<div>In recent years, the collective behaviors in nature have motivated rapidly expanding research efforts in the control of multi-agent systems. A multi-agent system is composed of multiple interacting subsystems (agents). In order to seek approaches that respect the network nature of multi-agent systems, distributed algorithms has recently received a significant amount of research attention, the goal of which is allowing multi-agent systems to accomplish global objectives through only local coordination. </div><div> Under this scope, we consider three major problems in this dissertation, namely, distributed computation, distributed optimization, and the resilience of distributed algorithms. First, for distributed computation, we devise distributed algorithms for solving linear equations, which can eliminate the initialization step for agents; converge to the minimum $l_1$ and $l_2$ solutions of under-determined linear equations; achieve ultimate scalability inters of agents' local storage and local states. Second, for distributed optimization, we introduce a new method for algorithm discretization so that the agents no longer have to carefully choose their step-size. We also introduce a new distributed optimization approach that can achieve better convergence rate with lower bandwidth requirement. Finally, for the resilience of distributed algorithms, we propose a new approach that allow normal agents in the multi-agent system to automatically isolate any false information from malicious agents without identification process. Though out the dissertation, all mentioned results are theoretically guaranteed and numerically validated.</div>

In this thesis, we look into the problem of forming and maintaining good committees that can represent a distributed network. The solution to this problem can be used as a sub-routine for Byzantine Agreement that only costs sub-quadratic message complexity. Most importantly, we make no cryptographic assumptions such as the Random Oracle assumption and the existence of private channels. However, we do assume the network to be peer-to-peer, where a message receiver knows who the message sender is. Under the synchronous full information model, our solution is to utilize an approximating disperser for selecting a good next committee with high probability, repeatedly. We consider several existing theoretical constructions (randomized and deterministic) for approximating dispersers, and examine the practical applicability of them, while improving constants for some constructions. This algorithm is robust against a semi-adaptive adversary who can decide the set of nodes to corrupt periodically. Thus, a new committee should be selected before the current committee gets corrupted. We also prove some constructions that do not work practically for our scenario. / Graduate

Indiana University-Purdue University Indianapolis (IUPUI) / Dynamic Binary Instrumentation (DBI) is one way to monitor a distributed system in real-time without modifying source code. Previous work has shown it is possible to instrument distributed systems using standards-based distributed middleware. Existing work, however, only applies to a single middleware, such as CORBA. This thesis therefore presents a tool named the Standards-based Distributed Middleware Monitor (SDMM), which generalizes two modern standards-based distributed middleware, the Data Distribution Service (DDS) and gRemote Procedure Call (gRPC). SDMM uses DBI to extract values and other data relevant to monitoring a distributed system in real-time. Using dynamic instrumentation allows SDMM to capture information without a priori knowledge of the distributed system under instrumentation. We applied SDMM to systems created with two DDS vendors, RTI Connext DDS and OpenDDS, as well as gRPC which is a complete remote procedure call framework. Our results show that the data collection process contributes to less than 2% of the run-time overhead in all test cases.

The distributed transactional memory (DTM) abstraction aims to simplify the development of distributed concurrent programs. It frees programmers from the complicated and error-prone task of explicit concurrency control based on locks (e.g., deadlocks, livelocks, non-scalability, non-composability), which are aggravated in a distributed environment due to the complexity of multi-node concurrency. At its core, DTM's atomic section-based synchronization abstraction enables the execution of a sequence of multi-node object operations with the classical serializability property, which significantly increases the programmability of distributed systems. In this thesis, we present the first ever DTM framework for distributed concurrency control in C++, called HyflowCPP. HyflowCPP provides distributed atomic sections, and pluggable support for concurrency control algorithms, directory lookup protocols, contention management policies, and network communication protocols. The framework uses the Transaction Forwarding Algorithm (or TFA) for concurrency control. While there exists implementations of TFA and other DTM concurrency control algorithms in Scala and Java, and concomitant DTM frameworks (e.g., HyflowJava, HyflowScala, D2STM, GenRSTM), HyflowCPP provides a uniquely distinguishing TFA/DTM implementation for C++. Also, HyflowCPP supports strong atomicity, transactional nesting models including closed and open nesting (supported using modifications to TFA), and checkpointing. We evaluated HyflowCPP through an experimental study that measured transactional throughput for a set of micro- and macro-benchmarks, and comparing with competitor DTM frameworks. Our results revealed that HyflowCPP achieves up to 600% performance improvement over competitor Java DTM frameworks including D2STM, GenRSTM, HyflowScala and HyflowJava, which can be attributed to the competitors' JVM overhead and rudimentary networking support. Additionally, our experimental studies revealed that checkpointing achieves up to 100% performance improvement over flat nesting and 50% over closed nesting. Open nesting model achieves up to 140% performance improvement over flat nesting and 90% over closed nesting. / Master of Science

No description available.

