Local Processing Costs Research Articles

Online Resource Procurement and Allocation in a Hybrid Edge-Cloud Computing System

By acquiring cloud-like capacities at the edge of a network, edge computing is expected to significantly improve user experience. In this paper, we formulate a hybrid edge-cloud computing system where an edge device with limited local resources can rent more from a cloud node and perform resource allocation to serve its users. The resource procurement and allocation decisions depend not only on the cloud's multiple rental options but also on the edge's local processing cost and capacity. We first propose an offline algorithm whose decisions are made with full information of future demand. Then, an online algorithm is proposed where the edge node makes irrevocable decisions in each timeslot without future information of demand. We show that both algorithms have constant performance bounds from the offline optimum. Numerical results acquired with Google cluster-usage traces indicate that the cost of the edge node can be substantially reduced by using the proposed algorithms, up to $80\%$ in comparison with baseline algorithms. We also observe how the cloud's pricing structure and edge's local cost influence the procurement decisions.

Distributed query plan generation using multiobjective genetic algorithm.

A distributed query processing strategy, which is a key performance determinant in accessing distributed databases, aims to minimize the total query processing cost. One way to achieve this is by generating efficient distributed query plans that involve fewer sites for processing a query. In the case of distributed relational databases, the number of possible query plans increases exponentially with respect to the number of relations accessed by the query and the number of sites where these relations reside. Consequently, computing optimal distributed query plans becomes a complex problem. This distributed query plan generation (DQPG) problem has already been addressed using single objective genetic algorithm, where the objective is to minimize the total query processing cost comprising the local processing cost (LPC) and the site-to-site communication cost (CC). In this paper, this DQPG problem is formulated and solved as a biobjective optimization problem with the two objectives being minimize total LPC and minimize total CC. These objectives are simultaneously optimized using a multiobjective genetic algorithm NSGA-II. Experimental comparison of the proposed NSGA-II based DQPG algorithm with the single objective genetic algorithm shows that the former performs comparatively better and converges quickly towards optimal solutions for an observed crossover and mutation probability.

Spectrum sensing in cognitive radio networks: Performance evaluation and optimization

This paper studies cooperative spectrum sensing in cognitive radio networks where secondary users collect local energy statistics and report their findings to a secondary base station, i.e., a fusion center. First, the average error probability is quantitively analyzed to capture the dynamic nature of both observation and fusion channels, assuming fixed amplifier gains for relaying local statistics to the fusion center. Second, the system level overhead of cooperative spectrum sensing is addressed by considering both the local processing cost and the transmission cost. Local processing cost incorporates the overhead of sample collection and energy calculation that must be conducted by each secondary user; the transmission cost accounts for the overhead of forwarding the energy statistic computed at each secondary user to the fusion center. Results show that when jointly designing the number of collected energy samples and transmission amplifier gains, only one secondary user needs to be actively engaged in spectrum sensing. Furthermore, when the number of energy samples or amplifier gains are fixed, closed form expressions for optimal solutions are derived and a generalized water-filling algorithm is provided.

The Role of Contrast in the Local Licensing of Scrambling in German: Evidence from Online Comprehension

We examine the role of contrast in the local licensing of scrambling in on-line language comprehension in German using event-related brain potentials (ERP). Although contrastive readings give rise to a higher acceptability of scrambled word orders, they do not lead to an attenuation of the processing difficulties observed at the position of the scrambled object itself. Thus, similar to previous findings on givenness, contrast leads to global but not local licensing of scrambled structures, a finding that speaks against an immediate interaction of all relevant information types. The pattern is reversed when the scrambled object induces a corrective focus reading. Here scrambling does not give rise to increased local processing cost, but global acceptability decreases. These findings suggest that corrective focus can override local syntactic requirements on the basis of its extraordinarily high communicative saliency.

Exploiting spatial indexes for semijoin-based join processing in distributed spatial databases

In a distributed spatial database system, a user may issue a query that relates two spatial relations not stored at the same site. Because of the sheer volume and complexity of spatial data, spatial joins between two spatial relations at different sites are expensive in terms of computational and transmission costs. In this paper, we address the problems of processing spatial joins in a distributed environment. We propose a semijoin-like operator, called the spatial semijoin, to prune away objects that do not contribute to the join result. This operator also reduces both the transmission and local processing costs for a later join operation. However, the cost of the elimination process must be taken into account, and we consider approaches to minimize these overheads. We also study and compare two families of distributed join algorithms that are based on the spatial semijoin operator. The first is based on multi-dimensional approximations obtained from an index such as the R-tree, and the second is based on single-dimensional approximations obtained from object mapping. We have conducted experiments on real data sets and report the results in this paper.

Optimizing distributed join queries: A genetic algorithm approach

ptimizing join queries is a major problem in distributed database systems, particularly when files are replicated and copies stored at different nodes in the network. A distributed query optimization algorithm must select file copies and determine how and where those files will be processed. Process decisions include which files to reduce via semijoins, if any, the sites at which to perform join operations, and the order in which to perform those join operations. We extend the scope of distributed query optimization research by develop-ing a model that, for the first time, includes all of these design decisions and considers both communication and local processing costs. We develop a genetic algorithm-based solution procedure for this model which quickly determines efficient query processing plans. We demonstrate that ignoring local processing costs or restricting join processing to the result site, as commonly done in prior research, can result in inefficient query execution plans.

