Proposed Hybrid Methodology Research Articles

A Hybrid Optimization Approach for Autonomy Enhancement of Nearly-Zero-Energy Buildings Based on Battery Performance and Artificial Neural Networks

Reducing the primary energy consumption in buildings and simultaneously increasing self-consumption from renewable energy sources in nearly-zero-energy buildings, as per the 2010/31/EU directive, is crucial nowadays. This work solved the problem of nearly zeroing the net grid electrical energy in buildings in real time. This target was achieved using linear programming (LP)—a convex optimization technique leading to global solutions—to optimally decide the daily charging or discharging (dispatch) of the energy storage in an adaptive manner, in real time, and hence control and minimize both the import and export grid energies. LP was assisted by equally powerful methods, such as artificial neural networks (ANN) for forecasting the building’s load demand and photovoltaic (PV) on a 24 hour basis, and genetic algorithm (GA)—a heuristic optimization technique—for driving the optimum dispatch. Moreover, to address the non-linear nature of the battery and model the energy dispatch in a more realistic manner, the proven freeware system advisor model (SAM) of National Renewable Energy Laboratory (NREL) was integrated with the proposed approach to give the final dispatch. Assessing the case of a building, the results showed that the annual hourly profile of the import and export energies was smoothed and flattened, as compared to the cases without storage and/or using a conventional controller. With the proposed approach, the annual aggregated grid usage was reduced by 53% and the building’s annual energy needs were covered by the renewable energy system at a rate of 60%. It was therefore concluded that the proposed hybrid methodology can provide a tool to maximize the autonomy of nearly-zero-energy buildings and bring them a step closer to implementation.

Development of new hybrid model of discrete wavelet decomposition and autoregressive integrated moving average (ARIMA) models in application to one month forecast the casualties cases of COVID-19.

Everywhere around the globe, the hot topic of discussion today is the ongoing and fast-spreading coronavirus disease (COVID-19), which is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-COV-2). Earlier detected in Wuhan, Hubei province, in China in December 2019, the deadly virus engulfed China and some neighboring countries, which claimed thousands of lives in February 2020. The proposed hybrid methodology involves the application of discreet wavelet decomposition to the dataset of deaths due to COVID-19, which splits the input data into component series and then applying an appropriate econometric model to each of the component series for making predictions of death cases in future. ARIMA models are well known econometric forecasting models capable of generating accurate forecasts when applied on wavelet decomposed time series. The input dataset consists of daily death cases from most affected five countries by COVID-19, which is given to the hybrid model for validation and to make one month ahead prediction of death cases. These predictions are compared with that obtained from an ARIMA model to estimate the performance of prediction. The predictions indicate a sharp rise in death cases despite various precautionary measures taken by governments of these countries.

A novel hybrid artificial intelligence-based decision support framework to predict lead time

ABSTRACT Inventory and routing are the two most important elements to company’s survival in supply chain environments. Hence, solution approaches of inventory routing problem (IRP) should assure adequate inventory level and also provide an efficient route. In this case, hybrid approaches can empower researchers to solve the IRP. The aim of this study is to develop a new hybrid methodology that includes two phases to provide a generic framework for IRP. In Phase I, genetic algorithm-based simulation optimisation is used to dynamically perform inventory control and routing decisions. In Phase II, artificial intelligence (AI)-based simulation in which the lead time of supply chain members is predicted is employed to extend the functionality of the method in Phase I. The proposed hybrid methodology gives insights into the cross-fertilisation of AI, simulation, and optimisation for researchers. Therefore, this integration can be applied to different supply chain problems by using similar methods.

A Hybrid Numerical Methodology Based on CFD and Porous Medium for Thermal Performance Evaluation of Gas to Gas Micro Heat Exchanger.

