Abstract Asynchronous evolutionary algorithms are becoming increasingly popular as a means of making full use of many processors while solving computationally expensive search and optimization problems. These algorithms excel at keeping large clusters fully utilized, but may sometimes inefficiently sample an excess of fast‐evaluating solutions at the expense of higher‐quality, slow‐evaluating ones. We have previously introduced a steady‐state parent selection strategy, SWEET (“Selection whilE EvaluaTing”), that sometimes selects individuals that are still being evaluated and allows them to reproduce early. We perform a takeover‐time analysis that confirms that this strategy gives slow‐evaluating individuals that have higher fitnesses an increased ability to multiply in the population. We also find that SWEET appears effective at improving optimization performance on problems in which solution quality is positively correlated with evaluation time. We evaluate our approach on six simulated real‐valued optimization problems and three real‐world applications: an autonomous vehicle controller problem that involves tuning a spiking neural network and two adversarial EA problems. We further evaluate SWEET versus a basic asynchronous process in a simulated setting. We present evidence that SWEET outperforms basic asynchronous processes in a use‐case in which performance is positively correlated with evaluation time, and performs comparably (and often better) than basic asynchronous processes in several use‐cases where performance is negatively correlated with evaluation time. That said, in the cases where performance and evaluation time are negatively correlated the variance of outcomes for SWEET is notably high.

Assessing critical infrastructure vulnerabilities is paramount to arranging efficient plans for their protection. Critical infrastructures are cyber-physical systems that can be represented as a network consisting of nodes and edges and highly interdependent in nature. Given the interdependent nature of critical infrastuctures, failure in one node may cause failure in many others resulting in a cascade of failures. In this paper, we propose a node criticality metric that uses Google’s PageRank algorithm to identify nodes that are likely to fail (are vulnerable), nodes whose failure may cascade to many other sites in the network (are important), and nodes that are both vulnerable and important (are critical). We then present a series of experiments to understand how protecting certain critical nodes can help mitigate massive cascading failures. Simulating failures in a real-world network with and without critical node protections demonstrates the importance of identifying critical nodes in an infrastructure network.

Modeling failure dynamics within a power system is a complex and challenging process due to multiple inter-dependencies and convoluted inter-domain relationships. Subject matter experts (SMEs) are interested in understanding these failure dynamics for reducing the impact from future disasters (i.e., losses or failures of power system components, such as transmission lines). Contingency analysis (CA) tools enable such ’what-if’ scenario analyses to evaluate the impacts on the power system. Analyzing all possible contingencies among N system components can be computationally expensive. An important step for performing CA is identifying a set of k ‘trigger’ components, which when failed initially can significantly impact the overall system by causing multiple failures. Currently SMEs focus on identifying these trigger components by running expensive simulations on all possible subsets, which quickly becomes infeasible. Hence finding a relevant set of trigger components (contingencies) rapidly to enable efficient and useful CA is crucial.In a collaboration between computer scientists and power system experts, we propose an efficient method for performing CA by exploiting network inter-dependencies in power system components. First, we construct a network with multiple electric grid infrastructure components and dependencies as connections among them. We reformulate the problem of finding a set of trigger components as a problem of identifying critical nodes in the network, which can cascade power failures through connected nodes and cause significant damage to the network. To guide the practical CA tools, we develop a network-based model with a probabilistic edge-weights setup using intricate domain rules. Then we conduct an empirical study on real power system data in the US for both regional and national levels. Firstly, we use power system datasets for the US to create a national-scale domain-driven model. Secondly, we demonstrate that network-based model outperforms the outputs from a real CA tool and show on average 25 × improved selection of contingencies, thereby showcasing practical benefits to the power experts.

Modern society is increasingly dependent on the stability of a complex system of interdependent infrastructure sectors. Vulnerability in critical infrastructures (CIs) is defined as a measure of system susceptibility to threat scenarios. Quantifying vulnerability in CIs has not been adequately addressed in the literature. This paper presents ongoing research on how the authors model CIs as network-based models and propose a set of metrics to quantify vulnerability in CI systems. The size and complexity of the CIs make this a challenging task. These metrics could be used for planning and efficient decision-making during extreme events.

Training neural networks for neuromorphic deployment is non-trivial. There have been a variety of approaches proposed to adapt back-propagation or back-propagation-like algorithms appropriate for training. Considering that these networks often have very different performance characteristics than traditional neural networks, it is often unclear how to set either the network topology or the hyperparameters to achieve optimal performance. In this work, we introduce a Bayesian approach for optimizing the hyperparameters of an algorithm for training binary communication networks that can be deployed to neuromorphic hardware. We show that by optimizing the hyperparameters on this algorithm for each dataset, we can achieve improvements in accuracy over the previous state-of-the-art for this algorithm on each dataset (by up to 15 percent). This jump in performance continues to emphasize the potential when converting traditional neural networks to binary communication applicable to neuromorphic hardware.

Though robustness and resilience are commonly quoted as features of neuromorphic computing systems, the expected performance of neuromorphic systems in the face of hardware failures is not clear. In this work, we study the effect of failures on the performance of four different training algorithms for spiking neural networks on neuromorphic systems: two back-propagation-based training approaches (Whetstone and SLAYER), a liquid state machine or reservoir computing approach, and an evolutionary optimization-based approach (EONS). We show that these four different approaches have very different resilience characteristics with respect to simulated hardware failures. We then analyze an approach for training more resilient spiking neural networks using the evolutionary optimization approach. We show how this approach produces more resilient networks and discuss how it can be extended to other spiking neural network training approaches as well.

As deep neural networks have been deployed in more and more applications over the past half decade and are finding their way into an ever increasing number of operational systems, their energy consumption becomes a concern whether running in the datacenter or on edge devices. Hyperparameter optimization and automated network design for deep learning is a quickly growing field, but much of the focus has remained only on optimizing for the performance of the machine learning task. In this work, we demonstrate that the best performing networks created through this automated network design process have radically different computational characteristics (e.g. energy usage, model size, inference time), presenting the opportunity to utilize this optimization process to make deep learning networks more energy efficient and deployable to smaller devices. Optimizing for these computational characteristics is critical as the number of applications of deep learning continues to expand.