The novel coronavirus disease (COVID-19) has rapidly spread around the globe in 2020, with U.S. becoming epicenter of COVID-19 cases since late March. As begins to gradually resume economic activity, it is imperative for policymakers and power system operators take a scientific approach understanding predicting impact on electricity sector. Here, we release first-of-its-kind cross-domain open-access data hub, integrating from across all existing wholesale markets case, weather, cellular...

This paper proposes a novel bi-level optimization model to study the strategic retail pricing and demand bidding problems of an electricity retailer that considers interactions between response market clearing process. In order accurately forecast day-ahead bids submitted by retailer, deep learning framework based on convolutional neural networks long short-term memory is proposed can capture both local trends long-term dependency forecasting data. addition, uncertainties about retailer's...

Abstract In electricity markets, locational marginal price (LMP) forecasting is particularly important for market participants in making reasonable bidding strategies, managing potential trading risks, and supporting efficient system planning operation. Unlike existing methods that only consider LMPs' temporal features, this paper tailors a spectral graph convolutional network (GCN) to greatly improve the accuracy of short‐term LMP forecasting. A three‐branch structure then designed match...

The battery performance and lifespan of electric vehicles (EVs) degrade significantly in cold climates, requiring a considerable amount energy to heat up the EV batteries. This paper proposes novel technology, namely temperature controlled smart charging, coordinate heating/charging power reduce use solar-powered charging station. Instead fixing setpoints, we track thermal dynamics inertia batteries, decide optimal timing proper allocated for heating. In addition, temperature-sensitive model...

Granular, localized data are essential for generating actionable insights that facilitate the transition to a net-zero energy system, particularly in underdeveloped regions. Understanding residential electricity consumption—especially response extreme weather events such as heatwaves and tropical storms—is critical enhancing grid resilience optimizing management strategies. However, often scarce. This study introduces comprehensive dataset comprising hourly transformer-level load collected...

Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees. Previous works tend express the constraints in an expectation form due ease of implementation, but this turns out be ineffective maintaining high probability. To end, we move quantile-constrained RL that enables higher level without any expectation-form approximations. We directly estimate quantile gradients through sampling provide theoretical proofs convergence....

There is an opportunity in modern power systems to explore the demand flexibility by incentivizing consumers with dynamic prices. In this paper, we quantify using efficient tool called time-varying elasticity, whose value may change depending on prices and decision dynamics. This particularly useful for evaluating response potential system reliability. Recent empirical evidences have highlighted some abnormal features when studying flexibility, such as delayed responses vanishing...

Supervised machine learning models are receiving increasing attention in electricity theft detection due to their high accuracy. However, performance depends on a massive amount of labeled training data, which comes from time-consuming and resource-intensive annotations. To maximize model within limited annotation budget, this paper aims reduce the effort through optimal sample selection. In particular, general framework three new strategies proposed select most valuable representative...

With dramatic breakthroughs in recent years, machine learning is showing great potential to upgrade the toolbox for power system optimization. Understanding strength and limitation of approaches crucial decide when how deploy them boost optimization performance. This paper pays special attention coordination between models, carefully evaluates such data-driven analysis may improve rule-based The typical references are selected categorized into four groups: boundary parameter improvement,...

Microgrid serves as a promising solution to integrate and manage distributed renewable energy resources. In this paper, we establish stochastic multi-objective sizing optimization (SMOSO) model for microgrid planning, which fully captures the battery degradation characteristics total carbon emissions. The operator aims simultaneously maximize economic benefits minimize emissions, of storage system (BESS) is modeled nonlinear function power throughput. A self-adaptive genetic algorithm...

The novel coronavirus disease (COVID-19) has rapidly spread around the globe in 2020, with U.S. becoming epicenter of COVID-19 cases since late March. As begins to gradually resume economic activity, it is imperative for policymakers and power system operators take a scientific approach understanding predicting impact on electricity sector. Here, we release first-of-its-kind cross-domain open-access data hub, integrating from across all existing wholesale markets case, weather, cellular...

Due to heavy computational burdens, existing demand-side bidding models have sacrifice the accuracy of uncertainty estimates in exchange for tractability, and therefore fail derive a high revenue as expected. To overcome this challenge, we analyze entire process, from scenario reduction curve construction, find out weak link that needs improvement. We further develop novel process save some resources by decomposing complex model, then reallocates these consider more scenarios precise curves....