Search results for: PV power forecasting
6571 Forecasting Performance Comparison of Autoregressive Fractional Integrated Moving Average and Jordan Recurrent Neural Network Models on the Turbidity of Stream Flows
Authors: Daniel Fulus Fom, Gau Patrick Damulak
Abstract:
In this study, the Autoregressive Fractional Integrated Moving Average (ARFIMA) and Jordan Recurrent Neural Network (JRNN) models were employed to model the forecasting performance of the daily turbidity flow of White Clay Creek (WCC). The two methods were applied to the log difference series of the daily turbidity flow series of WCC. The measurements of error employed to investigate the forecasting performance of the ARFIMA and JRNN models are the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). The outcome of the investigation revealed that the forecasting performance of the JRNN technique is better than the forecasting performance of the ARFIMA technique in the mean square error sense. The results of the ARFIMA and JRNN models were obtained by the simulation of the models using MATLAB version 8.03. The significance of using the log difference series rather than the difference series is that the log difference series stabilizes the turbidity flow series than the difference series on the ARFIMA and JRNN.Keywords: auto regressive, mean absolute error, neural network, root square mean error
Procedia PDF Downloads 2656570 Adaptive Neuro Fuzzy Inference System Model Based on Support Vector Regression for Stock Time Series Forecasting
Authors: Anita Setianingrum, Oki S. Jaya, Zuherman Rustam
Abstract:
Forecasting stock price is a challenging task due to the complex time series of the data. The complexity arises from many variables that affect the stock market. Many time series models have been proposed before, but those previous models still have some problems: 1) put the subjectivity of choosing the technical indicators, and 2) rely upon some assumptions about the variables, so it is limited to be applied to all datasets. Therefore, this paper studied a novel Adaptive Neuro-Fuzzy Inference System (ANFIS) time series model based on Support Vector Regression (SVR) for forecasting the stock market. In order to evaluate the performance of proposed models, stock market transaction data of TAIEX and HIS from January to December 2015 is collected as experimental datasets. As a result, the method has outperformed its counterparts in terms of accuracy.Keywords: ANFIS, fuzzy time series, stock forecasting, SVR
Procedia PDF Downloads 2386569 Load Forecasting Using Neural Network Integrated with Economic Dispatch Problem
Authors: Mariyam Arif, Ye Liu, Israr Ul Haq, Ahsan Ashfaq
Abstract:
High cost of fossil fuels and intensifying installations of alternate energy generation sources are intimidating main challenges in power systems. Making accurate load forecasting an important and challenging task for optimal energy planning and management at both distribution and generation side. There are many techniques to forecast load but each technique comes with its own limitation and requires data to accurately predict the forecast load. Artificial Neural Network (ANN) is one such technique to efficiently forecast the load. Comparison between two different ranges of input datasets has been applied to dynamic ANN technique using MATLAB Neural Network Toolbox. It has been observed that selection of input data on training of a network has significant effects on forecasted results. Day-wise input data forecasted the load accurately as compared to year-wise input data. The forecasted load is then distributed among the six generators by using the linear programming to get the optimal point of generation. The algorithm is then verified by comparing the results of each generator with their respective generation limits.Keywords: artificial neural networks, demand-side management, economic dispatch, linear programming, power generation dispatch
Procedia PDF Downloads 1846568 Decision Tree Modeling in Emergency Logistics Planning
Authors: Yousef Abu Nahleh, Arun Kumar, Fugen Daver, Reham Al-Hindawi
Abstract:
Despite the availability of natural disaster related time series data for last 110 years, there is no forecasting tool available to humanitarian relief organizations to determine forecasts for emergency logistics planning. This study develops a forecasting tool based on identifying probability of disaster for each country in the world by using decision tree modeling. Further, the determination of aggregate forecasts leads to efficient pre-disaster planning. Based on the research findings, the relief agencies can optimize the various resources allocation in emergency logistics planning.Keywords: decision tree modeling, forecasting, humanitarian relief, emergency supply chain
Procedia PDF Downloads 4766567 Performance Evaluation of the Classic seq2seq Model versus a Proposed Semi-supervised Long Short-Term Memory Autoencoder for Time Series Data Forecasting
Authors: Aswathi Thrivikraman, S. Advaith
Abstract:
