Research Interests:
Healthcare systems are facing various challenges such as high healthcare costs, aging population, increased number of patients with chronic illnesses, dissatisfied patients, lack of medical specialists. Use of big data analytics and... more
Healthcare systems are facing various challenges such as high healthcare costs, aging population, increased number of patients with chronic illnesses, dissatisfied patients, lack of medical specialists. Use of big data analytics and technologies is one of the ways to overcome problems and improve the current health systems. The main idea of this paper is to give a review of big data concept, summarize big data applications, and identify challenges in medical and healthcare with an overview of the current situation in Bosnia and Herzegovina.
Research Interests:
The University of Tuzla has in the recent past implemented all its activities in both institutional and legal terms. As a result, all higher education institutions (Faculties) are now integrated in one legal entity — the University. In... more
The University of Tuzla has in the recent past implemented all its activities in both institutional and legal terms. As a result, all higher education institutions (Faculties) are now integrated in one legal entity — the University. In doing so, the university has been guided by European standards in higher education. The Faculty of Electrical Engineering, as a member of the University of Tuzla, began to educate the first generation of undergraduate students in complete accordance with the Bologna Declaration in the academic year 2003/2004. At the same time the educational credit system ECTS (European Credit Transfer System) was established. In the academic year 2005/2006 Electrical Engineering was the first university faculty to establish one-year postgraduate studies with ECTS. Now students obtain a Bachelors degree after four years of study and a Masters degree after at least one additional year. An overview of the undergraduate and postgraduate course structure at the Faculty of Electrical Engineering is presented here.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Neuralnetworks havebroadapplicability to realpowersystemproblems. Oneoftheareasinpower systemwithhugeinterest inappliance ofneural networks is loadforecasting. Inthispapertheneuralnetworks were trained andtested using15-minute... more
Neuralnetworks havebroadapplicability to realpowersystemproblems. Oneoftheareasinpower systemwithhugeinterest inappliance ofneural networks is loadforecasting. Inthispapertheneuralnetworks were trained andtested using15-minute loaddatacollected in Portugal bytheelectric powercompanyEDP during a44 dayperiod. Theartificial neural networks showedasagood nonlinear approximator, giving promising results. Themain objective ofthepresented work isto interest power companiesin the Regionfor possible practical implementations. Keywordsartificial neural networks, loaddiagram, short termloadforecast
Research Interests:
Modelling of voltage dependent load is always a current topic due to existence of an adequate load model is a prerequisite for calculation of steady states and the analysis of transient regimes of power systems. Given that it is important... more
Modelling of voltage dependent load is always a current topic due to existence of an adequate load model is a prerequisite for calculation of steady states and the analysis of transient regimes of power systems. Given that it is important to know the load model parameters, we have performed the measurements in electric power system of Bosnia and Herzegovina (EPS BIH). The main idea is to identify the values of voltage parameters of dynamic load model. Therefore, this paper describes the dynamic load models and the methodology for exponential dynamic load model parameter identification. It also presents the voltage parameters of dynamic load model for a node in EPS BIH and compares them to similar published studies, concluding that the difference in given parameter values is the consequence of local load characteristics.
Research Interests:
In a power distribution network, network topology information is essential for an efficient operation of the network. This information is not accurately available, due to uninformed changes that happen from time to time, or uncertain... more
In a power distribution network, network topology information is essential for an efficient operation of the network. This information is not accurately available, due to uninformed changes that happen from time to time, or uncertain meter readings. Reliable prediction of system status is a highly demanded functionality of smart energy systems, which can enable users or human operators to react quickly to potential future system changes. This paper presents potential of artificial neural networks to determine missing power meter readings in medium voltage (MV) networks where the number of on-line measurements is limited, and state estimation relies heavily on estimates of power injections. The applicability of the approach is demonstrated through simulation using supervisory control and data acquisition and smart meter measurements recorded from an actual MV distribution network. Results are showing that artificial neural networks can have 100% measurements detection accuracy.
