Pub Date : 2023-05-07DOI: 10.1080/23080477.2023.2208398
Ashokkumar Parmar, P. Darji
ABSTRACT Supply-and-demand-side resource management and demand-side load management (DSLM) are important techniques for addressing power system uncertainties. Demand-side load management allows the load profile to be reshaped to reduce the peak demand and overall cost. Many demand-side load management problems have been solved using different demand response programmesprograms as well as conventional numeric and metaheuristic methods. However, it can be applied only toonly to a limited number of devices of certain types. Of the six direct load control demand response techniques for demand-side load management, the performance of the day-ahead load-shifting and flexible load curve DSLM techniques are compared in this study. These techniques can be used for a larger number of devices of more types. The demand-side load management problem is formulated as a minimization problem to achieve peak demand reduction and cost minimization. Novel metaheuristic optimizers are used to perform demand-side load management, and comparative analysis is conducted for the cost and peak load reduction. The simulation results are verified using the fmincon function of MATLAB. The simulation results indicate that the aforementioned algorithms can be applied to a larger number of devices of more types to achieve considerable savings by minimizing the cost and peak load demand. Moreover, the load-shifting demand-side load management technique is more beneficial from the system operator’s perspective than from the customer’s perspective. In contrast, the flexible load curve demand-side load management technique is more beneficial from the customer’s perspective. GRAPHICAL ABSTRACT
{"title":"Novel Metaheuristic Optimizers Based Load Shifting and Flexible Load Curve Techniques for Demand-side Load Management","authors":"Ashokkumar Parmar, P. Darji","doi":"10.1080/23080477.2023.2208398","DOIUrl":"https://doi.org/10.1080/23080477.2023.2208398","url":null,"abstract":"ABSTRACT Supply-and-demand-side resource management and demand-side load management (DSLM) are important techniques for addressing power system uncertainties. Demand-side load management allows the load profile to be reshaped to reduce the peak demand and overall cost. Many demand-side load management problems have been solved using different demand response programmesprograms as well as conventional numeric and metaheuristic methods. However, it can be applied only toonly to a limited number of devices of certain types. Of the six direct load control demand response techniques for demand-side load management, the performance of the day-ahead load-shifting and flexible load curve DSLM techniques are compared in this study. These techniques can be used for a larger number of devices of more types. The demand-side load management problem is formulated as a minimization problem to achieve peak demand reduction and cost minimization. Novel metaheuristic optimizers are used to perform demand-side load management, and comparative analysis is conducted for the cost and peak load reduction. The simulation results are verified using the fmincon function of MATLAB. The simulation results indicate that the aforementioned algorithms can be applied to a larger number of devices of more types to achieve considerable savings by minimizing the cost and peak load demand. Moreover, the load-shifting demand-side load management technique is more beneficial from the system operator’s perspective than from the customer’s perspective. In contrast, the flexible load curve demand-side load management technique is more beneficial from the customer’s perspective. GRAPHICAL ABSTRACT","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"538 - 567"},"PeriodicalIF":2.3,"publicationDate":"2023-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42365667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-29DOI: 10.1080/23080477.2023.2194765
P. Ramesh, Shanthi Veerappapillai
ABSTRACT Machine learning (ML) has been applied recently to develop prognostic classification models that can be used in individual cancer patients to forecast outcomes. Here, four different ML algorithms were built to predict survival rate of lung cancer patients using 1600 metadata records. Of note, the generated models were validated using test set and external validation data set consisting of 400 patient records each together with 10-fold cross-validation technique. The extratree classifier algorithm was employed to identify the influential descriptors for patients survival after incidence of metachronous second primary lung cancer. The models were assessed using five different performance metrices. The results from our study highlight that logistic regression model with all features and important features achieved an accuracy of 94% and 96%, respectively, for stratifying the survival status of lung cancer patients. On the other hand, logistic regression also outperformed external validation with an accuracy of 85%. Indeed, the results from our study will provide meaningful insights for the treatment and management of large community of lung cancer patients.
