Large Data Centers Research Articles

Explicit construction of minimum bandwidth rack-aware regenerating codes

In large data centers, storage nodes are organized in racks, and the cross-rack transmission dominates the bandwidth cost. For the repair of single node failures, codes achieving the tradeoff between the storage redundancy and cross-rack repair bandwidth are called rack-aware regenerating codes (RRCs). In this work, we give the first explicit construction of RRCs with the minimum repair bandwidth (i.e., the cross-rack bandwidth equals the storage size per node). Our construction applies to all admissible parameters and has the lowest sub-packetization level. Moreover, the underlying finite fields are of size comparable to the number of storage nodes, which makes our codes more implementable in practice. Finally, for the convenience of practical use, we also establish a transformation to convert our codes into systematic codes.

SDN Security Review: Threat Taxonomy, Implications, and Open Challenges

Software-Defined networking (SDN) is a networking paradigm to enable dynamic, flexible, and programmatically efficient configuration of networks to revolutionize network control and management via separation of the control plane and data plane. The SDN technology has evolved in response to the demands from large data centers toward all types of networks, from IoT, enterprise, to ISP networks. On the one hand, SDN has provided solutions for high-demand resources, managing unpredictable data traffic patterns, and rapid network reconfiguration. It is further used to enhance network virtualization and security. On the other hand, SDN is still subject to many traditional network security threats. It also introduces new security vulnerabilities, primarily due to its logically centralized control plane infrastructure and functions. In this paper, we conduct a comprehensive survey on the core functionality of SDN from the perspective of secure communication infrastructure at different scales. A specific focus is put forward to address the challenges in securing SDN-based communications, with efforts taken up to address them. We further categorize the appropriate solutions for specific threats at each layer of SDN infrastructures. Lastly, security implications and future research trends are highlighted to provide insights for future research.

Predlog realizacije razvodnih postrojenja velikih data centara

Large Data Centers (DCs) needs significant energy that enables uninterruptible and quality power supply for equipment and devices in the building. Connection between DC and Power System (PS) is realized through substations (SSs). Good design of SSs and connections between them, proper equipment dimensioning as well as enabling supervisioning and management of equipment in SSs are basis for achieving high reliability and redundancy in electrical energy power supply. The paper is divided in three parts. In the first part is given a proposal for SSs realization for different voltage levels. There are described components and devices of which SSs are composed and connections between them. Second part refers to protection systems for transformers, busbars and power lines. Special emphasis is on supervision and management for SSs equipment and systems that are described in the third part of paper. In the electrical power part the proposal for a 2N + 1 design of the redundant power supply for DC from PS is given. Challenge for protection system is to enable switch-off one or a few in the many transformers in the case of failure so that on all voltage levels, remaining transformers stay functional without interruption. Functional transformers equally take over the power load of one or more transformers that are in malfunction and turn off from busbars. In the case when one busbar or a busbar system is in fault, it is necessary to enable uninterruptible power supply of the DC through functional busbar systems. Substations equipment is connected to centralized supervisory and management system (SMS) realized according to IEC 61850 standard and Transmission Control Protocol / Internet Protocol (TCP/IP) architecture. The paper provides a brief view of protocols in IEC 61850 standard and TCP/IP stack that are used in the SMS design. A vision of future automation development and application of artificial intelligence in SSs is presented at the end of the paper.

HEA-PAS: A hybrid energy allocation strategy for parallel applications scheduling on heterogeneous computing systems

Heterogeneous Computing Systems (HCS) have received widespread attention due to their powerful computing power, low cost, and high scalability. In HCS ranging from small-embedded devices to large data centers, energy consumption is one of the crucial design constraints. Meanwhile, the schedule length (response time) of parallel applications directly affects their Quality of Service (QoS) experience. In this study, we address the problem of minimizing the schedule length of energy-constrained parallel applications (MSLEC) on heterogeneous computing systems. Firstly, we define the concept of task energy demand rate and energy allocation factor to reasonably allocate the allocatable energy. Secondly, We propose a two-stage hybrid energy allocation (HEA) strategy and divide the allocatable energy into two parts according to the energy allocation factor, namely static pre-allocate energy (SAE) and dynamic pre-allocate energy (DAE). In the first stage, we pre-allocate SAE for each task based on the minimum energy demand and energy demand rate before task scheduling. In the second stage, we dynamically allocate DAE to each task during the operation of the scheduling algorithm. Thirdly, We conduct a rigorous mathematical proof of the feasibility of the proposed strategy. Finally, according to the proposed strategy, we design a novel HEA-based parallel application scheduling (HEA-PAS) algorithm, which aims to solve the MSLEC problem. Experiments on real-world and randomly generated parallel applications show that the proposed HEA-PAS algorithm outperforms the state-of-the-art methods in terms of effectiveness.