In micro heat exchangers, due to the presence of distributing and collecting manifolds as well as hundreds of parallel microchannels, a complete conjugate heat transfer analysis requires a large amount of computational power. Therefore in this study, a novel methodology is developed to model the microchannels as a porous medium where a compressible gas is used as a working fluid. With the help of such a reduced model, a detailed flow analysis through individual microchannels can be avoided by studying the device as a whole at a considerably less computational cost. A micro heat exchanger with 133 parallel microchannels (average hydraulic diameter of m) in both cocurrent and counterflow configurations is investigated in the current study. Hot and cold streams are separated by a stainless-steel partition foil having a thickness of m. Microchannels have a rectangular cross section of m m with a wall thickness of m in between. As a first step, a numerical study for conjugate heat transfer analysis of microchannels only, without distributing and collecting manifolds is performed. Mass flow inside hot and cold fluid domains is increased such that inlet Reynolds number for both domains remains within the laminar regime. Inertial and viscous coefficients extracted from this study are then utilized to model pressure and temperature trends within the porous medium model. To cater for the density dependence of inertial and viscous coefficients due to the compressible nature of gas flow in microchannels, a modified formulation of Darcy–Forschheimer law is adopted. A complete model of a double layer micro heat exchanger with collecting and distributing manifolds where microchannels are modeled as the porous medium is finally developed and used to estimate the overall heat exchanger effectiveness of the investigated micro heat exchanger. A comparison of computational results using proposed hybrid methodology with previously published experimental results of the same micro heat exchanger showed that adopted methodology can predict the heat exchanger effectiveness within the experimental uncertainty for both cocurrent and counterflow configurations.

Optimal power flow studies in direct current grids: An application of the bio-inspired elephant swarm water search algorithm

Colombian power system is experienced important changes due to the large scale integration of renewable power generation based on solar and wind power; added to the fact that direct current networks have taken important attention, since they are efficient in terms of power loss and voltage profile at distribution or transmission levels For addressing this problem, this paper presents the application of an emerging bio-inspired metaheuristic optimization technique known as elephant swarm water search algorithm to the optimal power flow problem in direct current networks. A master-slave hybrid optimization strategy for optimal power flow analysis is addressed in this paper by decoupling this problem in two optimizing issues. The first problem corresponds to the selection of the power generated by all non-voltage controlled distributed generators; While the second problem lies in the solution of the classical power flow equations in direct current networks. The solution of the master problem (first problem) is made by applying the elephant swarm water search algorithm, while the second problem (slave problem) is solved by a conventional Gauss-Seidel numerical method. The proposed hybrid methodology allows solving the power flow problem by using any basic programming language with minimum computational effort and well-precision when is compared with optimizing packages such as general algebraic modeling system/CONOPT solver and conventional metaheuristic techniques such as genetic algorithms.

Modeling supplier selection in the era of Industry 4.0

PurposeThe problem of evaluating potential suppliers has always been based on finding an optimal tradeoff between supplier’s performance consistently meeting firms’ needs and acceptable cost. The purpose of this paper is to propose a hybrid multi-criteria decision framework to quantify this qualitative judgment and reduce ambiguity in selection of suppliers in the era of Industry 4.0.Design/methodology/approachA hybrid intuitionistic fuzzy entropy weight-based multi-criteria decision model with TOPSIS is proposed. The authors make use of the intuitionistic fuzzy weighted approach operator for aggregating individual decision maker’s opinions regarding each alternative over every criterion. Additionally, the authors employ the concept of Shannon’s entropy to calculate the criteria weights.FindingsResults obtained on the basis of the proposed hybrid methodology are analyzed against two more cases wherein the authors try to showcase the relevance of using IFS and entropy-based decision framework and find out the uniqueness of the proposed framework in supplier selection process.Practical implicationsThe proposed model is apposite to solve management problem of supplier selection in two ways: aggregating individual decision maker’s opinion for each of the predefined criteria along with individual decision maker’s importance and ranking the suppliers based on both positive and negative ideal solutions using TOPSIS.Originality/valueA robust framework incorporates not only suppliers’ performance but also provides weightage to key decision makers. Especially in the context of MCDMs wherein both qualitative and quantitative data is evaluated simultaneously, the proposed framework is unique in its practical implementation of reducing ambiguity in the supplier selection process.

