Scopus İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395

Browse

Filters

2013 - 201942020 - 20254

Settings

Subject: search.filters.subject.Intelligent Systems

Search Results

Now showing 1 - 8 of 8
  • Conference Object
    Citation - Scopus: 1
    Traffic Light Management Systems Using Reinforcement Learning
    (Institute of Electrical and Electronics Engineers Inc., 2022-09-07) Can, Sultan Kubra; Thahir, Adam Rizvi; Cos¸kun, Mustafa; Güngör, Vehbi Çağrı; Coskun, Mustafa
    While reducing traffic congestion and decrease the number of traffic accidents in the intersections, most of the traffic light management approaches cannot adapt well to fast changing traffic dynamics and growing demands of the intersections with modern world developments. To overcome this problem, adaptive traffic controllers are developed, and detectors and sensors are added to systems to enable adoption and dynamism. Recently, reinforcement learning has shown its capability to learn the dynamics of complex environments, such as urban traffic. Although it was studied in single junction systems, one of the problems was the lack of consistency with how the real world system works. Most of the systems assume that the environment is fully observable or actions would be freely executed using simulators. This study aims to merge usefulness of reinforcement learning methods with real-world traffic constraints. Comparative performance evaluations show that the reinforcement learning algorithm (Advantage Actor-Critic (A2C)) converges well while staying stable under changing traffic dynamics. © 2022 Elsevier B.V., All rights reserved.
  • Conference Object
    Citation - Scopus: 1
    TextNetTopics_TIS: Enhancing Textnettopics With Random Forest-Based Topic Importance Scoring
    (Institute of Electrical and Electronics Engineers Inc., 2024-10-16) Voskergian, Daniel; Bakir-Güngör, Burcu; Yousef, Malik
    TextNetTopics is an innovative Latent Dirichlet Allocation-based topic selection method for training text classification models. One main limitation is its computationally intensive scoring mechanism, especially when applied to many topics. This scoring mechanism involves training a machine learning model (i.e., Random Forest) on each topic using the Monte-Carlo Cross-Validation approach and assigning a score value based on a specific performance metric (e.g., accuracy or F1-score). Moreover, the measured score does not account for the interactions between all features residing in all topics. This paper presents a new topic-scoring mechanism called Topic Importance Scoring. This computationally efficient approach trains a Random Forest model on all topics simultaneously and leverages the extracted feature importance values to give each topic a score reflecting its classification potential. The experiments on three diverse datasets confirm that the proposed method's performance is superior to the Topic Performance Scoring, which was used in the original TextNetTopics method. © 2024 Elsevier B.V., All rights reserved.
  • Conference Object
    Citation - WoS: 5
    Citation - Scopus: 17
    Novel Hybrid Design for Microgrid Control
    (IEEE Computer Society, 2017-11) Bintoudi, Angelina D.; Zyglakis, Lampros; Apostolos, Tsolakis; Ioannidis, Dimosthenis K.; Al-Agtash, Salem Y.; Martinez-Ramos, J. L.; Martensen, Nis; Tzovaras, Dimitrios
    This paper proposes a new hybrid control system for an AC microgrid. The system uses both centralised and decentralised strategies to optimize the microgrid energy control while addressing the challenges introduced by current technologies and applied systems in real microgrid infrastructures. The well-known 3-level control (tertiary, secondary, primary) is employed with an enhanced hierarchical design using intelligent agent-based components in order to improve efficiency, diversity, modularity, and scalability. The main contribution of this paper is dual. During normal operation, the microgrid central controller (MGCC) is designed to undertake the management of the microgrid, while providing the local agents with the appropriate constraints for optimal power flow. During MGCC fault, a peer-to-peer communication is enabled between neighbouring agents in order to make their optimal decision locally. The initial design of the control structure and the detailed analysis of the different operating scenarios along with their requirements have shown the applicability of the new system in real microgrid environments. © 2023 Elsevier B.V., All rights reserved.
  • Conference Object
    Machine Learning Based Beamwidth Adaptation for mmWave Vehicular Communications
    (Institute of Electrical and Electronics Engineers Inc., 2023-12-10) Manic, Setinder; Heng Foh, Chuan; Köse, Abdulkadir; Lee, Haeyoung; Leow, Chee Yen; Chatzimisios, Periklis; Suthaputchakun, Chakkaphong; Foh, Chuan Heng
    The incorporation of mmWave technology in vehicular networks has unlocked a realm of possibilities, propelling the advancement of autonomous vehicles, enhancing interconnectedness, and facilitating communication for intelligent transportation systems (ITS). Despite these strides in connectivity, challenges such as high path-loss have arisen, impacting existing beam management procedures. This work aims to address this issue by improving beam management techniques, specifically focusing on enhancing the service time between vehicles and base stations through adaptive mmWave beamwidth adjustments, accomplished using a Contextual Multi-Armed Bandit Algorithm. By leveraging various conditions to train the ML agent of the Contextual Multi-Armed Bandit Algorithm, it seeks to learn about vehicle mobility profiles and optimize the usage of different antenna beamwidth settings to maximize seamless connection time. The extensive simulation results showcase the effectiveness of an adaptive beamwidth for mobility profiles, extending the connection time a vehicle experiences with a base station when compared to the existing strategies. © 2024 Elsevier B.V., All rights reserved.
