Statistics Project Topics

Time-Series Forecast of Nigeria’s Electricity Statistics Using Auto-Regressive Integrated Moving Average (ARIMA) Model

Time-Series Forecast of Nigeria's Electricity Statistics Using Auto-Regressive Integrated Moving Average (ARIMA) Model

Time-Series Forecast of Nigeria’s Electricity Statistics Using Auto-Regressive Integrated Moving Average (ARIMA) Model

Chapter One

Aim and Objectives

The study aims to investigate Time-Series Forecast Of Nigeria’s Electricity Statistics  Using Auto-Regressive Integrated Moving Average (ARIMA) MODEL. The specific objectives are;

  1. To carry out a statistical forecast of the energy data of Nigeria between the year 2012 and 2022 (20 years) using an efficient model.
  2. Predict based on the forecast obtained, the projected electricity production, consumption and transmission losses and demand estimate of the nation in the short-term future.



 Conceptual Review

 Electricity in Nigeria

According to the Nigerian Bureau of Statistics 2013 estimate, the country’s teeming population of about 200 million does not have enough electricity to meet its needs. Nigeria has one of the world’s lowest net power production per capita rates, according to the U.S. Energy Information Administration (E.I.A.). Load shedding, blackouts, and dependence on private generators are all consequences of inadequate electricity generation. As a result of recent privatisation, the nation’s eleven recognised power-producing businesses have been unable to keep up with demand.

Electricity is a prerequisite for both social progress and economic expansion. The primary goal of the electricity industry is to provide energy. Sustainable development and poverty alleviation activities rely heavily on the availability of energy (Sambo, 2005). Everything from access to water to agricultural production to health to population size to education to gender-related concerns is affected by climate change. The degree of productivity in industry, commerce, agriculture, and even the workplace is directly linked to the energy used. As a measure of a people’s or nation’s level of life, energy consumption per capita is one of the indicators or benchmarks (Sambo, 2005). As a result, there is little possibility of reaching enviable national development or even raising the level of life of the Nigerian people if the country’s energy supply cannot keep up with demand. The National Electricity Regulation Commission’s (NERC) administration must gather information indicating the population’s energy consumption and compile this data so policymakers, generating firms, and other key stakeholders can readily comprehend it. Such information should be collected and analysed by the Nigerian government’s energy regulatory agency to identify and highlight trends in the country’s energy output and consumption. Use of up-to-date statistics and forecasting tools and software may be used to make a projection of the predicted use pattern for electrical energy over a specific time in the short or long term. Additionally, with this new knowledge, the nation’s power industry can give a solution to and ensure that the country intends to fulfil its energy needs at any moment in the future, as portrayed by the forecast.

The Demand For Electricity in Nigeria

The amount of a product or service that a customer is willing and able to pay a certain price for at a specific moment is referred to as “demand” in the economics world. Time and pricing may affect demand. The globe is facing a constant rise in demand for alternative energy sources, such as electricity, as a replacement for fossil fuels, due to population growth, growing industrialisation, and governments’ attempts to minimise the burning of fossil fuels (Madueme, 1979).

Everything that happens in the manufacturing process—from concept to finished product—requires electricity in some form or another. Every nation’s socioeconomic and technical development depends heavily on it (Adebanjo, 2012). According to revelations by Nigeria’s Minister of Power, Prof Chinedu Nebo, it appears that the country is still a long way from becoming self-sufficient in electricity, as the country has shifted its target date for generating 10,000 megawatts from December 2013 to the first quarter of 2014, requiring about 200,000MW to meet current energy demands.

A lack of industrialisation means that Nigerians’ primary source of electrical energy is their own homes, which are the country’s only true end users. A large portion of the power produced goes to the manufacturing industry, as well as to educational institutions, health care parastatals, and private and public sector businesses (Abatan, 1979).

Electric arc furnace systems are increasingly being used by the steel and metallurgical industries in place of the conventional blast furnace system, which primarily utilises carbon-based fuels and coking materials to reduce reliance on fossil fuels. The Lord Mayor of the City of London, Roger, and a delegation of British businesses were informed by Nebo that the objective represents a major investment potential for local and international companies. According to him, investment in Nigeria’s power production sector is dominated by corporations from Asia and the United States of America. Nigeria now produces roughly 4,500mw of energy.