Research Interests:
This paper presents Forecast-Aided Distribution System State Estimation algorithm based on the Unscented Kalman Filter. It uses pseudo-measurements based on the forecasted load profiles and previous state estimation, in conjunction with... more
This paper presents Forecast-Aided Distribution System State Estimation algorithm based on the Unscented Kalman Filter. It uses pseudo-measurements based on the forecasted load profiles and previous state estimation, in conjunction with optimally placed limited number of load active and reactive power measurements. Presented estimation results are obtained by simulations on a 33 node test system using forty one day hourly load data. Results obtained using a test system are showing that this algorithm can make good estimate of the voltage amplitude even with high error of the forecasted loads.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Engineering, Computer Science, Power Systems, Production, Power System, and 12 moreSequential Monte Carlo, Monte Carlo Methods, Reliability Engineering, Wind Power, Bosnia and Herzegovina, Reliability, Electric Power System, Time Horizon, Reliability Assessment, Monte Carlo Method, Wind Power Generation, and Loss of Load Expectation
Increasing the number of generation units connected to the grid via power electronic devices potentially implies negative impacts on the power system frequency stability and, depending on the power system inertia value, implies the... more
Increasing the number of generation units connected to the grid via power electronic devices potentially implies negative impacts on the power system frequency stability and, depending on the power system inertia value, implies the necessary contribution of wind power plants to inertial response of the system. An alternative approach to the active power control of wind power plants, without the impact of local frequency deviation on the output power, is the application of a control strategies based on the center of inertia frequency. Since control schemes based on the input variable of the center of inertia frequency require a satisfactory level of signal transmission capacity in real time and the advanced telecommunication infrastructure of the power system, the paper considers an alternative approach to estimate the input signal value. According to the developed long short-term memory recurrent neural network, paper presents the idea of center of inertia frequency estimation by mo...
Research Interests:
Research Interests:
Research Interests:
Renewable energy sources such as hydro, wind and solar energy are taking an increasing share in the electricity mix. However, electricity production from thermal power plants is independent of the weather conditions and is still important... more
Renewable energy sources such as hydro, wind and solar energy are taking an increasing share in the electricity mix. However, electricity production from thermal power plants is independent of the weather conditions and is still important as a back-up power source to renewable energy sources. Given the fact that the electricity market is open, it is clear that each MWh is important. Therefore, auxiliary power systems as a part of thermal power plants should be also energy efficient. The main aim of the presented research was to investigate the efficient operation of different consumers in the auxiliary power system in the old-dated thermal power plant ‘’Tuzla’’ depending on different power at generator output. The performed analysis identified consumers suitable for electricity efficiency improvement giving results of power savings obtained on modestly available measurements and old-date technical documentation. Following obtained results, some recommendations for improving electric...
Research Interests:
Distribution System Operator (DSO) is obliged to provide the contracted power to the system user. The use of the distribution capacity below the contracted connection power causes the inefficient engagement of the available distribution... more
Distribution System Operator (DSO) is obliged to provide the contracted power to the system user. The use of the distribution capacity below the contracted connection power causes the inefficient engagement of the available distribution capacity. Investing, maintaining and managing of an unused power distribution capacity is an unjustified expense. In order to avoid undue costs, it is possible to create such tariff design, which would activate system users to use the contracted connection power more efficiently, through price signals. More efficient use of the contracted connection power by the system users has a positive effect through more efficient use of distribution capacities. Through the analysis of a part of the distribution network, the unused capacity and unjustified distribution network costs were detected. In this paper, it is suggested a way to activate system users for more efficient use of contracted power. More efficient use of the contracted connection power by the ...
