Search results for: composite forecasting

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 266

Authors: Tariku Nefo Duke

Abstract:

Herein, we synthesized three PIs/h-boron nitride composite films for corrosion resistance of mild steel material. The structures of these three polyimide/h-boron nitride composite films were confirmed using (FTIR, 1H NMR, 13C NMR, and 2D NMR) spectroscopy techniques. The synthesized PIs composite films have high mechanical properties, thermal stability, high glass-transition temperature (Tg), and insulating properties. It has been shown that the presence of electroactive TiO2, SiO2, and h-BN, in polymer coatings effectively inhibits corrosion. The h-BN displays an admirable anti-corrosion barrier for the 6F-OD and BT-OD films. PI/ h-BN composite films of 6F-OD exhibited better resistance to water vapor, high corrosion resistance, and positive corrosion voltage. Only four wt. percentage of h-BN in the composite is adequate.

Keywords: polyimide, corrosion resistance, electroactive, Tg

Procedia PDF Downloads 201

Authors: Elmo Thiago Lins Cöuras Ford, Valentina Alessandra Carvalho do Vale

Abstract:

Given the unquestionable need of environmental preservation, the natural fibers have been seen as a salutary alternative for production of composites in substitution to the synthetic fibers, vitreous and metallic. In this work, the behavior of a composite was analyzed done with fiber of the peel of the coconut as reinforcement and latex as head office, when submitted the source of heat. The temperature profiles were verified in the internal surfaces and it expresses of the composite as well as the temperature gradient in the same. It was also analyzed the behavior of this composite when submitted to a cold source. As consequence, in function of the answers of the system, conclusions were reached.

Keywords: natural fiber, composite, temperature, latex, gradient

Procedia PDF Downloads 817

Authors: Melby Chacko, Jagannath Nayak

Abstract:

The aging behaviour of 6061 Al-15 vol% SiC composite was investigated using Rockwell B hardness measurement. The composite was solutionized at 350°C and quenched in water. The composite was aged at room temperature (T4 treatment) and also at 140°C, 160°C, 180°C and 200°C (T6 treatment). The natural and artificial aging behaviour of composite was studied using aging curves determined at different temperatures. The aging period for peak aging for different temperatures was identified. The time required for attaining peak aging decreased with increase in the aging temperature. The peak hardness was found to increase with increase with aging temperature and the highest peak hardness was observed at 180ºC. Beyond 180ºC the peak hardness was found to be decreasing.

Keywords: 6061 Al-SiC composite, aging curve, Rockwell B hardness, T4, T6 treatments

Procedia PDF Downloads 267

Authors: G. Hemath Kumar, H. Mohit, K. Karthick

Abstract:

One of the most important issues in the composite technology is the repairing of parts of aircraft structures which is manufactured from composite materials. In such applications and also for joining various composite parts together, they are fastened together either using adhesives or mechanical fasteners. The tensile strength of these joints was carried out using Universal Testing Machine (UTM). A parametric study was also conducted to compare the performance of the hybrid joint with varying adherent thickness, adhesive thickness and overlap length. The composition of the material is combination of epoxy resin and carbon fibre under the method of reinforcement. To utilize the full potential of composite materials as structural elements, the strength and stress distribution of these joints must be understood. The study of tensile strength in the members involved under various design conditions and various joints were took place.

Keywords: carbon fiber, FRP composite, MMC, automotive

Procedia PDF Downloads 409

Authors: A. Chellil, A. Nour, S. Lecheb, H. Mechakra, A. Bouderba, H. Kebir

Abstract:

In this paper, the dynamic response for the instability of a composite rotor is presented, under dynamic loading response in the harmonic analysis condition. The analysis of the stress which operates the rotor is done. Calculations of different energies and the virtual work of the aerodynamic loads from the rotor blade is developed. The use of the composite material for the rotor, offers a good stability. Numerical calculations on the model develop of three dimensions prove that the damage effect has a negative effect on the stability of the rotor. The study of the composite rotor in transient system allowed to determine the vibratory responses due to various excitations.

