Duncan S. Callaway

Mengqi Yao, Meghana Bharadwaj, Zheng Zhang et al. · berkeley

This paper examines the use of risk models to predict the timing and location of wildfires caused by electricity infrastructure. Our data include historical ignition and wire-down points triggered by grid infrastructure collected between 2015 to 2019 in Pacific Gas & Electricity territory along with various weather, vegetation, and very high resolution data on grid infrastructure including location, age, materials. With these data we explore a range of machine learning methods and strategies to manage training data imbalance. The best area under the receiver operating characteristic we obtain is 0.776 for distribution feeder ignitions and 0.824 for transmission line wire-down events, both using the histogram-based gradient boosting tree algorithm (HGB) with under-sampling. We then use these models to identify which information provides the most predictive value. After line length, we find that weather and vegetation features dominate the list of top important features for ignition or wire-down risk. Distribution ignition models show more dependence on slow-varying vegetation variables such as burn index, energy release content, and tree height, whereas transmission wire-down models rely more on primary weather variables such as wind speed and precipitation. These results point to the importance of improved vegetation modeling for feeder ignition risk models, and improved weather forecasting for transmission wire-down models. We observe that infrastructure features make small but meaningful improvements to risk model predictive power.

Emre C. Kara, Ciaran M. Roberts, Michaelangelo Tabone et al.

This paper presents a set of methods for estimating the renewable energy generation downstream of a measurement device using real-world measurements. First, we present a generation disaggregation scheme where the only information available for estimation is the micro-synchrophasor measurements obtained at the substation or feeder head. We then propose two strategies in which we use measurements from the substation as well as a proxy solar irradiance measurement. Using these two measurement points, we first propose a multiple linear regression strategy, in which we estimate a relationship between the measured reactive power and the load active power consumption, which are then used in disaggregation. Finally, we expand this strategy to strategically manage the reconstruction errors in the estimators. We simultaneously disaggregate the solar generation and load. We show that it is possible to disaggragate the generation of a 7.5 megawatt photovoltaic site with a root-mean-squared error of approximately 450 kilowatts.

Antoine Lesage-Landry, Duncan S. Callaway

We formulate an efficient approximation for multi-agent batch reinforcement learning, the approximated multi-agent fitted Q iteration (AMAFQI). We present a detailed derivation of our approach. We propose an iterative policy search and show that it yields a greedy policy with respect to multiple approximations of the centralized, learned Q-function. In each iteration and policy evaluation, AMAFQI requires a number of computations that scales linearly with the number of agents whereas the analogous number of computations increase exponentially for the fitted Q iteration (FQI), a commonly used approaches in batch reinforcement learning. This property of AMAFQI is fundamental for the design of a tractable multi-agent approach. We evaluate the performance of AMAFQI and compare it to FQI in numerical simulations. The simulations illustrate the significant computation time reduction when using AMAFQI instead of FQI in multi-agent problems and corroborate the similar performance of both approaches.

Antoine Lesage-Landry, Joshua A. Taylor, Duncan S. Callaway

We consider online optimization with binary decision variables and convex loss functions. We design a new algorithm, binary online gradient descent (bOGD) and bound its expected dynamic regret. We provide a regret bound that holds for any time horizon and a specialized bound for finite time horizons. First, we present the regret as the sum of the relaxed, continuous round optimum tracking error and the rounding error of our update in which the former asymptomatically decreases with time under certain conditions. Then, we derive a finite-time bound that is sublinear in time and linear in the cumulative variation of the relaxed, continuous round optima. We apply bOGD to demand response with thermostatically controlled loads, in which binary constraints model discrete on/off settings. We also model uncertainty and varying load availability, which depend on temperature deadbands, lockout of cooling units and manual overrides. We test the performance of bOGD in several simulations based on demand response. The simulations corroborate that the use of randomization in bOGD does not significantly degrade performance while making the problem more tractable.

Antoine Lesage-Landry, Duncan S. Callaway

We extend the regret analysis of the online distributed weighted dual averaging (DWDA) algorithm [1] to the dynamic setting and provide the tightest dynamic regret bound known to date with respect to the time horizon for a distributed online convex optimization (OCO) algorithm. Our bound is linear in the cumulative difference between consecutive optima and does not depend explicitly on the time horizon. We use dynamic-online DWDA (D-ODWDA) and formulate a performance-guaranteed distributed online demand response approach for heating, ventilation, and air-conditioning (HVAC) systems of commercial buildings. We show the performance of our approach for fast timescale demand response in numerical simulations and obtain demand response decisions that closely reproduce the centralized optimal ones.

Joshua Adam Taylor, Sairaj V. Dhople, Duncan S. Callaway

The finiteness of fossil fuels implies that future electric power systems may predominantly source energy from fuel-free renewable resources like wind and solar. Evidently, these power systems without fuel will be environmentally benign, sustainable, and subject to milder failure scenarios. Many of these advantages were projected decades ago with the definition of the soft energy path, which describes a future where all energy is provided by numerous small, simple, and diverse renewable sources. Here we provide a thorough investigation of power systems without fuel from technical and economic standpoints. The paper is organized by timescale and covers issues like the irrelevance of unit commitment in networks without large, fuel-based generators, the dubiousness of nodal pricing without fuel costs, and the need for new system-level models and control methods for semiconductor-based energy-conversion interfaces.