The creation of mutually recognized study programs and constant monitoring and evaluation of study quality in Partner Countries is a good background for creation of join and double degree master level programs, and development of an... more
The creation of mutually recognized study programs and constant monitoring and evaluation of study quality in Partner Countries is a good background for creation of join and double degree master level programs, and development of an appropriate industry - academia cooperation strategy. The research demonstrates the Quality Assurance approach applied in the ERASMUS+ project, it evaluates cooperation experience and achievements of the Partner Countries HEIs in a Neighborhood region
Research Interests:
This paper presents an algorithm for Distributed Generation (DG) allocation planning, using fuzzy set theory and fuzzy multi criteria decision making based on the Bellman-Zadeh method. The proposed model considers power losses and... more
This paper presents an algorithm for Distributed Generation (DG) allocation planning, using fuzzy set theory and fuzzy multi criteria decision making based on the Bellman-Zadeh method. The proposed model considers power losses and investment deferral values on one side (goals) and line currents, node voltages and short circuit power values on the other (constraints). The objective of this work is to create a model which can be used to provide the best tradeoff between conflicting goals and constraints, inherently present in the DG allocation problem. The model is flexible and can be easily extended to include additional goals and constraints. In order to demonstrate its relevance, the proposed algorithm is applied to the realistic middle voltage (35 kV) distribution system in Bosnia and Herzegovina, in which various DG siting and sizing alternatives are considered. Results indicate that the algorithm is applicable to realistic systems and capable to provide valuable information regarding the influence of various DG allocation alternatives on system variables. It is expected that the algorithm will contribute towards the improvement of the existing DG planning process and it will be used in practical situations by planning engineers from the Utilities and Regulators.
Research Interests:
Research Interests:
One of the main sector important for energy efficiency is building. Results of a pilot study related to energy efficiency in an academic building were summarized in this paper. The pilot study was undertaken at the Faculty of Electrical... more
One of the main sector important for energy efficiency is building. Results of a pilot study related to energy efficiency in an academic building were summarized in this paper. The pilot study was undertaken at the Faculty of Electrical Engineering, University of Sarajevo. Ten necessary steps of developing energy efficiency improvement project were defined. Data of water, heating and electricity consumption and theirs costs were analyzed. Special attention was paid on 15-min load data for the case-study building to identify key characteristics of electricity use. Identification of potential energy savings and improvement of energy efficiency are considered after detailed analyses of available and collected data.
Research Interests:
Large reserves and worldwide availability of coal indicate that this energy will play an important role for electricity generation in the future even if there is a significant increase in production from renewables. Besides that, the... more
Large reserves and worldwide availability of coal indicate that this energy will play an important role for electricity generation in the future even if there is a significant increase in production from renewables. Besides that, the electricity market is open and the result is competition between the market actors. The goals of advanced thermal power plants are using as less as possible input energy to generate electricity as much as possible and reducing the CO2 emission. In thermal power plants, 7–15% of the generated energy on the generator does not reach the power plant’s threshold because it is geared back to pumps, fans and other auxiliary power systems. Given the fact that each MWh is important today, it is clear that auxiliary power systems of advanced thermal power plants must be energy efficient. In this paper contemporary regulated auxiliary power systems of advanced thermal power plant “Stanari” are presented. After an introduction, fresh air fan, flue gas fan and feed ...
Research Interests:
Solar energy is the main driving force of climate cycles and all life cycles on Earth. It is inexhaustible and it can be used in each country all over the world. Bosnia and Herzegovina is in line with EU guidelines on mandatory reductions... more
Solar energy is the main driving force of climate cycles and all life cycles on Earth. It is inexhaustible and it can be used in each country all over the world. Bosnia and Herzegovina is in line with EU guidelines on mandatory reductions of greenhouse gas emissions required to increase production of electricity from the renewable energy sources. The main scope of this paper is to investigate the power quality parameters measured during different periods and weather conditions on the first photovoltaic system “Eko Energija” connected to the distribution power network in Bosnia and Herzegovina. The results of these measurements are analysed and presented in this paper.