A Comprehensive Review on Data Security and Threats for Data Management in Cloud Computing

The cloud is a network of virtual computers that are linked together and may exhibit and offer computational capabilities continuously depending on certain Service Level Agreements (SLAs) that have been agreed between the parties to a contract between the clients and the internet provider. Cloud computing has several benefits, including endless computational resources, cheap cost, security controls, hypervisor protection, instantaneous elasticity, high throughput, and fault-tolerant solutions with increased performance. Since cloud computing is a comparatively recent computing model, there exists a lot of uncertainty about how well confidentiality of all levels, including host, network, data levels, and implementation, can be achieved. As a result, there still are important obstacles to cloud computing adoption. These constraints include security issues concerning privacy, compliance, and legal issues. When databases and software applications are moved from the cloud to large data centers, data management becomes a major challenge. Numerous security issues may develop while using cloud computing, including issues with privacy and control, virtualization and accessibility issues, confidentiality, management of credentials and identities, authentication of responding devices, and authenticity. In this paper, an effort is made to offer a comprehensive review of data security and threats in cloud computing.

The BondMachine, a moldable computer architecture

Future systems will be characterized by the presence of many computing core in a single device, on large scale data centers or even at the level of IoT devices. The ability to fully exploit computational architectures’ heterogeneity and concurrency will be a key point. In this manuscript we present the BondMachine (BM), an innovative prototype software ecosystem aimed at creating facilities where hardware and software are co-designed, guaranteeing a full exploitation of fabric capabilities (both in terms of concurrency and heterogeneity) with several hardware optimization possibilities. The fundamental innovation of the BM is to provide a new kind of computer architecture, where the hardware dynamically adapts to the specific computational problem rather than being static and generic, as in standard CPUs synthesized in silicon. Hardware can be designed to fit precisely any computational task needs, implementing only the processing units needed and discarding generic solutions. By using BMs within FPGA technologies end-to-end solutions could be realized, in which the creation of domain-specific hardware is part of the development process as much as the software stack. FPGA technology allows to create independent processing units on a single low-power board, and to design their interconnections “in silicon” to maximally fit the design needs. The processors of the BMs are suitable for computational structures like neural networks and tensor processing models. Machine Learning (ML) and Deep Learning (DL) popularity keeps increasing in scientific and industrial areas.

The Costs and Benefits of Supporting Data Centers: A General Equilibrium Analysis

Large data centers enjoy government support in many countries. These centers are not laborintensive, but energy-intensive, thus tending to push up electricity prices and possibly crowding out labor-intensive firms. In addition, when owned by multinational companies, profits are difficult to tax in the country of residence. We look at the benefits and costs of supporting data centers in a general equilibrium setting. We assume that an energy tax is reduced as a way of supporting such centers. We show that the net benefits of this policy depends crucially, in general equilibrium, on the value of a tax elasticity. This result can be interpreted as a ”sufficient statistics” regarding the welfare impact of such a tax-reform (in the country where the tax exemption is made). We also show, by an example, that the approach can also given useful information (in the sense of ”sufficient statistics” literature) even when the change is non-marginal.

Enhancing the Security and Performance of Cloud for E-Governance Infrastructure

E-Governance is getting momentous in India. Over the years, e-Governance has played a major part in every sphere of the economy. In this paper, we have proposed E-MODI (E-governance model for open distributed infrastructure) a centralized e-Governance system for government of India, the implementation of this system is technically based on open distributed infrastructure which comprises of various government bodies in one single centralized unit. Our proposed model identifies three different patterns of cloud computing which are DGC, SGC and CGC. In addition, readiness assessment of the services needs to migrate into cloud. In this paper, we propose energy efficient VM allocation algorithm to achieve higher energy efficiency in large scale cloud data centers when system on optimum mode. Our objectives have been explained in details and experiments were designed to demonstrate the robustness of the multi-layered security which is an integration of High secure lightweight block cipher CSL along with Ultra powerful BLAKE3 hashing function in order to maintain information security triad.

