Scenario generation is an important step in the operation and planning of power systems with high renewable penetrations. In this work, we proposed a data-driven approach for scenario generation using generative adversarial networks, which is based on two interconnected deep neural networks. Compared with existing methods based on probabilistic models that are often hard to scale or sample from, our method is data-driven, and captures renewable energy production patterns in both temporal and spatial dimensions for a large number of correlated resources. For validation, we use wind and solar times-series data from NREL integration data sets. We demonstrate that the proposed method is able to generate realistic wind and photovoltaic power profiles with full diversity of behaviors. We also illustrate how to generate scenarios based on different conditions of interest by using labeled data during training. For example, scenarios can be conditioned on weather events~(e.g. high wind day, intense ramp events or large forecasts errors) or time of the year~(e,g. solar generation for a day in July). Because of the feedforward nature of the neural networks, scenarios can be generated extremely efficiently without sophisticated sampling techniques

The dc optimal power flow (DCOPF) problem is a fundamental problem in power systems operations and planning. With high penetration of uncertain renewable resources in power systems, DCOPF needs to be solved repeatedly for a large amount of scenarios, which can be computationally challenging. As an alternative to iterative solvers, neural networks are often trained and used to solve DCOPF. These approaches can offer orders of magnitude reduction in computational time, but they cannot guarantee generalization, and small training error does not imply small testing errors. In this work, we propose a novel algorithm for solving DCOPF that guarantees the generalization performance. First, by utilizing the convexity of the DCOPF problem, we train an input convex neural network. Second, we construct the training loss based on Karush–Kuhn–Tucker optimality conditions. By combining these two techniques, the trained model has provable generalization properties, where small training error implies small testing errors. In experiments, our algorithm significantly outperforms other machine learning methods.

Recent proliferation of electric vehicle (EV) charging load has imposed vital stress on power grid. The stochasticity and volatility of EV charging behaviors render it challenging to manipulate the uncertain charging demand for grid operations and charging management. Charging scenario generation can serve for future EV integration by modeling charging load uncertainties and simulating various realistic charging sessions. To this end, we propose a denoising Diffusion-based Charging scenario generation model coined DiffCharge, which is capable of yielding both battery-level and station-level EV charging time-series data with distinct temporal properties. In principle, the devised model can progressively convert the simply known Gaussian noise to genuine charging demand profiles by learning a parameterized reversal of the forward diffusion process. Besides, we leverage the multi-head self-attention mechanism and prior conditions to capture the unique temporal correlations associated with battery or charging station types in actual charging dynamics. Moreover, we validate the superior generative capacity of DiffCharge on a real-world dataset involving ample charging session records, and attest the efficacy of produced charging scenarios on a practical EV operation problem in the day-ahead electricity market.

Distributed energy resources (DERs) can serve as non-wire alternatives (NWAs) to capacity expansion by managing peak load to avoid or delay traditional expansion projects. However, the value stream derived from using DERs as NWAs is usually not explicitly included in DER planning problems. In this paper, we study a planning problem that co-optimizes the investment and operation of DERs and the timing of capacity expansion. By including the timing of capacity expansion as a decision variable, we naturally incorporate the NWA-related value stream of DERs in the planning problem. Furthermore, we show that even though the resulting optimization problem could have millions of variables and is non-convex, an optimal solution can be found by solving a series of smaller linear problems. Finally, we present a NWAs planning problem using real data from the Seattle Campus of the University of Washington.

The prosperity of smart mobile devices has made mobile crowdsensing (MCS) a promising paradigm for completing complex sensing and computation tasks. In the past, great efforts have been made on the design of incentive mechanisms and task allocation strategies from MCS platform’s perspective to motivate mobile users’ participation. However, in practice, MCS participants face many uncertainties coming from their sensing environment as well as other participants’ strategies, and how do they interact with each other and make sensing decisions is not well understood. In this paper, we take MCS participants’ perspectives to derive an online sensing policy to maximize their payoffs via MCS participation. Specifically, we model the interactions of mobile users and sensing environments as a multi-agent Markov decision process. Each participant cannot observe others’ decisions, but needs to decide her effort level in sensing tasks only based on local information, e.g., her own record of sensed signals’ quality. To cope with the stochastic sensing environment, we develop an intelligent crowdsensing algorithm IntelligentCrowd by leveraging the power of multi-agent reinforcement learning (MARL). Our algorithm leads to the optimal sensing policy for each user to maximize the expected payoff against stochastic sensing environments, and can be implemented at the individual participant’s level in a distributed fashion. Numerical simulations demonstrate that IntelligentCrowd significantly improves users’ payoffs in sequential MCS tasks under various sensing dynamics.