Research Interests:
Supply interruptions depend on the reliability of the entire power system comprising a generation system and transmission and distribution networks. Transmission system faults quite rarely result in customer interruptions, but if they... more
Supply interruptions depend on the reliability of the entire power system comprising a generation system and transmission and distribution networks. Transmission system faults quite rarely result in customer interruptions, but if they occur the number of customers affected can be higher than in case of distribution system faults. This is the reason why it is important for the reliability of the transmission system to be on a high level. On the other hand, generation faults are not so frequent, but even if they occur the system is controlled and remains balanced. In this paperwork, reliability indices were evaluated for one part of modelled composite power network in Bosnia and Herzegovina (BIH) to which, in addition to conventional power plants, renewable sources were connected including the first wind farm which is under trial operation at present. Both simulations and the composite network were created using DIgSILENT PowerFactory 18 software package for the regimes of minimum and...
Research Interests:
This paper presents an application of artificial intelligence for the analysis of total losses in power transformers. The method is based on a multilayer feed-forward neural network that uses the Levenberg-Marquard algorithm to adjust the... more
This paper presents an application of artificial intelligence for the analysis of total losses in power transformers. The method is based on a multilayer feed-forward neural network that uses the Levenberg-Marquard algorithm to adjust the network parameters. The analysis was carried out on a three-phase dry transformer 1000 kVA, 6000/400 V. The data used for developing the neural network were obtained experimentally by measuring on low voltage side of the transformer. The inputs to the developed neural network are: the mean value of the load current, the temperature and the losses in the copper, and the output is the total losses. The database contains 1441 samples obtained by changing the load every 30 s in the interval of 12 h. The network model was developed for a temperature of 25 °C, and then the same model was used to determine total losses at a temperature of 68 °C. Obtained results from the developed neural network were compared with the measured data. The low error value in...
Research Interests:
This paper investigates the influence of electric vehicle charging station variations for the cases with and without supplementary renewable sources integration, concentrating on symmetry and voltage stability of the network. The study... more
This paper investigates the influence of electric vehicle charging station variations for the cases with and without supplementary renewable sources integration, concentrating on symmetry and voltage stability of the network. The study was performed on a realistic low voltage network using is the load flow analysis in DIgSILENT Power Factory software and P-V method. The analysis is based on defined variations for analysis of the baseline variation and electric vehicles with and no additional source as the PV system. It was demonstrated that the complementary operation of EVs and PV can, if planned properly, improve the power system voltage quality parameters.
Research Interests:
In this paper, CONOPT solver, embedded in program GAMS, is proposed for optimal power flow analysis in distribution network with renewable energy sources. CONOPT solver possibilities have been tested on IEEE 33 test system solving a... more
In this paper, CONOPT solver, embedded in program GAMS, is proposed for optimal power flow analysis in distribution network with renewable energy sources. CONOPT solver possibilities have been tested on IEEE 33 test system solving a problem o f minimizing active power losses in the network. Locations and sizes o f renewable energy sources were taken form available literature. The results obtained using CONOPT solver have been compared with results obtained by using metaheuristic and hybrid algorithms. It is shown that the CONOPT solver gives better results in terms o f minimum values o f active power losses.
Research Interests:
Limited resources of fossil fuels, as well as negative environmental effects, have led to a strategic turn in energy generation at many countries. In the new conditions of modern deregulated power systems, renewable energy sources play an... more
Limited resources of fossil fuels, as well as negative environmental effects, have led to a strategic turn in energy generation at many countries. In the new conditions of modern deregulated power systems, renewable energy sources play an important role, and their share in total electricity generation is increasing. In addition, due to intensive technological development, the range of clean and environmentally friendly energy sources is constantly expanding, and the price of electricity from already known renewable energy sources is decreasing. Further development in this area is highly dependent on the legal infrastructure, because it defines the level of incentives, without which the concept of renewable energy sources would be unsustainable. The aim of this paper is to present the current state of electricity generation from renewable energy sources in Slovenia, Bosnia and Herzegovina and Montenegro, as well as related legislations governing this area. The common goal is identifi...