{"title":"Prediction and validation of survival rate of metachronous second primary lung cancer patients using machine learning classifiers","authors":"P. Ramesh, Shanthi Veerappapillai","doi":"10.1080/23080477.2023.2194765","DOIUrl":"https://doi.org/10.1080/23080477.2023.2194765","url":null,"abstract":"ABSTRACT Machine learning (ML) has been applied recently to develop prognostic classification models that can be used in individual cancer patients to forecast outcomes. Here, four different ML algorithms were built to predict survival rate of lung cancer patients using 1600 metadata records. Of note, the generated models were validated using test set and external validation data set consisting of 400 patient records each together with 10-fold cross-validation technique. The extratree classifier algorithm was employed to identify the influential descriptors for patients survival after incidence of metachronous second primary lung cancer. The models were assessed using five different performance metrices. The results from our study highlight that logistic regression model with all features and important features achieved an accuracy of 94% and 96%, respectively, for stratifying the survival status of lung cancer patients. On the other hand, logistic regression also outperformed external validation with an accuracy of 85%. Indeed, the results from our study will provide meaningful insights for the treatment and management of large community of lung cancer patients.","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"395 - 407"},"PeriodicalIF":2.3,"publicationDate":"2023-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42505454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-20DOI: 10.1080/23080477.2023.2189628
Prince Kumar, K. Kumar, Aashish Kumar Bohre, Nabanita Adhikary
ABSTRACT Increased innovation and automation for higher comfort level of living beings have stressed power sector for more units of power to be generated and supplied. To meet this demand, several generating stations are needed to be connected to supply this enormous load to end consumers. While interconnecting generated power of multi-area system, several problems are being encountered. In the current proposed work, 2-area interconnected power system has been considered and automatic generation control problem for single area loading and multi-area multi-type loading has been solved with the help of intelligent control strategy using TLBO algorithm. The proposed work has been processed and simulated in MATLAB and SIMULINK environment. Three types of loadings are considered in the proposed work. First one is single area fixed loading, second one is both area loading with different fixed load, and third one is increasing type load for fixed duration of time in single area. Based on the nature of severity of disturbances in power network, a fitness function has been designed for these multi-type of loadings to improve its transient response to avoid failure of synchronism and improve resiliency of power network to supply uninterrupted power to end consumers.
{"title":"Intelligent priority based generation control for multi area system","authors":"Prince Kumar, K. Kumar, Aashish Kumar Bohre, Nabanita Adhikary","doi":"10.1080/23080477.2023.2189628","DOIUrl":"https://doi.org/10.1080/23080477.2023.2189628","url":null,"abstract":"ABSTRACT Increased innovation and automation for higher comfort level of living beings have stressed power sector for more units of power to be generated and supplied. To meet this demand, several generating stations are needed to be connected to supply this enormous load to end consumers. While interconnecting generated power of multi-area system, several problems are being encountered. In the current proposed work, 2-area interconnected power system has been considered and automatic generation control problem for single area loading and multi-area multi-type loading has been solved with the help of intelligent control strategy using TLBO algorithm. The proposed work has been processed and simulated in MATLAB and SIMULINK environment. Three types of loadings are considered in the proposed work. First one is single area fixed loading, second one is both area loading with different fixed load, and third one is increasing type load for fixed duration of time in single area. Based on the nature of severity of disturbances in power network, a fitness function has been designed for these multi-type of loadings to improve its transient response to avoid failure of synchronism and improve resiliency of power network to supply uninterrupted power to end consumers.","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"424 - 433"},"PeriodicalIF":2.3,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47986217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-19DOI: 10.1080/23080477.2023.2191498
