Browsing by Author "Onen A."

Now showing 1 - 4 of 4

Machine learning algorithms against hacking attack and detection success comparison
(Institute of Electrical and Electronics Engineers Inc., 2020) Yavuz L.; Soran A.; Onen A.; Muyeen S.M.; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
Power system protection units has got enormous importance with the growing risk of cyber-attacks. To create sustainable and well protected system, power system data must be healthy. For that purpose, many machine learning applications have been developed and used for bad data detection. However, each method has got different detection and application process. Methods has superiority over other methods. Although, an algorithm can detect some injections easily, same algorithm can be fail when injection type changed. So methods have got different success results when the injection types changed. For that reason, different injection types are applied on power system IEEE 14 bus system via created special hacking algorithm. PSCAD and python linkage has been used for simulation and detection parts. 3 different injection types created and applied on the system and five different most popular algorithms (SVM, k- NN, LDA, NB, LR) tested. Each algorithm's performances are compared and evaluated.
Microgrid environmental impact
(Institute of Electrical and Electronics Engineers Inc., 2020) Al-Agtash S.; Al-Hashem M.; Batarseh M.; Bintoudi A.D.; Tsolakis A.C.; Tzovaras D.; Martinez-Ramos J.; Onen A.; Azzopardi B.; Hadjidemetriou L.; Zacharia L.; Martensen N.; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü
Power plants have bad impacts on the environment. One of these impacts is Carbon Dioxide (CO2) emission resulted from power plants that depend on fossil fuel, oil and natural gas. Renewable energy is considered as an important solution for this problem since it is classified as clean and environmentally friendly source of energy and helps reducing the dependency on conventional power plants. High renewable energy penetration into power systems is a big challenge that can be solved by deploying the concept of smart Micro-Grids. This paper presents a study on how much reduction of CO2 emission can be resulted from deploying smart micro-grid concept on a university campus, German Jordanian University (GJU) campus was taken as a pilot. The micro-grid is meant to operate according to an optimum resource scheduling framework that guarantee a minimum operational cost while achieving high local power availability.
Modeling and real time digital simulation of microgrids for campuses Malta and Jordan based on multiple distributed energy resources
(Institute of Advanced Engineering and Science, 2020) Khiat S.; Chaker A.; Zacharia L.; Onen A.; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü
his paper presents the modeling and real-time digital simulation of two microgrids: The malta college of arts, science and technology (MCAST) and the German jordan university (GJU). The aim is to provide an overview of future microgrid situation and capabilities with the benefits of integrating renewable energy sources (RES), such as photovoltaic panels, diesel generators and energy storage systems for projects on both campuses. The significance of this work starts with the fact that real measurements were used from the two pilots, obtained by measuring the real physical systems. These measures were used to plan different solutions regarding RES and energy storage system (ESS) topologies and sizes. Also, the demand curves for the real microgrids of MCAST and GJU have been parameterized, which may serve as a test bed for other studies in this area. Based on actual data collected from the two pilots, a real-time digital simulation is performed using an RT-LAB platform. The results obtained by this tool allow the microgrid manager to have a very accurate vision of the facility operation, in terms of power flow and default responses. Several scenarios are studied, extracting valuable insight for implementing both projects in the future. Eventually, the proposed models would be a blueprint for training and research purposes in the microgrid field.
Optimal Control of Microgrids with Multi-stage Mixed-integer Nonlinear Programming Guided Q-learning Algorithm
(State Grid Electric Power Research Institute, 2020) Yoldas Y.; Goren S.; Onen A.; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü
This paper proposes an energy management system (EMS) for the real-time operation of a pilot stochastic and dynamic microgrid on a university campus in Malta consisting of a diesel generator, photovoltaic panels, and batteries. The objective is to minimize the total daily operation costs, which include the degradation cost of batteries, the cost of energy bought from the main grid, the fuel cost of the diesel generator, and the emission cost. The optimization problem is modeled as a finite Markov decision process (MDP) by combining network and technical constraints, and Q-learning algorithm is adopted to solve the sequential decision subproblems. The proposed algorithm decomposes a multi-stage mixed-integer nonlinear programming (MINLP) problem into a series of single-stage problems so that each subproblem can be solved by using Bellman's equation. To prove the effectiveness of the proposed algorithm, three case studies are taken into consideration: minimizing the daily energy cost; minimizing the emission cost; minimizing the daily energy cost and emission cost simultaneously. Moreover, each case is operated under different battery operation conditions to investigate the battery lifetime. Finally, performance comparisons are carried out with a conventional Q-learning algorithm.