, Musiliu Olushola Sunmonua, Abdulquadri Alakab Owolabi Raheema, Adeyemi Ikimot Adejokea

Abstract:

The development of healthy cookies for health-conscious consumers cannot be overemphasized in the present global health crisis. This study was aimed to evaluate and model the influence of ripeness levels of papaya puree (unripe, ripe and overripe), oven temperature (130°C, 150°C and 170°C) and oven rack speed (stationary, 10 and 20 rpm) on physicochemical properties of papaya-based cookies using Response Surface Methodology (RSM). The physicochemical properties (baking time, cookies mass, cookies thickness, spread ratio, proximate composition, Calcium, Vitamin C and Total Phenolic Content) were determined using standard procedures. The data obtained were statistically analysed at p≤0.05 using ANOVA. The polynomial regression model of response surface methodology was used to model the physicochemical properties. The adequacy of the models was determined using the coefficient of determination (R²) and the response optimizer of RSM was used to determine the optimum physicochemical properties for the papaya-based cookies. Cookies produced from overripe papaya puree were observed to have the shortest baking time; ripe papaya puree favors cookies spread ratio, while the unripe papaya puree gives cookies with the highest mass and thickness. The highest crude protein content, fiber content, calcium content, Vitamin C and Total Phenolic Content (TPC) were observed in papaya based-cookies produced from overripe puree. The models for baking time, cookies mass, cookies thickness, spread ratio, moisture content, crude protein and TPC were significant, with R2 ranging from 0.73 – 0.95. The optimum condition for producing papaya based-cookies with desirable physicochemical properties was obtained at 149°C oven temperature, 17 rpm oven rack speed and with the use of overripe papaya puree. The Information on the use of puree from unripe, ripe and overripe papaya can help to increase the use of underutilized unripe or overripe papaya and also serve as a strategic means of obtaining a fat substitute to produce new products with lower production cost and health benefit.

Keywords: papaya based-cookies, modeling, response surface methodology, physicochemical properties

Procedia PDF Downloads 132

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 232

Authors: Fouzia Brihmat

Abstract:

Economic planning models, which are used to build microgrids and distributed energy resources, are the current norm for expressing such confidence (DER). These models often decide both short-term DER dispatch and long-term DER investments. This research investigates the most cost-effective hybrid (photovoltaic-diesel) renewable energy system (HRES) based on Total Net Present Cost (TNPC) in an Algerian Saharan area, which has a high potential for solar irradiation and has a production capacity of 1GW/h. Lead-acid batteries have been around much longer and are easier to understand, but have limited storage capacity. Lithium-ion batteries last longer, are lighter, but generally more expensive. By combining the advantages of each chemistry, we produce cost-effective high-capacity battery banks that operate solely on AC coupling. The financial implications of this research describe the corrosion process that occurs at the interface between the active material and grid material of the positive plate of a lead-acid battery. The best cost study for the HRES is completed with the assistance of the HOMER Pro MATLAB Link. Additionally, during the course of the project's 20 years, the system is simulated for each time step. In this model, which takes into consideration decline in solar efficiency, changes in battery storage levels over time, and rises in fuel prices above the rate of inflation. The trade-off is that the model is more accurate, but it took longer to compute. As a consequence, the model is more precise, but the computation takes longer. We initially utilized the Optimizer to run the model without MultiYear in order to discover the best system architecture. The optimal system for the single-year scenario is the Danvest generator, which has 760 kW, 200 kWh of the necessary quantity of lead-acid storage, and a somewhat lower COE of $0.309/kWh. Different scenarios that account for fluctuations in the gasified biomass generator's production of electricity have been simulated, and various strategies to guarantee the balance between generation and consumption have been investigated. The technological optimization of the same system has been finished and is being reviewed in a recent paper study.

