Dynamic load balancing for the distributed mining of molecular structures

In molecular biology, it is often desirable to find common properties in large numbers of drug candidates. One family of methods stems from the data mining community, where algorithms to find frequent graphs have received increasing attention over the past years. However, the computational complexity of the underlying problem and the large amount of data to be explored essentially render sequential algorithms useless. In this paper, we present a distributed approach to the frequent subgraph mining problem to discover interesting patterns in molecular compounds. This problem is characterized by a highly irregular search tree, whereby no reliable workload prediction is available. We describe the three main aspects of the proposed distributed algorithm, namely, a dynamic partitioning of the search space, a distribution process based on a peer-to-peer communication framework, and a novel receiverinitiated load balancing algorithm. The effectiveness of the distributed method has been evaluated on the well-known National Cancer Institute’s HIV-screening data set, where we were able to show close-to linear speedup in a network of workstations. The proposed approach also allows for dynamic resource aggregation in a non dedicated computational environment. These features make it suitable for large-scale, multi-domain, heterogeneous environments, such as computational grids.

Decentralized load balancing for highly irregular search problems

In this paper, we present a distributed computing framework for problems characterized by a highly irregular search tree, whereby no reliable workload prediction is available. The framework is based on a peer-to-peer computing environment and dynamic load balancing. The system allows for dynamic resource aggregation, does not depend on any specific meta-computing middleware and is suitable for large-scale, multi-domain, heterogeneous environments, such as computational Grids. Dynamic load balancing policies based on global statistics are known to provide optimal load balancing performance, while randomized techniques provide high scalability. The proposed method combines both advantages and adopts distributed job-pools and a randomized polling technique. The framework has been successfully adopted in a parallel search algorithm for subgraph mining and evaluated on a molecular compounds dataset. The parallel application has shown good calability and close-to linear speedup in a distributed network of workstations.

Dynamic load balancing in parallel KD-tree k-means

One among the most influential and popular data mining methods is the k-Means algorithm for cluster analysis. Techniques for improving the efficiency of k-Means have been largely explored in two main directions. The amount of computation can be significantly reduced by adopting geometrical constraints and an efficient data structure, notably a multidimensional binary search tree (KD-Tree). These techniques allow to reduce the number of distance computations the algorithm performs at each iteration. A second direction is parallel processing, where data and computation loads are distributed over many processing nodes. However, little work has been done to provide a parallel formulation of the efficient sequential techniques based on KD-Trees. Such approaches are expected to have an irregular distribution of computation load and can suffer from load imbalance. This issue has so far limited the adoption of these efficient k-Means variants in parallel computing environments. In this work, we provide a parallel formulation of the KD-Tree based k-Means algorithm for distributed memory systems and address its load balancing issue. Three solutions have been developed and tested. Two approaches are based on a static partitioning of the data set and a third solution incorporates a dynamic load balancing policy.

Predicting mesh density for adaptive modelling of the global atmosphere

The shallow water equations are solved using a mesh of polygons on the sphere, which adapts infrequently to the predicted future solution. Infrequent mesh adaptation reduces the cost of adaptation and load-balancing and will thus allow for more accurate mapping on adaptation. We simulate the growth of a barotropically unstable jet adapting the mesh every 12 h. Using an adaptation criterion based largely on the gradient of the vorticity leads to a mesh with around 20 per cent of the cells of a uniform mesh that gives equivalent results. This is a similar proportion to previous studies of the same test case with mesh adaptation every 1–20 min. The prediction of the mesh density involves solving the shallow water equations on a coarse mesh in advance of the locally refined mesh in order to estimate where features requiring higher resolution will grow, decay or move to. The adaptation criterion consists of two parts: that resolved on the coarse mesh, and that which is not resolved and so is passively advected on the coarse mesh. This combination leads to a balance between resolving features controlled by the large-scale dynamics and maintaining fine-scale features.

A customizable multi-agent system for distributed data mining

We present a general Multi-Agent System framework for distributed data mining based on a Peer-to-Peer model. Agent protocols are implemented through message-based asynchronous communication. The framework adopts a dynamic load balancing policy that is particularly suitable for irregular search algorithms. A modular design allows a separation of the general-purpose system protocols and software components from the specific data mining algorithm. The experimental evaluation has been carried out on a parallel frequent subgraph mining algorithm, which has shown good scalability performances.

