Global Data Access Research Articles

Elementary flow mapping across life cycle inventory data systems: A case study for data interoperability under the Global Life Cycle Assessment Data Access (GLAD) initiative

PurposeLimited availability of life cycle assessment (LCA) data poses a significant challenge to its mainstream adoption, rendering it a central issue within the LCA community. The Global LCA Data Access (GLAD) network aims to increase the accessibility and interoperability of LCA data and offers benefits for different use cases. GLAD is an intergovernmental collaboration involving different stakeholders organized into working groups. The GLAD Nomenclature Working Group (NWG) developed a procedure and a set of criteria to map elementary flows among major nomenclature systems and reviewed bidirectional mappings. This paper provides an overview of the methodological approach followed by the NWG to achieve the resulting mapping files.MethodsThe mapping procedure involves several steps of flow and compartment matches and bilateral review. The procedure is supported by an ad hoc software tool called the “GLAD Mapper Tool” developed with the NWG and which is made available for free by the European Commission. The input files for the procedure are the properly formatted source and target flow lists and a file containing the mapping criteria. The four nomenclature systems mapped are those used in ecoinvent, Environmental Footprint, IDEA, and the U.S. Federal LCA Commons. The procedure included representatives from each of these nomenclature systems to ensure a multilateral agreement on the approach to verifying and assessing the quality of the results. The iterative mapping process included different stages of bidirectional reviews to achieve a balance between mapping coverage (i.e., percentage of source flows covered by the target list) and accuracy.Results and discussionThe mapping procedure proved to be an efficient approach for LCA practitioners in mappings between different nomenclature systems. After a relatively low number of iterations, mapping coverages higher than 90% were achieved, which is driven by the availability of unique substances (flow names) and the granularity of environmental compartments. Overall, none of the four flow lists achieved full coverage and the use of approximated matches (proxy matches) for environmental compartments and/or substances was necessary when a perfect matches between flows were not possible.ConclusionsThe NWG’s mapping activities may serve as a starting point towards defining a central hub for mapping impact assessment methods and datasets, improving data accessibility and interoperability for the LCA community as a step towards defining a unified nomenclature system. The GLAD mapping approach is open and transparent. The approach fosters traceability in the mapping process and offers the potential for greater interoperability across the LCA community, underlining the commitment to openness and collaboration.

Indexing legacy data-sets for global access and processing in multi-cloud environments

Global data access and processing for multi-cloud applications proves challenging where there is a need for efficient access to large pre-existing, legacy data-sets. To address this problem, we created an indexing subsystem, allowing us to index and gather the metadata of legacy data-sets. The gathered information is later incorporated into a multi-cloud data management system to achieve global integration of legacy storage systems containing large data-sets. The solution is based on metadata management, organization and periodic monitoring of legacy data-sets, which makes possible scheme-less co-existence of a legacy storage system and a multi-cloud data management system for managing the same data collections. The approach has been initially evaluated in a multi-cloud deployment scenario. A large data collection consisting of legacy cultural data-sets was exposed to public and commercial infrastructure for data access and processing.

Entity Relationship Modeling for IoT Data Fusion Driven by Dynamic Detecting Probe

To solve the problem of integrating and fusing scattered and heterogeneous data in the process of data space construction, we propose a novel entity association relationship modeling approach driven by dynamic detecting probes. By deploying acquisition units between the business logic layer and data access layer of different applications and dynamically collecting key information such as global data structure, related data, and access logs, the entity association model for enterprise data space is constructed from three levels: schema, instance, and log. At the schema association level, a multidimensional similarity discrimination algorithm combined with semantic analysis is used to achieve the rapid fusion of similar entities; at the instance association level, a combination of feature vector-based similarity analysis and deep learning is used to complete the association matching of different entities for structured data such as numeric and character data and unstructured data such as long text data; at the log association level, the association between different entities and attributes is established by analyzing the equivalence relationships in the data access logs. In addition, to address the uncertainty problem in the association construction process, a fuzzy logic-based inference model is applied to obtain the final entity association construction scheme.