  • Conference Object
    Citation - Scopus: 1
    Is the Smart Grid a Good Investment
    (Institute of Electrical and Electronics Engineers Inc., 2015-04) Onen, Ahmet; Broadwater, Robert P.
    Electric distribution design and operational goals include meeting customer reliability requirements at the lowest cost. Smart Grid investments have the potential for helping meet these goals, and this paper presents a series of analyses that evaluate the incremental economic benefits of smart grid automation investments. Smart Grid investments provide a number of benefits to customers. Here only benefits that can be objectively quantified in terms of economic savings are considered. Smart Grid automation investments in this work include investments in feeder efficiency, automated switches, and coordinated control of capacitor banks, voltage regulators and load tab changers. Benefits that come from these investments are improved efficiency, reduced demand, shortened storm restoration time, and improved performance during reconfiguration events. The analyses used in the evaluation are very detailed, involving hourly, quasi-steady state power flow analysis over a ten year period for calculating energy consumption and costs, and Monte Carlo simulations for six different storm types. The evaluation shows that similar to other industries, an investment in automation can be justified in terms of hard dollars. © 2017 Elsevier B.V., All rights reserved.
  • Book Part
    Hosting Capacity Calculation Methods
    (Elsevier, 2025) Oguzhan, Ceylan; Alper, Savasci
    In this chapter, we focus on hosting capacity (HC) calculations, by giving the methods to determine the maximum amount of distributed energy resources (DER) that can be integrated into power distribution network(s) without compromising reliability or performance. We detail methodologies such as power flow-based approaches, probabilistic techniques, and machine learning algorithms, with sample applications of HC calculations. Initially, we focus on power flow-based methods based on simulating power distribution network(s) to assess system voltage, current flow, and stability impacts from DER installations. Then, we will give the probabilistic approaches that use uncertainties in renewable generation and consumer demand, based on statistical techniques and Monte Carlo simulations aiming to reflect these variability. Machine learning (ML) techniques will also be given based on analyzing large data sets, detecting patterns, and predicting system responses. These kinds of methods include regression analysis and neural networks trained on historical data for optimized HC predictions. It should be stated that HC is impacted by several factors, such as network topology, load profiles, and DER characteristics, and these as well will be discussed. We will provide a practical example of an HC calculation on a 141-node distribution network using a step-by-step algorithm in Matpower, with simulation results based on an iterative deterministic method. Then, we will give the broader implications of HC assessments for grid modernization and energy policy, highlighting how accurate calculations support a more decentralized, sustainable, and resilient energy future. © 2025 Elsevier B.V., All rights reserved.
  • Conference Object
    Citation - Scopus: 4
    A Model Selection Algorithm for Mixture Model Clustering of Heterogeneous Multivariate Data
    (IEEE, 2013-06) Erol, H.
    A model selection algorithm is developed for finding the best model among a set of mixture of normal densities fitted to heterogeneous multivariate data. Model selection algorithm proposed first finds total number of mixture of normal densities then selects possible number of mixture of normal densities and finally searches the best model among them in mixture model clustering of heterogeneous multivariate data. Log-likelihood function, Akaike's information criteria and Bayesian information criteria values are computed and graphically ploted for each mixture of normal densities. The best model is chosen according to the values of these information criterions. © 2013 IEEE. © 2013 Elsevier B.V., All rights reserved.
  • Conference Object
    A Data Mining Method for Refining Groups in Data Using Dynamic Model Based Clustering
    (IEEE, 2013-06) Servi, Tayfun; Erol, H.
    A new data mining method is proposed for determining the number and structure of clusters, and refining groups in multivariate heterogeneous data set including groups, partly and completely overlapped group structures by using dynamic model based clustering. It is called dynamic model based clustering since the structure of model changes at each stage of refinement process dynamically. The proposed data mining method works without data reduction for high dimensional data in which some of variables including completely overlapped situations. © 2013 IEEE. © 2013 Elsevier B.V., All rights reserved.