Indiana University-Purdue University Indianapolis (IUPUI) / The interconnection of distributed resources requires specific voltage regulation, monitoring, protective relaying, power quality, and islanding detection. For this reason IEEE established standard IEEE 1547 that ensures the compliance with such requirements and it will help formulate technical specifications for grid interconnection with Distributed Generator (DG) resources. In search of meeting the IEEE 1547 standard requirement of detecting unintentional islanded operation, there has been ongoing research to develop anti-islanding methods that can detect the different changes that can occur when the grid is disconnected. A team of Electrical Engineering faculty at Indiana University Purdue University Indianapolis has worked previously on testing a DG unintentional Islanding Detection Scheme. This scheme uses an active anti-islanding method in which a small 1 Hz perturbation signal is added into the DG system and it helps detect when the grid is disconnected. The scheme uses the premise that a frequency deviation caused by perturbation to the system is smaller when the grid is connected than when it is in an island. In an initial dynamic simulation model for the islanding detection scheme, a two-machine microgrid system is used to explore frequency and voltage responses when the grid is disconnected. In this thesis, the two-machine microgrid is expanded to a ten-machine system so it can be shown that the frequency deviation caused by a perturbation signal is much smaller when the grid is connected even for a larger DG network. The 1 Hz component of the DG electrical frequency in a multiple machine microgrid system is also calculated in this thesis. This project was conducted in different stages. First, it was necessary to calculate the steady state power flow and electric power of a three-machine system and update the two-machine MATLAB program with the necessary changes. After making the changes, it was necessary to simulate the system and adjust the inertia of the machine that represents the grid to ensure that the simulation output was close in magnitude to previous testing results. When the three-machine system was successfully generated, a brand new program was created so a multiple machine system could be simulated. Then the multiple machine program was used to simulate and experiment with up to a ten-machine system. Finally a program to calculate the 1 Hz component of the DG electrical frequency was generated and used to show that the magnitude squared of the 1 Hz component is inversely proportional to the number of machines connected to the system. These last findings will later help set the threshold for islanding detection appropriately for different numbers of DG.

Although the nearing end of Moore’s Law has been predicted numerous times in the past, it will eventually come to pass. In forethought of this, many modern computing systems have become increasingly complex, distributed, and parallel. As software is developed on and for these complex systems, a common API is necessary for gathering vital performance related metrics while remaining transparent to the user, both in terms of system impact and ease of use. Several distributed performance monitoring and testing systems have been proposed and implemented by both research and commercial institutions. However, most of these systems do not meet several fundamental criterion for a truly useful distributed performance monitoring system: 1) variable data delivery models, 2) security, 3) scalability, 4) transparency, 5) completeness, 6) validity, and 7) portability. This work presents dCAMP: Distributed Common API for Measuring Performance, a distributed performance framework built on top of Mark Gabel and Michael Haungs’ work with CAMP. This work also presents an updated and extended set of criterion for evaluating distributed performance frameworks and uses these to evaluate dCAMP and several related works.

No description available.

