Meslek Yüksek Okulları / Vocational Schools

Permanent URI for this communityhttps://hdl.handle.net/11727/1410

Browse

Filters

2023 - 20242

Settings

Author: search.filters.author.Ciflikli, CebrailHas files: Yes

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Esra (Elevator Simulation, Research & Analysis): An Open-Source Software Tool For Elevator Traffic Simulation, Research, And Analysis
    (Başkent Üniversitesi Teknik Bilimler Meslek Yüksekokulu, 2024-04-05) Tartan, Emre Oner; Ciflikli, Cebrail
    Today, although elevator companies typically have their own elevator simulation and analysis tools, these remain inaccessible to the public due to commercial concerns and rivalry in the sector. Consequently, due to the lack of modular open-source software tools, interest in the design and development of elevator systems in academia is quite limited, contrary to the vast potential of the field. This paper addresses this gap introducing an open-source software tool, the Elevator Simulator for Research and Analysis (ESRA), developed using the MATLAB programming language and an object-oriented approach. ESRA features built-in control methods, and visualization options with the capability to save and reuse traffic data, facilitating in-depth comparative analysis. Moreover, its modular architecture allows a design and development basis for further research in the field. The proposed software aims to enable developers to design, implement, analyse, and compare their control algorithms with other methods.
  • No Thumbnail Available
    Item
    Sequential Decision Making for Elevator Control
    (2023) Tartan, Emre Oner; Ciflikli, Cebrail; 0000-0002-5688-4226; JVD-9650-2023
    In the last decade Reinforcement Learning (RL) has significantly changed the conventional control paradigm in many fields. RL approach is spreading with many applications such as autonomous driving and industry automation. Markov Decision Process (MDP) forms a mathematical idealized basis for RL if the explicit model is available. Dynamic programming allows to find an optimal policy for sequential decision making in a MDP. In this study we consider the elevator control as a sequential decision making problem, describe it as a MDP with finite state space and solve it using dynamic programming. At each decision making time step we aim to take the optimal action to minimize the total of hall call waiting times in the episodic task. We consider a sample 6-floor building and simulate the proposed method in comparison with the conventional Nearest Car Method (NCM).