Keywords: rotor, composite, damage, finite element, numerical

Procedia PDF Downloads 532

Authors: Soroor Ghaziof, Wei Gao

Abstract:

Sol-enhanced Zn-Ni-Al2O3 nano-composite coatings were electroplated on mild steel by our newly developed sol-enhanced electroplating method. In this method, transparent Al2O3 sol was added into the acidic Zn-Ni bath to produced Zn-Ni-Al2O3 nano-composite coatings. The chemical composition, microstructure and mechanical properties of the composite and alloy coatings deposited at two different agitation speed were investigated. The structure of all coatings was single γ-Ni5Zn21 phase. The composite coatings possess refined crystals with higher microhardness compared to Zn-Ni alloy coatings. The wear resistance of Zn-Ni coatings was improved significantly by incorporation of alumina nano particles into the coatings. Higher agitation speed provided more uniform coatings with smaller grain sized and slightly higher microhardness. Considering composite coatings, high agitation speeds may facilitate co-deposition of alumina in the coatings.

Keywords: microhardness, sol-enhanced electroplating, wear resistance, Zn-Ni-Al2O3 composite coatings

Procedia PDF Downloads 501

Authors: Daniel Fulus Fom, Gau Patrick Damulak

Abstract:

In this study, the Autoregressive Fractional Integrated Moving Average (ARFIMA) and Jordan Recurrent Neural Network (JRNN) models were employed to model the forecasting performance of the daily turbidity flow of White Clay Creek (WCC). The two methods were applied to the log difference series of the daily turbidity flow series of WCC. The measurements of error employed to investigate the forecasting performance of the ARFIMA and JRNN models are the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). The outcome of the investigation revealed that the forecasting performance of the JRNN technique is better than the forecasting performance of the ARFIMA technique in the mean square error sense. The results of the ARFIMA and JRNN models were obtained by the simulation of the models using MATLAB version 8.03. The significance of using the log difference series rather than the difference series is that the log difference series stabilizes the turbidity flow series than the difference series on the ARFIMA and JRNN.

Keywords: auto regressive, mean absolute error, neural network, root square mean error

Procedia PDF Downloads 268

Authors: Anita Setianingrum, Oki S. Jaya, Zuherman Rustam

Abstract:

Forecasting stock price is a challenging task due to the complex time series of the data. The complexity arises from many variables that affect the stock market. Many time series models have been proposed before, but those previous models still have some problems: 1) put the subjectivity of choosing the technical indicators, and 2) rely upon some assumptions about the variables, so it is limited to be applied to all datasets. Therefore, this paper studied a novel Adaptive Neuro-Fuzzy Inference System (ANFIS) time series model based on Support Vector Regression (SVR) for forecasting the stock market. In order to evaluate the performance of proposed models, stock market transaction data of TAIEX and HIS from January to December 2015 is collected as experimental datasets. As a result, the method has outperformed its counterparts in terms of accuracy.

Keywords: ANFIS, fuzzy time series, stock forecasting, SVR

Procedia PDF Downloads 247

Authors: Sudarat Issarapanacheewin, Katcharin Wetchakun, Sukon Phanichphant, Wiyong Kangwansupamonkon, Natda Wetchakun

Abstract:

The photocatalytic degradation of Methylene blue (MB) and Rhodamine B (RhB) in the presence of ZnWO4-Bi2WO6 composite under visible light irradiation (λ ≥ 400 nm) were studied in this research. The structural and photophysical properties of ZnWO4-Bi2WO6 composite on the photocatalytic degradation process were investigated. The as-prepared ZnWO4-Bi2WO6 composite photocatalyst exhibits wide absorption in the visible-light region and display superior visible-light-driven photocatalytic activities in degradation of MB and RhB. The enhanced photocatalytic activity was attributed to electron-hole separation with the appropriate band potential and the physicochemical properties of ZnWO4 and Bi2WO6. The main active species for the degradation of organic dyes were investigated to explain the enhancement of photocatalytic performance of ZnWO4-Bi2WO6 composite. The possible photocatalytic degradation pathway of aqueous MB and RhB dyes and charge transfer of ZnWO4-Bi2WO6 composite was proposed.