Keywords: battery, corrosion, diesel, economic planning optimization, hybrid energy system, lead-acid battery, multi-year planning, microgrid, price forecast, PV, total net present cost

Procedia PDF Downloads 64

Authors: Gulfam Haider, sana danish

Abstract:

Convolutional Neural Networks (CNNs) have emerged as powerful tools for image classification, and the choice of optimizers profoundly affects their performance. The study of optimizers and their adaptations remains a topic of significant importance in machine learning research. While numerous studies have explored and advocated for various optimizers, the efficacy of these optimization techniques is still subject to scrutiny. This work aims to address the challenges surrounding the effectiveness of optimizers by conducting a comprehensive analysis and evaluation. The primary focus of this investigation lies in examining the performance of different optimizers when employed in conjunction with the popular activation function, Rectified Linear Unit (ReLU). By incorporating ReLU, known for its favorable properties in prior research, the aim is to bolster the effectiveness of the optimizers under scrutiny. Specifically, we evaluate the adjustment of these optimizers with both the original Softmax activation function and the modified ReLU activation function, carefully assessing their impact on overall performance. To achieve this, a series of experiments are conducted using a well-established benchmark dataset for image classification tasks, namely the Canadian Institute for Advanced Research dataset (CIFAR-10). The selected optimizers for investigation encompass a range of prominent algorithms, including Adam, Root Mean Squared Propagation (RMSprop), Adaptive Learning Rate Method (Adadelta), Adaptive Gradient Algorithm (Adagrad), and Stochastic Gradient Descent (SGD). The performance analysis encompasses a comprehensive evaluation of the classification accuracy, convergence speed, and robustness of the CNN models trained with each optimizer. Through rigorous experimentation and meticulous assessment, we discern the strengths and weaknesses of the different optimization techniques, providing valuable insights into their suitability for image classification tasks. By conducting this in-depth study, we contribute to the existing body of knowledge surrounding optimizers in CNNs, shedding light on their performance characteristics for image classification. The findings gleaned from this research serve to guide researchers and practitioners in making informed decisions when selecting optimizers and activation functions, thus advancing the state-of-the-art in the field of image classification with convolutional neural networks.

Keywords: deep neural network, optimizers, RMsprop, ReLU, stochastic gradient descent

Procedia PDF Downloads 62

Authors: Francesca Schiavello

Abstract:

This work aims to create a hybrid algorithm, combining Quantum Approximate Optimization Algorithm (QAOA) with an Evolutionary Algorithm (EA) in the place of traditional gradient based optimization processes. QAOA’s were first introduced in 2014, where, at the time, their algorithm performed better than the traditional best known classical algorithm for Max-cut graphs. Whilst classical algorithms have improved since then and have returned to being faster and more efficient, this was a huge milestone for quantum computing, and their work is often used as a benchmarking tool and a foundational tool to explore variants of QAOA’s. This, alongside with other famous algorithms like Grover’s or Shor’s, highlights to the world the potential that quantum computing holds. It also presents the reality of a real quantum advantage where, if the hardware continues to improve, this could constitute a revolutionary era. Given that the hardware is not there yet, many scientists are working on the software side of things in the hopes of future progress. Some of the major limitations holding back quantum computing are the quality of qubits and the noisy interference they generate in creating solutions, the barren plateaus that effectively hinder the optimization search in the latent space, and the availability of number of qubits limiting the scale of the problem that can be solved. These three issues are intertwined and are part of the motivation for using EAs in this work. Firstly, EAs are not based on gradient or linear optimization methods for the search in the latent space, and because of their freedom from gradients, they should suffer less from barren plateaus. Secondly, given that this algorithm performs a search in the solution space through a population of solutions, it can also be parallelized to speed up the search and optimization problem. The evaluation of the cost function, like in many other algorithms, is notoriously slow, and the ability to parallelize it can drastically improve the competitiveness of QAOA’s with respect to purely classical algorithms. Thirdly, because of the nature and structure of EA’s, solutions can be carried forward in time, making them more robust to noise and uncertainty. Preliminary results show that the EA algorithm attached to QAOA can perform on par with the traditional QAOA with a Cobyla optimizer, which is a linear based method, and in some instances, it can even create a better Max-Cut. Whilst the final objective of the work is to create an algorithm that can consistently beat the original QAOA, or its variants, due to either speedups or quality of the solution, this initial result is promising and show the potential of EAs in this field. Further tests need to be performed on an array of different graphs with the parallelization aspect of the work commencing in October 2023 and tests on real hardware scheduled for early 2024.

