Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFeature-driven Improvement of Renewable Energy Forecasting and Trading
73
0
0.0
(
0
)
Added by
Juan M. Morales Dr.
Publication date
2019
fields
Mathematical Statistics
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Inspired from recent insights into the common ground of machine learning, optimization and decision-making, this paper proposes an easy-to-implement, but effective procedure to enhance both the quality of renewable energy forecasts and the competitive edge of renewable energy producers in electricity markets with a dual-price settlement of imbalances. The quality and economic gains brought by the proposed procedure essentially stem from the utilization of valuable predictors (also known as features) in a data-driven newsvendor model that renders a computationally inexpensive linear program. We illustrate the proposed procedure and numerically assess its benefits on a realistic case study that considers the aggregate wind power production in the Danish DK1 bidding zone as the variable to be predicted and traded. Within this context, our procedure leverages, among others, spatial information in the form of wind power forecasts issued by transmission system operators (TSO) in surrounding bidding zones and publicly available in online platforms. We show that our method is able to improve the quality of the wind power forecast issued by the Danish TSO by several percentage points (when measured in terms of the mean absolute or the root mean square error) and to significantly reduce the balancing costs incurred by the wind power producer.
rate research
Read More
This paper proposes a peer to peer (P2P), blockchain based energy trading market platform for residential communities with the objective of reducing overall community peak demand and household electricity bills. Smart homes within the community place energy bids for its available distributed energy resources (DERs) for each discrete trading period during a day, and a double auction mechanism is used to clear the market and compute the market clearing price (MCP). The marketplace is implemented on a permissioned blockchain infrastructure, where bids are stored to the immutable ledger and smart contracts are used to implement the MCP calculation and award service contracts to all winning bids. Utilizing the blockchain obviates the need for a trusted, centralized auctioneer, and eliminates vulnerability to a single point of failure. Simulation results show that the platform enables a community peak demand reduction of 46%, as well as a weekly savings of 6%. The platform is also tested at a real-world Canadian microgrid using the Hyperledger Fabric blockchain framework, to show the end to end connectivity of smart home DERs to the platform.
Intermittency is a common and challenging problem in demand forecasting. We introduce a new, unified framework for building intermittent demand forecasting models, which incorporates and allows to generalize existing methods in several directions. Our framework is based on extensions of well-established model-based methods to discrete-time renewal processes, which can parsimoniously account for patterns such as aging, clustering and quasi-periodicity in demand arrivals. The connection to discrete-time renewal processes allows not only for a principled extension of Croston-type models, but also for an natural inclusion of neural network based models---by replacing exponential smoothing with a recurrent neural network. We also demonstrate that modeling continuous-time demand arrivals, i.e., with a temporal point process, is possible via a trivial extension of our framework. This leads to more flexible modeling in scenarios where data of individual purchase orders are directly available with granular timestamps. Complementing this theoretical advancement, we demonstrate the efficacy of our framework for forecasting practice via an extensive empirical study on standard intermittent demand data sets, in which we report predictive accuracy in a variety of scenarios that compares favorably to the state of the art.
Efforts to efficiently promote the participation of distributed energy resources in community microgrids require new approaches to energy markets and transactions in power systems. In this paper, we contribute to the promising approach of peer-to-peer (P2P) energy trading. We first formalize a centralized welfare maximization model of an economic dispatch with perfect information based on the value of consumption with zero marginal-cost energy. We characterize the optimal solution and corresponding price to serve as a reference for P2P approaches and show that the profit-maximizing strategy for individuals with storage in response to an optimal price is not unique. Second, we develop a novel P2P algorithm for negotiating energy trades based on iterative price and quantity offers that yields physically feasible and at least weakly Pareto-optimal outcomes. We prove that the P2P algorithm converges to the centralized solution in the case of two agents negotiating for a single period, demonstrate convergence for the multi-agent, multi-period case through a large set of random simulations, and analyze the effects of storage penetration on the solution.
Battery storage is expected to play a crucial role in the low-carbon transformation of energy systems. The deployment of battery storage in the power gird, however, is currently severely limited by its low economic viability, which results from not only high capital costs but also the lack of flexible and efficient utilization schemes and business models. Making utility-scale battery storage portable through trucking unlocks its capability to provide various on-demand services. We introduce the potential applications of utility-scale portable energy storage and investigate its economics in California using a spatiotemporal decision model that determines the optimal operation and transportation schedules of portable storage. We show that mobilizing energy storage can increase its life-cycle revenues by 70% in some areas and improve renewable energy integration by relieving local transmission congestion. The life-cycle revenue of spatiotemporal arbitrage can fully compensate for the costs of portable energy storage system in several regions in California, including San Diego and the San Francisco Bay Area.
We move beyond Is Machine Learning Useful for Macroeconomic Forecasting? by adding the how. The current forecasting literature has focused on matching specific variables and horizons with a particularly successful algorithm. In contrast, we study the usefulness of the underlying features driving ML gains over standard macroeconometric methods. We distinguish four so-called features (nonlinearities, regularization, cross-validation and alternative loss function) and study their behavior in both the data-rich and data-poor environments. To do so, we design experiments that allow to identify the treatment effects of interest. We conclude that (i) nonlinearity is the true game changer for macroeconomic prediction, (ii) the standard factor model remains the best regularization, (iii) K-fold cross-validation is the best practice and (iv) the $L_2$ is preferred to the $bar epsilon$-insensitive in-sample loss. The forecasting gains of nonlinear techniques are associated with high macroeconomic uncertainty, financial stress and housing bubble bursts. This suggests that Machine Learning is useful for macroeconomic forecasting by mostly capturing important nonlinearities that arise in the context of uncertainty and financial frictions.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
