Bilgisayar Mühendisliği Bölümü Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1940
Browse
23 results
Search Results
Article Minimum Repair Bandwidth Ldpc Codes for Distributed Storage Systems(IEEE, 2023) Pourmandi, Massoud; Pusane, Ali Emre; Arslan , Şuayb Şefik; Haytaoğlu, ElifIn distributed storage systems (DSS), an optimal code design must meet the requirements of efficient local data regeneration in addition to reliable data retention. Recently, lowdensity parity-check (LDPC) codes have been proposed as a promising candidate that can secure high data rates as well as low repair bandwidth while maintaining low complexity in data reconstruction. The main objective of this study is to optimize the repair bandwidth characteristics of LDPC code families for a DSS application while meeting the data reliability requirements. First, a data access scenario in which nodes contact other available nodes randomly to download data is examined. Later, a minimum-bandwidth protocol is considered in which nodes make their selections based on the degree numbers of check nodes. Through formulating optimization problems for both protocols, a fundamental trade-off between the decoding threshold and the repair bandwidth is established for a given code rate. Finally, conclusions are confirmed by numerical results showing that irregular constructions have a large potential for establishing optimized LDPC code families for DSS applications.Conference Object Residual Data Usage in LDPC Codes(IEEE, 2022-05-15) Kaya, Erdi; Pourmandi, Massoud; Haytaoglu, Elif; Arslan, Şefik ŞuaybIn distributed storage systems/coded caching systems, padding operations should be performed when the encoded data cannot be divided by the number of storage nodes evenly. Thus, extra zero values are stored in one of the nodes to balance each node's storage content. In this study, distribution of data to storage nodes with no padding was investigated for distributed caching context in which a base station and devices both store the coded data. In other words, no redundancy (no-padding) is included into the encoded data. This approach is named as residual data distribution. LDPC codes are selected as the erasure code due to their low complexity encode/decode operations. Moreover, performance comparisons were conducted between using traditional data distribution approach (with padding) and using residual data (use of no-padding) (standard) in terms of repair time. In our work, the effect of no-padding data usage on the repair time and the ratios of storage savings have been also demonstrated.Conference Object Citation - Scopus: 1Improved Bounds on the Moments of Guessing Cost(IEEE, 2022-06-26) Arslan, Suayb S.; Haytaoglu, ElifGuessing a random variable with finite or countably infinite support in which each selection leads to a positive cost value has recently been studied within the context of "guessing cost". In those studies, similar to standard guesswork, upper and lower bounds for the rho-th moment of guessing cost are described in terms of the known measure Renyi's entropy. In this study, we non-trivially improve the known bounds using previous techniques along with new notions such as balancing cost. We have demonstrated that the novel lower bound proposed in this work, achieves 5.84%, 18.47% higher values than that of the known lower bound for rho = 1 and rho = 5, respectively. As for the upper bound, the novel expression provides 10.93%, 5.54% lower values than that of the previously presented bounds for rho = 1 and rho = 5, respectively.Conference Object Citation - WoS: 2Citation - Scopus: 2Base Station-Assisted Cooperative Network Coding for Cellular Systems With Link Constraints(IEEE, 2022-06-26) Arslan, Suayb S.; Pourmandi, Massoud; Haytaoglu, ElifWe consider a novel distributed data storage/caching scenario in a cellular network, where multiple nodes may fail/depart simultaneously To meet reliability, we allow cooperative regeneration of lost nodes with the help of base stations allocated in a set of hierarchical layers1. Due to this layered structure, a symbol download from each base station has a different cost, while the link capacities between the nodes of the cellular system and the base stations are also constrained. Under such a setting, we formulate the fundamental trade-off with closed form expressions between repair bandwidth cost and the storage space per node. Particularly, the minimum storage as well as bandwidth cost points are formulated. Finally, we provide an explicit optimal code construction for the minimum storage regeneration point for a special set of system parameters.Article Citation - WoS: 3Citation - Scopus: 3Array Bp-Xor Codes for Hierarchically Distributed Matrix Multiplication(IEEE, 2022-03-01) Arslan, Şuayb ŞefikA novel fault-tolerant computation technique based on array Belief Propagation (BP)-decodable XOR (BP-XOR) codes is proposed for distributed matrix-matrix multiplication. The proposed scheme is shown to be configurable and suited for modern hierarchical compute architectures such as Graphical Processing Units (GPUs) equipped with multiple nodes, whereby each has many small independent processing units with increased core-to-core communications. The proposed scheme is shown to outperform a few of the well–known earlier strategies in terms of total end-to-end execution time while in presence of slow nodes, called stragglers. This performance advantage is due to the careful design of array codes which distributes the encoding operation over the cluster (slave) nodes at the expense of increased master-slave communication. An interesting trade-off between end-to-end latency and total communication cost is precisely described. In addition, to be able to address an identified problem of scaling stragglers, an asymptotic version of array BP-XOR codes based on projection geometry is proposed at the expense of some computation overhead. A thorough latency analysis is conducted for all schemes to demonstrate that the proposed scheme achieves order-optimal computation in both the sublinear as well as the linear regimes in the size