According to him, the Nigerian government is committed to reducing the country’s reliance on gas and hydroelectric facilities by boosting electricity provided by wind, solar, and other biomass. It is not practical for the country to rely on just one or two energy sources; instead, we need a diverse portfolio. While wind turbines and solar panels are operational, Nigeria is still far from realising its full potential. The agreement to provide us with 1,000 solar panels annually for the next decade was only just reached with a South Korean business. Our off-grid rural citizens would benefit from a potent power mix of wind and solar energy, according to Ibidapo-Obe and Ajibola (2011), who claim that some rural regions of Nigeria are known to be windy.

Electricity Investment In Nigeria

One of Africa’s major economies, Nigeria has a significant amount of installed generating capacity of around 13.5 gigawatts (GW). Energy production should meet the country’s peak demand of 8.25 gigawatts (GW). There was just 3.7 GW of available power in 2019. Sixty percent of the population has access to electricity, but 16 million homes are still without it. Nearly 60% of the power produced is used by the home sector, with the remaining 25% going to business and public sector customers and users. Tariffs range from €c4.5/kWh to €c6/kWh, which is lower than many other nations in the area. The COVID-19 epidemic caused a delay in a tariff increase expected for the second quarter of 2020. Increasing people and a booming economy are predicted to increase peak power consumption to 15 GW by 2025. With a 90 percent electrification rate in mind by 2030, the government has set an ambitious goal of 45 GW of installed capacity.

Sub-Saharan Africa’s greatest economy is being held back by a lack of electricity. Put it another way: Nigeria has a lot of natural resource potential; it can create 12,522 megawatts from its current facilities. A nation of more over 195 million people can only generate roughly 4,000 MW on most days, which is not enough. With the aid of Power Africa, distribution businesses in Nigeria have increased income by over $250 million – money that can be put into the network, improving service and extending access.




This chapter reveals the research design, source of data, data analysis, measurement of variables and method of data analysis.

Research Design

As a result, Nigeria’s energy industry has been unable to meet the country’s need for electricity. In reality, there is a lack of coordination in data collecting that prevents the country’s true energy figures from being forecasted. Through the use of statistical forecasting, this study hopes to identify a long-term trend in Nigeria’s energy demand so that it may develop an energy demand time series prediction for later years. This paper’s statistical data aims to depict Nigeria’s energy demand in great detail. There would be little chance for Nigerians’ living standards to improve or even be envied if the country’s energy supply cannot keep up with the country’s energy demand. It is the responsibility of the NERC management team to collect detailed information about people’s energy demands and make that data available to policymakers, power producing firms, and other relevant stakeholders for the purpose of energy demand planning. The time series design was adopted in the study.

Source of Data

For the projection, the study utilised time series data for Nigeria from 2010-2022 on electricity production, consumption, and access to electricity. The Central Bank of Nigeria (CBN) Statistical Bulletins for 2001 and 2022 and the World Bank Bulletin for 2012 were used to compile this information.

Model Estimation

ARIMA (Box and Jenkins, 1978) is the name given to the forecasting technique supplied by them. Time series data may be examined for their stochastic or probabilistic properties without developing a single equation model or many equation models. Each variable’s lagged values and resulting stochastic error term are explained using the ARIMA model. Autoregressive moving average (ARMA) is an improvement on the autoregressive moving average model. You may use this formula to calculate the ARIMA (p, q). The ARMA (p, q) model uses time series data that have been different d times to render them stable.

The resulting data are then referred to as ARIMA series (p, d, q). ARIMA models need time series to be stationary or stationary at one or more difference points in order to work. Identification, estimate, diagnostic checking, and forecasting are all part of the ARIMA model procedure. The model specification parameters p, d, and q must be determined in order to perform identification. ACF and PACF are the primary tools for determining the identity of a given object or phenomenon. For identification, the ACF and PACF findings are shown on a correlogram versus the lag duration. Correlograms and formal unit root tests can be used to determine if the data are stationary or not. If they are non-stationary, the data remain different until they become stationary again. After determining the amount of differences needed to establish stationarity, the ARIMA model estimate values are calculated. A diagnostic check is performed on the estimated value. The data fitness is obtained by collecting the residual of the estimator and determining whether the AC or PAC of residuals is statistically significant. ‘ If the residuals aren’t statistically significant, the model’s ARIMA estimate is a good match for the data; if it is, it means the model’s residuals are completely random. As a result, a more suitable ARIMA standard is required instead. The forecast is then made using the model that has been fitted.



This chapter broadly divided into two viz., descriptive analysis where graphs, measures of central tendency and measures of dispersion were used and empirical analysis such as unit root or stationarity test and ARIMA.