Keywords: evolutionary algorithm, max cut, parallel simulation, quantum optimization

Procedia PDF Downloads 31

Authors: Rafael do Amaral Teodoro, Leandro Augusto da Silva

Abstract:

Originated from graphite, graphene is a two-dimensional (2D) material that promises to revolutionize technology in many different areas, such as energy, telecommunications, civil construction, aviation, textile, and medicine. This is possible because its structure, formed by carbon bonds, provides desirable optical, thermal, and mechanical characteristics that are interesting to multiple areas of the market. Thus, several research and development centers are studying different manufacturing methods and material applications of graphene, which are often compromised by the scarcity of more agile and accurate methodologies to characterize the material – that is to determine its composition, shape, size, and the number of layers and crystals. To engage in this search, this study proposes a computational methodology that applies deep learning to identify graphene oxide crystals in order to characterize samples by crystal sizes. To achieve this, a fully convolutional neural network called U-net has been trained to segment SEM graphene oxide images. The segmentation generated by the U-net is fine-tuned with a standard deviation technique by classes, which allows crystals to be distinguished with different labels through an object delimitation algorithm. As a next step, the characteristics of the position, area, perimeter, and lateral measures of each detected crystal are extracted from the images. This information generates a database with the dimensions of the crystals that compose the samples. Finally, graphs are automatically created showing the frequency distributions by area size and perimeter of the crystals. This methodological process resulted in a high capacity of segmentation of graphene oxide crystals, presenting accuracy and F-score equal to 95% and 94%, respectively, over the test set. Such performance demonstrates a high generalization capacity of the method in crystal segmentation, since its performance considers significant changes in image extraction quality. The measurement of non-overlapping crystals presented an average error of 6% for the different measurement metrics, thus suggesting that the model provides a high-performance measurement for non-overlapping segmentations. For overlapping crystals, however, a limitation of the model was identified. To overcome this limitation, it is important to ensure that the samples to be analyzed are properly prepared. This will minimize crystal overlap in the SEM image acquisition and guarantee a lower error in the measurements without greater efforts for data handling. All in all, the method developed is a time optimizer with a high measurement value, considering that it is capable of measuring hundreds of graphene oxide crystals in seconds, saving weeks of manual work.

Keywords: characterization, graphene oxide, nanomaterials, U-net, deep learning

Procedia PDF Downloads 134

Authors: A. Chatel, I. S. Torreguitart, T. Verstraete

Abstract:

The paper deals with a single point optimization of the LS89 turbine using an adjoint optimization and defining the design variables within a CAD system. The advantage of including the CAD model in the design system is that higher level constraints can be imposed on the shape, allowing the optimized model or component to be manufactured. However, CAD-based approaches restrict the design space compared to node-based approaches where every node is free to move. In order to preserve a rich design space, we develop a methodology to refine the CAD model during the optimization and to create the best parameterization to use at each time. This study presents a methodology to progressively refine the design space, which combines parametric effectiveness with a differential evolutionary algorithm in order to create an optimal parameterization. In this manuscript, we show that by doing the parameterization at the CAD level, we can impose higher level constraints on the shape, such as the axial chord length, the trailing edge radius and G2 geometric continuity between the suction side and pressure side at the leading edge. Additionally, the adjoint sensitivities are filtered out and only smooth shapes are produced during the optimization process. The use of algorithmic differentiation for the CAD kernel and grid generator allows computing the grid sensitivities to machine accuracy and avoid the limited arithmetic precision and the truncation error of finite differences. Then, the parametric effectiveness is computed to rate the ability of a set of CAD design parameters to produce the design shape change dictated by the adjoint sensitivities. During the optimization process, the design space is progressively enlarged using the knot insertion algorithm which allows introducing new control points whilst preserving the initial shape. The position of the inserted knots is generally assumed. However, this assumption can hinder the creation of better parameterizations that would allow producing more localized shape changes where the adjoint sensitivities dictate. To address this, we propose using a differential evolutionary algorithm to maximize the parametric effectiveness by optimizing the location of the inserted knots. This allows the optimizer to gradually explore larger design spaces and to use an optimal CAD-based parameterization during the course of the optimization. The method is tested on the LS89 turbine cascade and large aerodynamic improvements in the entropy generation are achieved whilst keeping the exit flow angle fixed. The trailing edge and axial chord length, which are kept fixed as manufacturing constraints. The optimization results show that the multilevel optimizations were more efficient than the single level optimization, even though they used the same number of design variables at the end of the multilevel optimizations. Furthermore, the multilevel optimization where the parameterization is created using the optimal knot positions results in a more efficient strategy to reach a better optimum than the multilevel optimization where the position of the knots is arbitrarily assumed.

