Distribution systems are growing rapidly in size and complexity with increased penetrations of distributed energy resources (DER) and electric vehicles (EVs), leading to operational challenges. Reactive power compensation from photovoltaic (PV) inverters and active power curtailment of PV output are commonly used to mitigate voltage-related problems. However, the charging/discharging flexibility of EVs can be used to avoid PV output curtailment and save energy motivating methods to coordinate EV charging with PVs. Unfortunately, a large number of control variables makes the centralized voltage control computationally expensive. In this work, a decentralized voltage control algorithm which considers the active and reactive power compensation from PV inverters and EVs is presented. The proposed approach helps to solve the voltage issues in a more effective way. The approach involves clustering of the distribution network based on modified modularity, an index that considers EV flexibility and prediction time period. A model predictive control (MPC)-based algorithm is proposed for each cluster to solve the voltage problem using the respective PVs and EVs, while ensuring that the EV charging demand is satisfied while contributing to the voltage regulation. The proposed algorithm is validated using the IEEE 123 node test systems under two PV and EV penetration levels and shown to be effective in solving the voltage regulation problem.

A significant amount of distributed photovoltaic (PV) generation is “invisible” to distribution system operators since it is behind the meter on customer premises and not directly monitored by the utility. The generation essentially adds an unknown varying negative demand to the system, which causes additional uncertainty in determining the total load. This uncertainty directly impacts system reliability, cold load pickup, load behavior modeling, and hence cost of operation. Thus, it is essential to create low-complexity localized models for estimating power generation from these invisible sites behind the meters. This article proposes an adaptive machine learning framework to: a) learn using weather data and a minimal number of BTM PV generation measurement sensors, b) forecast PV generation using weather, location of PV, and trained ML model at location for unmeasured BTM PV; c) use estimated PV and net load measured by smart meter or smart transformer to estimate total true load at each time step; and d) learn the specific load patterns eventually to adapt localized models. The proposed framework's core idea is to transform the data such that: a) the machine learning model can effectively utilize the time dependency of measurements; and b) the measurements are transformed into a lower dimensional space to reduce complexity while maintaining accuracy. The transformed measurements are then used to train the machine learning models for load/PV disaggregation. Machine learning models investigated include linear regression, decision tree, random forest (RF), and multilayer perceptron. The proposed framework's efficacy is demonstrated using two datasets, a real dataset from Hawaii and a simulated dataset using detailed models in GridLab-D. Several test/training split scenarios, including 90-10% split, one-month-out, one-season-out, and panel-independent split are presented to provide a thorough evaluation of the proposed framework. Results on both datasets show that the proposed framework can estimate PV generation with high accuracy using low-complexity methods. The accuracy results are comparable to higher complexity models (e.g., deep architectures), and RF is found to provide superior performance with these specific datasets compared to the other ML models investigated.

Intrusion Detection Systems (IDSs) are an essential element of modern cyber defense, alerting users to when and where cyber-attacks occur. Machine learning can enable IDSs to further distinguish between benign and malicious behaviors, but it comes with several challenges, including lack of quality training data and high false-positive rates. Generative Machine Learning Models (GMLMs) can help overcome these challenges. This article offers an in-depth exploration of GMLMs’ application to intrusion detection. It gives (1) a systematic mapping study of research at the intersection of GMLMs and IDSs, and (2) a detailed review providing insights and directions for future research.

This work examines the state-of-the-art of cybersecurity education in the United States by considering two sources of data. The first source consists of Programs of Study for cybersecurity programs at Centers of Academic Excellence in Cybersecurity designated by the National Security Agency. Statistics were aggregated from a sample of one hundred CAE-C institutions, trends and gaps are identified, and improvements are proposed. The second source is peer-reviewed research published in the field of cybersecurity education over the last decade. A review of this literature shows a strong focus on identifying instructional content and developing educational tools while simultaneously indicating a shortage of research into rigorous evaluation of the instructional approaches being used to teach cybersecurity. Our review of these two sources of data highlight two paths to improving cybersecurity education in the United States. First, institutions offering cybersecurity degrees could work more closely with groups such as NIST, ACM, and IEEE to ensure their curricula match the needs of industry and they are graduating work-ready cybersecurity specialists. While CAE-C designation provides certain requirements for the amount of cybersecurity content included in curricula, designated institutions vary widely in the types of programs they offer and how many cybersecurity-specific courses they provide. Second, cybersecurity education could benefit from an influx of ideas from educational psychology regarding instructional theories such as cognitive load theory.

Human activity recognition (HAR) plays a central role in health-care, fitness and sport applications because of its potential to enable context-aware human monitoring. With the increase in popularity of wearable devices, we are witnessing a large influx in availability of human activity data. For effective analysis and interpretation of these heterogeneous and high-volume streaming data, we need powerful algorithms. In particular, there is a strong need for developing algorithms for robust classification of human activity data that specifically address challenges associated with dynamic environments (e.g. different users, signal heterogeneity). We use the term robust here in two, orthogonal senses: 1) leveraging related data in such a way that knowledge is transferred to a new context; and 2) actively reconfiguring machine learning algorithms such that they can be applied in a new context. In this paper, we propose an architecture that combines an active learning approach with a novel deep network. Our deep neural network exploits both Convolutional and Long Short-Term Memory (LSTM) layers in order to learn hierarchical representation of features and capture time dependencies from raw-data. The active learning process allows us to choose the best instances for fine-tuning the deep network to the new setting in which the system operates (i.e. a new subject). We demonstrate the efficacy of the architecture using real data of human activity. We show that the accuracy of activity recognition reaches over 90% by annotating less than 20% of unlabeled data.