International Journal of Computer Applications (0975 – 8887) Volume 124 – No.7, August 2015 15 Functional Time series (FTS) Forecasting of Electricity Consumption in Pakistan Farah Yasmeen Department of Statistics University of Karachi Muhammad Sharif Department of Statistics University of Karachi ABSTRACT Electricity is one of the most important sources for economic and social development of a country. The growth in energy consumption is basically linked with the growth in economy. Energy demand increases due to different reasons, including higher Gross Domestic Product (GDP) growth, higher per capita consumption, the population growth and rapid development of industrial & commercial sectors. In this study, the monthly electricity consumption for the period of January 1990 through December 2011 in Pakistan is analysed using functional time series (FTS) technique. Electricity consumption model reveals a significant trend due to socio-economic factors. The monthly behavior of forecast values reveals that the electricity consumption is more for summer season and this demand will be increased in future. Forecast model and the forecast values show that the electricity consumption is increasing with the passage of time. The growing energy consumption in the country may be due to economic growth, urbanization process in the region, population growth and industrialization. Keywords Functional Time Series, Functional Data, Electricity Consumption, Principal Component, forecast 1. INTRODUCTION Electric energy consumption is the form of energy consumption that uses electric energy. Energy is the basic building block of economic development and the most flexible form of energy that constitutes one of the vital infra- structural inputs in socio-economic development. In Pakistan, electric power is becoming the main energy form relied upon in all economic sectors of the country. Also, the time series of electrical energy consumption in Pakistan is unique due to irregular power outages and increasing demand. It is therefore desirable to consider the future pattern, or to forecast the series. The electric power sector in Pakistan is operated by the Water and Power Development Authority (WAPDA),with additional generation contribution from Independent (private) Power Producers (IPPs). WAPDA is key responsible department for power management in Pakistan, with the exception of Karachi, which is supplied by KESC.. The National Electric Power Regulatory Authority (NEPRA) regulates the power sector in Pakistan, which includes power generation, transmission and distribution. NEPRA is also responsible for determining electricity rates in Pakistan. Forecasting electricity consumption with high accuracy is essential to prevent energy wasting and system failure. Electricity consumption forecasting is one of the most significant challenges in dealing supply and demand of the electricity, since the electricity demand is volatile in nature; it cannot be stored and has to be consumed immediately. Electricity consumption forecast are generally divided in two categories: short term and long term. Short term forecast are useful in daily operations of a utility companies whereas long term forecast are needed for strategic planning This paper is organized as follows: section 1 is introductory, while some previous literature is reviewed in section 2. Section 3 describes the forecasting method. Finally, some concluding remarks are given in section 4. 2. LITERATURE REVIEW Ali et al [1] studied the relationship between extreme temperature and electricity demand in Pakistan. The results show that there is significant linear correlation coefficient (0.412) between extreme temperature and electricity demand in Pakistan. The power demand is maximum in summer season and will be highest (6785.6 (GWh)) in July, 2020 due to increase in temperature. Khan and Ahmed [2] reported that the current electricity production of Pakistan is around 11,500 MW per day. The economy’s electricity jumped to around 20,000MW per day by 2010. This gap between the supply and demand in the energy sector suggests the magnitude of the energy crisis the economy faces. To fulfill increased electricity demand, planning and investment in infrastructure development is necessary. The unplanned outages may negatively affect economic growth. The government should adopt a policy so that a sustainable electricity supply may be ensured. There is abundant potential capacity of hydroelectricity in the country that can be tapped by constructing dams. Khan and Qayyum [3] justified that Pakistan has been facing severe imbalance between energy demand and energy supply. During the past 25 years, energy supply in Pakistan has been increased by around 40 times, but still the demand outstrips supply. According to research of Alter and Shabib [4], current electricity crisis has influenced the whole economy of Pakistan. Electricity crisis has mainly affected the industries, exports and employment. Where industrial losses have reached to 157 billion rupees, unemployment losses are about 400,000. Currently Pakistan is going through the worst energy and electricity crisis of its history. Electricity shortfall has increased about 5000 Mw, load shedding has increased from 8 to 14 hours daily, industrial growth has declined, and ultimately the whole economy has suffered. Zachariadis and Pashourtidou [5] used models based on econometrics method for forecasting electricity demand in Bangladesh. The forecasts of the electricity demand with