A multilayer perceptron neural network approach for optimizing solar irradiance forecasting in Central Africa with meteorological insights.

Promoting renewable energy sources, particularly in the solar industry, has the potential to address the energy shortfall in Central Africa. Nevertheless, a difficulty occurs due to the erratic characteristics of solar irradiance data, which is influenced by climatic fluctuations and challenging to regulate. The current investigation focuses on predicting solar irradiance on an inclined surface, taking into consideration the impact of climatic variables such as temperature, wind speed, humidity, and air pressure. The used methodology for this objective is Artificial Neural Network (ANN), and the inquiry is carried out in the metropolitan region of Douala. The data collection device used in this research is the meteorological station located at the IUT of Douala. This station was built as a component of the Douala sustainable city effort, in partnership with the CUD and the IRD. Data was collected at 30-min intervals for a duration of around 2 years, namely from January 17, 2019, to October 30, 2020. The aforementioned data has been saved in a database that underwent pre-processing in Excel and later employed MATLAB for the creation of the artificial neural network model. 80% of the available data was utilized for training the network, 15% was allotted for validation, and the remaining 5% was used for testing. Different combinations of input data were evaluated to ascertain their individual degrees of accuracy. The logistic Sigmoid function, with 50 hidden layer neurons, yielded a correlation coefficient of 98.883% between the observed and estimated sun irradiation. This function is suggested for evaluating the intensities of solar radiation at the place being researched and at other sites that have similar climatic conditions.

Unravelling the dynamics of human development and economic growth on crude oil production based on ARDL and NARDL models.

This paper estimates and establishes the causality between the Human Development Index (HDI), Gross Domestic Product (GDP), inflation and CO2 emissions on crude oil production (COP) in Cameroon from 1977 to 2019. To do so, the Augmented Dicky-Fuller and Zivot-Andrews stationarity tests, ARDL and NARDL modelling, as well as Toda-Yamamoto causality test are performed. Unlike previous studies on COP, this study incorporates the asymmetric impact (NARDL). The results indicate that CO2 emissions and GDP have a negative impact on COP in the long-run, while HDI and inflation have a positive impact in the short-run. GDP and HDI have a non-linear impact in the short run, while in the long-run inflation and CO2 emissions have a non-linear impact on COP. From these results, it is interesting to note that, in order to allow future generations to benefit from the oil windfall. The diversification of the Cameroonian economy, the control of inflation and the use of less polluting crude oil extraction technologies must be imperative.•A step-by-step procedure of the ARDL, NARDL and causality test is provided.•The multiplier effects of GDP, HDI, inflation and CO2 emissions on COP are simulated.•The impact of GDP and HDI on COP is non-linear.

Methodology for examining the relationship between oil rent and crude oil production: Evidence from Cameroon.

The relationship between oil rent and crude oil production remains unexplored in Cameroon. This study therefore aims to apply the Autoregressive Distributed Lag (ARDL) estimation technique and the Granger causality test using the Toda-Yamamoto procedure to capture the symmetric impact and causality links between oil rent and crude oil production in Cameroon. The study covers the period from 1977 to 2019, and includes crude oil prices, human development index (HDI) and corruption as other variables. The study indicates that there is a significant negative linear impact of crude oil production on oil rent and a bidirectional causality between oil rent and crude oil production. Finally, the price of crude oil, HDI and corruption are found to pass through production to influence oil rent. The results of this study will guide policy makers in managing and sustaining oil revenues for growth and prosperity.•The paper examines the linear impact of crude oil production on oil rent and the causal links between crude oil production and oil rent by incorporating crude oil prices, HDI and corruption.•Bidirectional causality between oil rent and crude oil production.•Convergence of crude oil price, HDI and corruption to crude oil production to influence oil rent.

Forecasting methodology with structural auto-adaptive intelligent grey models.

Accurate mid- and long-term petroleum products (PP) consumption forecasting is vital for strategic reserve management and energy planning. In order to address the issue of energy forecasting, a novel structural auto-adaptive intelligent grey model (SAIGM) is developed in this paper. To start with, a novel time response function for predictions that corrects the main weaknesses of the traditional grey model is established. Then, the optimal parameter values are calculated using SAIGM to increase adaptability and flexibility to deal with a variety of forecasting dilemmas. The viability and performance of SAIGM are examined with both ideal and real-world data. The former is constructed from algebraic series while the latter is made up Cameroon's PP consumption data. With its ingrained structural flexibility, SAIGM yields forecasts with RMSE of 3.10 and 1.54% MAPE. The proposed model performs better than competing intelligent grey systems that have been developed to date and is thus a valid forecasting tool that can be used to track the growth of Cameroon's PP demand.•The ability of SAIGM enhances the forecasting power of intelligent grey models to fully extracting the laws of a system, no matter the data specifications.•SAIGM is extended to include quasi-exponential series by addressing structural flexibility and parametrization concerns.•Input attributes determination and data preprocessing are not required for the proposed model.