Keywords: composite, dyes, photocatalytic activity, ZnWO4-Bi2WO6

Procedia PDF Downloads 302

Authors: Yousef Abu Nahleh, Arun Kumar, Fugen Daver, Reham Al-Hindawi

Abstract:

Despite the availability of natural disaster related time series data for last 110 years, there is no forecasting tool available to humanitarian relief organizations to determine forecasts for emergency logistics planning. This study develops a forecasting tool based on identifying probability of disaster for each country in the world by using decision tree modeling. Further, the determination of aggregate forecasts leads to efficient pre-disaster planning. Based on the research findings, the relief agencies can optimize the various resources allocation in emergency logistics planning.

Keywords: decision tree modeling, forecasting, humanitarian relief, emergency supply chain

Procedia PDF Downloads 483

Authors: Pattamaphorn Phuangngamphan, Rewadee Anuwattana, Narumon Soparatana, Nestchanok Yongpraderm, Atiporn Jinpayoon, Supinya Sutthima, Saroj Klangkongsub, Worapong Pattayawan

Abstract:

This research aims to utilize the agricultural waste and plastic waste in Thailand in a study of the optimum conditions for preparing composite materials from water hyacinth and oil palm fiber and plastic waste in landfills. The water hyacinth and oil palm fiber were prepared by alkaline treatment with NaOH (5, 15 wt%) at 25-60 °C for 1 h. The treated fiber (5 and 10 phr) was applied to plastic waste composite. The composite was prepared by using a screw extrusion process from 185 °C to 200 °C with a screw speed of 60 rpm. The result confirmed that alkaline treatment can remove lignin, hemicellulose and other impurities on the fiber surface and also increase the cellulose content. The optimum condition of composite material is 10 phr of fiber coupling with 3 wt% PE-g-MA as compatibilizer. The composite of plastic waste and oil palm fiber has good adhesion between fiber and plastic matrix. The PE-g-MA has improved fiber-plastic interaction. The results suggested that the composite material from plastic waste and agricultural waste has the potential to be used as value-added products.

Keywords: agricultural waste, waste utilization, biomaterials, cellulose fiber, composite material

Procedia PDF Downloads 422

Authors: A. Arabzadeh, H. R. Kazemi Nia Korrani

Abstract:

Composite steel plate shear wall is a lateral loading resistance system, which is used especially in tall buildings. This wall is made of a thin steel plate with reinforced a concrete cover, which is attached to one or both sides of the steel plate. This system is similar to stiffened steel plate shear wall, in which reinforced concrete replaces the steel stiffeners. Composite shear wall have in-plane and out-plane significant strength. Also, they have appropriate ductility. The present numerical investigations were focused on the effects of opening on wall mode shapes. In addition, frequencies of composite shear wall with and without opening are compared. For analyzing composite shear wall, a new program will be developed using of finite element theory and the effects of shape, size and position openings on the behavior of composite shear wall will be studied. Results indicated that the existence of opening decreases wall frequency.

Keywords: composite shear wall, opening, finite element method, modal analysis

Procedia PDF Downloads 540

Authors: H. J. Joshi, Satyajeet Patil, Parth Dandavate, Mihir Kulkarni, Harshita Agrawal

Abstract:

As the world looks towards a sustainable future, electric vehicles have become increasingly popular. Millions worldwide are looking to switch to Electric cars over the previously favored combustion engine-powered cars. This demand has seen an increase in Electric Vehicle Charging Stations. The big challenge is that the randomness of electrical energy makes it tough for these charging stations to provide an adequate amount of energy over a specific amount of time. Thus, it has become increasingly crucial to model these patterns and forecast the energy needs of power stations. This paper aims to analyze how different machine learning models perform on Electric Vehicle charging time-series data. The data set consists of authentic Electric Vehicle Data from the Netherlands. It has an overview of ten thousand transactions from public stations operated by EVnetNL.