The study is aimed at designing encoders for deciphering intricacies in time series data by redescribing the dynamics operating on a lower-dimensional manifold. A semi-supervised LSTM autoencoder is devised and investigated to see if the latent representation of the time series data can better forecast the data. End-to-end training of the LSTM autoencoder, together with another LSTM network that is connected to the latent space, forces the hidden states of the encoder to represent the most meaningful latent variables relevant for forecasting. Furthermore, the study compares the predictions with those of a traditional seq2seq model.Keywords: LSTM, autoencoder, forecasting, seq2seq model
Procedia PDF Downloads 1486566 Adjusting Electricity Demand Data to Account for the Impact of Loadshedding in Forecasting Models
Authors: Migael van Zyl, Stefanie Visser, Awelani Phaswana
Abstract:
The electricity landscape in South Africa is characterized by frequent occurrences of loadshedding, a measure implemented by Eskom to manage electricity generation shortages by curtailing demand. Loadshedding, classified into stages ranging from 1 to 8 based on severity, involves the systematic rotation of power cuts across municipalities according to predefined schedules. However, this practice introduces distortions in recorded electricity demand, posing challenges to accurate forecasting essential for budgeting, network planning, and generation scheduling. Addressing this challenge requires the development of a methodology to quantify the impact of loadshedding and integrate it back into metered electricity demand data. Fortunately, comprehensive records of loadshedding impacts are maintained in a database, enabling the alignment of Loadshedding effects with hourly demand data. This adjustment ensures that forecasts accurately reflect true demand patterns, independent of loadshedding's influence, thereby enhancing the reliability of electricity supply management in South Africa. This paper presents a methodology for determining the hourly impact of load scheduling and subsequently adjusting historical demand data to account for it. Furthermore, two forecasting models are developed: one utilizing the original dataset and the other using the adjusted data. A comparative analysis is conducted to evaluate forecast accuracy improvements resulting from the adjustment process. By implementing this methodology, stakeholders can make more informed decisions regarding electricity infrastructure investments, resource allocation, and operational planning, contributing to the overall stability and efficiency of South Africa's electricity supply system.Keywords: electricity demand forecasting, load shedding, demand side management, data science
Procedia PDF Downloads 536565 Novel Adaptive Radial Basis Function Neural Networks Based Approach for Short-Term Load Forecasting of Jordanian Power Grid
Authors: Eyad Almaita
Abstract:
In this paper, a novel adaptive Radial Basis Function Neural Networks (RBFNN) algorithm is used to forecast the hour by hour electrical load demand in Jordan. A small and effective RBFNN model is used to forecast the hourly total load demand based on a small number of features. These features are; the load in the previous day, the load in the same day in the previous week, the temperature in the same hour, the hour number, the day number, and the day type. The proposed adaptive RBFNN model can enhance the reliability of the conventional RBFNN after embedding the network in the system. This is achieved by introducing an adaptive algorithm that allows the change of the weights of the RBFNN after the training process is completed, which will eliminates the need to retrain the RBFNN model again. The data used in this paper is real data measured by National Electrical Power co. (Jordan). The data for the period Jan./2012-April/2013 is used train the RBFNN models and the data for the period May/2013- Sep. /2013 is used to validate the models effectiveness.Keywords: load forecasting, adaptive neural network, radial basis function, short-term, electricity consumption
Procedia PDF Downloads 3386564 The Problems of Current Earth Coordinate System for Earthquake Forecasting Using Single Layer Hierarchical Graph Neuron
Authors: Benny Benyamin Nasution, Rahmat Widia Sembiring, Abdul Rahman Dalimunthe, Nursiah Mustari, Nisfan Bahri, Berta br Ginting, Riadil Akhir Lubis, Rita Tavip Megawati, Indri Dithisari
Abstract:
The earth coordinate system is an important part of an attempt for earthquake forecasting, such as the one using Single Layer Hierarchical Graph Neuron (SLHGN). However, there are a number of problems that need to be worked out before the coordinate system can be utilized for the forecaster. One example of those is that SLHGN requires that the focused area of an earthquake must be constructed in a grid-like form. In fact, within the current earth coordinate system, the same longitude-difference would produce different distances. This can be observed at the distance on the Equator compared to distance at both poles. To deal with such a problem, a coordinate system has been developed, so that it can be used to support the ongoing earthquake forecasting using SLHGN. Two important issues have been developed in this system: 1) each location is not represented through two-value (longitude and latitude), but only a single value, 2) the conversion of the earth coordinate system to the x-y cartesian system requires no angular formulas, which is therefore fast. The accuracy and the performance have not been measured yet, since earthquake data is difficult to obtain. However, the characteristics of the SLHGN results show a very promising answer.Keywords: hierarchical graph neuron, multidimensional hierarchical graph neuron, single layer hierarchical graph neuron, natural disaster forecasting, earthquake forecasting, earth coordinate system
