Distributed System Perspective Research Articles

Information batteries

Coping with the intermittency of renewable power is a fundamental challenge, with load shifting and grid-scale storage as key responses. We propose Information Batteries (IB), in which energy is stored in the form of information---specifically, the results of completed computational tasks. Information Batteries thus provide storage through speculative load shifting, anticipating computation that will be performed in the future. We take a distributed systems perspective, and evaluate the extent to which an IB storage system can be made practical through augmentation of compiler toolchains, key-value stores, and other important elements in modern hyper-scale compute. In particular, we implement one specific IB prototype by augmenting the Rust compiler to enable transparent function-level precomputation and caching. We evaluate the overheads this imposes, along with macro-level job prediction and power prediction. We also evaluate the space of operation for an IB system, to identify the best case efficiency of any IB system for a given power and compute regime.

Engineering Challenges Ahead for Robot Teamwork in Dynamic Environments

The increasing number of robots around us creates a demand for connecting these robots in order to achieve goal-driven teamwork in heterogeneous multi-robot systems. In this paper, we focus on robot teamwork specifically in dynamic environments. While the conceptual modeling of multi-agent teamwork was studied extensively during the last two decades and commercial multi-agent applications were built based on the theoretical foundations, the steadily increasing use of autonomous robots in many application domains gave the topic new significance and shifted the focus more toward engineering concerns for multi-robot systems. From a distributed systems perspective, we discuss general engineering challenges that apply to robot teamwork in dynamic application domains and review state-of-the-art solution approaches for these challenges. This leads us to open research questions that need to be tackled in future work.

Efficiently repairing and measuring replica consistency in distributed databases

In a distributed database, maintaining large table replicas with frequent asynchronous insertions is a challenging problem that requires carefully managing a tradeoff between consistency and availability. With that motivation in mind, we propose efficient algorithms to repair and measure replica consistency. Specifically, we adapt, extend and optimize distributed set reconciliation algorithms to efficiently compute the symmetric difference between replicated tables in a distributed relational database. Our novel algorithms enable fast synchronization of replicas being updated with small sets of new records, measuring obsolence of replicas having many insertions and deciding when to update a replica, as each table replica is being continuously updated in an asynchronous manner. We first present an algorithm to repair and measure distributed consistency on a large table continuously updated with new records at several sites when the number of insertions is small. We then present a complementary algorithm that enables fast synchronization of a summarization table based on foreign keys when the number of insertions is large, but happening on a few foreign key values. From a distributed systems perspective, in the first algorithm the large table with data is reconciled, whereas in the second case, its summarization table is reconciled. Both distributed database algorithms have linear communication complexity and cubic time complexity in the size of the symmetric difference between the respective table replicas they work on. That is, they are effective when the network speed is smaller than CPU speed at each site. A performance experimental evaluation with synthetic and real databases shows our algorithms are faster than a previous state-of-the art algorithm as well as more efficient than transferring complete tables, assuming large replicated tables and sporadic asynchronous insertions.

A HIERARCHICAL MODEL FOR DISTRIBUTED COLLABORATIVE COMPUTATION IN WIRELESS SENSOR NETWORKS

In-network collaborative computation is essential for implementation of a large number of sensor applications. We approach the problem of computation in sensor networks from a parallel and distributed system's perspective. We define COSMOS, the Cluster-based, heterOgeneouSMOdel for Sensor networks. The model abstracts the key features of the class of cluster-based sensor applications. It assumes a hierarchical network architecture comprising of a large number of low cost sensors with limited computation capability, and fewer number of powerful clusterheads, uniformly distributed in a two dimensional terrain. The sensors are organized into single hop clusters, each managed by a distinct clusterhead. The clusterheads are organized in a mesh-like topology. All sensors in a cluster are time synchronized, whereas the clusterheads communicate asynchronously. The sensors are assumed to have multiple power states and a wakeup mechanism to facilitate power management. To illustrate algorithm design using our model, we discuss implementation of algorithms for sorting and summing in sensor networks.