Keywords: forecasting, smart grid, electric vehicle load forecasting, machine learning, time series forecasting

Procedia PDF Downloads 106

Authors: Assad Rashid, Umair Ahmed, Zafar Baig

Abstract:

A new trend in construction is widely influenced by the use of Steel-Concrete Composite Columns. The rapid growth in Steel-Concrete Composite construction has widely decreased the conventional R.C.C structures. Steel Concrete composite construction has obtained extensive receiving around the globe. It is considering the fact that R.C.C structures construction is most suitable and economical for low-rise construction, so it is used in farming systems in most of the buildings. However, increased dead load, span restriction, less stiffness and risky formwork make R.C.C construction uneconomical and not suitable when it comes to intermediate to high-rise buildings. A Base + Ground +11 storey commercial building was designed on ETABS 2017 and made a comparison between conventional R.C.C and encased composite column structure. After performing Equivalent Static non-linear analysis, it has been found that construction cost is 13.01% more than R.C.C structure but encased composite column building has 7.7% more floor area. This study will help in understanding the behavior of conventional R.C.C structure and Encased Composite column structure.

Keywords: composite columns structure, equivalent static non-linear analysis, comparison between R.C.C and encased composite column structures, cost-effective structure

Procedia PDF Downloads 199

Authors: S. Lecheb, A. Nour, A. Chellil, H. Mechakra, A. Zeggane, H. Kebir

Abstract:

In this work, repaired crack in 6061-T6 aluminum plate with composite patches presented, firstly we determine the displacement, strain, and stress, also the first six mode shape of the plate, secondly we took the same model adding central crack initiation, which is located in the center of the plate, its size vary from 20 mm to 60 mm and we compare the first results with second. Thirdly, we repair various cracks with the composite patch (carbon/epoxy) and for (2 layers, 4 layers). Finally, the comparison of stress, strain, displacement and six first natural frequencies between un-cracked specimen, crack propagation and composite patch repair.

Keywords: composite patch repair, crack growth, aluminum alloy plate, stress

Procedia PDF Downloads 598

Authors: Aswathi Thrivikraman, S. Advaith

Abstract:

The study is aimed at designing encoders for deciphering intricacies in time series data by redescribing the dynamics operating on a lower-dimensional manifold. A semi-supervised LSTM autoencoder is devised and investigated to see if the latent representation of the time series data can better forecast the data. End-to-end training of the LSTM autoencoder, together with another LSTM network that is connected to the latent space, forces the hidden states of the encoder to represent the most meaningful latent variables relevant for forecasting. Furthermore, the study compares the predictions with those of a traditional seq2seq model.

Keywords: LSTM, autoencoder, forecasting, seq2seq model

Procedia PDF Downloads 155

Authors: F. Sevim, E. Sevimli, F. Demir, T. Çalban

Abstract:

For the first time, nanofibers of PVA /nickel nitrate/silica/alumina izopropoxide/boric acid composite were prepared by using sol-gel processing and electrospinning technique. By high temperature calcinations of the above precursor fibers, nanofibers of NiO/Al2O3/B2O3/SiO2 composite with diameters of 500 nm could be successfully obtained. The fibers were characterized by TG/DTA, FT-IR, XRD and SEM analyses.