A renewable energy-aware power allocation for cloud data centers: A game theory approach

With the rapid emerging of Internet of Things (IoT) devices and the proliferation of cloud-based applications, the cloud computing industry is becoming a vital element for ensuring our daily services. However, cloud computing uses large scale data centers equipped with energy-hungry servers and huge power facilities that massively consume power. This presents a real challenge which can negatively influence the power grid, while exposing the environment to global warming issues. Therefore, minimizing cloud data center power consumption is a challenging problem and has to be addressed. In this paper, we look at renewable energy in the context of a smart grid–cloud architecture and investigate the issue of grid power dispatching to cloud data centers. Since cloud data centers have a non-cooperative nature regarding power demand from the power stations, we model our power allocation problem as a non-cooperative game. Afterwards, we prove the existence and the uniqueness of Nash equilibrium. Moreover, we formulate the payoff function of our game as a non-linear optimization problem before resolving it using Lagrange multipliers and Karush–Kuhn–Tucker (KKT) conditions. Thus, we determine the assigned optimal quantity to each data center based on three main criteria : renewable energy usage, number of critical running applications and workload charge. Extensive simulations are performed by comparing our scheme with an existing work. Results show that our scheme outperforms the comparing approach with a percentage of 31.2% in terms of power load rate and significantly reduces emissions of carbon dioxide.

Logic Locking in Single Flux Quantum Circuits

The hardware security of RSFQ circuits has become an issue of growing importance for prospective exascale computing systems. Hardware security in RSFQ circuits is particularly relevant to large scale data centers operating with sensitive information. The number of fabrication facilities for superconductive niobium-based technology is limited, and the supply chain for distributing fabricated circuits can be compromised. Logic locking is widely used in modern CMOS circuits to enhance security by masking the functionality of the circuit using a secret key. If an attacker possesses a physical circuit secured by logic locking, the attacker would be unable to determine the intended function. In this paper, a novel methodology for logic locking is proposed for SFQ circuits. Mutual inductances are used to apply additional currents to some or all of the logic gates. These currents behave as keys to access the functionality of the SFQ logic elements. In the proposed technique, only after an additional correct current is applied to all of the locked gates will the circuit produce the proper output. By using inductors with a positive and negative mutual inductance connected to the internal inductances of the gates, the range of current required to unlock a secured circuit is greatly narrowed. In this work, the operation of this proposed logic locking technique is demonstrated using modified SFQ OR gates to enable security while maintaining proper functionality. Less than 4% area overhead is achieved.

Layanan Berbasis Cloud Untuk Infrastruktur Jaringan Mobile First – Iot – Cloud Native Versi Aruba

The presence of industry 4.0, of course, has a huge impact on various industrial sectors, whose infrastructure is now being developed with the concept of cloud-based services for Mobile Network Infrastructure First - IoT - Cloud Native which is intended for large companies, campuses and data center services. employed remotely or known as the company's network infrastructure. This study aims to determine the extent to which the network technology developed by Aruba with a Cloud service model is able to provide the enterprise segment and has the freedom to choose and run cloud-based components. This study uses qualitative methods, with a research approach to the analysis of natural object concepts, with data collection techniques, explanations from resource persons and literature with natural data and describes all technological services implemented by Aruba, and uses techniques Data analysis used in this research is to use analysis in the form of documentation in the form of writing and organize the data into categories, describing it into units. The results of this study indicate that with the presence of ARUBA with cloud-based services for Mobile Network Infrastructure First - IoT - Cloud Native is able to provide and provide various kinds of solutions and is able to provide cloud services to large companies, campus data center services so that can increase business value by using the service concept offered by Aruba.