Procedia PDF Downloads 2096563 Evaluation of Football Forecasting Models: 2021 Brazilian Championship Case Study
Authors: Flavio Cordeiro Fontanella, Asla Medeiros e Sá, Moacyr Alvim Horta Barbosa da Silva
Abstract:
In the present work, we analyse the performance of football results forecasting models. In order to do so, we have performed the data collection from eight different forecasting models during the 2021 Brazilian football season. First, we guide the analysis through visual representations of the data, designed to highlight the most prominent features and enhance the interpretation of differences and similarities between the models. We propose using a 2-simplex triangle to investigate visual patterns from the results forecasting models. Next, we compute the expected points for every team playing in the championship and compare them to the final league standings, revealing interesting contrasts between actual to expected performances. Then, we evaluate forecasts’ accuracy using the Ranked Probability Score (RPS); models comparison accounts for tiny scale differences that may become consistent in time. Finally, we observe that the Wisdom of Crowds principle can be appropriately applied in the context, driving into a discussion of results forecasts usage in practice. This paper’s primary goal is to encourage football forecasts’ performance discussion. We hope to accomplish it by presenting appropriate criteria and easy-to-understand visual representations that can point out the relevant factors of the subject.Keywords: accuracy evaluation, Brazilian championship, football results forecasts, forecasting models, visual analysis
Procedia PDF Downloads 906562 Forecasting Model for Rainfall in Thailand: Case Study Nakhon Ratchasima Province
Authors: N. Sopipan
Abstract:
In this paper, we study of rainfall time series of weather stations in Nakhon Ratchasima province in Thailand using various statistical methods enabled to analyse the behaviour of rainfall in the study areas. Time-series analysis is an important tool in modelling and forecasting rainfall. ARIMA and Holt-Winter models based on exponential smoothing were built. All the models proved to be adequate. Therefore, could give information that can help decision makers establish strategies for proper planning of agriculture, drainage system and other water resource applications in Nakhon Ratchasima province. We found the best perform for forecasting is ARIMA(1,0,1)(1,0,1)12.Keywords: ARIMA Models, exponential smoothing, Holt-Winter model
Procedia PDF Downloads 2936561 Spatial Spillovers in Forecasting Market Diffusion of Electric Mobility
Authors: Reinhold Kosfeld, Andreas Gohs
Abstract:
In the reduction of CO₂ emissions, the transition to environmentally friendly transport modes has a high significance. In Germany, the climate protection programme 2030 includes various measures for promoting electromobility. Although electric cars at present hold a market share of just over one percent, its stock more than doubled in the past two years. Special measures like tax incentives and a buyer’s premium have been put in place to promote the shift towards electric cars and boost their diffusion. Knowledge of the future expansion of electric cars is required for planning purposes and adaptation measures. With a view of these objectives, we particularly investigate the effect of spatial spillovers on forecasting performance. For this purpose, time series econometrics and panel econometric models are designed for pure electric cars and hybrid cars for Germany. Regional forecasting models with spatial interactions are consistently estimated by using spatial econometric techniques. Regional data on the stocks of electric cars and their determinants at the district level (NUTS 3 regions) are available from the Federal Motor Transport Authority (Kraftfahrt-Bundesamt) for the period 2017 - 2019. A comparative examination of aggregated regional and national predictions provides quantitative information on accuracy gains by allowing for spatial spillovers in forecasting electric mobility.Keywords: electric mobility, forecasting market diffusion, regional panel data model, spatial interaction
Procedia PDF Downloads 1616560 Multi-Period Portfolio Optimization Using Predictive Machine Learning Models
Authors: Peng Liu, Chyng Wen Tee, Xiaofei Xu
Abstract:
This paper integrates machine learning forecasting techniques into the multi-period portfolio optimization framework, enabling dynamic asset allocation based on multiple future periods. We explore both theoretical foundations and practical applications, employing diverse machine learning models for return forecasting. This comprehensive guide demonstrates the superiority of multi-period optimization over single-period approaches, particularly in risk mitigation through strategic rebalancing and enhanced market trend forecasting. Our goal is to promote wider adoption of multi-period optimization, providing insights that can significantly enhance the decision-making capabilities of practitioners and researchers alike.Keywords: multi-period portfolio optimization, look-ahead constrained optimization, machine learning, sequential decision making
Procedia PDF Downloads 376559 Load Forecasting in Microgrid Systems with R and Cortana Intelligence Suite
Authors: F. Lazzeri, I. Reiter
Abstract:
Energy production optimization has been traditionally very important for utilities in order to improve resource consumption. However, load forecasting is a challenging task, as there are a large number of relevant variables that must be considered, and several strategies have been used to deal with this complex problem. This is especially true also in microgrids where many elements have to adjust their performance depending on the future generation and consumption conditions. The goal of this paper is to present a solution for short-term load forecasting in microgrids, based on three machine learning experiments developed in R and web services built and deployed with different components of Cortana Intelligence Suite: Azure Machine Learning, a fully managed cloud service that enables to easily build, deploy, and share predictive analytics solutions; SQL database, a Microsoft database service for app developers; and PowerBI, a suite of business analytics tools to analyze data and share insights. Our results show that Boosted Decision Tree and Fast Forest Quantile regression methods can be very useful to predict hourly short-term consumption in microgrids; moreover, we found that for these types of forecasting models, weather data (temperature, wind, humidity and dew point) can play a crucial role in improving the accuracy of the forecasting solution. Data cleaning and feature engineering methods performed in R and different types of machine learning algorithms (Boosted Decision Tree, Fast Forest Quantile and ARIMA) will be presented, and results and performance metrics discussed.
Keywords: time-series, features engineering methods for forecasting, energy demand forecasting, Azure Machine Learning
Procedia PDF Downloads 2896558 New Approach for Load Modeling
Authors: Slim Chokri
Abstract:
Load forecasting is one of the central functions in power systems operations. Electricity cannot be stored, which means that for electric utility, the estimate of the future demand is necessary in managing the production and purchasing in an economically reasonable way. A majority of the recently reported approaches are based on neural network. The attraction of the methods lies in the assumption that neural networks are able to learn properties of the load. However, the development of the methods is not finished, and the lack of comparative results on different model variations is a problem. This paper presents a new approach in order to predict the Tunisia daily peak load. The proposed method employs a computational intelligence scheme based on the Fuzzy neural network (FNN) and support vector regression (SVR). Experimental results obtained indicate that our proposed FNN-SVR technique gives significantly good prediction accuracy compared to some classical techniques.Keywords: neural network, load forecasting, fuzzy inference, machine learning, fuzzy modeling and rule extraction, support vector regression
Procedia PDF Downloads 4306557 EarlyWarning for Financial Stress Events:A Credit-Regime Switching Approach
Abstract:
We propose a new early warning model for predicting financial stress events for a given future time. In this model, we examine whether credit conditions play an important role as a nonlinear propagator of shocks when predicting the likelihood of occurrence of financial stress events for a given future time. This propagation takes the form of a threshold regression in which a regime change occurs if credit conditions cross a critical threshold. Given the new early warning model for financial stress events, we evaluate the performance of this model and currently available alternatives, such as the model from signal extraction approach, and linear regression model. In-sample forecasting results indicate that the three types of models are useful tools for predicting financial stress events while none of them outperforms others across all criteria considered. The out-of-sample forecasting results suggest that the credit-regime switching model performs better than the two others across all criteria and all forecasting horizons considered.Keywords: cut-off probability, early warning model, financial crisis, financial stress, regime-switching model, forecasting horizons
