<p> The Volta River Authority (VRA) is responsible for the generation and transmission of power in Ghana. For this purpose, VRA owns and operates two hydroelectric generating stations (at Akosombo and Kpong) with a combined installed capacity of 1060 Kw. The Akosombo plant is served by the Lake Volta Reservoir. Prediction of inflows into the Volta Lake is one of the important functions of the reservoir management group.</p> <p>For this project, some of the more recent methods of mathematical modelling are investigated with a view to building a simple stochastic model which adequately represents and forecasts the Volta river average monthly flow. The Box-Jenkins family of models are employed in this exercise. A parsimonious model in the form of a seasonal autoregressive integrated moving average (SARIMA) model is arrived at which adequately models and forecasts the available data.</p> <p>The selected model is reasonably easy to set up, has few parameters to estimate and therefore making the updating of these parameters a relatively simple task.</p> / Thesis / Master of Engineering (MEngr)

Thesis (Ph.D. (African Languages)) -- University of Limpopo, 2019 / Muhumbulo muhulwane wa ngudo, wo vha wa u sedzulusa na u sengulusa mbonalo ya mushumo wa vhutunguli nga ṅanga dza sialala ḽa mvelele ya Tshivenḓa. Ṱhoḓisiso yo vha yo sedzesaho kha tshenzhemo na vhupfiwa ha ṅanga dza sialala nga ha kuvhonele kwavho kwa mushumo wa vhutunguli kha mushumo wavho wa ḓuvha ḽiṅwe na ḽiṅwe. Tsenguluso yo vha ya u fhaṱusa lushaka nga ha ndeme ya vhutunguli kha vhutshilo ha ḓuvha ḽiṅwe na ḽiṅwe na u khakhulula kuhumbulele kwo shandeaho nga ha vhutunguli ha sialala ḽa Vhavenḓa sa vhu no fhura vhathu tshelede ngeno mishumo yaho i sa tendisei. Ngudo yo sumbedza vhuvha ha mushumo wa vhutunguli ha sialala u bva tsikoni u swika ṋamusi na thuso ine ya vhu ṋetshedza miṱani na kha shango, u tsivhudza lushaka nga u vhamba maano a u vhulunga nḓivho na uri i nga pfukiselwa hani kha vhaswa. Ho shumiswa madzhenele a khwalithethivi kha u kuvhanganya mafhungo. Mafhungo o kuvhanganywa nga nḓila ya inthaviyu vhathu vho livhana zwifhaṱuwo na nga luṱingo khathihi na u ṱalela nyito. Mafhungo o kuvhanganyiwaho o khoudiwa nga maitele a hone, ha bveledzwa thero. Thero dzo tumbulwaho dzo kona u livha kha mawanwa na themendelo. Tsedzuluso yo vhonala yo vula lushaka maṱo kha u dzhiela vhutunguli ha sialala nṱha.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

The purpose of this research is to provide an extensive evaluation of neural network models for the prediction and the simulation of some key air pollutants in Hamilton, Ontario, Canada. Hamilton experiences one of Canada's highest air pollution exposures because of the dual problem associated with continuing industrial emission and gradual increase of traffic related emissions along with the transboundary air pollutions from heavily industrialized neighboring north-eastern and mid-western US cities. These factors combined with meteorology, cause large degradation of Hamilton's air quality. Hence an appropriate and robust method is of most importance in order to get an early notification of the future air quality situation. Data driven methods such as neural networks (NNs) are becoming very popular due to their inherent capability to capture the complex non-linear relationships between pollutants, climatic and other non-climatic variables such as traffic variables, emission factors, etc. This study investigates dynamic neural networks, namely time lagged feed-forward neural network (TLFN), Bayesian neural network (BNN) and recurrent neural network (RNN) for short term forecasting. The results are being compared with the benchmark static multilayer perceptron (MLP) models. The analysis shows that TLFN model with its time delay memory and RNN with its adaptive memory has outperformed the static MLP models in ground level ozone (O_3) forecasting for up to 12 hours ahead. Furthermore the model developed using the annual database is able to map the variations in the seasonal concentrations. On the other hand, MLP model was quite competitive for nitrogen dioxide (NO_2) prediction when compared to the dynamic NN based models. The study further assesses the ability of the neural network models to generate pollutant concentrations at sites where sampling has not been done. Using these neural network models, data values were generated for total suspended particulate (TSP) and inhalable particulates (PM_10) concentrations. The obtained results show promising potential. Although there were under-predictions and over-predictions on some occasions, the neural network models, in general were able to generate the missing information and to obtain air quality situation in the study area. / Thesis / Master of Applied Science (MASc)