15 research outputs found
Demand Response Management in Smart Grid Networks: a Two-Stage Game-Theoretic Learning-Based Approach
No full textIn this diploma thesis, the combined problem of power company selection and Demand Response Management in a Smart Grid Network consisting of multiple power companies and multiple customers is studied via adopting a distributed learning and game-theoretic technique. Each power company is characterized by its reputation and competitiveness. The customers who act as learning automata select the most appropriate power company to be served, in terms of price and electricity needs’ fulfillment, via a distributed learning based mechanism. Given customers\u27 power company selection, the Demand Response Management problem is formulated as a two-stage game theoretic optimization framework, where at the first stage the optimal customers\u27 electricity consumption is determined and at the second stage the optimal power companies’ pricing is calculated. The output of the Demand Response Management problem feeds the learning system in order to build knowledge and conclude to the optimal power company selection. A two-stage Power Company learning selection and Demand Response Management (PC-DRM) iterative algorithm is proposed in order to realize the distributed learning power company selection and the two-stage distributed Demand Response Management framework. The performance of the proposed approach is evaluated via modeling and simulation and its superiority against other state of the art approaches is illustrated
Demand Response Management in Smart Grid Networks: a Two-Stage Game-Theoretic Learning-Based Approach
No full textIn this paper, the combined problem of power company selection and demand response management (DRM) in a smart grid network consisting of multiple power companies and multiple customers is studied via adopting a reinforcement learning and game-theoretic technique. Each power company is characterized by its reputation and competitiveness. The customers, acting as learning automata select the most appropriate power company to be served, in terms of price and electricity needs’ fulfillment, via a reinforcement learning based mechanism. Given customers’ power company selection, the DRM problem is formulated as a two-stage game theoretic optimization framework. At the first stage the optimal customers’ electricity consumption is determined and at the second stage the optimal power companies’ pricing is obtained. The output of the DRM problem feeds the learning system to build knowledge and to conclude to the optimal power company selection. To realize the aforementioned framework a two-stage Power Company learning selection and Demand Response Management (PC-DRM) iterative algorithm is introduced. The performance evaluation of the proposed approach is achieved via modeling and simulation and its superiority against other approaches is illustrated
Artificial Intelligent Risk-aware Autonomous Decision-Making in Resource-Constrained Computing Systems
No full textArtificial Intelligent autonomous systems are becoming increasingly ubiquitous in daily life. Mobile devices for example provide mechanical-generated intelligent support to humans, with various degrees of autonomy, and are a key part of the recent autonomous revolution. Autonomous intelligent systems aim to understand and interact with their users in a timely manner, while many of them are characterized by constrained resources. Despite that, the average person does not act in a formulaic and risk-neutral manner but instead exhibits risk-aware attitudes when performing a task that includes sources of uncertainties. When humans make decisions, they explore their surroundings, understand the emerging risks, perform actions, and evaluate their perceived outcomes. What a person characterizes as a satisfactory outcome is subjective to her own reasoning, behavior, and risk capacity. Therefore, an autonomous intelligent system should be enriched with human awareness, thus it should account for and sometimes mimic its owner\u27s cognitive behavior and behavioral patterns, such that the latter\u27s subjective satisfaction is optimized, and personalized service is provided. Furthermore, the proliferation of autonomous systems, e.g., mobile or wearable devices, boosts the data volume and service demand. Each autonomous system aims to optimize its owner\u27s experience in a self-centric manner, and in several application domains, its actions impact the others\u27 experience and decision-making process generally. To this end, the users\u27 subjective goals generate conflicts, and the autonomous intelligent systems are expected to make decisions in non-cooperative environments. In this thesis, we investigate and introduce distributed autonomous decision-making frameworks by focusing on motivating application domains with the aforementioned challenges. We utilize Game Theory for studying the strategic interaction of the autonomous intelligent systems in non-cooperative environments and tackling the necessity of non-centralized and scalable solutions. We build autonomous intelligent decision-making agents through Reinforcement Learning, which is a popular statistical Artificial Intelligence (AI) technique for controlling unknown environments with partial, and incomplete information. Reinforcement Learning (RL) introduces the concept of an agent that learns to interact with an unknown environment by performing actions that are mainly driven by particular observations, and by evaluating the resulted feedback. We extend the regular RL setting through reward reshaping for considering the user\u27s risk-aware characteristics that are exhibited in real life. We incorporate Prospect Theory, which belongs to the behavioral economic subgroup, and describes how individuals make decisions between probabilistic alternatives, where risk is involved, and the probability of different outcomes is unknown. In the considered non-cooperative environments, we seek distributed solutions, thus Equilibrium points, where each autonomous intelligent agent does not have the incentive to change its own decision unilaterally. Our investigation leads to autonomous intelligent decision-making frameworks that could serve as a step towards Artificial General Intelligence (AGI), where the computing systems learn to perform a task in a human-centric manner, thus in a similar way that the task would be completed by a person in real life
ESCAPE: Evacuation Strategy through Clustering and Autonomous Operation in Public Safety Systems
No full textNatural disasters and terrorist attacks pose a significant threat to human society, and have stressed an urgent need for the development of comprehensive and efficient evacuation strategies. In this paper, a novel evacuation-planning mechanism is introduced to support the distributed and autonomous evacuation process within the operation of a public safety system, where the evacuees exploit the capabilities of the proposed ESCAPE service, towards making the most beneficial actions for themselves. The ESCAPE service was developed based on the principles of reinforcement learning and game theory, and is executed at two decision-making layers. Initially, evacuees are modeled as stochastic learning automata that select an evacuation route that they want to go based on its physical characteristics and past decisions during the current evacuation. Consequently, a cluster of evacuees is created per evacuation route, and the evacuees decide if they will finally evacuate through the specific evacuation route at the current time slot or not. The evacuees’ competitive behavior is modeled as a non-co-operative minority game per each specific evacuation route. A distributed and low-complexity evacuation-planning algorithm (i.e., ESCAPE) is introduced to implement both the aforementioned evacuee decision-making layers. Finally, the proposed framework is evaluated through modeling and simulation under several scenarios, and its superiority and benefits are revealed and demonstrated
Intelligent Dynamic Data Offloading in a Competitive Mobile Edge Computing Market
No full textSoftware Defined Networks (SDN) and Mobile Edge Computing (MEC), capable of dynamically managing and satisfying the end-users computing demands, have emerged as key enabling technologies of 5G networks. In this paper, the joint problem of MEC server selection by the end-users and their optimal data offloading, as well as the optimal price setting by the MEC servers is studied in a multiple MEC servers and multiple end-users environment. The flexibility and programmability offered by the SDN technology enables the realistic implementation of the proposed framework. Initially, an SDN controller executes a reinforcement learning framework based on the theory of stochastic learning automata towards enabling the end-users to select a MEC server to offload their data. The discount offered by the MEC server, its congestion and its penetration in terms of serving end-users’ computing tasks, and its announced pricing for its computing services are considered in the overall MEC selection process. To determine the end-users’ data offloading portion to the selected MEC server, a non-cooperative game among the end-users of each server is formulated and the existence and uniqueness of the corresponding Nash Equilibrium is shown. An optimization problem of maximizing the MEC servers’ profit is formulated and solved to determine the MEC servers’ optimal pricing with respect to their offered computing services and the received offloaded data. To realize the proposed framework, an iterative and low-complexity algorithm is introduced and designed. The performance of the proposed approach was evaluated through modeling and simulation under several scenarios, with both homogeneous and heterogeneous end-users
Βέλτιστη επιλογή εταιρείας ηλεκτρικής ενέργειας & διαχείριση της απόκρισης της ζήτησης βασισμένη στη μηχανική μάθηση και στη θεωρία παιγνίων
No full text
Redesigning Resource Management in Wireless Networks based on Games in Satisfaction Form
No full text
