arXiv subjects

Öznur Özkasap

Publications and source records attributed to Öznur Özkasap.

At least 19 recordsLinked to original sources

arXiv2025

FedBWO: Enhancing Communication Efficiency in Federated Learning

Federated Learning (FL) is a distributed Machine Learning (ML) setup, where a shared model is collaboratively trained by various clients using their local datasets while keeping the data private. Considering resource-constrained devices, FL clients often suffer from restricted transmission capacity. Aiming to enhance the system performance, the communication between clients and server needs to be diminished. Current FL strategies transmit a tremendous amount of data (model weights) within the FL process, which needs a high communication bandwidth. Considering resource constraints, increasing the number of clients and, consequently, the amount of data (model weights) can lead to a bottleneck. In this paper, we introduce the Federated Black Widow Optimization (FedBWO) technique to decrease the amount of transmitted data by transmitting only a performance score rather than the local model weights from clients. FedBWO employs the BWO algorithm to improve local model updates. The conducted experiments prove that FedBWO remarkably improves the performance of the global model and the communication efficiency of the overall system. According to the experimental outcomes, FedBWO enhances the global model accuracy by an average of 21% over FedAvg, and 12% over FedGWO. Furthermore, FedBWO dramatically decreases the communication cost compared to other methods.

cs.LG↗

arXiv2025

ED-DAO: Energy Donation Algorithms based on Decentralized Autonomous Organization

Energy is a fundamental component of modern life, driving nearly all aspects of daily activities. As such, the inability to access energy when needed is a significant issue that requires innovative solutions. In this paper, we propose ED-DAO, a novel fully transparent and community-driven decentralized autonomous organization (DAO) designed to facilitate energy donations. We analyze the energy donation process by exploring various approaches and categorizing them based on both the source of donated energy and funding origins. We propose a novel Hybrid Energy Donation (HED) algorithm, which enables contributions from both external and internal donors. External donations are payments sourced from entities such as charities and organizations, where energy is sourced from the utility grid and prosumers. Internal donations, on the other hand, come from peer contributors with surplus energy. HED prioritizes donations in the following sequence: peer-sourced energy (P2D), utilitygrid-sourced energy (UG2D), and direct energy donations by peers (P2PD). By merging these donation approaches, the HED algorithm increases the volume of donated energy, providing a more effective means to address energy poverty. Experiments were conducted on a dataset to evaluate the effectiveness of the proposed method. The results showed that HED increased the total donated energy by at least 0.43% (64 megawatts) compared to the other algorithms (UG2D, P2D, and P2PD).

cs.DC↗

arXiv2024

DiabML: AI-assisted diabetes diagnosis method with meta-heuristic-based feature selection

Diabetes is a chronic disorder identified by the high sugar level in the blood that can cause various different disorders such as kidney failure, heart attack, sightlessness, and stroke. Developments in the healthcare domain by facilitating the early detection of diabetes risk can help not only caregivers but also patients. AIoMT is a recent technology that integrates IoT and machine learning methods to give services for medical purposes, which is a powerful technology for the early detection of diabetes. In this paper, we take advantage of AIoMT and propose a hybrid diabetes risk detection method, DiabML, which uses the BWO algorithm and ML methods. BWO is utilized for feature selection and SMOTE for imbalance handling in the pre-processing procedure. The simulation results prove the superiority of the proposed DiabML method compared to the existing works. DiabML achieves 86.1\% classification accuracy by AdaBoost classifier outperforms the relevant existing methods.