Procedia PDF Downloads 4306556 Input Data Balancing in a Neural Network PM-10 Forecasting System
Authors: Suk-Hyun Yu, Heeyong Kwon
Abstract:
Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.Keywords: artificial intelligence, air quality prediction, neural networks, pattern recognition, PM-10
Procedia PDF Downloads 2246555 Assessing the Cumulative Impact of PM₂.₅ Emissions from Power Plants by Using the Hybrid Air Quality Model and Evaluating the Contributing Salient Factor in South Taiwan
Authors: Jackson Simon Lusagalika, Lai Hsin-Chih, Dai Yu-Tung
Abstract:
Particles with an aerodynamic diameter of 2.5 meters or less are referred to as "fine particulate matter" (PM₂.₅) are easily inhaled and can go deeper into the lungs than other particles in the atmosphere, where it may have detrimental health consequences. In this study, we use a hybrid model that combined CMAQ and AERMOD as well as initial meteorological fields from the Weather Research and Forecasting (WRF) model to study the impact of power plant PM₂.₅ emissions in South Taiwan since it frequently experiences higher PM₂.₅ levels. A specific date of March 3, 2022, was chosen as a result of a power outage that prompted the bulk of power plants to shut down. In some way, it is not conceivable anywhere in the world to turn off the power for the sole purpose of doing research. Therefore, this catastrophe involving a power outage and the shutdown of power plants offers a great occasion to evaluate the impact of air pollution driven by this power sector. As a result, four numerical experiments were conducted in the study using the Continuous Emission Data System (CEMS), assuming that the power plants continued to function normally after the power outage. The hybrid model results revealed that power plants have a minor impact in the study region. However, we examined the accumulation of PM₂.₅ in the study and discovered that once the vortex at 925hPa was established and moved to the north of Taiwan's coast, the study region experienced higher observed PM₂.₅ concentrations influenced by meteorological factors. This study recommends that decision-makers take into account not only control techniques, specifically emission reductions, but also the atmospheric and meteorological implications for future investigations.Keywords: PM₂.₅ concentration, powerplants, hybrid air quality model, CEMS, Vorticity
Procedia PDF Downloads 716554 Application of Support Vector Machines in Forecasting Non-Residential
Authors: Wiwat Kittinaraporn, Napat Harnpornchai, Sutja Boonyachut
Abstract:
This paper deals with the application of a novel neural network technique, so-called Support Vector Machine (SVM). The objective of this study is to explore the variable and parameter of forecasting factors in the construction industry to build up forecasting model for construction quantity in Thailand. The scope of the research is to study the non-residential construction quantity in Thailand. There are 44 sets of yearly data available, ranging from 1965 to 2009. The correlation between economic indicators and construction demand with the lag of one year was developed by Apichat Buakla. The selected variables are used to develop SVM models to forecast the non-residential construction quantity in Thailand. The parameters are selected by using ten-fold cross-validation method. The results are indicated in term of Mean Absolute Percentage Error (MAPE). The MAPE value for the non-residential construction quantity predicted by Epsilon-SVR in corporation with Radial Basis Function (RBF) of kernel function type is 5.90. Analysis of the experimental results show that the support vector machine modelling technique can be applied to forecast construction quantity time series which is useful for decision planning and management purpose.Keywords: forecasting, non-residential, construction, support vector machines
Procedia PDF Downloads 4296553 Forecasting Residential Water Consumption in Hamilton, New Zealand
Authors: Farnaz Farhangi
Abstract:
Many people in New Zealand believe that the access to water is inexhaustible, and it comes from a history of virtually unrestricted access to it. For the region like Hamilton which is one of New Zealand’s fastest growing cities, it is crucial for policy makers to know about the future water consumption and implementation of rules and regulation such as universal water metering. Hamilton residents use water freely and they do not have any idea about how much water they use. Hence, one of proposed objectives of this research is focusing on forecasting water consumption using different methods. Residential water consumption time series exhibits seasonal and trend variations. Seasonality is the pattern caused by repeating events such as weather conditions in summer and winter, public holidays, etc. The problem with this seasonal fluctuation is that, it dominates other time series components and makes difficulties in determining other variations (such as educational campaign’s effect, regulation, etc.) in time series. Apart from seasonality, a stochastic trend is also combined with seasonality and makes different effects on results of