Parvez Ahmad, N. Choudhary, Nitin Singh, A. K. Singh
ABSTRACT The increasing penetration level of electric vehicles (EVs) shows that they will enter into the category of distributed energy sources in the near future. Major upgradation is required in the conventional power system to handle upcoming challenges due to electrification in the transportation sector and generate opportunities for the power system. The energy storage capability of batteries and advancement in fast switching converters enable EVs to support the grid with different ancillary services, e.g. primary frequency control (PFC). However, an effective charging strategy/controller is required to support the grid with PFC without violating constraints from grid and EVs. This paper proposes a novel fuzzy-based controller to decide EV’s availability for PFC with an optimized participation level considering different operational modes and EV charging demand. The controller computes the participation level of EVs based on real-time inputs from EVs, magnitude of frequency deviation and availability of primary reserve. The Spanish power system model has been employed to show the proposed controller’s efficacy and compare it with other recently reported controllers. The MATLAB/Simulink platform has been used to perform frequency and power response analysis for four different defined cases. Results show that EVs with the proposed fuzzy-based controller can effectively support the grid with PFC service without violating the grid’s and EV’s limits. GRAPHICAL ABSTRACT
{"title":"Primary frequency control by fuzzy-based participation controller for plug-in electric vehicles","authors":"Parvez Ahmad, N. Choudhary, Nitin Singh, A. K. Singh","doi":"10.1080/23080477.2023.2191498","DOIUrl":"https://doi.org/10.1080/23080477.2023.2191498","url":null,"abstract":"ABSTRACT The increasing penetration level of electric vehicles (EVs) shows that they will enter into the category of distributed energy sources in the near future. Major upgradation is required in the conventional power system to handle upcoming challenges due to electrification in the transportation sector and generate opportunities for the power system. The energy storage capability of batteries and advancement in fast switching converters enable EVs to support the grid with different ancillary services, e.g. primary frequency control (PFC). However, an effective charging strategy/controller is required to support the grid with PFC without violating constraints from grid and EVs. This paper proposes a novel fuzzy-based controller to decide EV’s availability for PFC with an optimized participation level considering different operational modes and EV charging demand. The controller computes the participation level of EVs based on real-time inputs from EVs, magnitude of frequency deviation and availability of primary reserve. The Spanish power system model has been employed to show the proposed controller’s efficacy and compare it with other recently reported controllers. The MATLAB/Simulink platform has been used to perform frequency and power response analysis for four different defined cases. Results show that EVs with the proposed fuzzy-based controller can effectively support the grid with PFC service without violating the grid’s and EV’s limits. GRAPHICAL ABSTRACT","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"447 - 459"},"PeriodicalIF":2.3,"publicationDate":"2023-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45604957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-16DOI: 10.1080/23080477.2023.2191496
Ramya Krishna Nakkala, Balaji Maddiboyina, Shanmukha Chakravarthi Bolisetti, Harekrishna Roy
ABSTRACT The primary purpose of this study is to develop and evaluate an effective and reliable delayed-release dosage form of Duloxetine hydrochloride enteric-coated pellets in capsules. Duloxetine hydrochloride dissolves in an acidic environment, yet pellets maintain their enteric coating due to the Wurster expansion process for the Fluidized Bed Processor. Four distinct layers comprise enteric-coated pellets: a pharmaceutical layer, a barrier layer, an enteric layer, and a coating on the inert core pellets. A suspension layering approach protects the acidic environment from the drug by coating it with an enteric layer composed of hydroxyl propyl methyl cellulose phthalate HP55. We also determined the bulk and tapped densities, Hausner’s ratio, compressibility index, and moisture content of all formulations. The produced pellets are being evaluated for in-vitro release tests using UV-Visible spectroscopy. The zero-order model, the first-order model, and Higuchi’s square root equation, Hixson-Crowell, Korsemeyer peppas, and the Weibull model were used to evaluate the released kinetics models. Investigations using FT-IR (infrared spectroscopy) are still being undertaken to determine the drug’s compatibility with various excipients. Formulation ‘F7’ exhibited highest similarity factor of 56.1. Stability tests conducted over a three-month period under accelerated settings established that the optimized formulation is stable. GRAPHICAL ABSTRACT