Keywords: adjoint, CAD, knots, multilevel, optimization, parametric effectiveness

Procedia PDF Downloads 89

Authors: Ferzat Anka

Abstract:

Many types of problems can be solved using traditional analytical methods. However, these methods take a long time and cause inefficient use of resources. In particular, different approaches may be required in solving complex and global engineering problems that we frequently encounter in real life. The bigger and more complex a problem, the harder it is to solve. Such problems are called Nondeterministic Polynomial time (NP-hard) in the literature. The main reasons for recommending different metaheuristic algorithms for various problems are the use of simple concepts, the use of simple mathematical equations and structures, the use of non-derivative mechanisms, the avoidance of local optima, and their fast convergence. They are also flexible, as they can be applied to different problems without very specific modifications. Thanks to these features, it can be easily embedded even in many hardware devices. Accordingly, this approach can also be used in trend application areas such as IoT, big data, and parallel structures. Indeed, the metaheuristic approaches are algorithms that return near-optimal results for solving large-scale optimization problems. This study is focused on the new metaheuristic method that has been merged with the chaotic approach. It is based on the chaos theorem and helps relevant algorithms to improve the diversity of the population and fast convergence. This approach is based on Chimp Optimization Algorithm (ChOA), that is a recently introduced metaheuristic algorithm inspired by nature. This algorithm identified four types of chimpanzee groups: attacker, barrier, chaser, and driver, and proposed a suitable mathematical model for them based on the various intelligence and sexual motivations of chimpanzees. However, this algorithm is not more successful in the convergence rate and escaping of the local optimum trap in solving high-dimensional problems. Although it and some of its variants use some strategies to overcome these problems, it is observed that it is not sufficient. Therefore, in this study, a newly expanded variant is described. In the algorithm called Ex-ChOA, hybrid models are proposed for position updates of search agents, and a dynamic switching mechanism is provided for transition phases. This flexible structure solves the slow convergence problem of ChOA and improves its accuracy in multidimensional problems. Therefore, it tries to achieve success in solving global, complex, and constrained problems. The main contribution of this study is 1) It improves the accuracy and solves the slow convergence problem of the ChOA. 2) It proposes new hybrid movement strategy models for position updates of search agents. 3) It provides success in solving global, complex, and constrained problems. 4) It provides a dynamic switching mechanism between phases. The performance of the Ex-ChOA algorithm is analyzed on a total of 8 benchmark functions, as well as a total of 2 classical and constrained engineering problems. The proposed algorithm is compared with the ChoA, and several well-known variants (Weighted-ChoA, Enhanced-ChoA) are used. In addition, an Improved algorithm from the Grey Wolf Optimizer (I-GWO) method is chosen for comparison since the working model is similar. The obtained results depict that the proposed algorithm performs better or equivalently to the compared algorithms.

Keywords: optimization, metaheuristic, chimp optimization algorithm, engineering constrained problems

Procedia PDF Downloads 50