forecasting. According to the forecasting literature, preprocessing (de-trending and de-seasonalization) is essential to have more performed forecasting results, while some other researchers mention that seasonally non-adjusted data should be used. Hence, I answer the question that is pre-processing essential? A wide range of forecasting methods exists with different pros and cons. In this research, I apply double seasonal ARIMA and Artificial Neural Network (ANN), considering diverse elements such as seasonality and calendar effects (public and school holidays) and combine their results to find the best predicted values. My hypothesis is the examination the results of combined method (hybrid model) and individual methods and comparing the accuracy and robustness. In order to use ARIMA, the data should be stationary. Also, ANN has successful forecasting applications in terms of forecasting seasonal and trend time series. Using a hybrid model is a way to improve the accuracy of the methods. Due to the fact that water demand is dominated by different seasonality, in order to find their sensitivity to weather conditions or calendar effects or other seasonal patterns, I combine different methods. The advantage of this combination is reduction of errors by averaging of each individual model. It is also useful when we are not sure about the accuracy of each forecasting model and it can ease the problem of model selection. Using daily residential water consumption data from January 2000 to July 2015 in Hamilton, I indicate how prediction by different methods varies. ANN has more accurate forecasting results than other method and preprocessing is essential when we use seasonal time series. Using hybrid model reduces forecasting average errors and increases the performance.Keywords: artificial neural network (ANN), double seasonal ARIMA, forecasting, hybrid model
Procedia PDF Downloads 3316552 Groundwater Level Prediction Using hybrid Particle Swarm Optimization-Long-Short Term Memory Model and Performance Evaluation
Authors: Sneha Thakur, Sanjeev Karmakar
Abstract:
This paper proposed hybrid Particle Swarm Optimization (PSO) – Long-Short Term Memory (LSTM) model for groundwater level prediction. The evaluation of the performance is realized using the parameters: root mean square error (RMSE) and mean absolute error (MAE). Ground water level forecasting will be very effective for planning water harvesting. Proper calculation of water level forecasting can overcome the problem of drought and flood to some extent. The objective of this work is to develop a ground water level forecasting model using deep learning technique integrated with optimization technique PSO by applying 29 years data of Chhattisgarh state, In-dia. It is important to find the precise forecasting in case of ground water level so that various water resource planning and water harvesting can be managed effectively.Keywords: long short-term memory, particle swarm optimization, prediction, deep learning, groundwater level
Procedia PDF Downloads 706551 Composite Forecasts Accuracy for Automobile Sales in Thailand
Authors: Watchareeporn Chaimongkol
Abstract:
In this paper, we compare the statistical measures accuracy of composite forecasting model to estimate automobile customer demand in Thailand. A modified simple exponential smoothing and autoregressive integrate moving average (ARIMA) forecasting model is built to estimate customer demand of passenger cars, instead of using information of historical sales data. Our model takes into account special characteristic of the Thai automobile market such as sales promotion, advertising and publicity, petrol price, and interest rate for loan. We evaluate our forecasting model by comparing forecasts with actual data using six accuracy measurements, mean absolute percentage error (MAPE), geometric mean absolute error (GMAE), symmetric mean absolute percentage error (sMAPE), mean absolute scaled error (MASE), median relative absolute error (MdRAE), and geometric mean relative absolute error (GMRAE).Keywords: composite forecasting, simple exponential smoothing model, autoregressive integrate moving average model selection, accuracy measurements
Procedia PDF Downloads 3556550 Demand Forecasting Using Artificial Neural Networks Optimized by Particle Swarm Optimization
Authors: Daham Owaid Matrood, Naqaa Hussein Raheem
Abstract:
Evolutionary algorithms and Artificial neural networks (ANN) are two relatively young research areas that were subject to a steadily growing interest during the past years. This paper examines the use of Particle Swarm Optimization (PSO) to train a multi-layer feed forward neural network for demand forecasting. We use in this paper weekly demand data for packed cement and towels, which have been outfitted by the Northern General Company for Cement and General Company of prepared clothes respectively. The results showed superiority of trained neural networks using particle swarm optimization on neural networks trained using error back propagation because their ability to escape from local optima.Keywords: artificial neural network, demand forecasting, particle swarm optimization, weight optimization