{"title":"Duloxetine hydrochloride enteric-coated pellets in capsules with delayed release: formulation and evaluation","authors":"Ramya Krishna Nakkala, Balaji Maddiboyina, Shanmukha Chakravarthi Bolisetti, Harekrishna Roy","doi":"10.1080/23080477.2023.2191496","DOIUrl":"https://doi.org/10.1080/23080477.2023.2191496","url":null,"abstract":"ABSTRACT The primary purpose of this study is to develop and evaluate an effective and reliable delayed-release dosage form of Duloxetine hydrochloride enteric-coated pellets in capsules. Duloxetine hydrochloride dissolves in an acidic environment, yet pellets maintain their enteric coating due to the Wurster expansion process for the Fluidized Bed Processor. Four distinct layers comprise enteric-coated pellets: a pharmaceutical layer, a barrier layer, an enteric layer, and a coating on the inert core pellets. A suspension layering approach protects the acidic environment from the drug by coating it with an enteric layer composed of hydroxyl propyl methyl cellulose phthalate HP55. We also determined the bulk and tapped densities, Hausner’s ratio, compressibility index, and moisture content of all formulations. The produced pellets are being evaluated for in-vitro release tests using UV-Visible spectroscopy. The zero-order model, the first-order model, and Higuchi’s square root equation, Hixson-Crowell, Korsemeyer peppas, and the Weibull model were used to evaluate the released kinetics models. Investigations using FT-IR (infrared spectroscopy) are still being undertaken to determine the drug’s compatibility with various excipients. Formulation ‘F7’ exhibited highest similarity factor of 56.1. Stability tests conducted over a three-month period under accelerated settings established that the optimized formulation is stable. GRAPHICAL ABSTRACT","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"434 - 446"},"PeriodicalIF":2.3,"publicationDate":"2023-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43838218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-09DOI: 10.1080/23080477.2023.2187528
Abebaw Degu Workneh, Maha Gmira
ABSTRACT The stochasticity and randomly changing nature of the production environment posed a significant challenge in developing real-time responsive scheduling solutions. Many previous scheduling solutions assumed static environments, user-anticipated, and hand-crafted dynamic scenarios. However, real-world production environment events are random and unpredictable. This study considers Job Shop Scheduling Problem (JSSP) as an iterative decision-making problem, and Deep Reinforcement Learning (DRL)-based solution is designed to address these challenges. A deep neural network is utilized for function approximation, and the input feature vectors are extracted iteratively to be used in the sequential decision-making process. The production states are expressed with randomly changing feature vectors of each job’s operations and the corresponding machines. This work proposes Double Deep Q Network (DDQN) methods to train the model. Results are evaluated on the renowned OR-Library benchmark problems. The evaluation result indicates that the proposed approach is comparative in benchmark problems, and the scheduling agent can get good results in unseen instances with an average of 94.86% of the scheduling score. Graphical abstract
{"title":"Learning to schedule (L2S): adaptive job shop scheduling using double deep Q network","authors":"Abebaw Degu Workneh, Maha Gmira","doi":"10.1080/23080477.2023.2187528","DOIUrl":"https://doi.org/10.1080/23080477.2023.2187528","url":null,"abstract":"ABSTRACT The stochasticity and randomly changing nature of the production environment posed a significant challenge in developing real-time responsive scheduling solutions. Many previous scheduling solutions assumed static environments, user-anticipated, and hand-crafted dynamic scenarios. However, real-world production environment events are random and unpredictable. This study considers Job Shop Scheduling Problem (JSSP) as an iterative decision-making problem, and Deep Reinforcement Learning (DRL)-based solution is designed to address these challenges. A deep neural network is utilized for function approximation, and the input feature vectors are extracted iteratively to be used in the sequential decision-making process. The production states are expressed with