New approach to global data access in computational infrastructures

Data access and management on a large, global scale is currently at the center of scientific interest. This follows from the need for data access from multi- and hybrid-cloud applications. In most cases existing solutions provide sufficient functionality to scale computing resources but scaling resources in terms of efficient data access e.g. for data-intensive applications is still not comprehensively resolved.In this paper, we present a new approach to global data access that supports the execution of data-intensive applications on globally distributed heterogeneous resources provided and managed by independent providers. We identify the functionality, representation, and processing of contextual information in the form of metadata, and the organization of data, resulting in four models describing the details of the approach. An experimental evaluation of this approach is discussed. We show overheads for single- and multi-site environments, system scalability, and usage of context awareness to achieve desired behavior proving insignificant overhead introduced by the system. The results confirm usability of the approach to supporting computations in heterogeneous environments with unified access to data distributed worldwide achieved by using broad contextual information.

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.

GraphH: A Processing-in-Memory Architecture for Large-Scale Graph Processing

Large-scale graph processing requires the high bandwidth of data access. However, as graph computing continues to scale, it becomes increasingly challenging to achieve a high bandwidth on generic computing architectures. The primary reasons include: the random access pattern causing local bandwidth degradation, the poor locality leading to unpredictable global data access, heavy conflicts on updating the same vertex, and unbalanced workloads across processing units. Processing-in-memory (PIM) has been explored as a promising solution to providing high bandwidth, yet open questions of graph processing on PIM devices remain in: 1) how to design hardware specializations and the interconnection scheme to fully utilize bandwidth of PIM devices and ensure locality and 2) how to allocate data and schedule processing flow to avoid conflicts and balance workloads. In this paper, we propose GraphH, a PIM architecture for graph processing on the hybrid memory cube array, to tackle all four problems mentioned above. From the architecture perspective, we integrate SRAM-based on-chip vertex buffers to eliminate local bandwidth degradation. We also introduce reconfigurable double-mesh connection to provide high global bandwidth. From the algorithm perspective, partitioning and scheduling methods like index mapping interval-block and round interval pair are introduced to GraphH, thus workloads are balanced and conflicts are avoided. Two optimization methods are further introduced to reduce synchronization overhead and reuse on-chip data. The experimental results on graphs with billions of edges demonstrate that GraphH outperforms DDR-based graph processing systems by up to two orders of magnitude and $5.12 {\times }$ speedup against the previous PIM design.

국제 Life Cycle Inventory (LCI) Database (DB) 구축 현황 조사 및 국가 LCI DB 구축방향 제언

The current international status of Life Cycle Inventory (LCI) Database (DB) was investigated. Based on this investigation, this study suggested the direction for national LCI DB development. This study probed into the major countries such as USA, Japan, Europe, and the major institutions(Ecoinvent, Gabi, Chinese Life Cycle Database (CLCD)) also investigated in order to analyze the current development status of LCI DB. This study also analyze the LCI DB network and hub such as Life Cycle Data Network (LCDN), Global LCA Data Access (GLAD), openLCA nexus. Through this, this study made three suggestions about the direction of national LCI DB development; 1) Establishment of national LCI DB development road map, 2) Development of LCI DB based on general information, 3) Activation of overseas activities of LCI DB institution.