cs.LG↗

arXiv2024

Blockchain-enabled Energy Trading and Battery-based Sharing in Microgrids

Carbon footprint reduction can be achieved through various methods, including the adoption of renewable energy sources. The installation of such sources, like photovoltaic panels, while environmentally beneficial, is cost-prohibitive for many. Those lacking photovoltaic solutions typically resort to purchasing energy from utility grids that often rely on fossil fuels. Moreover, when users produce their own energy, they may generate excess that goes unused, leading to inefficiencies. To address these challenges, this paper proposes innovative blockchain-enabled energy-sharing algorithms that allow consumers -- without financial means -- to access energy through the use of their own energy storage units. We explore two sharing models: a centralized method and a peer-to-peer (P2P) one. Our analysis reveals that the P2P model is more effective, enhancing the sharing process significantly compared to the centralized method. We also demonstrate that, when contrasted with traditional battery-supported trading algorithm, the P2P sharing algorithm substantially reduces wasted energy and energy purchases from the grid by 73.6%, and 12.3% respectively. The proposed system utilizes smart contracts to decentralize its structure, address the single point of failure concern, improve overall system transparency, and facilitate peer-to-peer payments.

cs.DC↗

arXiv2023

Decentralized Healthcare Systems with Federated Learning and Blockchain

Artificial intelligence (AI) and deep learning techniques have gained significant attraction in recent years, owing to their remarkable capability of achieving high performance across a broad range of applications. However, a crucial challenge in training such models is the acquisition of vast amounts of data, which is often limited in fields like healthcare. In this domain, medical data is typically scattered across various sources such as hospitals, clinics, and wearable devices. The aggregated data collected from multiple sources in the healthcare domain is sufficient for training advanced deep learning models. However, these sources are frequently hesitant to share such data due to privacy considerations. To address this challenge, researchers have proposed the integration of blockchain and federated learning to develop a system that facilitates the secure sharing of medical records. This work provides a succinct review of the current state of the art in the use of blockchain and federated learning in the decentralized healthcare domain.

cs.DC↗

arXiv2023

Blockchain-based Federated Learning for Decentralized Energy Management Systems

The Internet of Energy (IoE) is a distributed paradigm that leverages smart networks and distributed system technologies to enable decentralized energy systems. In contrast to the traditional centralized energy systems, distributed Energy Internet systems comprise multiple components and communication requirements that demand innovative technologies for decentralization, reliability, efficiency, and security. Recent advances in blockchain architectures, smart contracts, and distributed federated learning technologies have opened up new opportunities for realizing decentralized Energy Internet services. In this paper, we present a comprehensive analysis and classification of state-of-the-art solutions that employ blockchain, smart contracts, and federated learning for the IoE domains. Specifically, we identify four representative system models and discuss their key aspects. These models demonstrate the diverse ways in which blockchain, smart contracts, and federated learning can be integrated to support the main domains of IoE, namely distributed energy trading and sharing, smart microgrid energy networks, and electric and connected vehicle management. Furthermore, we provide a detailed comparison of the different levels of decentralization, the advantages of federated learning, and the benefits of using blockchain for the IoE systems. Additionally, we identify open issues and areas for future research for integrating federated learning and blockchain in the Internet of Energy domains.

cs.DC↗

arXiv2022

FLAGS Framework for Comparative Analysis of Federated Learning Algorithms

Federated Learning (FL) has become a key choice for distributed machine learning. Initially focused on centralized aggregation, recent works in FL have emphasized greater decentralization to adapt to the highly heterogeneous network edge. Among these, Hierarchical, Device-to-Device and Gossip Federated Learning (HFL, D2DFL \& GFL respectively) can be considered as foundational FL algorithms employing fundamental aggregation strategies. A number of FL algorithms were subsequently proposed employing multiple fundamental aggregation schemes jointly. Existing research, however, subjects the FL algorithms to varied conditions and gauges the performance of these algorithms mainly against Federated Averaging (FedAvg) only. This work consolidates the FL landscape and offers an objective analysis of the major FL algorithms through a comprehensive cross-evaluation for a wide range of operating conditions. In addition to the three foundational FL algorithms, this work also analyzes six derived algorithms. To enable a uniform assessment, a multi-FL framework named FLAGS: Federated Learning AlGorithms Simulation has been developed for rapid configuration of multiple FL algorithms. Our experiments indicate that fully decentralized FL algorithms achieve comparable accuracy under multiple operating conditions, including asynchronous aggregation and the presence of stragglers. Furthermore, decentralized FL can also operate in noisy environments and with a comparably higher local update rate. However, the impact of extremely skewed data distributions on decentralized FL is much more adverse than on centralized variants. The results indicate that it may not be necessary to restrict the devices to a single FL algorithm; rather, multi-FL nodes may operate with greater efficiency.