of the computed product from an end-to-end delay perspective.Article Citation - WoS: 4Citation - Scopus: 6Data Repair-Efficient Fault Tolerance for Cellular Networks Using Ldpc Codes(IEEE, 2022-01-01) Haytaoglu, Elif; Kaya, Erdi; Arslan, Şuayb ŞefikThe base station-mobile device communication traffic has dramatically increased recently due to mobile data, which in turn heavily overloaded the underlying infrastructure. To decrease Base Station (BS) interaction, intra-cell communication between local devices, known as Device-to-Device, is utilized for distributed data caching. Nevertheless, due to the continuous departure of existing nodes and the arrival of newcomers, the missing cached data may lead to permanent data loss. In this study, we propose and analyze a class of LDPC codes for distributed data caching in cellular networks. Contrary to traditional distributed storage, a novel repair algorithm for LDPC codes is proposed which is designed to exploit the minimal direct BS communication. To assess the versatility of LDPC codes and establish performance comparisons to classic coding techniques, novel theoretical and experimental evaluations are derived. Essentially, the theoretical/numerical results for repair bandwidth cost in presence of BS are presented in a distributed caching setting. Accordingly, when the gap between the cost of downloading a symbol from BS and from other local network nodes is not dramatically high, we demonstrate that LDPC codes can be considered as a viable fault-tolerance alternative in cellular systems with caching capabilities for both low and high code rates.Conference Object Citation - WoS: 3Citation - Scopus: 3Data Repair in Bs-Assisted Distributed Data Caching(IEEE, 2020-10-05) Kaya, Erdi; Haytaoğlu, Elif; Arslan, Şuayb ŞefikIn this paper, centralized and independent repair approaches based on device-to-device communication for the repair of the lost nodes have been investigated in a cellular network where distributed caching is applied whose fault tolerance is provided by erasure codes. The caching mechanisms based on Reed-Solomon codes and minimum bandwidth regenerating codes are adopted. The proposed approaches are analyzed in a simulation environment in terms of base station utilization load during the repair process. Based on the intuitive assumption that the base station is usually more costly than device-to-device communication, the centralized repair approach demonstrates a better performance than the independent repair approaches on the number of symbols retrieved from the base station. On the other hand, the centralized approach has not achieved a dramatic reduction in the number of symbols downloaded from the other devices.Conference Object Citation - WoS: 1Citation - Scopus: 1Adaptive Boosting of Dnn Ensembles for Brain-Computer Interface Spellers(IEEE, 2021-06-09) Çatak, Yiğit; Aksoy, Can; Özkan, Hüseyin; Güney, Osman Berke; Koç, Emirhan; Arslan, Şuayb ŞefikSteady-state visual evoked potentials (SSVEP) are commonly used in brain computer interface (BCI) applications such as spelling systems, due to their advantages over other paradigms. In this study, we develop a method for SSVEP-based BCI speller systems, using a known deep neural network (DNN), which includes transfer and ensemble learning techniques. We test performance of our method on publicly available benchmark and BETA datasets with leave-one-subject-out procedure. Our method consists of two stages. In the first stage, a global DNN is trained using data from all subjects except one subject that is excluded for testing. In the second stage, the global model is fine-tuned to each subject whose data are used in the training. Combining the responses of trained DNNs with different weights for each test subject, rather than an equal weight, provide better performance as brain signals may differ significantly between individuals. To this end, weights of DNNs are learnt with SAMME algorithm with using data belonging to the test subject. Our method significantly outperforms canonical correlation analysis (CCA) and filter bank canonical correlation analysis (FBCCA) methods.Conference Object Citation - WoS: 2Citation - Scopus: 1Average Bandwidth-Cost Vs. Storage Trade-Off for Bs-Assisted Distributed Storage Networks(IEEE, 2021-06-09) Tengiz, Ayse Ceyda; Haytaoğlu, Elif; Pusane, Ali Emre; Arslan, Şuayb Şefik; Pourmandi, MassoudIn this study, we consider a hierarchically structured base station (BS)-assisted cellular system equipped with a backend distributed data storage in which nodes randomly arrive and depart the cell. We numerically motivate and characterize the fundamental trade-off between the average repair bandwidth cost versus storage space where BS communication cost (higher than that of local) and link capacity constraints exist while the number of failed nodes can vary dynamically. We establish the capacity region that is most relevant to 5G and beyond networks, which are layered by design. We hope that this study shall motivate novel regeneration code constructions that will be able to achieve the presented limits.Conference Object Fault-Tolerant Strassen-Like Matrix Multiplication(IEEE, 2020) Arslan, Şuayb Şefik; Güney, Osman B.; Oblokulov, MuhtashamIn this study, we propose a simple method for fault-tolerant Strassen-like matrix multiplications. The proposed method is based on using two distinct Strassen-like algorithms instead of replicating a given one. We have realized that using two different algorithms, new check relations arise resulting in more local computations. These local computations are found using computer aided search. To improve performance, special parity (extra) sub-matrix multiplications (PSMMs) are generated (two of them) at the expense of increasing communication/computation cost of the system. Our preliminary results demonstrate that the proposed method outperforms a Strassen-like algorithm with two copies and secures a very close performance to three copy version using only 2 PSMMs, reducing the total number of compute nodes by around 24% i.e., from 21 to 16.
- «
- 1 (current)
- 2
- 3
- »