Legal Access to the Global Cloud

Increased use of the cloud and its international scope raise significant challenges to traditional legal authorities that permit access to data stored outside the United States. The resulting stakes are high. This area of law affects a wide range of important matters concerning law enforcement, national security, and civil litigation. Up until now, however, policymakers in this area have failed to fully appreciate the technological distinctions between different types of data clouds. This Article develops and distinguishes between three models of cloud computing to provide greater clarity for courts when evaluating international data access requests. These models are the Data Shard, Data Localization, and Data Trust clouds. This new typology reveals how the same legal authority will lead to notably different results in data access cases depending on the technical architecture of the cloud network. To illustrate, this Article assesses the likely results for each type of cloud under the full range of American legal authorities that permit parties to seek digital information held abroad — namely, the Fourth Amendment, the Stored Communications Act, Mutual Legal Assistance Treaties, administrative or grand jury subpoenas, and the Foreign Intelligence Surveillance Act. This Article’s analysis of cloud models also points to the profound instability of current American data access rules. The writing is on the wall. Companies and individuals outside of the United States now have multiple ways, including changing their cloud management models, to shelter data beyond the exclusive reach of U.S. law, which will increase the importance of non-U.S. access rules. This trend will spell the end of unilateral decisionmaking by U.S. courts concerning the legal process to be applied when the government or civil litigants seek data stored extraterritorially. In response, this Article advances two principles for a world of omnipresent global cloud computing. First, U.S. law should treat extraterritorial data requests equally, regardless of the location of the cloud provider’s headquarters. This legal approach would foster a level playing field for global cloud companies and encourage innovation, rather than further balkanization of the internet. Second, there is a need for international cooperation to create reciprocity. The “Pax Americana” of unilateral U.S. governance in this area is ending, and the wisest course for U.S. policy is to establish new international agreements for global data access. As this Article details, the CLOUD Act of 2018 takes a major step toward incorporation of these principles in an effort to preserve the internet as a global space. But the Act also encourages a know-your-customer regime, where the ultimate cost may be paid in users’ privacy.

Global Data Access Optimization Via Load/Store Instruction Extension

The widening gap between processor speed and memory latency makes memory accesses become a major performance bottleneck for modern processor architectures. Eliminating the memory access and improving the program locality may help to improve the performance. This paper proposes the extension design of load and store instructions, describes the hardware/software cooperative optimization idea for global data access. The research work is based on the synthetic analysis of program data access behavior and compiler optimization ability observation, which has a great influence on the design decision. Compared with the popular GP-addressing technique, our method may not only save the dedicated registers, but also eliminate the overhead of calling functions in dynamic shared objects. Experiment results show an average reduction of 5.92% in dynamic memory access instructions and an average improvement by 2.16% in code size for SPEC programs.

Efficient Cache Management for Network-Coding-Assisted Data Broadcast

Network coding has been proven to be an effective technique in improving the performance of data broadcast systems. Previous studies have shown that the performance of network-coding-assisted data broadcast systems is highly related to client cache contents. In this paper, we investigate the cache management problem in network-coding-assisted data broadcast environments with the objective of minimizing the overall response time. We formulate the problem and prove that it is NP-hard. Furthermore, we derive a probabilistic model to analyze the decoding probability to give insight into the importance of the cache management scheme. On this basis, we propose a decoding-oriented cache management scheme, which is called decoding-oriented least recently used (DLRU), which incorporates decoding information in making cache replacement decisions. In addition, since individual clients may observe the global data access pattern from encoded packets broadcast by the server, we loosen the cache admission control policy and allow clients to cache decodable and potentially useful data items that are not currently being requested. Based on this idea, we further propose a variant scheme, which is called DLRU with cache partitioning (DLRU-CP), which couples the cache partitioning policy to DLRU. We build a simulation model and implement the most competing alternative solutions in the literature for performance evaluation. The simulation results conclusively demonstrate the superiority of the proposed schemes in terms of reducing the request response time in network-coding-assisted data broadcast systems.

Semantic catalogs for life cycle assessment data

Life cycle assessment (LCA) is a highly interdisciplinary field that requires knowledge from different domains to be gathered and interpreted together. Although there are relatively few major data sources for LCA, the data themselves are presented with highly heterogeneous formats, interfaces, and distribution mechanisms. The lack of agreement among data providers for descriptions of processes and flows creates substantial barriers for information sharing and reuse of practitioners’ models.Nevertheless, the many data resources share a common logic. The use of Semantic Web technologies and text mining techniques can facilitate the interpretation of data from diverse sources. Numerous existing efforts have been made to articulate a knowledge model for LCA. In March of 2015 a joint workshop was held that brought together leading international domain experts with ontology engineers to develop a set of simple models called ontology design patterns (ODPs) for LCA information. In this paper we build on the outcomes of the workshop, as well as prior published works, to derive a minimal “consensus model” for LCA. We use the consensus model to derive a description of an LCA “catalog” that can be used to express the semantic content of a data resource. We generate catalogs of several prominent databases, and make those catalogs available to the public for independent use. Finally, we “link” those catalogs to existing knowledge models using JSON-LD, a linked data format that can expose the catalog contents to Semantic Web tools.We then show by example how the catalogs may be used to answer questions about the scope, coverage, and comparability of data, both within and across data sources, that are difficult to answer when the contents of the catalogs are provided independently and inconsistently. We discuss how the use of semantic catalogs can help address challenges that initiatives such as the “Global Network of Interoperable LCA Databases – Global LCA Data Access” are facing today.