Keywords: nano fibers, NiO/Al2O3/B2O3/SiO2 composite, sol-gel processing, electro spinning

Procedia PDF Downloads 337

Authors: Benny Benyamin Nasution, Rahmat Widia Sembiring, Abdul Rahman Dalimunthe, Nursiah Mustari, Nisfan Bahri, Berta br Ginting, Riadil Akhir Lubis, Rita Tavip Megawati, Indri Dithisari

Abstract:

The earth coordinate system is an important part of an attempt for earthquake forecasting, such as the one using Single Layer Hierarchical Graph Neuron (SLHGN). However, there are a number of problems that need to be worked out before the coordinate system can be utilized for the forecaster. One example of those is that SLHGN requires that the focused area of an earthquake must be constructed in a grid-like form. In fact, within the current earth coordinate system, the same longitude-difference would produce different distances. This can be observed at the distance on the Equator compared to distance at both poles. To deal with such a problem, a coordinate system has been developed, so that it can be used to support the ongoing earthquake forecasting using SLHGN. Two important issues have been developed in this system: 1) each location is not represented through two-value (longitude and latitude), but only a single value, 2) the conversion of the earth coordinate system to the x-y cartesian system requires no angular formulas, which is therefore fast. The accuracy and the performance have not been measured yet, since earthquake data is difficult to obtain. However, the characteristics of the SLHGN results show a very promising answer.

Keywords: hierarchical graph neuron, multidimensional hierarchical graph neuron, single layer hierarchical graph neuron, natural disaster forecasting, earthquake forecasting, earth coordinate system

Procedia PDF Downloads 216

Authors: Flavio Cordeiro Fontanella, Asla Medeiros e Sá, Moacyr Alvim Horta Barbosa da Silva

Abstract:

In the present work, we analyse the performance of football results forecasting models. In order to do so, we have performed the data collection from eight different forecasting models during the 2021 Brazilian football season. First, we guide the analysis through visual representations of the data, designed to highlight the most prominent features and enhance the interpretation of differences and similarities between the models. We propose using a 2-simplex triangle to investigate visual patterns from the results forecasting models. Next, we compute the expected points for every team playing in the championship and compare them to the final league standings, revealing interesting contrasts between actual to expected performances. Then, we evaluate forecasts’ accuracy using the Ranked Probability Score (RPS); models comparison accounts for tiny scale differences that may become consistent in time. Finally, we observe that the Wisdom of Crowds principle can be appropriately applied in the context, driving into a discussion of results forecasts usage in practice. This paper’s primary goal is to encourage football forecasts’ performance discussion. We hope to accomplish it by presenting appropriate criteria and easy-to-understand visual representations that can point out the relevant factors of the subject.

Keywords: accuracy evaluation, Brazilian championship, football results forecasts, forecasting models, visual analysis

Procedia PDF Downloads 95

Authors: A. Boumedine, K. Benfriha, S. Lecheb

Abstract:

Manufacturing methods for products and structures made of composite materials reduce the number of parts and integrate technical functions, this advantage of composite materials leads to a lot of innovation but also to a reduction of costs and a gain in quality. A material has attributes: its density, it’s resistance, it’s cost, it’s resistance to corrosion. For the design of a product, a certain profile of these attributes is required: low density, resistance removed, low cost. The problem is then to identify this attribute profile and to compare it with those of the materials, in order to find the one that comes closest. The aim of this work is to demonstrate the feasibility of characterizing a mini turbine made of 3D printed fiber-filled composite material by the process of additive manufacturing, then compare the performance of the alloy turbine with the composite turbine according to the results of the simulation by Abaqus software.

Keywords: additive manufacturing, composite materials, design, 3D printer, turbine

Procedia PDF Downloads 134

Authors: Melby Chacko, Jagannath Nayak

Abstract:

6061 Al-SiCp composite was solutionized at 350 °C for 30 minutes and water quenched. It was then underaged at 140 °C (T6 treatment). The aging behaviour of the composite was studied using Rockwell B hardness measurement. Corrosion behaviour of the underaged sample was studied in different concentrations of acetic acid and at different temperatures. Benzimidazole at different concentrations was used for the inhibition studies. Inhibition efficiency of benzimidazole was calculated for different experimental conditions. Thermodynamic parameters were found out which suggested benzimidazole is an efficient inhibitor and it adsorbed onto the surface of composite by mixed adsorption where chemisorption is predominant.