Denial-of-Service on FPGA-based Cloud Infrastructures — Attack and Defense

This paper presents attacks targeting the FPGAs of AWS F1 instances at the electrical level through power-hammering, where excessive dynamic power is used to crash FPGA instances. We demonstrate different power-hammering attacks that pass all AWS security fences implemented on F1 instances, including the FPGA vendor design rule checks. In addition, we fingerprint the FPGA instances to observe the responsiveness of the instances, which indicates a successful denial-of-service attack. Most importantly, we provide an FPGA virus scanner framework, which was improved to support large datacenter FPGAs for preventing such attacks, including virtually all currently demonstrated side-channel attacks. Our experiments showed that an AWS F1 instance crashes immediately by starting an FPGA design demanding 369W. By using FPGA-fingerprinting, we found that crashed instances are unavailable for about one to over 200 hours.

Effective Utilization of Resources Through Optimal Allocation and Opportunistic Migration of Virtual Machines in Cloud Environment

Cloud computing has become more prominent, and it is used in large data centers. Distribution of well-organized resources (bandwidth, CPU, and memory) is the major problem in the data centers. The genetically enhanced shuffling frog leaping algorithm (GESFLA) framework is proposed to select the optimal virtual machines to schedule the tasks and allocate them in physical machines (PMs). The proposed GESFLA-based resource allocation technique is useful in minimizing the wastage of resource usage and also minimizes the power consumption of the data center. The proposed GESFL algorithm is compared with task-based particle swarm optimization (TBPSO) for efficiency. The experimental results show the excellence of GESFLA over TBPSO in terms of resource usage ratio, migration time, and total execution time. The proposed GESFLA framework reduces the energy consumption of data center up to 79%, migration time by 67%, and CPU utilization is improved by 9% for Planet Lab workload traces. For the random workload, the execution time is minimized by 71%, transfer time is reduced up to 99%, and the CPU consumption is improved by 17% when compared to TBPSO.

Networking for Cloud Robotics: The DewROS Platform and Its Application

With the advances in networking technologies, robots can use the almost unlimited resources of large data centers, overcoming the severe limitations imposed by onboard resources: this is the vision of Cloud Robotics. In this context, we present DewROS, a framework based on the Robot Operating System (ROS) which embodies the three-layer, Dew-Robotics architecture, where computation and storage can be distributed among the robot, the network devices close to it, and the Cloud. After presenting the design and implementation of DewROS, we show its application in a real use-case called SHERPA, which foresees a mixed ground and aerial robotic platform for search and rescue in an alpine environment. We used DewROS to analyze the video acquired by the drones in the Cloud and quickly spot signs of human beings in danger. We perform a wide experimental evaluation using different network technologies and Cloud services from Google and Amazon. We evaluated the impact of several variables on the performance of the system. Our results show that, for example, the video length has a minimal impact on the response time with respect to the video size. In addition, we show that the response time depends on the Round Trip Time (RTT) of the network connection when the video is already loaded into the Cloud provider side. Finally, we present a model of the annotation time that considers the RTT of the connection used to reach the Cloud, discussing results and insights into how to improve current Cloud Robotics applications.

A Privacy-Preserving Outsourcing Data Storage Scheme with Oruta Data Auditing

Cloud Computing has been envisioned as the next generation architecture of IT Enterprise. In contrast to traditional solutions, where the IT services are under proper physical, logical and personnel controls, Cloud Computing moves the application software and databases to the large data centers, where the management of the data and services may not be fully trustworthy. With cloud computing and storage, users are able to access and to share resources offered by cloud service providers at a lower marginal cost. With cloud computing and storage services, data is not only stored in the cloud, but routinely shared among a large number of users in a group. In this project, we propose Oruta, a privacy-preserving auditing scheme for shared data with large groups in the cloud. We utilize ring signatures to compute verification information on shared data, so that the TPA is able to audit the correctness of shared data, but cannot reveal the identity of the signer on each block. We can implement the batch auditing scheme to perform efficient public auditing to protect both identity and data privacy in cloud environments.

Fault-Tolerant and Unicast Performances of the Data Center Network HSDC

In order to satisfy the rapidly increasing demand for data volume, large data center networks (DCNs) have been proposed. In 2019, Zhang et al. proposed a new highly scalable DCN architecture named HSDC (Highly Scalable Data Center Network), which can achieve greater incremental scalability. In this paper, we give the definition of the logical graph of HSDC, named $$H_n$$ , which can be treated as a compound graph of hypercube and complete graph of the same dimension. First, we prove that the connectivity and tightly super connectivity of $$H_n$$ are both n. Then, we give an O(n) shortest unicast algorithm to find a shortest path between any two distinct nodes in $$H_n$$ , and prove the correctness of this algorithm. In fact, we also prove that the length of the shortest path constructed by this algorithm is no more than $$2d+1$$ if $$d<n$$ and at most 2d if $$d=n$$ , where d is the Hamming distance between the start and end nodes, and the diameter of $$H_n$$ is 2n.