The Implementation of a Hybrid Model for Hilly Sub-Watershed Prioritization Using Morphometric Variables: Case Study in India

Among several components of watershed prioritization, morphometric parameters are considered to be essential elements for appropriate water resource planning and management. In the current study, nine hilly sub-watersheds are prioritized using novel hybrid model based on morphometric variables analysis at Bino Watershed (BW) located in the upper Ramganga basin, India. The proposed model is based on the hybridization of principal component analysis (PCA) with weighted-sum approach (WSA), presenting a single-frame methodology (PCWSA) for sub-watershed prioritization. The prioritization process was conducted based on several morphometric parameters including linear, areal, and shape. The PCA was performed to identify the significant correlated factor-loading matrix whereas WSA was established to provide the weights for the morphometric parameters and fix their priority ranking (PR) to be categorized based on compound factor value. The findings showed that 37.81% of total area is under highly susceptible zone sub-watersheds (SW-6 and SW-7). This is verifying the necessity for appropriate soil and water conservation measures for the area. The proposed hybrid methodology demonstrated a reliable approach for water resource planning and management, agriculture, and irrigation activities in the study region.

Forecasting dengue epidemics using a hybrid methodology

Dengue case management is an alarmingly important global health issue. The effective allocation of resources is often difficult due to external and internal factors imposing nonlinear fluctuations in the prevalence of dengue fever. We aimed to construct an early-warning system that could accurately forecast subsequent dengue cases in three dengue endemic regions, namely San Juan, Iquitos, and the Philippines. The problem is solely regarded as a time series forecasting problem ignoring the known epidemiology of dengue fever as well as the other meteorological variables. Autoregressive integrated moving average (ARIMA) model is a popular classical time series model for linear data structures whereas with the advent of neural networks, nonlinear structures in the data set can be handled. In this paper, we propose a novel hybrid model combining ARIMA and neural network autoregressive (NNAR) model to capture both linearity and nonlinearity in the data sets. The ARIMA model filters out linear tendencies in the data and passes on the residual values to the NNAR model. The proposed hybrid approach is applied to three dengue time-series data sets and is found to give better forecasting accuracy in comparison to the state-of-the-art. The results of this study indicate that dengue cases can be accurately forecasted over a sufficient time period using the proposed hybrid methodology.

Reliability evaluation of power system incorporating wind farm for generation expansion planning based on ANLSA approach

AbstractReliability evaluation of power‐generating systems gives a mechanism to guarantee proper system operations in the face of different uncertainties including equipment failures. It is regularly not attainable to identify all possible failure states to figure the reliability indices because of the large number of system states engaged with system operations. Therefore, a hybrid optimization technique is required to analyse the reliability of the power system. This paper proposes a hybrid optimization technique to evaluate the reliability of a power system for the generation expansion planning incorporating wind energy source. The proposed hybrid methodology is the joined execution of both ant lion optimization algorithm (ALO) and lightning search algorithm (LSA), and it is named as ANLSA. ALO searching behavior is enhanced by LSA. Through the inherent convergence mechanisms, ANLSA search the meaningful system states. The most probable failure states contribute reliability indices of power generating system including mean down time (MDT), loss of load probability (LOLP), loss of load expectation (LOLE), loss of load frequency (LOLF), and expected demand not supplied (EDNS). Furthermore, ANLSA is utilized to assess the reliability of system under normal condition, integration of wind farm with capacity of 150 MW, and considering spinning reserve requirement (SRR). By then, the proposed work is actualized in MATLAB/Simulink platform and it is demonstrated on IEEE reliability test system (IEEE RTS‐79). Furthermore, the statistical analysis of proposed and existing techniques such as Monte Carlo simulation (MCS) and discrete convolution (DC) is considered. The comparison results demonstrate that proposed approach confirms its ability for evaluating the power system reliability.

