Electricity is crucial for daily life due to the number of activities that depend on it. To forecast future electric load, which changes over time and depends on various factors, grid operators (GOs) must create forecasting models for various time horizons with a high degree of accuracy because the results have a huge impact on their decision-making regarding, for example, the scheduling of power units to supply user consumption in the short or long term or the installation of new power plants. This has led to the exploration of multiple techniques like statistical models and Artificial Intelligence (AI), with Machine-Learning and Deep-Learning algorithms being the most popular in this latter field. This paper proposes a neural network-based model to forecast short-term load for a Colombian grid operator, considering a seven-day time horizon and using an LSTM recurrent neural network with historical load values from a region in Colombia and calendar features such as holidays and the current month corresponding to the target week. Unlike other LSTM implementations found in the literature, in this work, the LSTM cells read multiple load measurements at once, and the additional information (holidays and current month) is concatenated to the output of the LSTM. The result is used to feed a fully connected neural network to obtain the desired forecast. Due to social problems in the country, the load data presents a strange behavior, which, in principle, affects the prediction capacity of the model. Still, it is eventually able to adjust its forecasts accordingly. The regression metric MAPE measures the model performance, with the best predicted week having an error of 1.65% and the worst week having an error of 26.22%. Additionally, prediction intervals are estimated using bootstrapping.

The success of many projects linked to the management and planning of water resources depends mainly on the quality of the climatic and hydrological data that is provided. Nevertheless, the missing data are frequently found in hydroclimatic variables due to measuring instrument failures, observation recording errors, meteorological extremes, and the challenges associated with accessing measurement areas. Hence, it is necessary to apply an appropriate fill of missing data before any analysis. This paper is intended to present the filling of missing data of monthly rainfall of 45 gauge stations located in southwestern Colombia. The series analyzed covers 34 years of observations between 1983 and 2016, available from the Instituto de Hidrología, Meteorología y Estudios Ambientales (IDEAM). The estimation of missing data was done using Non-linear Principal Component Analysis (NLPCA); a non-linear generalization of the standard Principal Component Analysis Method via an Artificial Neural Networks (ANN) approach. The best result was obtained using a network with a [45-44-45] architecture. The estimated mean squared error in the imputation of missing data was approximately 9.8 mm. month-1, showing that the NLPCA approach constitutes a powerful methodology in the imputation of missing rainfall data. The estimated rainfall dataset helps reduce uncertainty for further studies related to homogeneity analyses, conglomerates, trends, multivariate statistics and meteorological forecasts in regions with information deficits such as southwestern Colombia.

Oceanic-atmospheric phenomena of different time scales concurrently might affect the streamflow in several basins around the world. The Atrato River Basin (ARB) and Patía River Basin (PRB) of the Colombian Pacific region are examples of such basins. Nevertheless, the relations between the streamflows in the ARB and PRB and the oceanic-atmospheric factors have not been examined considering different temporal scales. Hence, this article studies the relations of the climate indices and the variability of the streamflows in the ARB and PRB at interannual and decadal timescales. To this, the streamflow variability modes were obtained from the principal component analysis (PCA); furthermore, their linear dependence with indices of the El Niño/Southern Oscillation (ENSO), precipitation (PRP), the Choco low-level jet (CJ), and other indices were quantified through (a) Pearson and Kendall’s tau correlations, and (b) wavelet transform. The PCA presented a single significant mode for each basin, with an explained variance of around 80%. The correlation analyses between the PC1s of the ARB and PRB, and the climate indices showed significant positive (negative) high correlations with PRP, CJ, and Southern Oscillation Index (SOI) (ENSO indices). The wavelet coherence analysis showed significant coherencies between ENSO and ARB: at interannual (2–7 years) and decadal scale (8–14), preferably with the sea surface temperature (SST) in the east and west Tropical Pacific Ocean (TPO). For PRB with the SST in the central and western regions of the TPO in the interannual (4–8 years) and decadal (8–14 years) scales, the decreases (increases) in streamflow precede the El Niño (La Niña) events. These results indicate multiscale relations between the basins’ streamflow and climate phenomena not documented in previous works, relevant to forecast the extreme flow events in the Colombian Pacific rivers and for planning and implementing strategies for the sustainable use of water resources in the basins studied.

Improving the accuracy of rainfall forecasting is relevant for adequate water resources planning and management. This research project evaluated the performance of the combination of three Artificial Neural Networks (ANN) approaches in the forecasting of the monthly rainfall anomalies for Southwestern Colombia. For this purpose, we applied the Non-linear Principal Component Analysis (NLPCA) approach to get the main modes, a Neural Network Autoregressive Moving Average with eXogenous variables (NNARMAX) as a model, and an Inverse NLPCA approach for reconstructing the monthly rainfall anomalies forecasting in the Andean Region (AR) and the Pacific Region (PR) of Southwestern Colombia, respectively. For the model, we used monthly rainfall lagged values of the eight large-scale climate indices linked to the El Niño Southern Oscillation (ENSO) phenomenon as exogenous variables. They were cross-correlated with the main modes of the rainfall variability of AR and PR obtained using NLPCA. Subsequently, both NNARMAX models were trained from 1983 to 2014 and tested for two years (2015–2016). Finally, the reconstructed outputs from the NNARMAX models were used as inputs for the Inverse NLPCA approach. The performance of the ANN approaches was measured using three different performance metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Pearson’s correlation (r). The results showed suitable forecasting performance for AR and PR, and the combination of these ANN approaches demonstrated the possibility of rainfall forecasting in these sub-regions five months in advance and provided useful information for the decision-makers in Southwestern Colombia.

The Advanced Metering Infrastructure (AMI) data represent a source of information in real time not only about electricity consumption but also as an indicator of other social, demographic, and economic dynamics within a city. This paper presents a Data Analytics/Big Data framework applied to AMI data as a tool to leverage the potential of this data within the applications in a Smart City. The framework includes three fundamental aspects. First, the architectural view places AMI within the Smart Grids Architecture Model-SGAM. Second, the methodological view describes the transformation of raw data into knowledge represented by the DIKW hierarchy and the NIST Big Data interoperability model. Finally, a binding element between the two views is represented by human expertise and skills to obtain a deeper understanding of the results and transform knowledge into wisdom. Our new view faces the challenges arriving in energy markets by adding a binding element that gives support for optimal and efficient decision-making. To show how our framework works, we developed a case study. The case implements each component of the framework for a load forecasting application in a Colombian Retail Electricity Provider (REP). The MAPE for some of the REP’s markets was less than $5\%$. In addition, the case shows the effect of the binding element as it raises new development alternatives and becomes a feedback mechanism for more assertive decision making.