Search for: All records

Integration of distributed renewable energy sources (D- RES) has been introduced as a viable solution to offer cheap and clean energy to customers in decentralized power system. D- RES can offer local generation to flexible customers based on their servicing deadline and constraints, benefiting both D- RES owners and customers in terms of providing economic revenue and reducing the cost of supplied energy. In this context, this paper proposes a dynamic matching framework using model predictive control (MPC) to enable local energy sharing in power system operation. The proposed matching framework matches flexible customers with D- RES to maximize social welfare in the matching market, while meeting the customers' servicing constraints prior to their deadline. Simulations are conducted on a test power system using multiple matching algorithms across different load and generation scenarios and the results highlighted the efficiency of proposed framework in matching flexible customers with the appropriate supply sources to maximize social welfare in the matching market. 

In autonomous vehicles (AVs), early warning systems rely on collision prediction to ensure occupant safety. However, state-of-the-art methods using deep convolutional networks either fail at modeling collisions or are too expensive/slow, making them less suitable for deployment on AV edge hardware. To address these limitations, we propose SG2VEC, a spatio-temporal scene-graph embedding methodology that uses Graph Neural Network (GNN) and Long Short-Term Memory (LSTM) layers to predict future collisions via visual scene perception. We demonstrate that SG2VEC predicts collisions 8.11% more accurately and 39.07% earlier than the state-of-the-art method on synthesized datasets, and 29.47% more accurately on a challenging realworld collision dataset. We also show that SG2VEC is better than the state-of-the-art at transferring knowledge from synthetic datasets to real-world driving datasets. Finally, we demonstrate that SG2VEC performs inference 9.3x faster with an 88.0% smaller model, 32.4% less power, and 92.8% less energy than the state-of-the-art method on the industry-standard Nvidia DRIVE PX 2 platform, making it more suitable for implementation on the edge. 

As miniaturization of electrical and mechanical components used in modern technology progresses, there is an increasing need for high-throughput and low-cost micro-scale assembly techniques. Many current micro-assembly methods are serial in nature, resulting in unfeasibly low throughput. Additionally, the need for increasingly smaller tools to pick and place individual microparts makes these methods cost prohibitive. Alternatively, parallel self-assembly or directed-assembly techniques can be employed by utilizing forces dominant at the micro and nano scales such as electro-kinetic, thermal, and capillary forces. However, these forces are governed by complex equations and often act on microparts simultaneously and competitively, making modeling and simulation difficult. The research in this paper presents a novel phenomenological approach to directed micro-assembly through the use of artificial intelligence to correlate micro-particle movement via dielectrophoretic and electro-osmotic forces in response to varying frequency of an applied non-uniform electric field. This research serves as a proof of concept of the application of artificial intelligence to create high yield low-cost micro-assembly techniques, which will prove useful in a variety of fields including micro-electrical-mechanical systems (MEMS), biotechnology, and tissue engineering.