Forecasting CO2 emissions from road fuel combustion using grey prediction models: A novel approach.

This paper proposes an optimized wavelet transform Hausdorff multivariate grey model (OWTHGM(1,N)) that addresses some of the weaknesses of the conventional GM(1,N) model such as inaccurate prediction and poor stability. Three improvements have been made: First, all inputs are filtered using a wavelet transform; second, a new time response function is established using the Hausdorff derivative; and finally, the use of Rao's algorithm to optimise the model's parameters as well as the ξ-order accumulated value of the observation data described by the Hausdorff derivative. In order to demonstrate the effectiveness of OWTHGM(1,N), it is applied to predict CO2 emissions from road fuel combustion. The new model scores 1.27% MAPE and 79.983 RMSE, and is therefore more accurate than competing models. OWTHGM(1,N) could therefore serve a reliable forecasting tool and used to monitor the evolution of CO2 emissions in Cameroon. The forecast results also serve as a sound foundation for the formulation of energy consumption strategies and environmental policies. • Modification, extension and optimization of grey multivariate model is done. • The model is very generic can be applied to a wide variety of energy sectors. • OWTHGM(1,N) is a valid forecasting tool that can be used to track CO2 emissions.

A novel prediction approach using wavelet transform and grey multivariate convolution model.

It is crucial to develop highly accurate forecasting techniques for electricity consumption in order to monitor and anticipate its evolution. In this work, a novel version of the discrete grey multivariate convolution model (ODGMC(1,N)) is proposed. A linear corrective term is included in the conventional GMC(1,N) structure, parameter estimation is carried out in a manner consistent with the modelling process, and an iterative technique is used to get the cumulated forecasting function of ODGMC(1,N). As a result, the forecasting capacity of ODGMC(1,N) is more reliable and its stability is enhanced. For validation purposes, ODGM(1,N) is applied to forecast Cameroon's annual electricity demand. The results show that the novel model scores 1.74% MAPE and 132.16 RMSE and is more precise than competing models.•ODGMC(1,N) corrects the linear impact of t on the forecasting performance.•Wavelet transform is used to remove irrelevant information from input data.•The proposed model can be used to track annual electricity demand.

Analysis of household LPG demand elasticity in Cameroon and policy implications.

Liquefied petroleum gas (LPG) is rapidly becoming a key part of Cameroon's energy mix, with enormous future potential. However, there are still many uncertainties about the extent of its potential market, which has so far often led to supply shortages. These shortages therefore constitute a major obstacle to the objective of promoting LPG as the main fuel in Cameroonian households. Accordingly, the short and long-run elasticities of LPG consumption in Cameroon are investigated in this work. This work uses annual time series data from 1994 to 2017. A basic model and four alternative specifications are used. Mid-run price and income elasticities of LPG consumption are found to be between -0.330 and -0.401, and, 0.159 and 0.569, respectively. Of all the five models, the error correction model is the most robust and the elasticities estimates reveal that price, income and urbanization are important determinants of LPG consumption in Cameroon. These results are consistent with those given by the other models, and in line with previous research on developing countries whose economic and demographic situation is similar to that of Cameroon. These results have serious implications on demand side management and calls for policy makers to promote widespread use of LPG especially in the savannah zone in order to reduce deforestation and overdependence on biomass.

A technique for improving petroleum products forecasts using grey convolution models and genetic algorithms.

Forecasting energy consumption is a major concern for policymakers, oil industry companies, and many other associated businesses. Though there exist many forecasting tool, selecting the most appropriate one is critical. GM(1,1) has proven to be one of the most successful forecasting tool. GM(1,1) does not require any specific information and can be adapted to predict energy consumption using a minimum of four observations. Unfortunately, GM(1,1) on its own will generate too large forecast errors because it performs well only when data follow an exponential trend and should be implemented in a political-socio-economic free environment. To reduce these short-comings, this paper proposes a new GM(1,n) convolution model optimized by genetic algorithms integrating a sequential selection mechanism and arc consistency, abbreviated Sequential-GMC(1,n)-GA. The new model, like some recent hybrid versions, is robust and reliable, with MAPE of 1.44%, and RMSE of 0.833.•Modification, extension and optimization of grey multivariate model is done.•The model is very generic can be applied to a wide variety of energy sectors.•The new hybrid model is a valid forecasting tool that can be used to track the growth of households' energy demand.

Forecasting petroleum products consumption in Cameroon's household sector using a sequential GMC(1,n) model optimized by genetic algorithms.