Research Interests:
Abstrakt U današnje vrijeme za analizu karakteristika i pogonskih stanja elektroenergetskih sistema (EES-a) koriste se dinamički proračuni [1], odnosno digitalne simulacije, koje se izvode na računaru pomoću odgovarajućeg modela... more
Abstrakt U današnje vrijeme za analizu karakteristika i pogonskih stanja elektroenergetskih sistema (EES-a) koriste se dinamički proračuni [1], odnosno digitalne simulacije, koje se izvode na računaru pomoću odgovarajućeg modela posmatranog EES-a, i nemaju nikakav uticaj na sam rad EES-a. Na taj način eliminiše se mogućnost ispada sistema, a moguće je i analizirati ponašanje EES-a uzimajući u obzir elektroenergetske objekte koji još nisu izgrađeni. U ovom radu izrađen je dinamički model elektroenergetskog sistema BiH korištenjem programskog paketa MATLAB/Simulink/SimPowerSys, sastavljen od idealnih modela pojedinih elemenata [4]. Nakon formiranja dinamičkog modela EES-a potrebno je izvršiti i njegovu potvrdu, odnosno uporediti rezultate dobijene računarskom simulacijom, i rezultate dobijene mjerenjima na stvarnom EES-u. Ovakav dinamički model EES-a omogućava analizu stacionarnih i prijelaznih pogonskih stanja, a moguće je analizirati i stanja sistema uzimajući u obzir elektroenerget...
Electrical energy should satisfy the proper quality requirements. The highest quality demands are set on the voltage level of the consumers. Standard EN 50160 defines many important characteristics of low supply voltage that have to be... more
Electrical energy should satisfy the proper quality requirements. The highest quality demands are set on the voltage level of the consumers. Standard EN 50160 defines many important characteristics of low supply voltage that have to be observed. Different disturbances can appear in a power system and they can cause deviation of defined power system quality. In the past, fault simulations in a real system due to research and measuring were possible. Nowadays, fault simulations and their measurements in the real system are practically impossible due to huge economical losses. Therefore, development of adequate dynamic power system model using available software tools is very important for analysing different states of the system. In this paper, dynamic model of the Bosnia and Herzegovina (B&H) power system is presented and verified in order to analyse influence of disturbance on the voltage dips in the electrical networks with different voltage levels. Disturbance transiting among vol...
This paper reports the building of a system for predicting load curves at low voltage substations supplying a set of consumers of different types (residential, industrial, etc.). The system is built by the aggregation of individual fuzzy... more
This paper reports the building of a system for predicting load curves at low voltage substations supplying a set of consumers of different types (residential, industrial, etc.). The system is built by the aggregation of individual fuzzy inference systems of the Takagi-Sugeno type. The paper describes how actual measurements formed a base of raw data and how test and training sets could be built from this base. Results produced by the prediction system and their comparison with actual load curves confirm the good performance of the model
Research Interests:
ABSTRACT Main principle of a tariff system for electricity is that customers should cover all costs appeared in the power system, but as realistic as it possible in accordance with a place and time of delivered energy. Defining real... more
ABSTRACT Main principle of a tariff system for electricity is that customers should cover all costs appeared in the power system, but as realistic as it possible in accordance with a place and time of delivered energy. Defining real economical price of electricity for customers at the low voltage distribution level presents main problem due to a lack of data related to daily load diagram. Fuzzy logic and fuzzy c-means clustering was applied to development of a model for consumers' classification. Obtained results could be used as an input for more realistic calculation of cost for electrical energy consumption of customers in household category. Additionally, the difference in calculation of electricity consumption cost based on the obtained values from proposed model and on current tariff system in Bosnia and Herzegovina is discussed.