Keywords: 6061 Al-SiCp composite, T6 treatment, corrosion inhibition, chemisorption

Procedia PDF Downloads 398

Authors: N. Sopipan

Abstract:

In this paper, we study of rainfall time series of weather stations in Nakhon Ratchasima province in Thailand using various statistical methods enabled to analyse the behaviour of rainfall in the study areas. Time-series analysis is an important tool in modelling and forecasting rainfall. ARIMA and Holt-Winter models based on exponential smoothing were built. All the models proved to be adequate. Therefore, could give information that can help decision makers establish strategies for proper planning of agriculture, drainage system and other water resource applications in Nakhon Ratchasima province. We found the best perform for forecasting is ARIMA(1,0,1)(1,0,1)12.

Keywords: ARIMA Models, exponential smoothing, Holt-Winter model

Procedia PDF Downloads 300

Authors: Reinhold Kosfeld, Andreas Gohs

Abstract:

In the reduction of CO₂ emissions, the transition to environmentally friendly transport modes has a high significance. In Germany, the climate protection programme 2030 includes various measures for promoting electromobility. Although electric cars at present hold a market share of just over one percent, its stock more than doubled in the past two years. Special measures like tax incentives and a buyer’s premium have been put in place to promote the shift towards electric cars and boost their diffusion. Knowledge of the future expansion of electric cars is required for planning purposes and adaptation measures. With a view of these objectives, we particularly investigate the effect of spatial spillovers on forecasting performance. For this purpose, time series econometrics and panel econometric models are designed for pure electric cars and hybrid cars for Germany. Regional forecasting models with spatial interactions are consistently estimated by using spatial econometric techniques. Regional data on the stocks of electric cars and their determinants at the district level (NUTS 3 regions) are available from the Federal Motor Transport Authority (Kraftfahrt-Bundesamt) for the period 2017 - 2019. A comparative examination of aggregated regional and national predictions provides quantitative information on accuracy gains by allowing for spatial spillovers in forecasting electric mobility.

Keywords: electric mobility, forecasting market diffusion, regional panel data model, spatial interaction

Procedia PDF Downloads 175

Authors: Hande Taşdemir, Meral Şahin, Mehmet Saçak

Abstract:

Conductive composite materials obtained by physical or chemical mixing of two or more components having conducting and insulating properties have been increasingly attracted. Kaolinite in kaolin clays is one of silicates with two layers of molecular sheets of (Si2O5)2− and [Al2(OH)4]2+ with the chemical composition Al2Si2O5(OH)4. The most abundant hydrophillic kaolinite is extensively used in industrial processes and therefore it is convenient for the preparation of organic/inorganic composites. In this study, conductive poly(N-ethylaniline)/kaolinite composite was prepared by chemical polymerization of N-ethyl aniline in the presence of kaolinite particles using ammonium persulfate as oxidant in aqueous acidic medium. Poly(N-ethylaniline) content and conductivity of composite prepared were systematically investigated as a function of polymerization conditions such as ammonium persulfate, N-ethyl aniline and HCl concentrations. Poly(N-ethylaniline) content and conductivity of composite increased with increasing oxidant and monomer concentrations up to 0.1 M and 0.2 M, respectively, and decreased at higher concentrations. The maximum yield of polymer in the composite (15.0%) and the highest conductivity value of the composite (5.0×10-5 S/cm) was achieved by polymerization for 2 hours at 20°C in HCl of 0.5 M. The structure, morphological analyses and thermal behaviours of poly(N-ethylaniline)/kaolinite composite were characterized by FTIR and XRD spectroscopy, SEM and TGA techniques.

Keywords: kaolinite, poly(N-ethylaniline), conductive composite, chemical polymerization

Procedia PDF Downloads 292

Authors: Peng Liu, Chyng Wen Tee, Xiaofei Xu

Abstract:

This paper integrates machine learning forecasting techniques into the multi-period portfolio optimization framework, enabling dynamic asset allocation based on multiple future periods. We explore both theoretical foundations and practical applications, employing diverse machine learning models for return forecasting. This comprehensive guide demonstrates the superiority of multi-period optimization over single-period approaches, particularly in risk mitigation through strategic rebalancing and enhanced market trend forecasting. Our goal is to promote wider adoption of multi-period optimization, providing insights that can significantly enhance the decision-making capabilities of practitioners and researchers alike.