Multi-objective-based robust unit commitment using hydro-thermal-wind: a hybrid technique

PurposeThe purpose of this paper is to solve economic emission dispatch problem in connection of wind with hydro-thermal units.Design/methodology/approachThe proposed hybrid methodology is the joined execution of both the modified salp swarm optimization algorithm (MSSA) with artificial intelligence technique aided with particle swarm optimization (PSO) technique.FindingsThe proposed approach is introduced to figure out the optimal power generated power from the thermal, wind farms and hydro units by minimizing the emission level and cost of generation simultaneously. The best compromise solution of the generation power outputs and related gas emission are subject to the equality and inequality constraints of the system. Here, MSSA is used to generate the optimal combination of thermal generator with the objective of minimum fuel and emission objective function. The proposed method also considers wind speed probability factor via PSO-artificial neural network (ANN) technique and hydro power generation at peak load demand condition to ensure economic utilization.Originality/valueTo validate the advantage of the proposed approach, six- and ten-units thermal systems are studied with fuel and emission cost. For minimizing the fuel and emission cost of the thermal system with the predicted wind speed factor, the proposed approach is used. The proposed approach is actualized in MATLAB/Simulink, and the results are examined with considering generation units and compared with various solution techniques. The comparison reveals the closeness of the proposed approach and proclaims its capability for handling multi-objective optimization problems of power systems.

A hybrid method based on neural network and improved environmental adaptation method using Controlled Gaussian Mutation with real parameter for short-term load forecasting

Abstract Load forecasting is a challenging task in power markets that require attention in generating accurate and stable load to deal with planning and management strategies. In past few years, several intelligence-based models have been introduced for precise load forecast. Among them, artificial neural network (ANN) seems more effective and capable to handle the non-linear behavior of load and generates an accurate forecast. However, it suffers from overfitting problem thus reducing the accuracy of load forecasts. To overcome this problem, a hybrid methodology namely ANN-IEAMCGM-R, for short-term load forecast is proposed in this paper. ANN is integrated with an enhanced evolutionary algorithm (IEAMCGM-R) to find optimal network weights. This evolutionary algorithm is composed of improved environmental adaptation method with real parameters (IEAM-R) and our proposed Controlled Gaussian Mutation (CGM) method to bring greater diversity within the population resulting in a higher convergence of solutions. The electric load data from the New England Power Pool (NEPOOL, ISO New England) and Australian Energy Market Operator (New South Wales (NSW), Australia) have been used to illustrate the efficacy of the proposed hybrid methodology. Results show that the proposed hybrid methodology generates higher accuracy than other state-of-the-art algorithms.

Reconstruction of gene regulatory networks using S-system with a genetic algorithm and flower pollination algorithm hybrid

Accurate reconstruction of gene regulatory networks from time-series gene expression data is a significant challenge for computer scientists. In this paper, we have proposed a genetic algorithm and flower pollination algorithm hybrid for the reverse engineering of gene regulatory network based on decoupled S-systems. Here, genetic algorithm has been used to select the best combination of genes, which act as regulators in the network. Flower pollination algorithm has been used to calculate the best possible S-system parameters for which the training error is minimal for those regulators. The proposed method has been tested on small-scale and medium-scale; synthetic benchmark networks and in-slico benchmark networks extracted from the GeneNetWeaver database, as well as the real-world experimental datasets of the yeast IMRA and DNA SOS repair network of Escherichia coli. The experiments reveal that the proposed hybrid methodology is capable of inferring gene regulatory networks more accurately with lesser training data and in lesser computational time compared to other existing methods.

Carbon pricing prediction based on wavelet transform and K-ELM optimized by bat optimization algorithm in China ETS: the case of Shanghai and Hubei carbon markets

Carbon pricing is regarded as a crucial enabler for an accelerated low-carbon energy economy transformation to achieve temperature control targets. This paper studies carbon price forecasting considering historical carbon price series as an influencing factor. A hybrid model of a kernel-based extreme learning machine (KELM) optimized by the bat optimization algorithm based on wavelet transform is proposed. Firstly, the wavelet transform is used to eliminate the high-frequency components of the previous day’s carbon price data to improve the accuracy of prediction. Then, the partial auto-correlation function (PACF) is applied to analyse the correlation among historical carbon prices to select the inputs for the forecasting model. Additionally, adding a kernel function improves to some extent the fitting accuracy and stability of the traditional extreme learning machine. Finally, the parameters of the KELM model are optimized by the bat optimization algorithm. Two types of carbon prices in the China ETS were used to examine the forecasting ability of the proposed hybrid methodology. The empirical results show that the proposed hybrid methodology is more robust than other comparison models for carbon price forecasting.