cs.LG↗

arXiv2022

DHT-based Edge and Fog Computing Systems: Infrastructures and Applications

Intending to support new emerging applications with latency requirements below what can be offered by the cloud data centers, the edge and fog computing paradigms have reared. In such systems, the real-time instant data is processed closer to the edge of the network, instead of the remote data centers. With the advances in edge and fog computing systems, novel and efficient solutions based on Distributed Hash Tables (DHTs) emerge and play critical roles in system design. Several DHT-based solutions have been proposed to either augment the scalability and efficiency of edge and fog computing infrastructures or to enable application-specific functionalities such as task and resource management. This paper presents the first comprehensive study on the state-of-the-art DHT-based architectures in edge and fog computing systems from the lenses of infrastructure and application. Moreover, the paper details the open problems and discusses future research guidelines for the DHT-based edge and fog computing systems.

cs.DC↗

arXiv2021

DHT-based Communications Survey: Architectures and Use Cases

Several distributed system paradigms utilize Distributed Hash Tables (DHTs) to realize structured peer-to-peer (P2P) overlays. DHT structures arise as the most commonly used organizations for peers that can efficiently perform crucial services such as data storage, replication, query resolution, and load balancing. With the advances in various distributed system technologies, novel and efficient solutions based on DHTs emerge and play critical roles in system design. DHT-based methods and communications have been proposed to address challenges such as scalability, availability, reliability and performance, by considering unique characteristics of these technologies. In this article, we propose a classification of the state-of-the-art DHT-based methods focusing on their system architecture, communication, routing and technological aspects across various system domains. To the best of our knowledge, there is no comprehensive survey on DHT-based applications from system architecture and communication perspectives that spans various domains of recent distributed system technologies. We investigate the recently emerged DHT-based solutions in the seven key domains of edge and fog computing, cloud computing, blockchain, the Internet of Things (IoT), Online Social Networks (OSNs), Mobile Ad Hoc Networks (MANETs), and Vehicular Ad Hoc Networks (VANETs). In contrast to the existing surveys, our study goes beyond the commonly known DHT methods such as storage, routing, and lookup, and identifies diverse DHT-based solutions including but not limited to aggregation, task scheduling, resource management and discovery, clustering and group management, federation, data dependency management, and data transmission. Furthermore, we identify open problems and discuss future research guidelines for each domain.

cs.DC↗

arXiv2021

LightChain: Scalable DHT-Based Blockchain

As an append-only distributed database, blockchain is utilized in a vast variety of applications including the cryptocurrency and Internet-of-Things (IoT). The existing blockchain solutions show downsides in communication and storage scalability, as well as decentralization. In this article, we propose LightChain , which is the first blockchain architecture that operates over a Distributed Hash Table (DHT) of participating peers. LightChain is a permissionless blockchain that provides addressable blocks and transactions within the network, which makes them efficiently accessible by all peers. Each block and transaction is replicated within the DHT of peers and is retrieved in an on-demand manner. Hence, peers in LightChain are not required to retrieve or keep the entire ledger. LightChain is fair as all of the participating peers have a uniform chance of being involved in the consensus regardless of their influence such as hashing power or stake. We provide formal mathematical analysis and experimental results (simulations and cloud deployment) to demonstrate the security, efficiency, and fairness of LightChain , and show that LightChain is the only existing blockchain that can provide integrity under the corrupted majority power of peers. As we experimentally demonstrate, compared to the mainstream blockchains such as Bitcoin and Ethereum, LightChain requires around 66 times smaller per node storage, and is around 380 times faster on bootstrapping a new node to the system, and each LightChain node is rewarded equally likely for participating in the protocol.