With the help of the ARIMA, The studywas able to create a statistical Time-series forecast of Nigeria’s electricity production, consumption, demand estimate and transmission and distribution losses between 2001 and 2022 by using the absolute figures of these parameters obtained from the relevant agencies in and outside of Nigeria. Accuracy tests such as the MAPE, RMSE, and others have been applied to the predictions. If the MAPE number is less than 10, the prediction is regarded as accurate and reliable, while a forecast with a MAPE value of 1 to 5 is also considered reliable. Forecasts below the 10th percentile had a MAPE of 1.207, while those between the 10th and 25th percentiles had a MAPE of 1.714, corresponding to the period between 2012 and 2017. As the model provided additional projections, this number grew to 25.037.

Consequently, the estimates from 2012 to 2017 are quite accurate and authoritative. MAPE (Mean Absolute Prediction Error) grows as the number of predictions is created and the distance between the forecasts and observations increases. The MAPE is 8.750 on average over the whole prediction. For projections below the 10% percentile, the RMSE value is 1.043, and for values at the 25% and 50% percentiles, the RMSE values are 1.192 and 2.026, respectively. As the model produced additional projections, this value rose to 12.405 and the mean RMSE was 4.221. These error estimates allow us to conclude that our electricity regulatory commission and other relevant statistical agencies’ forecasts were reasonably accurate, and the model we used has proven to be particularly capable of making these forecasts in order to help them figure out how to manage data that gives a good picture of electricity demand, production, and consumption patterns to help them figure out


The National Integrated Power Project’s (NIPP) significant investment in electrical infrastructure development is unmatched and provides a solid platform for increased energy output. However, the foreseen difficulty is the policy implementation failure and political transitional breach, which will result in the policy’s abandonment. The current power sector reform in Nigeria is at risk of being abandoned if the next federal election results in a change of administration at the federal level. This is one of the most serious obstacles to the forecast’s success. Another risk is that politicians’ and policymakers’ lack of financial restraint might shorten the useful life of infrastructure projects and encourage the use of subpar equipment. Allocating funds to a project is one step; putting those funds to use for the project’s intended purpose is another. Corruption and financial irresponsibility are widespread among government officials and institutions in Nigeria. These factors, together with others, are likely to prevent a growth in power consumption of 10%, 20%, or even more throughout the projection period.

However, achieving an energy usage of 5000kW per capita does not ensure a top-20 ranking for Nigeria. The reasons for this are not implausible; electricity is just a required but not sufficient requirement for a nation to achieve top economic rankings. Because of this, the world’s top economies will continue to take use of the available resources to boost their own economy, preventing Nigeria from moving up to the 20th place. However, if the forecast is realised, Nigeria would have seen significant development and transition throughout the years.


The NERC should evaluate these projections as a potential indication of the country’s energy statistics trend, and will make that recommendation. Moreover, suppose it can produce a forecast with the accuracy it has. In that case, a trained statistician in the Nigerian Bureau of Statistics, for example, may have an idea about how to customise its working formulas to create a customised model that can work more accurately for the intricacies that make up our nation’s model. This research has been completed as part of the United Nations Environment Program’s Egain Forecasting Model.


  • Abatan, A.O. (1979). Optimizing Energy Utilization and Conservation. A Presentation submitted to the Federal Government of Nigeria on Fundamental Energy Policy Considerations Page 711 – 720.
  • Ajayi, O.O. (2006). Mainstreaming Statistics with Policy Processes and National Development Programmes. A Paper presented to the National Strategies for the Development of Statistics, November 21 2006.
  • Akinlo, A. (2008). A Study of the relationship between energy consumption and economic growth for eleven countries in Sub-Saharan Africa using the Auto-Regressive Distributed Lag Bounds test. Retrieved March 16, 2014 from
  • Anaekwe, C. (2010). European Scientific Journal February 2013 9(4). ISSN: 1857 – 7881 (Print), e – ISSN 1857- 7431 28).
  • Bozarth, C. (1998). Forecasting Principles: What you need to know About Forecasting.
  • Retrieved February 28, 2014 from
  • Bozarth, C. (2011). Measuring Forecast Accuracy: Approaches to Forecasting. Retrieved March 13, 2014 from
  • Central Bank of Nigeria. (1999). Statistical Bulletin of the Central Bank of Nigeria. Retrieved March 15, 2014 from
WeCreativez WhatsApp Support
Our customer support team is here to answer your questions. Ask us anything!