Adaptive Join Algorithms in Dynamic Distributed Databases

This paper addresses the problem of query optimization for dynamic databases in distributed environments where data frequently change their values. An adaptive query optimization algorithm is proposed to evaluate queries. Rather than constructing a full plan for an access path and executing it, the algorithm constructs a partial plan, executes it, updates the statistics, and constructs a new partial plan. Since a partial plan is constructed based on the latest statistics, the algorithm is adaptive to data modifications and errors from the statistics. The algorithm extends the SDD-1 algorithm by considering local processing cost as well as communication cost. Whereas the SDD-1 algorithm only uses semi-joins to reduce communication cost, the algorithm reduces it with joins as well. It is proved that the adaptive algorithm is more efficient than the SDD-1 algorithm.

Underconstrained knowledge-intensive constraint satisfaction search

Abstract This paper describes a methodology to efficiently solve underconstrained knowledge-intensive constraint satisfaction problems (CSPs) where solutions are ordered by a cost measure. The methodology exploits a segmentation of the CSP imposed by the application domain. Constraints and variables are clustered into CSP segments which support local constraint processing and solution cost estimation. The methodology employs heuristic search to develop solutions in an incremental fashion. The goal of search is to find one or several of a set of 'satisficing', i.e. good enough, solutions. Solution cost is defined as distance to a normal solution. The heuristic evaluation function is non-admissible and favours depth-first search because finding a good solution is more important than finding the absolute best one. The value of the evaluation function of a search node may change during processing in response to results of exploring nearby nodes. It attempts to improve its estimate of the remaining path cost b...

Allocating data and operations to nodes in distributed database design

The allocation of data and operations to nodes in a computer communications network is a critical issue in distributed database design. An efficient distributed database design must trade off performance and cost among retrieval and update activities at the various nodes. It must consider the concurrency control mechanism used as well as capacity constraints at nodes and on links in the network. It must determine where data will be allocated, the degree of data replication, which copy of the data will be used for each retrieval activity, and where operations such as select, project, join, and union will be performed. We develop a comprehensive mathematical modeling approach for this problem. The approach first generates units of data (file fragments) to be allocated from a logical data model representation and a characterization of retrieval and update activities. Retrieval and update activities are then decomposed into relational operations on these fragments. Both fragments and operations on them are then allocated to nodes using a mathematical modeling approach. The mathematical model considers network communication, local processing, and data storage costs. A genetic algorithm is developed to solve this mathematical formulation.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

An efficient way to reestablish B+ trees in a distributed environment

When a file is transferred from one site to another in a distributed environment, fast access paths supported by indices of the file like the B + tree at the sending site may become useless because of memory reallocation at the receiving site. It is known that (re-)establishing a B + tree at a receiving site is rather expensive. In this paper, we propose a method which allows us to obtain a data file and efficiently construct a similar B + tree on the file at a receiving site (the term similar is in the sense that both B + trees at the sending site and at the receiving site are indexed on the same attribute of the file, although they need not be identical) in a distributed environment. Both local processing cost and communication cost in terms of page I/Os are taken into consideration. We demonstrate that our approach is more cost-effective than the usual approach (which transfers the data file and then uses the data file to establish its B + index at the receiving site) despite a modest communication overhead. Under a typical situation, the usual approach is about 2 times more expensive than our approach in terms of page I/Os. Extensive performance study is also provided. The method is then generalized to situations where different sites may have different page sizes. Finally, the file reorganization problem is addressed, that is, useless data records such as empty records and records marked “deleted” in a file are not transferred, and a “fresh” file is established at the receiving site. File reorganization is also shown to be applicable to efficient database reloading and database reorganization.

An integer programming formulation embedded in an algorithm for query processing optimization in distributed relational database systems

In this paper, an algorithm is presented which determines the combination of the project, select and equi-join relational operators and their respective processing sites, in a distributed relational database system, in response to a query or class of queries. Part of this algorithm, is an integer programming model which determines the files in the network to be joined and their respective processing sites so as to minimize the sum of the network transmission and local processing costs. The algorithm is executed and illustrated using an example.

A state transition model for distributed query processing

A state transition model for the optimization of query processing in a distributed database system is presented. The problem is parameterized by means of a state describing the amount of processing that has been performed at each site where the database is located. A state transition occurs each time a new join or semijoin is executed. Dynamic programming is used to compute recursively the costs of the states and the globally optimal solution, taking into account communication and local processing costs. The state transition model is general enough to account for the possibility of parallel processing among the various sites, as well as for redundancy in the database. The model also permits significant reductions of the necessary computations by taking advantage of simple additivity and site-uniformity properties of a cost model, and of clever strategies that improve on the basic dynamic programming algorithm.