cs.DC↗

arXiv2020

State-of-the-art Techniques in Deep Edge Intelligence

The potential held by the gargantuan volumes of data being generated across networks worldwide has been truly unlocked by machine learning techniques and more recently Deep Learning. The advantages offered by the latter have seen it rapidly becoming a framework of choice for various applications. However, the centralization of computational resources and the need for data aggregation have long been limiting factors in the democratization of Deep Learning applications. Edge Computing is an emerging paradigm that aims to utilize the hitherto untapped processing resources available at the network periphery. Edge Intelligence (EI) has quickly emerged as a powerful alternative to enable learning using the concepts of Edge Computing. Deep Learning-based Edge Intelligence or Deep Edge Intelligence (DEI) lies in this rapidly evolving domain. In this article, we provide an overview of the major constraints in operationalizing DEI. The major research avenues in DEI have been consolidated under Federated Learning, Distributed Computation, Compression Schemes and Conditional Computation. We also present some of the prevalent challenges and highlight prospective research avenues.

cs.AI↗

arXiv2020

LightChain: A DHT-based Blockchain for Resource Constrained Environments

As an append-only distributed database, blockchain is utilized in a vast variety of applications including the cryptocurrency and Internet-of-Things (IoT). The existing blockchain solutions have downsides in communication and storage efficiency, convergence to centralization, and consistency problems. In this paper, we propose LightChain, which is the first blockchain architecture that operates over a Distributed Hash Table (DHT) of participating peers. LightChain is a permissionless blockchain that provides addressable blocks and transactions within the network, which makes them efficiently accessible by all the peers. Each block and transaction is replicated within the DHT of peers and is retrieved in an on-demand manner. Hence, peers in LightChain are not required to retrieve or keep the entire blockchain. LightChain is fair as all of the participating peers have a uniform chance of being involved in the consensus regardless of their influence such as hashing power or stake. LightChain provides a deterministic fork-resolving strategy as well as a blacklisting mechanism, and it is secure against colluding adversarial peers attacking the availability and integrity of the system. We provide mathematical analysis and experimental results on scenarios involving 10K nodes to demonstrate the security and fairness of LightChain. As we experimentally show in this paper, compared to the mainstream blockchains like Bitcoin and Ethereum, LightChain requires around 66 times less per node storage, and is around 380 times faster on bootstrapping a new node to the system, while each LightChain node is rewarded equally likely for participating in the protocol.

cs.DC↗

arXiv2020

SkipSim: Scalable Skip Graph Simulator

SkipSim is an offline Skip Graph simulator that enables Skip Graph-based algorithms including blockchains and P2P cloud storage to be simulated while preserving their scalability and decentralized nature. To the best of our knowledge, it is the first Skip Graph simulator that provides several features for experimentation on Skip Graph-based overlay networks. In this demo paper, we present SkipSim features, its architecture, as well as a sample blockchain demo scenario.

cs.DC↗

arXiv2020

A containerized proof-of-concept implementation of LightChain system

LightChain is the first Distributed Hash Table (DHT)-based blockchain with a logarithmic asymptotic message and memory complexity. In this demo paper, we present the software architecture of our open-source implementation of LightChain, as well as a novel deployment scenario of the entire LightChain system on a single machine aiming at results reproducibility.

cs.DC↗

arXiv2020

Demo: A Proof-of-Concept Implementation of Guard Secure Routing Protocol

Skip Graphs belong to the family of Distributed Hash Table (DHT) structures that are utilized as routing overlays in various peer-to-peer applications including blockchains, cloud storage, and social networks. In a Skip Graph overlay, any misbehavior of peers during the routing of a query compromises the system functionality. Guard is the first authenticated search mechanism for Skip Graphs, enables reliable search operation in a fully decentralized manner. In this demo paper, we present a proof-of-concept implementation of Guard on Skip Graph nodes as well as a deployment demo scenario.