randomly changing feature vectors of each job’s operations and the corresponding machines. This work proposes Double Deep Q Network (DDQN) methods to train the model. Results are evaluated on the renowned OR-Library benchmark problems. The evaluation result indicates that the proposed approach is comparative in benchmark problems, and the scheduling agent can get good results in unseen instances with an average of 94.86% of the scheduling score. Graphical abstract","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"409 - 423"},"PeriodicalIF":2.3,"publicationDate":"2023-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45165694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-20DOI: 10.1080/23080477.2023.2172706
Komal Agrawal, R. Negi, V. C. Pal, Nehal Srivastava
ABSTRACT In this digital era, the basis of every smart instrument is discrete signal models e.g. in Networked control systems, Cyber physical systems etc. It has been shown that time-delays are unavoidable during the digital implementation of an engineering system. Therefore, the stabilization of discrete time delayed systems is gaining the high importance [1–10]. Although a lot of literature is found on the stabilization of time delayed systems for a long time using the construction of proper non-negative Lyapunov functional. Recalling some existing results on this issue, the LMI-based stability conditions are obtained by its forward difference negative-definite in direction to claim the less conservative results [15–25]. In order to seek less conservative stability criteria, this paper introduces an anti-windup scheme appended with Wirtinger inequality, reciprocal convex approach and delay partitioning of a discrete-time delayed systems by using Lyapunov Krasovskii functional. To accomplish this task, delay partitioning technique may be utilized to develop improved stability conditions for the considered system. The Wirtinger-based inequality and reciprocal convex approach has been employed to derive less conservative results. On employing the delay partitioning, a novel linear matrix inequality-based criterion is proposed to stabilize such systems. The considered Lyapunov-Krasovskii functional includes the information of intermediate delay to acknowledge the delay information implicitly that ensures the considered system to be regular, impulse free and stable in terms of linear matrix inequalities. The estimation of the attraction basin is to ensure that the state remains inside the level set of a certain Lyapunov function. Numerical simulation verifies that the presented method reduces conservatism than the existing results.
{"title":"Delay partitioning approach to the delay-dependent stability of discrete-time systems with anti-windup","authors":"Komal Agrawal, R. Negi, V. C. Pal, Nehal Srivastava","doi":"10.1080/23080477.2023.2172706","DOIUrl":"https://doi.org/10.1080/23080477.2023.2172706","url":null,"abstract":"ABSTRACT In this digital era, the basis of every smart instrument is discrete signal models e.g. in Networked control systems, Cyber physical systems etc. It has been shown that time-delays are unavoidable during the digital implementation of an engineering system. Therefore, the stabilization of discrete time delayed systems is gaining the high importance [1–10]. Although a lot of literature is found on the stabilization of time delayed systems for a long time using the construction of proper non-negative Lyapunov functional. Recalling some existing results on this issue, the LMI-based stability conditions are obtained by its forward difference negative-definite in direction to claim the less conservative results [15–25]. In order to seek less conservative stability criteria, this paper introduces an anti-windup scheme appended with Wirtinger inequality, reciprocal convex approach and delay partitioning of a discrete-time delayed systems by using Lyapunov Krasovskii functional. To accomplish this task, delay partitioning technique may be utilized to develop improved stability conditions for the considered system. The Wirtinger-based inequality and reciprocal convex approach has been employed to derive less conservative results. On employing the delay partitioning, a novel linear matrix inequality-based criterion is proposed to stabilize such systems. The considered Lyapunov-Krasovskii functional includes the information of intermediate delay to acknowledge the delay information implicitly that ensures the considered system to be regular, impulse free and stable in terms of linear matrix inequalities. The estimation of the attraction basin is to ensure that the state remains inside the level set of a certain Lyapunov function. Numerical simulation verifies that the presented method reduces conservatism than the existing results.","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"583 - 604"},"PeriodicalIF":2.3,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48396834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-20DOI: 10.1080/23080477.2023.2176749
