- Show all
- Asset Management
- Buoy
- Canal
- Climate Change
- Controls
- Dam Safety
- Environmental Impact
- Fish and Aquatic Resources
- Future Grid
- Generator
- Governor
- Hydraulic Forecasting
- Hydraulic Optimization
- Hydrokinetic
- Intake Gates
- Markets
- Penstock
- Regulatory Process
- Renewable Integration
- Sediment Transport
- Shoreline and Riparian Resources
- Spillgates
- Tidal
- Transmission Services
- Turbine
- Water Management
- Water Resources
- Water Systems
- Wave
- Conventional Hydro
TIP 417: CEATI – Hydropower Operations and Planning Technical Program Services
Lead Companies
CEATI
Lead Researcher (s)
- Erik Pytlak, BPA
The long term strategic direction of this group will be to develop new and innovative technological approaches and options to support the role of the water manager in managing and enhancing the underlying fundamental value of the industry, and to provide a knowledge-based leading edge technological resource to assist the hydropower industry in meeting its many new challenges.
Technology Application
Conventional Hydro
Research Category
Interconnect Integration and Markets
Research Sub-Category
Hydraulic Forecasting
Status
ongoing
Completion Date
2020
- Conventional Hydro
Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning
Lead Companies
Upstream Tech
Lead Researcher (s)
- Frederik Kratzert
- Daniel Klotz
- Mathew Herrnegger
Long short‐term memory (LSTM) networks offer unprecedented accuracy for prediction in ungauged basins. We trained and tested several LSTMs on 531 basins from the CAMELS data set using k‐fold validation, so that predictions were made in basins that supplied no training data. The training and test data set included ∼30 years of daily rainfall‐runoff data from catchments in the United States ranging in size from 4 to 2,000 km2 with aridity index from 0.22 to 5.20, and including 12 of the 13 IGPB vegetated land cover classifications. This effectively “ungauged” model was benchmarked over a 15‐year validation period against the Sacramento Soil Moisture Accounting (SAC‐SMA) model and also against the NOAA National Water Model reanalysis. SAC‐SMA was calibrated separately for each basin using 15 years of daily data. The out‐of‐sample LSTM had higher median Nash‐Sutcliffe Efficiencies across the 531 basins (0.69) than either the calibrated SAC‐SMA (0.64) or the National Water Model (0.58). This indicates that there is (typically) sufficient information in available catchment attributes data about similarities and differences between catchment‐level rainfall‐runoff behaviors to provide out‐of‐sample simulations that are generally more accurate than current models under ideal (i.e., calibrated) conditions. We found evidence that adding physical constraints to the LSTM models might improve simulations, which we suggest motivates future research related to physics‐guided machine learning.
Technology Application
Conventional Hydro
Research Category
Interconnect Integration and Markets
Research Sub-Category
Hydraulic Forecasting
Status
complete
Completion Date
2019
- Conventional Hydro
Using Remote Sensing and Ground Measurements to Improve Evaporation Estimation and Reservoir Management
Lead Companies
Bureau of Reclamation
Lead Researcher (s)
- Dagmar Llewellyn
Evaporative losses from reservoirs are not well understood due to climatic conditions, size and shape of the reservoir, and reservoir operations. However, these losses have the potential to be managed through science based decision making tools. The current method(s) used to estimate and account for evaporative losses rely upon technology from a century ago (i.e. Class A Evaporation Pan) and area-capacity tables for individual reservoirs. Technological advances using remote sensing (e.g. LandSat-8) and highly sensitive instrumentation (i.e. 3-D Sonic Anemometer with hygrometer, infrared sensor, etc.) have shown the potential to be used in estimating evaporation losses on spatial and temporal scale with more accuracy. Preliminary studies (BoR Technical Report RO5AC40438 2013) have been conducted at Elephant Butte and Caballo reservoirs by US Bureau of Reclamation and New Mexico State University.
Technology Application
Conventional Hydro
Research Category
Interconnect Integration and Markets
Research Sub-Category
Hydraulic Forecasting
Status
ongoing
Completion Date
2021
- Conventional Hydro
Value of flow forecasts to power system analytics [HydroWIRES]
Lead Companies
PNNL, INL
Lead Researcher (s)
- Nathalie Voisin, Nathalie.voisin@pnnl.gov
Hydropower operators use weekly water inflow forecasts to optimize reservoir releases and unit commitment and to meet power grid needs. The accuracy of inflow forecasts, combined with related scheduling adjustments, contracts, and market opportunities, are reflected in a utilities’ revenue. One of the goals of the HydroWIRES Initiative is to quantify the flexibility of hydropower operations and understand its adaptability to changes in water supply, regulation, markets, and power grid needs. In partnership with North Carolina State University and the National Corporation of Atmospheric Research, researchers from PNNL and INL will use inflow forecasts, reservoir and power system models, and case studies to demonstrate the contribution of flow forecast to provide hydropower services to the grid. Flow forecast accuracy metrics, combined with regional power system analytics (including regional economics and generation portfolios), will help detangle the value of incremental improvement in flow forecasts. This research supports DOE in developing strategic partnerships with other institutions to invest in information products and decision-support practices for meeting power grid needs. Technology Application
Conventional Hydro
Research Category
Interconnect Integration and Markets
Research Sub-Category
Hydraulic Forecasting
Status
ongoing
Completion Date
TBD
- Conventional Hydro
Web-Based Decision Support System for the Upper Colorado River Basins
Lead Companies
Bureau of Reclamation
Lead Researcher (s)
- Claudia Leon Salazar
In an effort to improve the coordination and transparency of water management operations within the Upper Colorado River basin, Eastern Colorado Area Office (ECAO) is proposing to develop a Web-Based Decision Support System (DSS). The DSS would enable real-time sharing of a visual representation of the Upper Colorado River as it responds to actual and anticipated reservoir releases, diversions and return flows. The proposed DSS would provide a tool for immediately assessing and visually displaying the aggregate effects of operational changes at key locations within the basin.
Technology Application
Conventional Hydro
Research Category
Interconnect Integration and Markets
Research Sub-Category
Hydraulic Forecasting
Status
ongoing
Completion Date
2021
Don’t see your waterpower research?
Have questions about WaRP?
Contact Marla Barnes at: marla@hydro.org