Federated Learning for Distributed Reasoning on Edge Computing

Firouzi, Ramin; Rahmani, Rahim; Kanter, Theo

doi:10.1016/j.procs.2021.03.053

Cited by 12 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Federated frameworks offer promising models for processing data using ML algorithms at the edge nodes and orchestrating a global model in the cloud [11]. However, their applications in smart-grid scenarios and integration with new real-time context-aware energy asset-management services are limited.…”

Section: Data and Edge Aimentioning

confidence: 99%

“…Additionally, the adoption of IoT devices in the smart grid generates significant big data that requires AI to process, with stringent time processing requirements to prevent energy shortages [5,9]. Edge-fog-cloud federated frameworks offer promising solutions for processing data using AI at the edge nodes and orchestrating a global model in the cloud [10,11]. Nevertheless, their applications in smart-grid scenarios and integration with new real-time context-aware energy asset-management services are rather limited, even though they bring clear benefits in terms of data management in smart grid, privacy, and security, or addressing latency impact on services' delivery.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Edge Offloading in Smart Grid

Arcas,

Cioara,

Anghel

et al. 2024

Smart Cities

View full text Add to dashboard Cite

The management of decentralized energy resources and smart grids needs novel data-driven low-latency applications and services to improve resilience and responsiveness and ensure closer to real-time control. However, the large-scale integration of Internet of Things (IoT) devices has led to the generation of significant amounts of data at the edge of the grid, posing challenges for the traditional cloud-based smart-grid architectures to meet the stringent latency and response time requirements of emerging applications. In this paper, we delve into the energy grid and computational distribution architectures, including edge–fog–cloud models, computational orchestration, and smart-grid frameworks to support the design and offloading of grid applications across the computational continuum. Key factors influencing the offloading process, such as network performance, data and Artificial Intelligence (AI) processes, computational requirements, application-specific factors, and energy efficiency, are analyzed considering the smart-grid operational requirements. We conduct a comprehensive overview of the current research landscape to support decision-making regarding offloading strategies from cloud to fog or edge. The focus is on metaheuristics for identifying near-optimal solutions and reinforcement learning for adaptively optimizing the process. A macro perspective on determining when and what to offload in the smart grid is provided for the next-generation AI applications, offering an overview of the features and trade-offs for selecting between federated learning and edge AI solutions. Finally, the work contributes to a comprehensive understanding of edge offloading in smart grids, providing a Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis to support cost–benefit analysis in decision-making regarding offloading strategies.

show abstract

Section: Data and Edge Aimentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Edge Offloading in Smart Grid

Arcas,

Cioara,

Anghel

et al. 2024

Smart Cities

View full text Add to dashboard Cite

show abstract

“…The system server will collect these data and analyze the correlation between them, and then generate new data based on the written data. The work branch is resubmitted to the user for operation [12][13]. Of course, the primary source of tasks remains researchers.…”

Section: Architecture Of Ds CMmentioning

confidence: 99%

Distributed System Computation Model Based on Mobile Agent Development Platform

2020

DPS

View full text Add to dashboard Cite

With the advancement of Internet technology, people's requirements for data computing and processing are getting higher and higher, and it is difficult for a single computer to meet efficient task computing and data transmission. Therefore, multiple computers are connected to complete a large-scale project. The needs of the task are becoming more and more urgent. With the increase of this demand, the distributed system(DS) emerges as the times require, and the mobile agent technology provides a new way to solve the distributed computing(DC) problem. For the system proposed in this paper, the service quality of computing tasks is evaluated by the transparent memory(TM) usage effect of the DC system. The experiments show that the TM algorithm is the most robust to the amount of memory contributed by nodes; and then through the multi-queue node scheduling experiment, it is found that the low priority The response time of the task is higher than that of the high priority task.

show abstract

“…In federated learning, a global model is built which constitutes the main objective presented in [6,7]. In this approach, the main focus is on data protection and data privacy [8].…”

Section: Introductionmentioning

confidence: 99%

Study on the Use of Artificially Generated Objects in the Process of Training MLP Neural Networks Based on Dispersed Data

Marfo

Przybyła–Kasperek

2023

Entropy

View full text Add to dashboard Cite

This study concerns dispersed data stored in independent local tables with different sets of attributes. The paper proposes a new method for training a single neural network—a multilayer perceptron based on dispersed data. The idea is to train local models that have identical structures based on local tables; however, due to different sets of conditional attributes present in local tables, it is necessary to generate some artificial objects to train local models. The paper presents a study on the use of varying parameter values in the proposed method of creating artificial objects to train local models. The paper presents an exhaustive comparison in terms of the number of artificial objects generated based on a single original object, the degree of data dispersion, data balancing, and different network structures—the number of neurons in the hidden layer. It was found that for data sets with a large number of objects, a smaller number of artificial objects is optimal. For smaller data sets, a greater number of artificial objects (three or four) produces better results. For large data sets, data balancing and the degree of dispersion have no significant impact on quality of classification. Rather, a greater number of neurons in the hidden layer produces better results (ranging from three to five times the number of neurons in the input layer).

show abstract

Federated Learning for Distributed Reasoning on Edge Computing

Cited by 12 publications

References 15 publications

Edge Offloading in Smart Grid

Edge Offloading in Smart Grid

Distributed System Computation Model Based on Mobile Agent Development Platform

Study on the Use of Artificially Generated Objects in the Process of Training MLP Neural Networks Based on Dispersed Data

Contact Info

Product

Resources

About