GA-ANN Short-Term Electricity Load Forecasting

This paper presents a methodology for short-term load forecasting based on genetic algorithm feature selection and artificial neural network modeling. A feed forward artificial neural network is used to model the 24-h ahead load based on past consumption, weather and stock index data. A genetic algorithm is used in order to find the best subset of variables for modeling. Three data sets of different geographical locations, encompassing areas of different dimensions with distinct load profiles are used in order to evaluate the methodology. The developed approach was found to generate models achieving a minimum mean average percentage error under 2 %. The feature selection algorithm was able to significantly reduce the number of used features and increase the accuracy of the models.

Measuring persistence in inflation: evidence for Angola

The purpose of this paper is to examine the degree of persistence in five inflation indicators for Angola, and to identify the implications for decision-making. Understanding inflation persistence in Angola is crucial because the National Bank of Angola is preparing to change its monetary policy focus to a more inflation-targeting regime. Our results suggest that when structural breaks are accounted for, all five inflation indicators are stationary, so that a shock will give temporary effects. Secondly, our findings suggest that persistence is not too high. Moreover, the degree of persistence is similar among the five inflation indicators and throughout the sample period. Finally, our results also show that extracting the most volatile components of the headline inflation indicator does not generate a new inflation indicator that is less volatile and more persistent than the original. These results have important implications for the design, implementation and effectiveness of monetary policy in Angola, especially when following an inflation-targeting regime. First, a not too high degree of persistence means monetary policy aiming for price stability must be implemented with a permanent policy stance. Secondly, a low degree of persistence also means that inflation can be stabilized in a short period of time following a shock. Lastly, the results are also relevant for prediction and modeling purposes.