A refined parametric model for short term load forecasting

Abstract We present a refined parametric model for forecasting electricity demand which performed particularly well in the recent Global Energy Forecasting Competition (GEFCom 2012). We begin by motivating and presenting a simple parametric model, treating the electricity demand as a function of the temperature and day of the data. We then set out a series of refinements of the model, explaining the rationale for each, and using the competition scores to demonstrate that each successive refinement step increases the accuracy of the model’s predictions. These refinements include combining models from multiple weather stations, removing outliers from the historical data, and special treatments of public holidays.

Information content and forecasting ability of sentiment indicators: case of real estate market

We evaluate a number of real estate sentiment indices to ascertain current and forward-looking information content that may be useful for forecasting demand and supply activities. Analyzing the dynamic relationships within a Vector Auto-Regression (VAR) framework and using the quarterly US data over 1988-2010, we test the efficacy of several sentiment measures by comparing them with other coincident economic indicators. Overall, our analysis suggests that the sentiment in real estate convey valuable information that can help predict changes in real estate returns. These findings have important implications for investment decisions, from consumers' as well as institutional investors' perspectives.

Modeling and forecasting long-term natural gas (NG) consumption in Iran, using particle swarm optimization (PSO)

The gradual changes in the world development have brought energy issues back into high profile. An ongoing challenge for countries around the world is to balance the development gains against its effects on the environment. The energy management is the key factor of any sustainable development program. All the aspects of development in agriculture, power generation, social welfare and industry in Iran are crucially related to the energy and its revenue. Forecasting end-use natural gas consumption is an important Factor for efficient system operation and a basis for planning decisions. In this thesis, particle swarm optimization (PSO) used to forecast long run natural gas consumption in Iran. Gas consumption data in Iran for the previous 34 years is used to predict the consumption for the coming years. Four linear and nonlinear models proposed and six factors such as Gross Domestic Product (GDP), Population, National Income (NI), Temperature, Consumer Price Index (CPI) and yearly Natural Gas (NG) demand investigated.

Forecasting Fiji's exports and imports, 2003-2020

Purpose – The purpose of this paper is to forecast Fiji's exports and imports for the period 2003-2020.

Design/methodology/approach – To achieve the goal of this paper, the autoregressive moving average with explanatory variables (ARMAX) model was applied. To this end, the paper drew on the published export demand model and the import demand model of Narayan and Narayan for Fiji.

Findings – The paper's main findings are: Fiji's imports will outperform exports over the 2003-2020 period; and current account deficits will escalate to be around F$934.4 million on average over the 2003-2020 period.

Originality/value – Exports and imports are crucial for macroeconomic policymaking. It measures the degree of openness of a country and it signals the trade balance and current account balances. This has implications for inflation and exchange rate. By forecasting Fiji's exports and imports, the paper provides policy makers with a set of information that will be useful for devising macroeconomic policies.

Will residential aged care facilities meet long-term demand?

Purpose – This paper aims to provide an invaluable insight into long-term forecasting of demand for aged care facilities. This will ensure the provision of adequate supply by government bodies, stakeholders and developers in order to meet the anticipated level of demand, without creating an over-supply or an under-supply scenario.

Design/methodology/approach – Using an innovative approach, different data sources were collectively used to forecast separate individual supply and demand levels, which were then examined together in order to measure the difference between the two variables between 2009-2020. A case study approach was used for Victoria, Australia.

Findings – The paper finds that, although there is excess supply between 2009-2010 and 2019-2020, the period between 2010 and 2019 will experience an under-supply period which cannot be easily rectified over the short term.

Research limitations/implications – The case study was limited to residential care facilities in Victoria, Australia, although some countries have substantially different age profiles and accommodation supply for older residents. Forecasts are based on information sources from various data suppliers and collectively analysed.

Practical implications – The results are also of direct interest to place managers and planning authorities who are charged with providing medium- and long-term visions and plans for specific locations. This type of research is essential when planning for the eventual aging of the population, where the methodology can be replicated in different areas. Most importantly, this research approach provides a solid basis for decisions regarding the supply of residential aged care facilities as opposed to a simple estimate.

Originality/value – The study adopted a unique approach to analysing the individual supply and demand components for aged care facilities over the long term. This approach is able to accurately determine when there will be an under-supply or over-supply situation and thus provide the opportunity to address the difference before it occurs. This will allow informed decisions about planning aged care facilities in the future to be made as required.