Foad Esmaeili, Fereshteh Mafakheri, F. Nasiri
ABSTRACT Biomass sources have the potential to mitigate carbon emissions as a renewable source while reducing waste and residues. Seasonality and disruption risks are some of the disadvantages of biomass resources requiring that biomass supply chains be managed such that to withstand disruptions. There has been very limited research on integrating predictions for smart management on supply or demand sides of biomass supply chains. In this study, a number of predictive models are investigated for building energy demand and biomass stock availability subject to forecasts of weather conditions. On that basis, an allocation algorithm is proposed for optimal collection and logistics of biomass from land to depots. Accordingly, Google Maps API will be used to identify the best distribution routes for delivering biomass from depots to end-users. A case study with real (supply and demand) data is considered. The proposed integrated data-driven approach aims at improving the accuracy of biomass supply and demand predictions and coordinating these predictions to enhance the resiliency of bioenergy supply chain routing decisions. Graphical Abstract
{"title":"Biomass supply chain resilience: integrating demand and availability predictions into routing decisions using machine learning","authors":"Foad Esmaeili, Fereshteh Mafakheri, F. Nasiri","doi":"10.1080/23080477.2023.2176749","DOIUrl":"https://doi.org/10.1080/23080477.2023.2176749","url":null,"abstract":"ABSTRACT Biomass sources have the potential to mitigate carbon emissions as a renewable source while reducing waste and residues. Seasonality and disruption risks are some of the disadvantages of biomass resources requiring that biomass supply chains be managed such that to withstand disruptions. There has been very limited research on integrating predictions for smart management on supply or demand sides of biomass supply chains. In this study, a number of predictive models are investigated for building energy demand and biomass stock availability subject to forecasts of weather conditions. On that basis, an allocation algorithm is proposed for optimal collection and logistics of biomass from land to depots. Accordingly, Google Maps API will be used to identify the best distribution routes for delivering biomass from depots to end-users. A case study with real (supply and demand) data is considered. The proposed integrated data-driven approach aims at improving the accuracy of biomass supply and demand predictions and coordinating these predictions to enhance the resiliency of bioenergy supply chain routing decisions. Graphical Abstract","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"293 - 317"},"PeriodicalIF":2.3,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45715243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-07DOI: 10.1080/23080477.2023.2171696
T. M. Dao, Truong Hoang Bao Huy, Duy-Phuong N. Do, Dieu Ngoc Vo
ABSTRACT Optimal power flow (OPF) is one of the common problems in power systems. In general, the branch resistance of the system is assumed to be constant with respect to temperature variation in conventional optimal power flow. However, the temperature correlation of the branch resistance should be taken into account to enhance the accurate calculation of the power flow and branch losses. This paper suggests a new and efficient method, which is chaotic equilibrium optimization (CEO) to deal with the temperature-dependent optimal power flow (TDOPF) problem. The CEO is validated on IEEE 30-bus and 118-bus networks with different objective functions, including generating fuel cost, total active power losses, voltage profile enhancement, voltage stability improvement, and emission reduction. Furthermore, the temperature effect on the TDOPF problem is also analyzed. In the case of fuel cost optimization in the 30-bus network, fuel cost increases from 799.85 $/h to 802.9474 $/h when the temperature increases from 0°C to 100°C, corresponding to a fuel cost increase of 0.04% for each 10°C. From the obtained outcomes, the efficacy of the CEO has been proven in finding accurate solutions for the TDOPF problem. GRAPHICAL ABSTRACT