Research Interests:
ABSTRACT Solar energy is the main driving force of climate cycles and all life cycles on Earth, it is inexhaustible and it can be used in all countries of the world. Bosnia and Herzegovina is in line with EU guidelines on mandatory... more
ABSTRACT Solar energy is the main driving force of climate cycles and all life cycles on Earth, it is inexhaustible and it can be used in all countries of the world. Bosnia and Herzegovina is in line with EU guidelines on mandatory reductions of greenhouse gas emissions required to increase production of electricity from the renewable energy sources. This paper describes first photovoltaic system directly connected to distribution network in Bosnia and Herzegovina and its components. Power quality measurement during different periods and weather conditions have been performed on the first photovoltaic system in Bosnia and Herzegovina. The results are presented in this paper.
Research Interests:
ABSTRACT The term "coupled problem" is used in many numerical approaches and applications. The electromagnetic-thermal problem in general consists of two finite element systems and two coupling functions (losses and... more
ABSTRACT The term "coupled problem" is used in many numerical approaches and applications. The electromagnetic-thermal problem in general consists of two finite element systems and two coupling functions (losses and thermal dependency of the material parameters). On the basic of problems nature, great temperature time's constants in related on the electromagnetic proceses, we have chosen quasi-tranzient algorithm. In the paper, we showed the algorithm to simultaneously solution for electromagnetic field and temperature field and we gave results of calculated. The results of calculated were compared with the experimental data obtained with the physical model. Differences between calculated and measured temperatures are less then 7,16%.
Research Interests:
The text explains that the fuzzy approaches have the objective to bring the decision process in planning closer to the decision maker, by allowing him to understand better the diversity of aspects that must be considered in planning... more
The text explains that the fuzzy approaches have the objective to bring the decision process in planning closer to the decision maker, by allowing him to understand better the diversity of aspects that must be considered in planning decisions and helping the decision process while keeping as much information as possible, represented in the definition of fuzzy sets. The paper
Research Interests:
... qy, ew.eeogrg8cneecshm 20 IEEE 06 Preliminary comparison of different neural-fuzzy mappers for load curve short term prediction Dzenana Malkocevic6 , Tatjana Konjic**, and Vladimiro Miranda*** Abstract - This paper is ...
Research Interests:
ABSTRACT Neural networks have broad applicability to real power system problems. One of the areas in power system with huge interest in appliance of neural networks is load forecasting. In this paper the neural networks were trained and... more
ABSTRACT Neural networks have broad applicability to real power system problems. One of the areas in power system with huge interest in appliance of neural networks is load forecasting. In this paper the neural networks were trained and tested using 15-minute load data collected in Portugal by the electric power company EDP during a 44 day period. The artificial neural networks showed as a good nonlinear approximator, giving promising results. The main objective of the presented work is to interest power companies in the region for possible practical implementations
Research Interests:
Research Interests: Engineering, Computer Science, Fuzzy Logic, Fuzzy set theory, Consumer Behavior, and 15 moreFuzzy Systems, Economic Forecasting, Artificial Neural Networks, Estimation, Predictive models, Electric Power System, Fuzzy System, Voltage, Load Forecasting, Power Distribution, Fuzzy Inference System, Artificial Neural Network, Electrical And Electronic Engineering, Low voltage, and Neural nets
This article focuses on detecting, classifying and locating faults in power system using Artificial Neural Networks (ANNs). Feed-forward neural networks have been employed and trained with back-propagation algorithm. The model of WSCC 9... more
This article focuses on detecting, classifying and locating faults in power system using Artificial Neural Networks (ANNs). Feed-forward neural networks have been employed and trained with back-propagation algorithm. The model of WSCC 9 bus test system has been modelled in Matlab/Simulink, and used to validate the proposed fault detection system. First, normal state of the model was observed. After determination of normal state, different types of faults have been simulated on all nine buses and on all lines of the model. Voltage and current magnitudes, obtained by the fault simulation, are used as inputs of the ANN. Output of the ANN should provide information about the fault type and location in case the fault occurs. Number of hidden layers and neurons per hidden layer is determined by testing performance and training time of each developed neural network.