Optimal siting of electric vehicle charging stations: A GIS-based fuzzy Multi-Criteria Decision Analysis

Electric vehicles (EVs) are both economic and ecological vehicles which get their power from rechargeable batteries inside the car. Since they have a lot advantages as producing nearly no carbon emissions or pollution, being cost effective and less noisy; the main disadvantage of these vehicles are recharge related problems. One approach to deal with this problem is to construct electric vehicle charging stations (EVCS). A proper EVCS also should be located very carefully to maximize EV usage. Thus in this paper a geographic information system (GIS)-based MCDA approach is applied to address the EVCS site selection. Fuzzy analytical hierarchy process (AHP) and technique for order preference by similarity to ideal solution (TOPSIS) methods are applied to choose the optimal EVCS sites. A four-step solution approach is developed for the problem: (i) determination of 15 criteria from different perspectives, (ii) using GIS to assign EVCS site availability score, (iii) prioritizing the criteria using fuzzy AHP and finally (iv) ranking the potential sites by using TOPSIS. Proposed hybrid methodology is applied to Ankara (capital city of Turkey) as a case study. Results show that suggested alternative locations outperform the current locations of 12 EVCS in terms of considered criteria.

Integration of Z-numbers and Bayesian decision theory: A hybrid approach to decision making under uncertainty and imprecision

For over four decades decision support systems have been emerging to facilitate decision making under uncertain conditions and in a rapidly changing unstructured environment. Most decision support approaches, such as Bayesian decision theory and computing with words (CW), compare and analyze the consequences of different decision alternatives. Bayesian decision methods use probability theory to handle uncertainty and have been widely used in different areas for estimation and prediction as well as offering decision support. On the other hand, computing with words and approximate reasoning apply fuzzy set theory to deal with imprecise measurements and inexact information and are most concerned with propositions stated in natural language. The concept of a Z-number [1] has been recently introduced to represent propositions and their reliability in natural language. This work proposes a methodology that integrates Z-numbers and Bayesian decision theory to provide decision support when precise measurements and exact values of parameters and probabilities are not available. The relationships and computing methods required for such integration are derived and mathematically proved. The proposed hybrid methodology benefits from both approaches and provides a decision support system based on imprecise and uncertain information drawn from natural language. In order to demonstrate the proof of concept, the proposed methodology has been applied to a realistic case study on breast cancer diagnosis.

Grey relational analysis-based genetic algorithm optimization of electrical discharge drilling of Nimonic-90 superalloy

Nickel-based superalloys are being increasingly used in aerospace, automotive industries due to their excellent thermo-mechanical properties. These applications require complex shapes and profiles which may not be obtained by conventional machining processes. These materials are also known as difficult-to-machine due to their excellent thermo-mechanical properties. The electrical discharge drilling proves its suitability in the precision drilling of superalloys. During, the electrical discharge drilling of these materials, hole taper, hole circularity and hole dilation are key attributes which influence the drilled hole quality. In this research paper, the experiments have been conducted by L27 orthogonal array and this experimental data have been utilized for developing the models of different geometrical quality characteristics such as hole circularity, hole taper and hole dilation. Further, a new hybrid approach grey relational analysis-based genetic algorithm has been proposed and implemented for the multi-objective optimization of different quality characteristics. The effects of different process parameters on various geometrical quality characteristics have also been discussed. Finally, the confirmation tests have been performed to validate the predicted results obtained by the proposed hybrid methodology to the experimental results. It has been observed by the comparison results that the machining performance in the electrical discharge drilling process has been remarkably improved through proposed approach.

