An official website of the United States government
Although hydropower produces a relatively small portion of the electricity we use in the United States, it is a flexible and dispatchable resource that serves various critical functions for managing the electricity grid. Climate-induced changes to water availability will affect future hydropower production, and such changes could impact how the areas where the supply and demand of electricity are balanced, called balancing authority areas, are able to meet decarbonization goals. We calculate hydroclimate risk to hydropower at the balancing authority scale, which is previously underexplored in the literature and has real implications for decarbonization and resilience-building. Our results show that, by 2050, most balancing authority areas could experience significant changes in water availability in areas where they have hydropower. Balancing areas facing the greatest changes are located in diverse geographic areas, not just the Western and Northwestern United States, and vary in hydropower generation capacity. The range of projected changes experienced within each balancing area could exacerbate or offset existing hydropower generation deficits. As power producers and managers undertake increasing regional cooperation to account for introducing more variable renewable energy into the grid, analysis of risk at this regional scale will become increasingly salient.
more »
« less
Forecasting the Evolution of Hydropower Generation
Hydropower is the largest renewable energy source for electricity generation in the world, with numerous benefits in terms of: environment protection (near-zero air pollution and climate impact), cost-effectiveness (long-term use, without significant impacts of market fluctuation), and reliability (quickly respond to surge in demand). However, the effectiveness of hydropower plants is affected by multiple factors such as reservoir capacity, rainfall, temperature and fluctuating electricity demand, and particularly their complicated relationships, which make the prediction/recommendation of station operational output a difficult challenge. In this paper, we present DeepHydro, a novel stochastic method for modeling multivariate time series (e.g., water inflow/outflow and temperature) and forecasting power generation of hydropower stations. DeepHydro captures temporal dependencies in co-evolving time series with a new conditioned latent recurrent neural networks, which not only considers the hidden states of observations but also preserves the uncertainty of latent variables. We introduce a generative network parameterized on a continuous normalizing flow to approximate the complex posterior distribution of multivariate time series data, and further use neural ordinary differential equations to estimate the continuous-time dynamics of the latent variables constituting the observable data. This allows our model to deal with the discrete observations in the context of continuous dynamic systems, while being robust to the noise. We conduct extensive experiments on real-world datasets from a large power generation company consisting of cascade hydropower stations. The experimental results demonstrate that the proposed method can effectively predict the power production and significantly outperform the possible candidate baseline approaches.
more »
« less
- Award ID(s):
- 1823279
- PAR ID:
- 10211114
- Date Published:
- Journal Name:
- The 26th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining, CA, August 2020
- Page Range / eLocation ID:
- 2861 to 2870
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Over the period 2012–2016, the state of California in the United States (U.S.) experienced a drought considered to be one of the worst in state history. Drought’s direct impacts on California’s electric power sector are understood. Extremely low streamflow manifests as reduced hydropower availability, and if drought is also marked by elevated temperatures, these can increase building electricity demands for cooling. Collectively, these impacts force system operators to increase reliance on natural gas power plants, increasing market prices and emissions. However, previous investigations have relied mostly on ex post analysis of observational data to develop estimates of increases in costs and carbon dioxide (CO 2 ) emissions due to the 2012–2016 drought. This has made it difficult to control for confounding variables (e.g. growing renewable energy capacity, volatile natural gas prices) in assessing the drought’s impacts. In this study, we use a power system simulation model to isolate the direct impacts of several hydrometeorological phenomena observed during the 2012–2016 drought on system wide CO 2 emissions and wholesale electricity prices in the California market. We find that the impacts of drought conditions on wholesale electricity prices were modest (annual prices increased by $0–3 MWh −1 , although much larger within-year increases are also observed). Instead, it was an increase in natural gas prices, punctuated by the 2014 polar vortex event that affected much of the Eastern U.S., which caused wholesale electricity prices to increase during the drought. Costs from the drought were very different for the state’s three investor owned utilities. Overall, we find that increased cooling demands (electricity demand) during the drought may have represented a larger economic cost ($3.8 billion) than lost hydropower generation ($1.9 billion). We also find the potential for renewable energy to mitigate drought-cased increases in CO 2 emissions to be negligible, standing in contrast to some previous studies.more » « less
-
The current practice of discrete-time electricity pricing starts to fall short in providing an accurate economic signal reflecting the continuous-time variations of load and generation schedule in power systems. This paper introduces the fundamental mathematical theory of continuous-time marginal electricity pricing. We first formulate the continuous-time unit commitment (UC) problem as a constrained variational problem, and subsequently define the continuous-time economic dispatch (ED) problem where the binary commitment variables are fixed to their optimal values. We then prove that the continuous-time marginal electricity price equals to the Lagrange multiplier of the variational power balance constraint in the continuous-time ED problem. The proposed continuous-time marginal price is not only dependent to the incremental generation cost rate, but also to the incremental ramping cost rate of the units, thus embedding the ramping costs in calculation of the marginal electricity price. The numerical results demonstrate that the continuous-time marginal price manifests the behavior of the constantly varying load and generation schedule in power systems.more » « less
-
Gaining money and high profit is the dream of electricity market investors; however, it requires accurate financial knowledge and price forecasting ability. Most of the investors are used the electricity market historical information for forecasting power generation, consumption, and utility price. Unfortunately, electricity market time-series profile is high volatility and change over time, so the factual data cannot accurately reflect the electricity market states such as power consumption and generation. In the literature, there is no systematic way or suitable models that can fit, analyze, and predict electricity market system states over time. Interestingly, this paper proposes an electricity market state-space model which is obtained by a set of electricity market differential equations. After simplifying of these equations, the continuous-time electricity market state-space model is derived. Using discrete-time step size parameter, the continuous-time system is discretised. Furthermore, the noisy measurements are obtained by a set of smart sensors. Finally, the Kalmna filter based electricity market state forecasting algorithm is developed based on noisy measurements. Simulation results show that the proposed algorithm can properly forecast the electricity market states. Consequently, this kind of model and algorithm can help to develop the electricity market simulator and assist investor to participate/invest electricity market regardless of the world economic downtown.more » « less
-
Electric load forecasting refers to forecasting the electricity demand at aggregated levels. Utilities use the predictions of this technique to keep a balance between electricity generation and consumption at each time and make accurate decision for power system planning, operations, and maintenance, etc. Based on prediction time horizon, electric load forecasting is classified to very short-term, short-term, medium-term, and long-term. In this paper, a multiple output Gaussian processes with multiple kernel learning is proposed to predict short-term electric load forecasting (predicting 24 load values for the next day) based on load, temperature, and dew point values of previous days. Mean absolute percentage error (MAPE) is used as a measure of prediction accuracy. By comparing MAPE values of the proposed method with the persistence method, it can been seen that the proposed method improves the persistence method MAPE up to 4%.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- https://doi.org/10.1145/3394486.3403337