Forecasting energy consumption is a major concern for policymakers, oil industry companies, and many other associated businesses. Though there exist many forecasting methodologies, selecting the most appropriate one is critical. GM(1,1) has proven to be one of the most successful forecasting tool. GM(1,1) does not require any specific information and can be adapted to predict energy consumption using a minimum of four observations. Unfortunately, GM(1,1) on its own will generate too large forecast errors because it performs well only when data follow an exponential trend and should be implemented in a political-socio-economic free environment. To reduce these errors, this study proposes a new GM(1,n) convolution model optimized by genetic algorithms integrating a sequential selection mechanism and arc consistency, abbreviated Sequential-GMC(1,n)-GA. Practically, the proposed approach, on one hand, highlights the forecast for petroleum products consumption in Cameroon's household sector. On the other hand, it estimates the amount of CO2 that would be reduced if petroleum products in this sector were switched to clean energy. The new model, like some recent hybrid versions, is robust and reliable, according to the results. Households petroleum products needs by 2025 are estimated to be 150,318 kilo tons of oil equivalent with MAPE of 1.44%, and RMSE of 0.833. Therefore, households GHG emissions would be reduced by 733.85 kilo tons of CO2 equivalent if clean energy was used instead of petroleum products. As a result, the new hybrid model is a valid forecasting tool that can be used to track the growth of Cameroon's household energy demand.

Analysis and improvement of the efficiency of NH3-NaSCN single effect absorption cooling system.

This work aims at reinforcing simultaneously the coefficient of performance (COP) and the exergetic coefficient of performance (ECOP), in order to improve the operation of an absorption chiller to be used in tropical areas. It uses a new method based on the determination of variable one-line matrix that allows to find the NH3 mass fraction of NH3-NaSCN solution on each branch of the system. This matrix is obtained by substitution between the empirical formulae of NH3 and NH3-NaSCN from two different approaches, with the aim of making the current model more simple and less complex than those commonly used by other researchers. The approach developed is a direct digital method, easy to implement and allowing to find and understand some hidden functions of the black boxes of several energy simulation softwares, such as the Engineering Solver Equation (EES). The modeling of the system is carried out in Matlab to predict the temperatures and mass flows that can upgrade the system. The purpose is to contribute to the improvement and commissioning of an absorption chiller operating at thermal comfort temperatures in two cities in Cameroon: Douala and Yaoundé. The results show that the temperatures in the generator, condenser and absorber for which the COP and ECOP are maximum are respectively [92 °C; 100 °C]; 35 °C, and [35 °C; 40.8 °C], and those of the mass flow rates of the refrigerant leaving the generator and condenser are respectively [0.44 kg/s; 0.86 kg/s] and 0.98 kg/s. The evaporator does not show these remarks. The simulation results can be used for thermodynamic optimisation of the cooling capacity (CC) and reduction of electrical energy consumption of the current system.

Experimental data showing the thermal behaviour of a residential building in a hot and humid climate on three scenarios: An empty room with a closed door, an empty room with an open door, and a normal inhabited room.

Data presented on this paper are from the collection on the experimental site during a 12 months period, corresponding to the two seasons of the year. The site is located in the city of Douala in Cameroon, in a hot and humid zone. The experimental premises are located above the ground floor of a storey-building. They are built of 20 cm thick hollow breezeblocks with interior and exterior cement plastering, and they consist of the following: an open uninhabited room; a closed uninhabited room; and an inhabited room. The data acquisition system was achieved by the thermo-hygrometers and the anemometer placed in the rooms in accordance with the ASHRAE 55 standard [1], on instruments for measuring thermal comfort parameters in buildings. Collected data consists of the following: temperature, relative humidity and air velocity outside the site; the temperature and relative humidity inside the different rooms. These parameters are collected with a one-hour time step. The matlab software is used to calculate the maximum, minimum, average and standard deviation for each measured parameter. several areas are used for data processing: the search for causal links between the climatic parameters of the site, and those of the indoor environments of the buildings; data prediction on a one year's history basis; the impact of each experimental scenario on the thermal behaviour of the room; the assessment of the heat transfer in the room; the evaluation of the potential for energy savings in the room.

Methodology for forecasting electricity consumption by Grey and Vector autoregressive models.

Forecasting energy demand in general, and electricity demand in particular, requires the developing reliable forecasting tools that can be used to monitor the evolution of consumers' energy needs more accurately. The proposed new hybrid GM(1,1)-VAR(1) model is meant for that purpose. The latter is based on the Grey and Vector autoregressive approaches, and makes it possible to predict future demand, by taking into account economic and demographic determinants with an exponential growth trend. With an associated APE of 1.5, a MAPE of 1.628%, and an RMSE of 15.42, this new model thus presents better accuracy indicators than hybrid models of the same nature. Also, it proves to be as accurate as some recent hybrid artificial intelligence models. The model is thus a reliable forecasting tool that can be used to monitor the evolution of energy demand.•The Grey and Vector autoregressive models are coupled to improve their accuracy.•Five economic and demographic parameters are included in the new hybrid model.•This new model is a reliable forecasting tool for assessing energy demand.