Fuzzy Leaky Bucket System for Intelligent Management of Consumer Electricity Elastic Load in Smart Grids

Abstract

This paper frames itself in an informational rich smart electricity grid where consumers have access to various streams of information and make decisions over their daily consumption pattern. In particular, a new intelligent management system to accommodate possible optimal decisions for elastic load consumption is discussed. The energy management system implements a fuzzy driven leaky bucket that manages the elastic load of a consumer by controlling the token rate buffer via a set of four fuzzy variables (among them the electricity price). The goal of this innovative system is to allow loads that are identified as elastic to be scheduled only when it is potentially beneficial to the consumer. To that end, a fuzzy algorithm comprised of a set of rules is developed to manage the token rate of the leaky bucket and through that the decisions over the fate of elastic loads. The developed system is applied on a set of real-world electricity consumption data taken from a residential consumer, and benchmarked against a full scheduling method, where the elastic load is fully scheduled offline. Results exhibit that the proposed fuzzy logic method outperforms the full scheduling method in the vast majority of the cases, i.e., over 79% of the cases with respect to consumption cost. Furthermore, they validate its ability to conduct real time decision making with no human in the loop.

Creativity in Generative Musical Networks: Evidence From Two Case Studies

“…Research in the field of robot musicianship has a rich history ( Rowe, 2004 ) and it has experienced an increasing interest in recent times ( Bretan and Weinberg, 2016 ). Currently there are robotic performers that can achieve very expressive performance levels, particularly with reinforcement learning approaches ( Hantrakul et al, 2018 ) and machines that can compose music in real-time based on inference rules ( Cádiz, 2020 ), or with direct interaction with its environment and people ( Miranda and Tikhanoff, 2005 ). However, the question of creativity in robot musicianship remains elusive.…”

Exploring Roughness in Left Almost Semigroups and Its Connections to Fuzzy Lie Algebras

“…One such domain is the study of energy systems and their optimization. For instance, Alamaniotis (2020) proposed a fuzzy leaky bucket system for intelligent management of consumer electricity elastic load in smart grids, demonstrating the practical implications of algebraic concepts in optimizing energy consumption [6]. Additionally, Li et al (2022) utilized the variable fuzzy set theory to assess the risk of landslide hazards in the Three Gorges region, showcasing the applicability of algebraic models in hazard analysis [7].…”

The Trifecta of Single-Cell, Systems-Biology, and Machine-Learning Approaches

“…Deep-learning architectures use multiple layers of networks to reveal high-level features. The two most common subclasses of deep learning are recurrent neural networks (RNN), which progressively feed into themselves recursively, and convolutional neural networks (CNN), which start with convolutional layers that can emphasize input features before feeding into learning layers [ 5 ]. These architectures possess unique strengths, making them suitable for differing data types and tasks which have been described in more depth by several review articles [ 4 , 5 , 6 , 7 ].…”

“…The two most common subclasses of deep learning are recurrent neural networks (RNN), which progressively feed into themselves recursively, and convolutional neural networks (CNN), which start with convolutional layers that can emphasize input features before feeding into learning layers [ 5 ]. These architectures possess unique strengths, making them suitable for differing data types and tasks which have been described in more depth by several review articles [ 4 , 5 , 6 , 7 ]. A second unique category of machine-learning approaches includes causal discovery algorithms like probabilistic graphical models which can be used to infer causal relationships, and thus are heavily used in the inference of biological networks [ 8 ].…”