Scalability of efficient parallel K-Means

Clustering is defined as the grouping of similar items in a set, and is an important process within the field of data mining. As the amount of data for various applications continues to increase, in terms of its size and dimensionality, it is necessary to have efficient clustering methods. A popular clustering algorithm is K-Means, which adopts a greedy approach to produce a set of K-clusters with associated centres of mass, and uses a squared error distortion measure to determine convergence. Methods for improving the efficiency of K-Means have been largely explored in two main directions. The amount of computation can be significantly reduced by adopting a more efficient data structure, notably a multi-dimensional binary search tree (KD-Tree) to store either centroids or data points. A second direction is parallel processing, where data and computation loads are distributed over many processing nodes. However, little work has been done to provide a parallel formulation of the efficient sequential techniques based on KD-Trees. Such approaches are expected to have an irregular distribution of computation load and can suffer from load imbalance. This issue has so far limited the adoption of these efficient K-Means techniques in parallel computational environments. In this work, we provide a parallel formulation for the KD-Tree based K-Means algorithm and address its load balancing issues.

A hierarchical distributed approach for mining molecular fragments

Recently, two approaches have been introduced that distribute the molecular fragment mining problem. The first approach applies a master/worker topology, the second approach, a completely distributed peer-to-peer system, solves the scalability problem due to the bottleneck at the master node. However, in many real world scenarios the participating computing nodes cannot communicate directly due to administrative policies such as security restrictions. Thus, potential computing power is not accessible to accelerate the mining run. To solve this shortcoming, this work introduces a hierarchical topology of computing resources, which distributes the management over several levels and adapts to the natural structure of those multi-domain architectures. The most important aspect is the load balancing scheme, which has been designed and optimized for the hierarchical structure. The approach allows dynamic aggregation of heterogenous computing resources and is applied to wide area network scenarios.

High performance subgraph mining in molecular compounds

Structured data represented in the form of graphs arises in several fields of the science and the growing amount of available data makes distributed graph mining techniques particularly relevant. In this paper, we present a distributed approach to the frequent subgraph mining problem to discover interesting patterns in molecular compounds. The problem is characterized by a highly irregular search tree, whereby no reliable workload prediction is available. We describe the three main aspects of the proposed distributed algorithm, namely a dynamic partitioning of the search space, a distribution process based on a peer-to-peer communication framework, and a novel receiver-initiated, load balancing algorithm. The effectiveness of the distributed method has been evaluated on the well-known National Cancer Institute’s HIV-screening dataset, where the approach attains close-to linear speedup in a network of workstations.

Linear predicted two-pass hexagonal algorithm with parallel implementation for motion estimation

This paper presents a paralleled Two-Pass Hexagonal (TPA) algorithm constituted by Linear Hashtable Motion Estimation Algorithm (LHMEA) and Hexagonal Search (HEXBS) for motion estimation. In the TPA., Motion Vectors (MV) are generated from the first-pass LHMEA and are used as predictors for second-pass HEXBS motion estimation, which only searches a small number of Macroblocks (MBs). We introduced hashtable into video processing and completed parallel implementation. We propose and evaluate parallel implementations of the LHMEA of TPA on clusters of workstations for real time video compression. It discusses how parallel video coding on load balanced multiprocessor systems can help, especially on motion estimation. The effect of load balancing for improved performance is discussed. The performance or the algorithm is evaluated by using standard video sequences and the results are compared to current algorithms.

Paralelled Two-Pass Hexagonal algorithm for motion estimation

This paper presents a paralleled Two-Pass Hexagonal (TPA) algorithm constituted by Linear Hashtable Motion Estimation Algorithm (LHMEA) and Hexagonal Search (HEXBS) for motion estimation. In the TPA, Motion Vectors (MV) are generated from the first-pass LHMEA and are used as predictors for second-pass HEXBS motion estimation, which only searches a small number of Macroblocks (MBs). We introduced hashtable into video processing and completed parallel implementation. We propose and evaluate parallel implementations of the LHMEA of TPA on clusters of workstations for real time video compression. It discusses how parallel video coding on load balanced multiprocessor systems can help, especially on motion estimation. The effect of load balancing for improved performance is discussed. The performance of the algorithm is evaluated by using standard video sequences and the results are compared to current algorithms.

Two-pass hexagonal algorithm with parallel implementation for video coding

This paper presents a paralleled Two-Pass Hexagonal (TPA) algorithm constituted by Linear Hashtable Motion Estimation Algorithm (LHMEA) and Hexagonal Search (HEXBS) for motion estimation. In the TPA, Motion Vectors (MV) are generated from the first-pass LHMEA and are used as predictors for second-pass HEXBS motion estimation, which only searches a small number of Macroblocks (MBs). We introduced hashtable into video processing and completed parallel implementation. We propose and evaluate parallel implementations of the LHMEA of TPA on clusters of workstations for real time video compression. It discusses how parallel video coding on load balanced multiprocessor systems can help, especially on motion estimation. The effect of load balancing for improved performance is discussed. The performance of the algorithm is evaluated by using standard video sequences and the results are compared to current algorithms.