Short term load forecasting using a hybrid neural network

Short Term Load Forecasting (STLF) is very important from the power systems grid operation point of view. STLF involves forecasting load demand in a short term time frame. The short term time frame may consist of half hourly prediction up to weekly prediction. Accurate forecasting would benefit the utility in terms of reliability and stability of the grid ensuring adequate supply is present to meet with the load demand. Apart from that it would also affect the financial performance of the utility company. An accurate forecast would result in better savings while maintaining the security of the grid. This paper outlines the STLF using a novel hybrid online learning neural network, known as the Gaussian Regression (GR). This new hybrid neural network is a combination of two existing online learning neural networks which are the Gaussian Adaptive Resonance Theory (GA) and the Generalized Regression Neural Network (GRNN). Both GA and GRNN implemented online learning, but each of them suffers from limitation. Originally GA is used for unsupervised clustering by compressing the training samples into several categories. A supervised version of GA is available, namely Gaussian ARTMAP (GAM). However, the GAM is still not capable on solving regression problem. On the other hand, GRNN is designed for solving real value estimation (regression) problem, but the learning process would involve of memorizing all training samples, hence high computational cost. The hybrid GR is considered an enhanced version of GRNN with compression ability while still maintains online learning properties. Simulation results show that GR has comparable prediction accuracy and has less prototype as compared to the original GRNN as well as the Support Vector Regression.

Improving load forecasting accuracy through combination of best forecasts

Neural network (NN) models have been widely used in the literature for short-term load forecasting. Their popularity is mainly due to their excellent learning and approximation capability. However, their forecasting performance significantly depends on several factors including initializing parameters, training algorithm, and NN structure. To minimize negative effects of these factors, this paper proposes a practically simple, yet effective and an efficient method to combine forecasts generated by NN models. The proposed method includes three main phases: (i) training NNs with different structures, (ii) selecting best NN models based on their forecasting performance for a validation set, and (iii) combination of forecasts for selected best NNs. Forecast combination is performed through calculating the mean of forecasts generated by best NN models. The performance of the proposed method is examined using real world data set. Comparative studies demonstrate that the accuracy of combined forecasts is significantly superior to those obtained from individual NN models.

Sustainable construction : reliable forecasting for building construction prices

A reliable forecasting for future construction costs or prices would help to ensure the budget of a construction project can be well planned and limited resources can be allocated more appropriately in construction firms. Although many studies have been focused on the construction price modelling and forecasting, few researchers have considered the impacts of the global economic events and seasonality in price modelling and forecasting. In this study, an advanced multivariate modelling technique, namely the vector correction (VEC) model with dummy variables was employed and the impacts of the global economic event and seasonality were factored into the forecasting model for the building construction price in the Australian construction market. Research findings suggest that a long-run equilibrium relationship exists among the price, levels of supply and demand in the construction market. The reliability of forecasting models was examined by mean absolute percentage error (MAPE) and The Theil's inequality coefficient U tests. The results of MAPE and U tests suggest that the conventional VEC model and the VEC model with dummy variable are both acceptable for forecasting building construction prices, while the VEC model that considered external impacts achieves higher prediction accuracy than the conventional VEC model does.

Market effects on forecasting construction prices using vector error correction models

Construction price forecasting is an essential component to facilitate decision-making for construction contractors, investors and related financial institutions. Construction economists are increasingly interested in seeking a more analytical method to forecast construction prices. Although many studies have focused on construction price modelling and forecasting, few have considered the impacts of large-scale economic events and seasonality. In this study, an advanced multivariate modelling technique, namely the vector correction (VEC) model with dummy variables, was employed. The impacts of global economic events and seasonality are factored into the model to forecast the construction price in the Australian construction market. Research findings suggest that both long-run and dynamic short-term causal relationships exist among the price and levels of supply and demand in the construction market. These relationships drive the construction price and supply and demand, which interact with one another as a loop system. The reliability of forecasting models was examined by the mean absolute percentage error (MAPE) and the Theil's inequality coefficient U tests. The test results suggest that the conventional VEC model and the VEC model with dummy variable are both acceptable for forecasting the construction price, while the VEC model considering external impacts achieves higher prediction accuracy than the conventional VEC model. © 2014 © 2014 Taylor & Francis.