Keywords: multi-period portfolio optimization, look-ahead constrained optimization, machine learning, sequential decision making

Procedia PDF Downloads 48

Authors: F. Lazzeri, I. Reiter

Abstract:

Energy production optimization has been traditionally very important for utilities in order to improve resource consumption. However, load forecasting is a challenging task, as there are a large number of relevant variables that must be considered, and several strategies have been used to deal with this complex problem. This is especially true also in microgrids where many elements have to adjust their performance depending on the future generation and consumption conditions. The goal of this paper is to present a solution for short-term load forecasting in microgrids, based on three machine learning experiments developed in R and web services built and deployed with different components of Cortana Intelligence Suite: Azure Machine Learning, a fully managed cloud service that enables to easily build, deploy, and share predictive analytics solutions; SQL database, a Microsoft database service for app developers; and PowerBI, a suite of business analytics tools to analyze data and share insights. Our results show that Boosted Decision Tree and Fast Forest Quantile regression methods can be very useful to predict hourly short-term consumption in microgrids; moreover, we found that for these types of forecasting models, weather data (temperature, wind, humidity and dew point) can play a crucial role in improving the accuracy of the forecasting solution. Data cleaning and feature engineering methods performed in R and different types of machine learning algorithms (Boosted Decision Tree, Fast Forest Quantile and ARIMA) will be presented, and results and performance metrics discussed.

Keywords: time-series, features engineering methods for forecasting, energy demand forecasting, Azure Machine Learning

Procedia PDF Downloads 297

Authors: Navneetinder Singh, Harprabhjot Singh, Harpreet Singh, Supreet Singh

Abstract:

Many materials are known to mankind that is widely used for synthesis of corrosion resistant hydrophobic coatings. In the current work, novel hydrophobic composite was synthesized by mixing polytetrafluoroethylene (PTFE) and 20 weight% ceria particles followed by sintering. This composite had same hydrophobic behavior as PTFE. Moreover, composite showed better scratch resistance than virgin PTFE. Pits of plasma sprayed Ni₃Al coating were exploited to hold PTFE composite on the substrate as Superni-75 alloy surface through sintering process. Plasma sprayed surface showed good adhesion with the composite coating during scratch test. Potentiodynamic corrosion test showed 100 fold decreases in corrosion rate of coated sample this may be attributed to inert and hydrophobic nature of PTFE and ceria.

Keywords: polytetrafluoroethylene, PTFE, ceria, coating, corrosion

Procedia PDF Downloads 383

Authors: Fuchun Li, Hong Xiao

Abstract:

We propose a new early warning model for predicting financial stress events for a given future time. In this model, we examine whether credit conditions play an important role as a nonlinear propagator of shocks when predicting the likelihood of occurrence of financial stress events for a given future time. This propagation takes the form of a threshold regression in which a regime change occurs if credit conditions cross a critical threshold. Given the new early warning model for financial stress events, we evaluate the performance of this model and currently available alternatives, such as the model from signal extraction approach, and linear regression model. In-sample forecasting results indicate that the three types of models are useful tools for predicting financial stress events while none of them outperforms others across all criteria considered. The out-of-sample forecasting results suggest that the credit-regime switching model performs better than the two others across all criteria and all forecasting horizons considered.

Keywords: cut-off probability, early warning model, financial crisis, financial stress, regime-switching model, forecasting horizons

Procedia PDF Downloads 435

Authors: Suk-Hyun Yu, Heeyong Kwon

Abstract:

Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.

Keywords: artificial intelligence, air quality prediction, neural networks, pattern recognition, PM-10

Procedia PDF Downloads 232