43 research outputs found
Smart Scheduling of EVs Through Intelligent Home Energy Management Using Deep Reinforcement Learning
No full textThis article presents the deep reinforcement learning (DRL) based smart scheduling in intelligent home energy management system (SSIHEMS) for electric vehicles (EVs) scheduling by utilizing the photovoltaic (PV) on the rooftop for economic dispatch problems. Therefore, optimizing home appliances to minimize consumption cost is challenging because of the randomness of electricity prices and poses a challenge for efficient scheduling. The data-driven model-free DRL-based SSIHEMS is utilized to optimize the decision by managing different home appliances and offering appropriate scheduling EVs to overcome the shortcomings. The decision includes the proper scheduling of battery charging, discharging, and EV to reduce the dependency on the electric grid through a collaborative approach. In addition, the proposed work covers designing a gym-based environment that incorporates the states fed to an agent and receives the reward based on the action taken for scheduling. Hence, the case study is performed to validate the proposed approach. It is verified that the decisions for battery charging, discharging, and EV scheduling are managed well through PV generation with respect to time. Furthermore, to verify the robustness and effectiveness, a comparison of different algorithms such as deep Q-network (DQN), double DQN, and dueling DQN
Un langage de programmation agent intégrant la planification temporelle et les mécanismes de coordination de plans
No full textPARIS-BIUSJ-Mathématiques rech (751052111) / SudocSudocFranceF
Extending SATPLAN to Multiple Agents
No full textAbstract Multi-agent planning is a core issue in the multi-agent systems field. In this work we focus on the coordination of multiple agents in a setting where agents are able to achieve individual goals that may be either independent, or necessary for the achievement of a global common goal. The agents are able to generate individual plans in order to achieve their own goals, but, as they share the same environment, they need to find a coordinated course of action that avoids harmful (or negative) interactions, and benefits from positive interactions, whenever this is possible. Moreover, agents are interested in finding plans with optimal length where preference is given to the length of the joint plan. We formalize these problems in a more general way with respect to previous works and present a coordination algorithm which provides the optimal solution in the case of two agents. In this algorithm, agents use µ-SATPLAN as the underlying planner for generating individual and joint consistent plans. This planner is an extension of the well known classical planner SATPLAN, aiming to deal with negative and positive interactions and, therefore, with multi-agent planning problem. Finally we present the experimental results using the multi-agent planning problems from the domains proposed and used in classical planning, which demonstrate the effectiveness of µ-SATPLAN and the coordination algorithm.
Pre-Christ Wisdom and Civilization in Aag Ka Darya
No full textQurratulain Hayder is a renowned fiction writer of the twentieth century. Her novel Aag ka Darya (also translated as River of Fire) is considered to be a classic in the tradition of Urdu fiction writing. This novel deals with Indian civilization and wisdom emanating from there in pre-Christ era. She has presented various constituting elements of Indian civilization through this narrative. Besides that, the thoughts and the teachings of the wise of that age, namely, Gautam Buddha, Mahavir, Kapil, Panini and Chankya have also been interwoven in the story. This article explores these themes and civilzational details in the novel.</p
