Reservoir Inflow Prediction using Multi-model Ensemble System

Kishore, S.; Swaroop, Ganesh; Prasad, B S

doi:10.1109/c2i451079.2020.9368942

Cited by 3 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LMST network is chosen in this research because it allows solving analytical problems [11], as is the case of the flow where there will be noise, in which it will be impossible to include all the variables that affect the model, but it will be possible to obtain better predictions in temporal dependency problems larger than recursive networks [12]. The calculation process of the cellular unit of the LSTM neural network is as follows:…”

Section: Methodsmentioning

confidence: 99%

“…In the research [11], presents the methodology of implementing machine learning algorithms for the accurate prediction of future probabilities based on previous flow data using statistical methods as a basis, these techniques can be applied to train the machine model in meteorological reports and capacity data for energy production of reservoirs built along rivers. Figure 2.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Subsequently, the model of the artificial neural network is selected, for which LSTM was chosen, which is of great short-term memory. The LSTM (see figure 3), introduces the "forget gate", "input gate" and "output gate" mechanism to choose between "remembering" or "forgetting" the state information at a given time state information at a given time [11].…”

Section: Literature Reviewmentioning

confidence: 99%

See 2 more Smart Citations

Flow Prediction for Hydropower Generation using LMST Neural Networks

Achig,

Gonzales,

Hidalgo

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The objective of this investigation is to predict the necessary flow to satisfy the demand in order to guarantee the generation of energy in a hydropower, for which the artificial neural network LMST (Long Short-Term Memory) was used. In this context, in this article, historical data from the years 2010 to 2019 of flow and power of the plant was used, which were provided by it, in the first instance the data was purified to group them and graph the heat diagram with which the variables of interest were determined, then the training was carried out with which the network was structured with 10 neurons, 2 hidden layers, 2 freezing layers and 1 output layer. In addition, the RMSprop optimizer was selected with 10 numbers of delays with which an absolute error of 5.12% was obtained, finally tests were made comparing the results obtained in the training with data from one day after those that were used in the training and testing database. It is worth mentioning that by predicting the flow for the production of electrical energy, it contributes to the National Development Plan “Toda una Vida” of Ecuador, which is why it focuses on optimizing the use of water resources for required production levels.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation