Ram Machlev

Bio: Ram Machlev is an academic researcher from Technion – Israel Institute of Technology. The author has contributed to research in topics: Computer science & Artificial intelligence. The author has an hindex of 7, co-authored 15 publications receiving 120 citations. Previous affiliations of Ram Machlev include Tel Aviv University.

Effects of the COVID-19 Pandemic on Energy Systems and Electric Power Grids—A Review of the Challenges Ahead

Abstract: The COVID-19 pandemic represents not just a global health crisis, but may signal the beginning of a new era of economic activity, the potential consequences of which we currently do not fully understand. In this context, the mid-to-long-range impacts of the pandemic on the energy sector have been studied extensively in the last few months. Despite these efforts, the pandemic still raises many open questions concerning the long-term operation and planning of power systems. For instance, how will the pandemic affect the integration of renewable energy sources? Should current power system expansion plans change in light of the COVID-19 pandemic? What new tools should be provided to support system operators during global health crises? It is the purpose of this paper to better understand the many aspects of these open questions by reviewing the relevant recent literature and by analyzing measured data. We point out the main challenges that the pandemic introduced by presenting patterns of electricity generation and demand, frequency deviations, and load forecasting. Moreover, we suggest directions for future research that may assist in coping with the mentioned challenges. We hope that this paper will trigger fruitful discussions and encourage further research on these important emerging topics.

Modified Cross-Entropy Method for Classification of Events in NILM Systems

Abstract: Non-intrusive load monitoring is an algorithm or process that disaggregates the total power in a facility to identify consumption of individual appliances In this paper, a new algorithm is proposed to classify events of appliance states based on modification of the cross-entropy (CE) method The main contribution is a formulation and solution of the problem with the CE method as a constrained optimization problem This new technique is called the modified CE method The proposed algorithm is simple, as it operates in real time, using low rate sampling of the active power In addition, there is no need to train the system or to use complex hardware The algorithm is tested using the REDD and AMPds datasets and the results are compared to several state-of-the-art techniques

Readiness of Small Energy Markets and Electric Power Grids to Global Health Crises: Lessons From the COVID-19 Pandemic

Abstract: In this paper we explore how the COVID-19 pandemic, also known as Coronavirus pandemic, affected the operation of small electric grids, and what can this event teach us on the readiness of such grids in the face of future global health crises. We focus on three major effects: changing patterns of generation and consumption, frequency stability, and the joint impact of low consumption and high share of renewable energy sources. Specifically, we analyze changes in consumption in the Israeli, Estonian, and Finnish grids, and attempt to identify patterns of consumption changes that may be explained by the pandemic. We also analyze changes in voltage and frequency, and show that the low consumption caused significant deviations from the nominal values of both parameters. One main conclusion is that the reduced energy consumption during the pandemic is critical, and has a major effect on the operation of small electric grids. Another conclusion is that since the pandemic pushed the relative share of renewable energy to record highs, this event may help us to better understand the influence of a high share of renewables on small grids, thus offering a glance into a renewable-rich future.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.