Alexandru Hamza-Lup

Alexandru Hamza-Lup

Auto-generated profile, based on publicly available information

Alexandru Hamza-Lup


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
FHFelix Hamza-Lup
Felix Hamza-Lup
AHAlexandru Hamza-Lup
Alexandru Hamza-Lup
IIOANA RALUCA Goldbach
IOANA RALUCA Goldbach
Over the past decade, the deployment of edge computing has experienced substantial growth, facilitating decentralized data processing across the extensive networks of sensors embedded within Internet of Things (IoT) ecosystems. The widespread proliferation of smartphones equipped with multimodal sensing capabilities, alongside the exponential escalation in data generation and computational demands, has precipitated the emergence of novel requirements for efficient, low-latency computing at the network periphery. Edge computing addresses these emerging challenges by provisioning computational resources, data storage, and network services near the data sources. This paradigm shift effectively migrates communication and processing tasks from centralized cloud infrastructures toward the edge of the network, thereby reducing latency, bandwidth utilization, and dependency on remote data centers. Furthermore, it enhances system responsiveness, privacy preservation, and operational resilience within distributed environments. In addition to performance benefits, edge computing presents significant opportunities for energy optimization. These efficiencies can be realized through the development of energy-aware algorithms and the implementation of complementary strategies across the hardware, software, and communication protocol layers. The exploration of such techniques forms a central focus of this paper, with the aim of elucidating their collective contribution to sustainable and high-performance edge computing architectures. Emerging paradigms such as TinyML, federated learning at the edge, and LLM inference on resource-constrained devices are also reviewed as frontier directions shaping the next generation of energy-aware distributed systems.

11 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
FHFelix Hamza-Lup
Felix Hamza-Lup
AHAlexandru Hamza-Lup
Alexandru Hamza-Lup
IIOANA RALUCA Goldbach
IOANA RALUCA Goldbach
Over the past decade, the deployment of edge computing has experienced substantial growth, facilitating decentralized data processing across the extensive networks of sensors embedded within Internet of Things (IoT) ecosystems. The widespread proliferation of smartphones equipped with multimodal sensing capabilities, alongside the exponential escalation in data generation and computational demands, has precipitated the emergence of novel requirements for efficient, low-latency computing at the network periphery. Edge computing addresses these emerging challenges by provisioning computational resources, data storage, and network services near the data sources. This paradigm shift effectively migrates communication and processing tasks from centralized cloud infrastructures toward the edge of the network, thereby reducing latency, bandwidth utilization, and dependency on remote data centers. Furthermore, it enhances system responsiveness, privacy preservation, and operational resilience within distributed environments. In addition to performance benefits, edge computing presents significant opportunities for energy optimization. These efficiencies can be realized through the development of energy-aware algorithms and the implementation of complementary strategies across the hardware, software, and communication protocol layers. The exploration of such techniques forms a central focus of this paper, with the aim of elucidating their collective contribution to sustainable and high-performance edge computing architectures. Emerging paradigms such as TinyML, federated learning at the edge, and LLM inference on resource-constrained devices are also reviewed as frontier directions shaping the next generation of energy-aware distributed systems.