Distributed Transactional Memory (DTM) is an emerging, alternative concurrency control model that aims to overcome the challenges of distributed-lock based synchronization. DTM employs transactions in order to guarantee consistency in a concurrent execution. When two or more transactions conflict, all but one need to be delayed or rolled back. Transactional Memory supports code composability by nesting transactions. Nesting how- ever can be used as a strategy to improve performance. The closed nesting model enables partial rollback by allowing a sub-transaction to abort without aborting its parent, thus reducing the amount of work that needs to be retried. In the open nesting model, sub- transactions can commit to the shared state independently of their parents. This reduces isolation and increases concurrency. Our first main contribution in this dissertation are two extensions to the existing Transac- tional Forwarding Algorithm (TFA). Our extensions are N-TFA and TFA-ON, and support closed nesting and open nesting, respectively. We additionally extend the existing SCORe algorithm with support for open nesting (we call the result SCORe-ON). We implement these algorithms in a Java DTM framework and evaluate them. This represents the first study of transaction nesting in the context of DTM, and contributes the first DTM implementation which supports closed nesting or open nesting. Closed nesting through our N-TFA implementation proved insufficient for any significant throughput improvements. It ran on average 2% faster than flat nesting, while performance for individual tests varied between 42% slowdown and 84% speedup. The workloads that benefit most from closed nesting are characterized by short transactions, with between two and five sub-transactions. Open nesting, as exemplified by our TFA-ON and SCORe-ON implementations, showed promising results. We determined performance improvement to be a trade-off between the overhead of additional commits and the fundamental conflict rate. For write-intensive, high- conflict workloads, open nesting may not be appropriate, and we observed a maximum speedup of 30%. On the other hand, for lower fundamental-conflict workloads, open nesting enabled speedups of up to 167% in our tests. In addition to the two nesting algorithms, we also develop Hyflow2, a high-performance DTM framework for the Java Virtual Machine, written in Scala. It has a clean Scala API and a compatibility Java API. Hyflow2 was on average two times faster than Hyflow on high-contention workloads, and up to 16 times faster in low-contention workloads. Our second main contribution for improving DTM performance is automated data partition- ing. Modern transactional processing systems need to be fast and scalable, but this means many such systems settled for weak consistency models. It is however possible to achieve all of strong consistency, high scalability and high performance, by using fine-grained partitions and light-weight concurrency control that avoids superfluous synchronization and other over- heads such as lock management. Independent transactions are one such mechanism, that rely on good partitions and appropriately defined transactions. On the downside, it is not usually straightforward to determine optimal partitioning schemes, especially when dealing with non-trivial amounts of data. Our work attempts to solve this problem by automating the partitioning process, choosing the correct transactional primitive, and routing transactions appropriately. Our third main contribution is Alvin, a system for managing concurrently running trans- actions on a geographically replicated data-store. Alvin supports general-purpose transactions, and guarantees strong consistency criteria. Through a novel partial order broadcast protocol, Alvin maximizes the parallelism of ordering and local transaction processing, resulting in low client-perceived latency. Alvin can process read-only transactions either lo- cally or globally, according to the desired consistency criterion. Conflicting transactions are ordered across all sites. We built Alvin in the Go programming language. We conducted our evaluation study on Amazon EC2 infrastructure and compared against Paxos- and EPaxos- based state machine replication protocols. Our results reveal that Alvin provides significant speed-up for read-dominated TPC-C workloads: as much as 4.8x when compared to EPaxos on 7 datacenters, and up to 26% in write-intensive workloads. Our fourth and final contribution is M2Paxos, a multi-leader implementation of Generalized Consensus. Single leader-based consensus protocols are known to stop scaling once the leader reaches its saturation point. Ordering commands based on conflicts is appealing due to the potentially higher parallelism, but is imperfect due to the higher quorum sizes required for fast decisions and the need to compare commands and track their dependencies. M2Paxos on the other hand exploits fast decisions (i.e., delivery of a command in two communication delays) by leveraging a classic quorum size, matching a majority of nodes deployed. M2Paxos does not establish command dependencies based on conflicts, but it binds accessed objects to nodes, making sure commands operating on the same object will be ordered by the same node. Our evaluation study of M2Paxos (also built in Go) confirms the effectiveness of this approach, getting up to 7⨉ improvements in performance over state- of-the-art consensus and generalized consensus algorithms. / Ph. D.

There is an increasing integration of distributed energy resources (DER), controllable loads, and other technologies that are making the grid more robust, reliable, and decentralized. Communication is a major aspect that enables this decentralization and can improve control of important system parameters by allowing different grid components to communicate their states with each other. This information exchange requires a reliable and fast communication infrastructure. Different communication techniques can be used towards this objective, but with recent technological advancements, 5G communication is proving to be a very viable option. 5G is being widely deployed throughout the world due to its high data rates combined with increased reliability compared with its predecessor technologies. This thesis focuses on application and performance analysis of a 5G network for different power system test cases. These test cases are microgrids, and consist of DERs that use distributed control for efficient operation. Under distributed control, the DERs communicate with each other to achieve fast and improved dynamic response. This work develops a co-simulation platform to analyze the impact that a 5G network has in this distributed control objective. This offers key insights on 5G's capability to support critical functions. Different scenarios including set point changes and transients are evaluated. Since distributed control is a time-critical application and DERs rely on the availability of up-to-date information, the scheduling aspect of 5G becomes very important and is given more focus. Information freshness measured using age of information (AoI) is used in this work. Information freshness is a measure of how recent and updated the information communicated by DERs is. This thesis compares the performance of AoI-based schedulers against standard schedulers. These different schedulers are then used on test systems employing distributed control. / Master of Science / Communication has become an important aspect of modern power systems due to increased integration of distributed energy resources (DER), controllable loads and other components that have communication capabilities for improved grid performance. Of the various communication techniques available for power systems, 5G is very promising due to its advantages over its predecessors and other wired communication methods. This work develops a cosimulation framework to implement a 5G network for different microgrid test cases that employ distributed control. Under distributed control, the DERs communicate with each other to achieve fast and improved dynamic response. Due to the time-critical nature of distributed control, DERs rely on the availability of up-to-date information. Hence the scheduling aspect of 5G becomes very important and is given more focus in this work. 5G schedulers that account for the availability of up-to-date information, also referred to as information freshness, are compared with standard 5G schedulers and their performance in distributed control test systems is analyzed.