Goto

Collaborating Authors

 network sensor


Accelerating AI Development with Cyber Arenas

Cashman, William, Milner, Chasen, Houle, Michael, Jones, Michael, Jananthan, Hayden, Kepner, Jeremy, Michaleas, Peter, Pentland, Alex

arXiv.org Artificial Intelligence

Abstract--AI development requires high fidelity testing environments to effectively transition from the laboratory to operations. The flexibility offered by cyber arenas presents a novel opportunity to test new artificial intelligence (AI) capabilities with users. Cyber arenas are designed to expose end-users to real-world situations and must rapidly incorporate evolving capabilities to meet their core objectives. T o explore this concept the MIT/IEEE/Amazon Graph Challenge Anonymized Network Sensor was deployed in a cyber arena during a National Guard exercise. The increased complexity of the interactions between cyberspace and cyber-operators drive the complexity of the platforms emulating this relationship.


Machine-Learning Solar Tracking Technology Nudges PV Field Production Nearer Optimum Levels

#artificialintelligence

Solar energy products and services developers and vendors continue to leverage the latest in distributed information and communications technology (ICT) in bids to drive further declines in the cost and boost the productivity of solar energy systems. Development and use of an expanding range of machine-to-machine (M2M) communications and "Internet of Things" devices – wireless network sensors and "smart," network-connected inverters, meters and other devices – along with high-reliability wireless/mobile networking and cloud software- and infrastructure-as-a-service (SaaS and IaaS) platforms are enabling vendors and their customers to collect, analyze and act upon continuous streams of digital data and approach ideal maximum electrical power and energy production while coincidentally minimizing installation, operations and maintenance costs. With more than nine gigawatts (GWs) worth of its products installed on five continents, in 1991 Fremont, California-based NEXTracker published a groundbreaking white paper describing a new algorithm that improved solar tracking and resulted in gains of around three percent in solar PV facility production. While that methodology continues to be applied in nearly all solar energy tracking systems today, NEXTracker is pushing the technological envelope out further. On July 11, the company introduced its latest innovation to the market, a "first-of-its-kind intelligent, self-adjusting tracker control system for solar power plants."