Electricity load and price forecasting with influential factors in a deregulated power industry

With the emergence of smart power grid and distributed generation technologies in recent years, there is need to introduce new advanced models for forecasting. Electricity load and price forecasts are two primary factors needed in a deregulated power industry. The performances of the demand response programs are likely to be deteriorated in the absence of accurate load and price forecasting. Electricity generation companies, system operators, and consumers are highly reliant on the accuracy of the forecasting models. However, historical prices from the financial market, weekly price/load information, historical loads and day type are some of the explanatory factors that affect the accuracy of the forecasting. In this paper, a neural network (NN) model that considers different influential factors as feedback to the model is presented. This model is implemented with historical data from the ISO New England. It is observed during experiments that price forecasting is more complicated and hence less accurate than the load forecasting.

Prediction interval estimation for electricity price and demand using support vector machines

Uncertainty is known to be a concomitant factor of almost all the real world commodities such as oil prices, stock prices, sales and demand of products. As a consequence, forecasting problems are becoming more and more challenging and ridden with uncertainty. Such uncertainties are generally quantified by statistical tools such as prediction intervals (Pis). Pis quantify the uncertainty related to forecasts by estimating the ranges of the targeted quantities. Pis generated by traditional neural network based approaches are limited by high computational burden and impractical assumptions about the distribution of the data. A novel technique for constructing high quality Pis using support vector machines (SVMs) is being proposed in this paper. The proposed technique directly estimates the upper and lower bounds of the PI in a short time and without any assumptions about the data distribution. The SVM parameters are tuned using particle swarm optimization technique by minimization of a modified Pi-based objective function. Electricity price and demand data of the Ontario electricity market is used to validate the performance of the proposed technique. Several case studies for different months indicate the superior performance of the proposed method in terms of high quality PI generation and shorter computational times.

Applying choice based conjoint measurement to forcast demand for a new restaurant category

This paper examines the use of Choice Based Conjointexperimentation for forecasting demand for a new restaurant category.The results of the forecasting experiment are compared to demand forexisting restaurant categories to determine whether the choice experimentreplicates actual category shares in the sampled region. The analysisshows that Choice Based Conjoint experiments are able to predictcategory shares for existing restaurant categories. It is then shown howthe approach may be used to estimate demand for a new category.

Short-Term Multinodal Load Forecasting Using a Modified General Regression Neural Network

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Short-term multinodal load forecasting in distribution systems using general regression neural networks

Multinodal load forecasting deals with the loads of several interest nodes in an electrical network system, which is also known as bus load forecasting. To perform this demand, it is necessary a technique that is precise, trustable and has a short-time processing. This paper proposes two methodologies based on general regression neural networks for short-term multinodal load forecasting. The first individually forecast the local loads and the second forecast the global load and individually forecast the load participation factors to estimate the local loads. To design the forecasters it wasn't necessary the previous study of the local loads. Tests were made using a New Zealand distribution subsystem and the results obtained are compatible with the ones founded in the specialized literature. © 2011 IEEE.

Forecasting the need for medical specialists in Spain: application of a system dynamics model

[EN] Background: Spain has gone from a surplus to a shortage of medical doctors in very few years. Medium and long-term planning for health professionals has become a high priority for health authorities. Methods: We created a supply and demand/need simulation model for 43 medical specialties using system dynamics. The model includes demographic, education and labour market variables. Several scenarios were defined. Variables controllable by health planners can be set as parameters to simulate different scenarios. The model calculates the supply and the deficit or surplus. Experts set the ratio of specialists needed per 1000 inhabitants with a Delphi method. Results: In the scenario of the baseline model with moderate population growth, the deficit of medical specialists will grow from 2% at present (2800 specialists) to 14.3% in 2025 (almost 21 000). The specialties with the greatest medium-term shortages are Anesthesiology, Orthopedic and Traumatic Surgery, Pediatric Surgery, Plastic Aesthetic and Reparatory Surgery, Family and Community Medicine, Pediatrics, Radiology, and Urology. Conclusions: The model suggests the need to increase the number of students admitted to medical school. Training itineraries should be redesigned to facilitate mobility among specialties. In the meantime, the need to make more flexible the supply in the short term is being filled by the immigration of physicians from new members of the European Union and from Latin America.