Learning Large Electrical Loads via Flexible Contracts With Commitment

Large electricity customers (e.g., large data centers) can exhibit huge and variable electricity demands, which poses significant challenges for the electricity suppliers to plan for sufficient capacity. Thus, it is desirable to design incentive and coordination mechanisms between the customers and the supplier to lower the capacity cost. This paper proposes a novel scheme based on flexible contracts. Unlike existing demand-side management schemes in the literature, a flexible contract leads to information revelation. That is, a customer committing to a flexible contract reveals valuable information about its future demand to the supplier. Such information revelation allows the customers and the supplier to share the risk of future demand uncertainty. On the other hand, the customer will still retain its autonomy in operation. We address two key challenges for the design of optimal flexible contracts: i) the contract design is a non-convex optimization problem and is intractable for a large number of customer types, and ii) the design should be robust to unexpected or adverse responses of the customers, i.e., a customer facing more than one contract yielding the same benefit may choose the contract less favorable to the supplier. We address these challenges by proposing sub-optimal contracts of low computational complexity that can achieve a provable fraction of the performance gain under the global optimum.

Minimizing energy on homogeneous processors with shared memory

Energy efficiency is a crucial desideratum in the design of computer systems, from small-sized mobile devices with limited battery to large scale data centers. In such computing systems, processors and memory are considered as two major power consumers among all the system components. One recent trend to reduce power consumption is using shared memory in multi-core systems, such architecture has become ubiquitous nowadays. However, implementing the energy-efficient methods to the multi-core processor and the shared memory separately is not trivial. In this work, we consider the energy-efficient task scheduling problem, which coordinates the power consumption of both the multi-core processor and the shared memory, especially focus on the general situation in which the number of tasks is more than the number of cores. We devise an approximation algorithm with guaranteed performance in the multiple cores system. We tackle the problem by first presenting an optimal algorithm when the assignment of tasks to cores is given. Then we propose an approximation assignment for the general task scheduling.

Task Allocation Framework For Software-Defined Fog v-RAN

The fifth-generation wireless technology (5G) has been developed with an aim to provide ubiquitous and scalable connectivity for Internet-of-Things (IoT) nodes. Likewise, the cloud radio access network (C-RAN) architecture can be exploited to enable efficient network access to IoT nodes. Nevertheless, the 5G C-RAN architecture is based on large data centers geographically located far apart, which introduces an inevitable overhead. Therefore, to supply real-time data services near by the data terminals, fog computing emerges as a promising solution. However, constrained physical fog resources and delay-sensitive services hinder the application of new virtualization technologies in the baseband unit (BBU) task allocation management of the fog network. To tackle these challenges, a task allocation framework for hierarchical software-defined fog virtual radio access networks (v-RANs) is proposed in this article. Precisely, we apply an enhanced ant colony optimization (ACO) in combination with a max-min algorithm to efficiently determine the optimal path for BBU task allocation management, while minimizing the transmission time for parallel task execution scheduling. Experimental results demonstrate that the queue delay in our approach is 98.38% and 98.82% lower than the round-robin (RR) algorithm and least connection technique (LCT), respectively.

End-to-End Provisioning of Latency and Availability Constrained 5G Services

We address a key challenge of 5G networks by proposing a strategy for the resource-efficient and end-to-end allocation of compute and connectivity resources in a dynamic 5G service provisioning scenario, such that the service latency and availability requirements are guaranteed. Our heuristic algorithm shows that resource efficiency is significantly improved by processing services in the large core data centers (DCs) with a rich amount of compute resources and exploiting the benefits of traffic grooming over the metro and core fiber links. Moreover, our resource-efficient provisioning algorithm avoids possible violation of the service availability requirements caused by reaching the central DC locations by adding backup connectivity resources. Our simulation results demonstrate a resource efficiency improvement reflected by lowering the service blocking probability by up to four orders of magnitude compared to the conventional service provisioning methods utilizing distributed small DCs.