{"title":"A chaotic equilibrium optimization for temperature-dependent optimal power flow","authors":"T. M. Dao, Truong Hoang Bao Huy, Duy-Phuong N. Do, Dieu Ngoc Vo","doi":"10.1080/23080477.2023.2171696","DOIUrl":"https://doi.org/10.1080/23080477.2023.2171696","url":null,"abstract":"ABSTRACT Optimal power flow (OPF) is one of the common problems in power systems. In general, the branch resistance of the system is assumed to be constant with respect to temperature variation in conventional optimal power flow. However, the temperature correlation of the branch resistance should be taken into account to enhance the accurate calculation of the power flow and branch losses. This paper suggests a new and efficient method, which is chaotic equilibrium optimization (CEO) to deal with the temperature-dependent optimal power flow (TDOPF) problem. The CEO is validated on IEEE 30-bus and 118-bus networks with different objective functions, including generating fuel cost, total active power losses, voltage profile enhancement, voltage stability improvement, and emission reduction. Furthermore, the temperature effect on the TDOPF problem is also analyzed. In the case of fuel cost optimization in the 30-bus network, fuel cost increases from 799.85 $/h to 802.9474 $/h when the temperature increases from 0°C to 100°C, corresponding to a fuel cost increase of 0.04% for each 10°C. From the obtained outcomes, the efficacy of the CEO has been proven in finding accurate solutions for the TDOPF problem. GRAPHICAL ABSTRACT","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"380 - 394"},"PeriodicalIF":2.3,"publicationDate":"2023-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44617580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-06DOI: 10.1080/23080477.2022.2152933
J. Manokaran, G. Vairavel
ABSTRACT The Internet of Things (IoT) is a smart technology that has switched the conventional way of living into smart living. As their usage becomes unavoidable, malware attacks in IoT networks have also increased. Many investigations and studies have proposed different methods to detect malware attacks, but these measures have some performance degradation in terms of accuracy, error, and lack of comprehensiveness. The cloud-based IoT infrastructure further creates latency and security problems. The machine learning (ML)-based edge computing can overcome these complications by automating the responses and moving the computation nearer to the network edge, where data is created. In this work, the performance of various prominent ML algorithms, such as logistic regression (LR), naive Bayes (NB), support vector machine (SVM), decision tree (DT), random forest (RF), and k-nearest neighbor (KNN), has been compared to predict malware attack accurately in IoT-edge environment. To enhance the prediction accuracy of the ML algorithms, the unbalanced data is converted into balanced data using the synthetic minority oversampling technique (SMOTE) and optimum features are selected using the Gini impurity-based weighted RF feature selection technique (GIWRF). The investigational results show that among six ML algorithms, RF with GIWRF attained the highest accuracy of 99.39%. GRAPHICAL ABSTRACT
{"title":"GIWRF-SMOTE: Gini impurity-based weighted random forest with SMOTE for effective malware attack and anomaly detection in IoT-Edge","authors":"J. Manokaran, G. Vairavel","doi":"10.1080/23080477.2022.2152933","DOIUrl":"https://doi.org/10.1080/23080477.2022.2152933","url":null,"abstract":"ABSTRACT The Internet of Things (IoT) is a smart technology that has switched the conventional way of living into smart living. As their usage becomes unavoidable, malware attacks in IoT networks have also increased. Many investigations and studies have proposed different methods to detect malware attacks, but these measures have some performance degradation in terms of accuracy, error, and lack of comprehensiveness. The cloud-based IoT infrastructure further creates latency and security problems. The machine learning (ML)-based edge computing can overcome these complications by automating the responses and moving the computation nearer to the network edge, where data is created. In this work, the performance of various prominent ML algorithms, such as logistic regression (LR), naive Bayes (NB), support vector machine (SVM), decision tree (DT), random forest (RF), and k-nearest neighbor (KNN), has been compared to predict malware attack accurately in IoT-edge environment. To enhance the prediction accuracy of the ML algorithms, the unbalanced data is converted into balanced data using the synthetic minority oversampling technique (SMOTE) and optimum features are selected using the Gini impurity-based weighted RF feature selection technique (GIWRF). The investigational results show that among six ML algorithms, RF with GIWRF attained the highest accuracy of 99.39%. GRAPHICAL ABSTRACT","PeriodicalId":53436,"journal":{"name":"Smart Science","volume":"11 1","pages":"276 - 292"},"PeriodicalIF":2.3,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44212317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：