Chaitanya Poolla

Chaitanya Poolla, Abraham K. Ishihara, Rodolfo Milito

With the rapid growth in renewable energy and battery storage technologies, there exists significant opportunity to improve energy efficiency and reduce costs through optimization. However, optimization algorithms must take into account the underlying dynamics and uncertainties of the various interconnected subsystems in order to fully realize this potential. To this end, we formulate and solve an energy management optimization problem as a Markov Decision Process (MDP) consisting of battery storage dynamics, a stochastic demand model, a stochastic solar generation model, and an electricity pricing scheme. The stochastic model for predicting solar generation is constructed based on weather forecast data from the National Oceanic and Atmospheric Administration. A near-optimal policy design is proposed via stochastic dynamic programming. Simulation results are presented in the context of storage and solar-integrated residential and commercial building environments. Results indicate that the near-optimal policy significantly reduces the operating costs compared to several heuristic alternatives. The proposed framework facilitates the design and evaluation of energy management policies with configurable demand-supply-storage parameters in the presence of weather-induced uncertainties.

Chaitanya Poolla, Abraham K. Ishihara

With the recent interest in net-zero sustainability for commercial buildings, integration of photovoltaic (PV) assets becomes even more important. This integration remains a challenge due to high solar variability and uncertainty in the prediction of PV output. Most existing methods predict PV output using either local power/weather history or global weather forecasts, thereby ignoring either the impending global phenomena or the relevant local characteristics, respectively. This work proposes to leverage weather data from both local weather history and global forecasts based on time series modeling with exogenous inputs. The proposed model results in eighteen hour ahead forecasts with a mean accuracy of $\approx$ 80\% and uses data from the National Ocean and Atmospheric Administration's (NOAA) High-Resolution Rapid Refresh (HRRR) model.

Chaitanya Poolla, Rahul Saxena

The problem of learning parallel computer performance is investigated in the context of multicore processors. Given a fixed workload, the effect of varying system configuration on performance is sought. Conventionally, the performance speedup due to a single resource enhancement is formulated using Amdahl's law. However, in case of multiple configurable resources the conventional formulation results in several disconnected speedup equations that cannot be combined together to determine the overall speedup. To solve this problem, we propose to (1) extend Amdahl's law to accommodate multiple configurable resources into the overall speedup equation, and (2) transform the speedup equation into a multivariable regression problem suitable for machine learning. Using experimental data from fifty-eight tests spanning two benchmarks (SPECCPU 2017 and PCMark 10) and four hardware platforms (Intel Xeon 8180M, AMD EPYC 7702P, Intel CoffeeLake 8700K, and AMD Ryzen 3900X), analytical models are developed and cross-validated. Findings indicate that in most cases, the models result in an average cross-validated accuracy higher than 95%, thereby validating the proposed extension of Amdahl's law. The proposed methodology enables rapid generation of multivariable analytical models to support future industrial development, optimization, and simulation needs.

Chaitanya Poolla, Abraham K. Ishihara, Dan Liddell et al.

Commercial buildings account for approximately 35% of total US electricity consumption, of which nearly two-thirds is met by fossil fuels resulting in an adverse impact on the environment. This adverse impact can be mitigated by lowering energy consumption via control of occupant plugload usage in a closed-loop building environment. In this work, we conducted multiple experiments to analyze changes in occupant plugload energy consumption due to incentives and/or visual feedback. The incentives entailed daily monetary values between $5 and $50 administered in a randomized order and the visual feedback consisted of a web-based dashboard aimed at increasing the energy awareness of participants. Experiments were performed in government office and university buildings at NASA Ames Research Park located in Moffett Field, CA. Autoregressive models were constructed to predict expected plugload savings in the presence of exogenous variables. Analysis of the data revealed modulation of plugload energy consumption can be achieved via visual feedback and incentive mechanisms suggesting that occupant-in-the-loop control architectures may be effective in the commercial building environment. Our findings indicate that the mean energy reduction due to visual feedback in office and university environments were ~9.52% and ~21.61%, respectively. By augmenting the visual feedback in the university environment with a monetary incentive, the mean energy reduction was found to be ~24.22%