Engineering Commons^™

Towards Real-Time Reinforcement Learning Control Of A Wave Energy Converter, Enrico Anderlini, Salman Husain, Gordon Parker, Mohammad Abusara, Giles Thomas

Michigan Tech Publications

The levellised cost of energy of wave energy converters (WECs) is not competitive with fossil fuel-powered stations yet. To improve the feasibility of wave energy, it is necessary to develop effective control strategies that maximise energy absorption in mild sea states, whilst limiting motions in high waves. Due to their model-based nature, state-of-the-art control schemes struggle to deal with model uncertainties, adapt to changes in the system dynamics with time, and provide real-time centralised control for large arrays of WECs. Here, an alternative solution is introduced to address these challenges, applying deep reinforcement learning (DRL) to the control of WECs …

Eco-Driving Systems For Connected Automated Vehicles: Multi-Objective Trajectory Optimization, Ke Huang, Xianfeng Yang

Mineta Transportation Institute

This study aims to leverage advances in connected automated vehicle (CAV) technology to design an eco-driving and platooning system that can improve the fuel and operational efficiency of vehicles during freeway driving. Following a two-stage control logic, the proposed algorithm optimizes CAVs’ trajectories with three objectives: travel time minimization, fuel consumption minimization, and traffic safety improvement. The first stage, designed for CAV trajectory planning, is carried out with two optimization models. The second stage, for real-time control purposes, is developed to ensure the operational safety of CAVs. Based on extensive numerical simulations, the results have confirmed the effectiveness of the …

Evaluating Driving Performance Of A Novel Behavior Planning Model On Connected Autonomous Vehicles, Keyur Shah

Honors Scholar Theses

Many current algorithms and approaches in autonomous driving attempt to solve the "trajectory generation" or "trajectory following” problems: given a target behavior (e.g. stay in the current lane at the speed limit or change lane), what trajectory should the vehicle follow, and what inputs should the driving agent apply to the throttle and brake to achieve this trajectory? In this work, we instead focus on the “behavior planning” problem—specifically, should an autonomous vehicle change lane or keep lane given the current state of the system?

In addition, current theory mainly focuses on single-vehicle systems, where vehicles do not communicate with …

Applying Control Abstraction To The Design Of Human–Agent Teams, Clifford D. Johnson, Michael E. Miller, Christina F. Rusnock, David R. Jacques

Faculty Publications

Levels of Automation (LOA) provide a method for describing authority granted to automated system elements to make individual decisions. However, these levels are technology-centric and provide little insight into overall system operation. The current research discusses an alternate classification scheme, referred to as the Level of Human Control Abstraction (LHCA). LHCA is an operator-centric framework that classifies a system’s state based on the required operator inputs. The framework consists of five levels, each requiring less granularity of human control: Direct, Augmented, Parametric, Goal-Oriented, and Mission-Capable. An analysis was conducted of several existing systems. This analysis illustrates the presence of each …

Coupled Modelling And Advanced Control For Smooth Operation Of A Grid Connected Linear Electric Generator Based Wave-To-Wire System, Safdar Rasool, Md Rabiul Islam, Kashem M. Muttaqi, Danny Sutanto

Faculty of Engineering and Information Sciences - Papers: Part B

The perpetual oscillations of ocean waves produce potential energy, which can be converted to electrical energy with the help of direct drive linear generators. The fluctuating generated power poses a major challenge when it is supplied to the power grid. In this paper, a supercapacitor provides the short-term energy storage to buffer and smooth out the power fluctuations. A new coupled model of a wave energy converter and a linear generator is proposed for its response characterization under varying system conditions. The developed model and an advanced control strategy is used to exhibit a smooth and stable operation of the …

Model Predictive Control For A New Magnetic Linked Multilevel Inverter To Integrate Solar Photovoltaic Systems With The Power Grids, A M. Mahfuz-Ur-Rahman, Md Rabiul Islam, Kashem M. Muttaqi, Danny Sutanto

Faculty of Engineering and Information Sciences - Papers: Part B

The multilevel inverters are becoming increasingly popular for use in the grid integration of wind and photovoltaic (PV) power plants due to their higher voltage handling capability and the better output power quality. There are several types of multilevel inverters that have been proposed in the literature; among them the active neutral point clamp (ANPC) multilevel inverters have been drawing significant attention specially for solving the problems with other multilevel inverters. However, with the increase of number of levels, the ANPC requires more electronic switches and flying capacitors, by which the complexity and the cost increases. In this paper, an …

An Edge Based Multi-Agent Auto Communication Method For Traffic Light Control, Qiang Wu, Jianqing Wu, Jun Shen, Binbin Yong, Qingguo Zhou

Faculty of Engineering and Information Sciences - Papers: Part B

With smart city infrastructures growing, the Internet of Things (IoT) has been widely used in the intelligent transportation systems (ITS). The traditional adaptive traffic signal control method based on reinforcement learning (RL) has expanded from one intersection to multiple intersections. In this paper, we propose a multi-agent auto communication (MAAC) algorithm, which is an innovative adaptive global traffic light control method based on multi-agent reinforcement learning (MARL) and an auto communication protocol in edge computing architecture. The MAAC algorithm combines multi-agent auto communication protocol with MARL, allowing an agent to communicate the learned strategies with others for achieving global optimization …

Robust Extended H∞ Control Strategy Using Linear Matrix Inequality Approach For Islanded Microgrid, Maniza Armin, Mizanur Rahman, Md Mukidur Rahman, Subrata K. Sarker, Sajal Das, Md Rabiul Islam, Abbas Z. Kouzani, M. A Parvez Mahmud

Faculty of Engineering and Information Sciences - Papers: Part B

This paper presents the design of an extended parameterisations of H∞ controller for off grid operation of a microgrid. The microgrid consists of distributed generation units, filters and local loads. The filters are used to achieve accurate sinusoidal output voltage. However, loads which are connected to the microgrid are parametrically uncertain. Hence, it undergoes with unknown loads uncertainties. These unknown loads may create unknown loads harmonics, non-linearities which may reduce the voltage and current profile of the microgrid. As a result, the sudden rise and fall of voltage current profile damages the domestic and commercial loads. The proposed controller provides …