cs.DC↗

arXiv2020

EdgeKV: Decentralized, scalable, and consistent storage for the edge

Edge computing moves the computation closer to the data and the data closer to the user to overcome the high latency communication of cloud computing. Storage at the edge allows data access with high speeds that enable latency-sensitive applications in areas such as autonomous driving and smart grid. However, several distributed services are typically designed for the cloud and building an efficient edge-enabled storage system is challenging because of the distributed and heterogeneous nature of the edge and its limited resources. In this paper, we propose EdgeKV, a decentralized storage system designed for the network edge. EdgeKV offers fast and reliable storage, utilizing data replication with strong consistency guarantees. With a location-transparent and interface-based design, EdgeKV can scale with a heterogeneous system of edge nodes. We implement a prototype of the EdgeKV modules in Golang and evaluate it in both the edge and cloud settings on the Grid'5000 testbed. We utilize the Yahoo! Cloud Serving Benchmark (YCSB) to analyze the system's performance under realistic workloads. Our evaluation results show that EdgeKV outperforms the cloud storage setting with both local and global data access with an average write response time and throughput improvements of 26% and 19% respectively under the same settings. Our evaluations also show that EdgeKV can scale with the number of clients, without sacrificing performance. Finally, we discuss the energy efficiency improvement when utilizing edge resources with EdgeKV instead of a centralized cloud.

cs.DC↗

arXiv2019

RESDN: A Novel Metric and Method for Energy Efficient Routing in Software Defined Networks

Software-defined networking (SDN) paradigm, with the flexible and logically centralized control, enables dynamically minimizing the network energy consumption by redirecting paths of packets. However, the links and switches are designed to accommodate maximum traffic volume and their power consumption is not traffic proportional. Moreover, there exists a trade-off between energy efficiency and network performance that need to be considered together. Addressing these issues, we propose an energy efficiency metric named Ratio for Energy Saving in SDN (RESDN) that quantifies energy efficiency based on link utility intervals. We provide integer programming formulation and method for maximizing the RESDN of the network. To the best of our knowledge, RESDN approach is novel as it measures how links are profitably utilized in terms of the amount of energy they consume with respect to their utility. We analyze our approach considering various metrics of interest, and different types of SDN enabled switches. Experiments show that maximizing the RESDN value improves energy efficiency while maintaining acceptable network performance. In comparison to state-of-the-art utility-based heuristics, RESDN method achieves up to 30% better ratio for energy saving, 14.7 watts per switch power saving, 38% link saving, 2 hops decrease in average path length, 5% improved traffic proportionality.

cs.NI↗

arXiv2019

A Survey of Energy Efficiency in SDN Software Based Methods and Optimization Models

Software Defined Networking (SDN) paradigm has the benefits of programmable network elements by separating the control and the forwarding planes, efficiency through optimized routing and flexibility in network management. As the energy costs contribute largely to the overall costs in networks, energy efficiency has become a significant design requirement for modern networking mechanisms. However, designing energy efficient solutions is non-trivial since they need to tackle the trade-off between energy efficiency and network performance. In this article, we address the energy efficiency capabilities that can be utilized in the emerging SDN. We provide a comprehensive and novel classification of software-based energy efficient solutions into subcategories of traffic aware, end system aware and rule placement. We propose general optimization models for each subcategory, and present the objective function, the parameters and constraints to be considered in each model. Detailed information on the characteristics of state-of-the-art methods, their advantages, drawbacks are provided. Hardware-based solutions used to enhance the efficiency of switches are also described. Furthermore, we discuss the open issues and future research directions in the area of energy efficiency in SDN.

cs.NI↗