5G advancements like Massive Multiple Input Multiple Output (MIMO) bring high capacity and low latency, but also intensify interference challenges. Static and dynamic coordination techniques address this, often at the cost of increased power draw. We introduce Cookie-Jar (CJ), an interference coordination (IC) framework using reinforcement learning for multi-goal optimization. By dynamically adjusting network, power, and topology parameters based on realtime conditions, CJ improves Signal to Noise and Interference Ratio (SINR) while minimizing power consumption. Simulated 5G experiments showcase CJ's potential, achieving a 15% SINR improvement with near-identical power draw compared to existing methods.

Online deep learning (ODL) has become an important methodology for modeling time-based performance of computer systems. An open problem is the intelligent selection of features from raw workload traces of computer systems. The best methods are overly sensitive to noisy data, causing frequent feature changes and re-training. Using all available features inflates training time and introduces model artifacts if some features should have been dropped. We present WinnowML, a method for automatically determining the most relevant feature subset for a predictive time-series model. WinnowML combines existing feature ranking algorithms and a history of each feature’s ranking to iteratively rank a feature set to lower prediction error and maximize long term relevance. From this ranked feature set, the most relevant and stable subset is selected to train a model. Experimentally, we show how WinnowML can lower a model’s mean absolute relative error up to 42% on average compared to the closest performing approach. Additionally, we lower the fluctuation in feature ranking and selection up to 65%. We also demonstrate how to combine WinnowML and a model search tool to provide improvements in performance of up to 14.5% when compared to using all the feature available.

In large networked systems, a sudden increase in traffic could slowdown the network significantly, impacting network quality for multiple users. We present Diolkos, a system that leverages smart switches to dynamically re-reroute data flows in response to drops in performance. In contrast to other techniques, our tool predicts the future throughput at each port in a switch if a data flow were to be sent through it, and updates which port should be taken to maximize throughput. We use several techniques to predict network switch performance on a software defined network (SDN) mimicking topologies commonly found in datacenters. Experimentally, we demonstrate the effectiveness of choosing a port to send flows through based on predicted performance. We found that using a distributed predictive technique achieves a 24% improvement over using a traditional heuristic technique.

The size and complexity of large storage systems, such as high-performance computing (HPC) systems, inhibit rapid effective restructuring of data layouts to maintain performance as workloads shift. To address this issue, we have developed Geomancy, a tool that models the placement of data within a distributed storage system and reacts to drops in performance. Our approach to optimizing throughput offers benefits for storage systems such as avoiding potential bottlenecks and increasing overall I/O throughput from 11% to 30%.

Removing hard drives from a data center may expose sensitive data, such as encryption keys or passwords. To prevent exposure, data centers have security policies in place to physically secure drives in the system, and securely delete data from drives that are removed. Despite advances in security technology and best practices, implementation of these security measures is often done incorrectly. We anticipate that physical security will fail, and fixing the issue after the failure is costly and ineffective.

Parameter tuning is an important task of storage performance optimization. Current practice usually involves numerous tweak-benchmark cycles that are slow and costly. To address this issue, we developed CAPES, a model-less deep reinforcement learning-based unsupervised parameter tuning system driven by a deep neural network (DNN). It is designed to find the optimal values of tunable parameters in computer systems, from a simple client-server system to a large data center, where human tuning can be costly and often cannot achieve optimal performance. CAPES takes periodic measurements of a target computer system's state, and trains a DNN which uses Q-learning to suggest changes to the system's current parameter values. CAPES is minimally intrusive, and can be deployed into a production system to collect training data and suggest tuning actions during the system's daily operation. Evaluation of a prototype on a Lustre file system demonstrates an increase in I/O throughput up to 45% at saturation point.

This paper introduces a new environment for programming robots and physical computing devices---the Spatial Computing Platform (SCP)---and compares it to a text-based programming environment (the Cricket Logo). The SCP simplifies the process of constructing conditional statements that link the robot's inputs and outputs together. It does this by providing the user with a virtual canvas that they can draw rectangles on using the mouse. Each rectangle represents a range of sensor values, and specific outputs can be assigned to each rectangle. When the sensor values enter into the specified range, the outputs will turn on. We designed a study with 60 youth to compare this environment to Cricket Logo, a well-known variant of Logo designed to control robotic devices. We found that participants using the spatial computing platform were able to build programs of higher complexity and make more changes to their programs over the course of an hour-long workshop.