Geometrical quality evaluation in laser cutting of Inconel-718 sheet by using Taguchi based regression analysis and particle swarm optimization

The Inconel-718 is one of the most demanding advanced engineering materials because of its superior quality. The conventional machining techniques are facing many problems to cut intricate profiles on these materials due to its minimum thermal conductivity, minimum elastic property and maximum chemical affinity at magnified temperature. The laser beam cutting is one of the advanced cutting method that may be used to achieve the geometrical accuracy with more precision by the suitable management of input process parameters. In this research work, the experimental investigation during the pulsed Nd:YAG laser cutting of Inconel-718 has been carried out. The experiments have been conducted by using the well planned orthogonal array L27. The experimentally measured values of different quality characteristics have been used for developing the second order regression models of bottom kerf deviation (KD), bottom kerf width (KW) and kerf taper (KT). The developed models of different quality characteristics have been utilized as a quality function for single–objective optimization by using particle swarm optimization (PSO) method. The optimum results obtained by the proposed hybrid methodology have been compared with experimental results. The comparison of optimized results with the experimental results shows that an individual improvement of 75%, 12.67% and 33.70% in bottom kerf deviation, bottom kerf width, and kerf taper has been observed. The parametric effects of different most significant input process parameters on quality characteristics have also been discussed.

Multi-Response Optimization of Al2024/red mud MMC using Hybrid Taguchi-GRA-Entropy Optimization Technique

In this paper multi-response optimization of the stir casting process has been carried using the hybrid Taguchi-GRA-Entropy methodology. Al2024/red mud composite is prepared with the help of two-step stir casting process under the influence of argon gas. Taguchi’s design of experiment is utilized for conducting the experiments. The process parameters under investigation are reinforcement percentage, grain size and blade angle which are varied at three levels and their effect on the response variables such as tensile strength and microhardness are studied. Grey relational analysis is used to derive the grey relational coefficients and Entropy method is used to establish the weights of the individual quality characteristics. Grey relational grades are calculated which act as a single response to the multi-response optimization problem which are analyzed using the Taguchi method in order to identify the optimum conditions of the process parameters. Using ANOVA contribution of process parameters on the grey relational grades are evaluated. Confirmatory experiments are performed which showcases that the proposed hybrid methodology can be successfully applied for enhancing the performance of the stir casting process.

Adaptive neuro-fuzzy inference system for classification of mammographic image using electromagnetism-like optimisation

Breast cancer diagnosis system plays a vital role in medical field. This system helps the doctors to diagnose in much more efficient way. Breast cancer is a very common class of cancer among women. This paper mainly focuses on breast cancer recurrence problem, hybridising two methodologies; Electro-Magnetism-like Optimisation (EMO) and Adaptive Neuro-Fuzzy Inference System (ANFIS), to develop a good diagnosis system. EMO has been used as a multilevel segmentation algorithm which can effectively identify the threshold values of a digital image within the reduced number of iterations and decreasing the computational complexity. Original proposals show better results in diagnosing cancer affected cells to find the best features, whilst ANFIS algorithm is used as a classifier. ANFIS model combines the neural network adaptive capabilities and the fuzzy logic qualitative approach. The robustness of the proposed hybrid methodology is examined using classification accuracy, sensitivity, and specificity.

Adaptive neuro-fuzzy inference system for classification of mammographic image using electromagnetism-like optimisation

Breast cancer diagnosis system plays a vital role in medical field. This system helps the doctors to diagnose in much more efficient way. Breast cancer is a very common class of cancer among women. This paper mainly focuses on breast cancer recurrence problem, hybridising two methodologies; Electro-Magnetism-like Optimisation (EMO) and Adaptive Neuro-Fuzzy Inference System (ANFIS), to develop a good diagnosis system. EMO has been used as a multilevel segmentation algorithm which can effectively identify the threshold values of a digital image within the reduced number of iterations and decreasing the computational complexity. Original proposals show better results in diagnosing cancer affected cells to find the best features, whilst ANFIS algorithm is used as a classifier. ANFIS model combines the neural network adaptive capabilities and the fuzzy logic qualitative approach. The robustness of the proposed hybrid methodology is examined using classification accuracy, sensitivity, and specificity.