The massive penetration of Renewables into the energy mix and the existence of IoT-enabled Distributed Energy Resources (DERs) in the emerging smart grid, while a blessing towards de-carbonization, increase considerably the operations and planning functions of the grid. Cloud processing of IoT/DER data facilitates the deployment of various Demand-Response (DR) and other DER asset scenarios, the organization of distribution grids into Local Energy Markets (LEM) and the efficient computation of load forecasting and power flow. Cloud computing enables a plethora of service provisions to the grid including frequency response. The decentralized nature of DERs at the edge of the distribution grid requires nodal approaches for the computation of power grid congestion constraints and power flow solutions. We present here a cloud-edge continuum approach, anchored on the new generation of communications infrastructure, which expedites the computation time of the load and DER forecasting and optimal power flow calculations. The proposed approach allows the LEM operator to respond to Fast Frequency Response service procurement signals issued by the balancing authority requiring even sub-second latency for service settlement. The proposed cloud-edge architecture has been tested on the IEEE European Low Voltage Benchmark model and provides scalability and elasticity for various DR/DER configurations.

The extreme ultraviolet (EUV) photolithography process is a cornerstone of semiconductor manufacturing and operates under demanding precision standards realized via nanometer-level overlay (OVL) error modeling. This procedure allows the machine to anticipate and correct OVL errors before impacting the wafer, thereby facilitating near-optimal image exposure while simultaneously minimizing the overall OVL error. Such models are usually high dimensional and exhibit rigorous statistical phenomena such as collinearities that play a crucial role in the process of tuning their parameters. Ordinary least squares (OLS) is the most widely used method for parameters tuning of overlay models, but in most cases it fails to compensate for such phenomena. In this paper, we propose the usage of ridge regression, a widely known machine learning (ML) algorithm especially suitable for datasets that exhibit high multicollinearity. The proposed method was applied in perturbed data from a 300 mm wafer fab, and the results show reduced residuals when ridge regression is applied instead of OLS.