Tology-Aware Optimal Data Placement Algorithm for Network Traffic Optimization

We propose a new optimal data placement technique to improve the performance of MapReduce in cloud data centers by considering not only the data locality but also the global data access costs. We first conducted an analytical and experimental study to identify the performance issues of MapReduce in data centers and to show that MapReduce tasks that are involved in unexpected remote data access have much greater communication costs and execution time, and can significantly deteriorate the overall performance. Next, we formulated the problem of optimal data placement and proposed a generative model to minimize global data access cost in data centers and showed that the optimal data placement problem is NP-hard. To solve the optimal data placement problem, we propose a topology-aware heuristic algorithm by first constructing a replica-balanced distribution tree for the abstract tree structure, and then building a replica-similarity distribution tree for detail tree construction, to construct an optimal replica distribution tree. The experimental results demonstrated that our optimal data placement approach can improve the performance of MapReduce with lower communication and computation costs by effectively minimizing global data access costs, more specifically reducing unexpected remote data access.

Data publication with the structural biology data grid supports live analysis.

Access to experimental X-ray diffraction image data is fundamental for validation and reproduction of macromolecular models and indispensable for development of structural biology processing methods. Here, we established a diffraction data publication and dissemination system, Structural Biology Data Grid (SBDG; data.sbgrid.org), to preserve primary experimental data sets that support scientific publications. Data sets are accessible to researchers through a community driven data grid, which facilitates global data access. Our analysis of a pilot collection of crystallographic data sets demonstrates that the information archived by SBDG is sufficient to reprocess data to statistics that meet or exceed the quality of the original published structures. SBDG has extended its services to the entire community and is used to develop support for other types of biomedical data sets. It is anticipated that access to the experimental data sets will enhance the paradigm shift in the community towards a much more dynamic body of continuously improving data analysis.

Location‐only and use‐availability data: analysis methods converge

Location‐only and use‐availability data: analysis methods converge

A compiler framework for extracting superword level parallelism

SIMD (single-instruction multiple-data) instruction set extensions are quite common today in both high performance and embedded microprocessors, and enable the exploitation of a specific type of data parallelism called SLP (Superword Level Parallelism). While prior research shows that significant performance savings are possible when SLP is exploited, placing SIMD instructions in an application code manually can be very difficult and error prone. In this paper, we propose a novel automated compiler framework for improving superword level parallelism exploitation. The key part of our framework consists of two stages: superword statement generation and data layout optimization. The first stage is our main contribution and has two phases, statement grouping and statement scheduling, of which the primary goals are to increase SIMD parallelism and, more importantly, capture more superword reuses among the superword statements through global data access and reuse pattern analysis. Further, as a complementary optimization, our data layout optimization organizes data in memory space such that the price of memory operations for SLP is minimized. The results from our compiler implementation and tests on two systems indicate performance improvements as high as 15.2% over a state-of-the-art SLP optimization algorithm.

Mobile operators work towards global data access

Mobile operators work towards global data access

Performance of hypercube architecture with shared memory

The performance of hypercube architectures depends on the topology of the problem being solved. Specifically, they are unsuitable for knowledge-based applications where global data access is very often required. In this work, a new architecture is proposed that can be used in such applications. The proposed architecture uses both the shared memory and the distributed memories. In this architecture, shared memory is connected to the basic hypercubes using multistage interconnection networks (MINs). In this analysis, the Omega network is considered. When global memory and distributed memories are used, multiple copies of shared data deteriorate the system performance because of data invalidation traffic in the network, and the coherency implementation overhead. Maintaining single copies of the shared data can eliminate the invalidation traffic and the coherency related activities. However, the single copies are to be dynamically moved using a data movement policy to serve the memory references. Analytical m...