Implementing intelligent cores using processor virtualization for fault tolerance

Processor virtualization for process migration in distributed parallel computing systems has formed a significant component of research on load balancing. In contrast, the potential of processor virtualization for fault tolerance has been addressed minimally. The work reported in this paper is motivated towards extending concepts of processor virtualization towards ‘intelligent cores’ as a means to achieve fault tolerance in distributed parallel computing systems. Intelligent cores are an abstraction of the hardware processing cores, with the incorporation of cognitive capabilities, on which parallel tasks can be executed and migrated. When a processing core executing a task is predicted to fail the task being executed is proactively transferred onto another core. A parallel reduction algorithm incorporating concepts of intelligent cores is implemented on a computer cluster using Adaptive MPI and Charm ++. Preliminary results confirm the feasibility of the approach.

Non-uniform data distribution for communication-efficient parallel clustering

Global communicationrequirements andloadimbalanceof someparalleldataminingalgorithms arethe major obstacles to exploitthe computational power of large-scale systems. This work investigates how non-uniform data distributions can be exploited to remove the global communication requirement and to reduce the communication costin parallel data mining algorithms and, in particular, in the k-means algorithm for cluster analysis. In the straightforward parallel formulation of the k-means algorithm, data and computation loads are uniformly distributed over the processing nodes. This approach has excellent load balancing characteristics that may suggest it could scale up to large and extreme-scale parallel computing systems. However, at each iteration step the algorithm requires a global reduction operationwhichhinders thescalabilityoftheapproach.Thisworkstudiesadifferentparallelformulation of the algorithm where the requirement of global communication is removed, while maintaining the same deterministic nature ofthe centralised algorithm. The proposed approach exploits a non-uniform data distribution which can be either found in real-world distributed applications or can be induced by means ofmulti-dimensional binary searchtrees. The approachcanalso be extended to accommodate an approximation error which allows a further reduction ofthe communication costs. The effectiveness of the exact and approximate methods has been tested in a parallel computing system with 64 processors and in simulations with 1024 processing element

Mesh adaptation on the sphere using optimal transport and the numerical solution of a Monge-Ampère type equation

An equation of Monge-Ampère type has, for the first time, been solved numerically on the surface of the sphere in order to generate optimally transported (OT) meshes, equidistributed with respect to a monitor function. Optimal transport generates meshes that keep the same connectivity as the original mesh, making them suitable for r-adaptive simulations, in which the equations of motion can be solved in a moving frame of reference in order to avoid mapping the solution between old and new meshes and to avoid load balancing problems on parallel computers. The semi-implicit solution of the Monge-Ampère type equation involves a new linearisation of the Hessian term, and exponential maps are used to map from old to new meshes on the sphere. The determinant of the Hessian is evaluated as the change in volume between old and new mesh cells, rather than using numerical approximations to the gradients. OT meshes are generated to compare with centroidal Voronoi tesselations on the sphere and are found to have advantages and disadvantages; OT equidistribution is more accurate, the number of iterations to convergence is independent of the mesh size, face skewness is reduced and the connectivity does not change. However anisotropy is higher and the OT meshes are non-orthogonal. It is shown that optimal transport on the sphere leads to meshes that do not tangle. However, tangling can be introduced by numerical errors in calculating the gradient of the mesh potential. Methods for alleviating this problem are explored. Finally, OT meshes are generated using observed precipitation as a monitor function, in order to demonstrate the potential power of the technique.

Reductions in insecticide use from adoption of Bt cotton in South Africa: impacts on economic performance and toxic load to the environment

The study reported presents the findings relating to commercial growing of genetically-modified Bt cotton in South Africa by a large sample of smallholder farmers over three seasons (1998/99, 1999/2000, 2000/01) following adoption. The analysis presents constructs and compares groupwise differences for key variables in Bt v. non-Bt technology and uses regressions to further analyse the production and profit impacts of Bt adoption. Analysis of the distribution of benefits between farmers due to the technology is also presented. In parallel with these socio-economic measures, the toxic loads being presented to the environment following the introduction of Bt cotton are monitored in terms of insecticide active ingredient (ai) and the Biocide Index. The latter adjusts ai to allow for differing persistence and toxicity of insecticides. Results show substantial and significant financial benefits to smallholder cotton growers of adopting Bt cotton over three seasons in terms of increased yields, lower insecticide spray costs and higher gross margins. This includes one particularly wet, poor growing season. In addition, those with the smaller holdings appeared to benefit proportionately more from the technology (in terms of higher gross margins) than those with larger holdings. Analysis using the Gini-coefficient suggests that the Bt technology has helped to reduce inequality amongst smallholder cotton growers in Makhathini compared to what may have been the position if they had grown conventional cotton. However, while Bt growers applied lower amounts of insecticide and had lower Biocide Indices (per ha) than growers of non-Bt cotton, some of this advantage was due to a reduction in non-bollworm insecticide. Indeed, the Biocide Index for all farmers in the population actually increased with the introduction of Bt cotton. The results indicate the complexity of such studies on the socio-economic and environmental impacts of GM varieties in the developing world.