Procedia PDF Downloads 4436549 Comparing Forecasting Performances of the Bass Diffusion Model and Time Series Methods for Sales of Electric Vehicles
Authors: Andreas Gohs, Reinhold Kosfeld
Abstract:
This study should be of interest for practitioners who want to predict precisely the sales numbers of vehicles equipped with an innovative propulsion technology as well as for researchers interested in applied (regional) time series analysis. The study is based on the numbers of new registrations of pure electric and hybrid cars. Methods of time series analysis like ARIMA are compared with the Bass Diffusion-model concerning their forecasting performances for new registrations in Germany at the national and federal state levels. Especially it is investigated if the additional information content from regional data increases the forecasting accuracy for the national level by adding predictions for the federal states. Results of parameters of the Bass Diffusion Model estimated for Germany and its sixteen federal states are reported. While the focus of this research is on the German market, estimation results are also provided for selected European and other countries. Concerning Bass-parameters and forecasting performances, we get very different results for Germany's federal states and the member states of the European Union. This corresponds to differences across the EU-member states in the adoption process of this innovative technology. Concerning the German market, the adoption is rather proceeded in southern Germany and stays behind in Eastern Germany except for Berlin.Keywords: bass diffusion model, electric vehicles, forecasting performance, market diffusion
Procedia PDF Downloads 1596548 Development of pm2.5 Forecasting System in Seoul, South Korea Using Chemical Transport Modeling and ConvLSTM-DNN
Authors: Ji-Seok Koo, Hee‑Yong Kwon, Hui-Young Yun, Kyung-Hui Wang, Youn-Seo Koo
Abstract:
This paper presents a forecasting system for PM2.5 levels in Seoul, South Korea, leveraging a combination of chemical transport modeling and ConvLSTM-DNN machine learning technology. Exposure to PM2.5 has known detrimental impacts on public health, making its prediction crucial for establishing preventive measures. Existing forecasting models, like the Community Multiscale Air Quality (CMAQ) and Weather Research and Forecasting (WRF), are hindered by their reliance on uncertain input data, such as anthropogenic emissions and meteorological patterns, as well as certain intrinsic model limitations. The system we've developed specifically addresses these issues by integrating machine learning and using carefully selected input features that account for local and distant sources of PM2.5. In South Korea, the PM2.5 concentration is greatly influenced by both local emissions and long-range transport from China, and our model effectively captures these spatial and temporal dynamics. Our PM2.5 prediction system combines the strengths of advanced hybrid machine learning algorithms, convLSTM and DNN, to improve upon the limitations of the traditional CMAQ model. Data used in the system include forecasted information from CMAQ and WRF models, along with actual PM2.5 concentration and weather variable data from monitoring stations in China and South Korea. The system was implemented specifically for Seoul's PM2.5 forecasting.Keywords: PM2.5 forecast, machine learning, convLSTM, DNN
Procedia PDF Downloads 506547 The Reliability of Management Earnings Forecasts in IPO Prospectuses: A Study of Managers’ Forecasting Preferences
Authors: Maha Hammami, Olfa Benouda Sioud
Abstract:
This study investigates the reliability of management earnings forecasts with reference to these two ingredients: verifiability and neutrality. Specifically, we examine the biasedness (or accuracy) of management earnings forecasts and company specific characteristics that can be associated with accuracy. Based on sample of 102 IPO prospectuses published for admission on NYSE Euronext Paris from 2002 to 2010, we found that these forecasts are on average optimistic and two of the five test variables, earnings variability and financial leverage are significant in explaining ex post bias. Acknowledging the possibility that the bias is the result of the managers’ forecasting behavior, we then examine whether managers decide to under-predict, over-predict or forecast accurately for self-serving purposes. Explicitly, we examine the role of financial distress, operating performance, ownership by insiders and the economy state in influencing managers’ forecasting preferences. We find that managers of distressed firms seem to over-predict future earnings. We also find that when managers are given more stock options, they tend to under-predict future earnings. Finally, we conclude that the management earnings forecasts are affected by an intentional bias due to managers’ forecasting preferences.Keywords: intentional bias, management earnings forecasts, neutrality, verifiability
Procedia PDF Downloads 2306546 A Smart Contract Project: Peer-to-Peer Energy Trading with Price Forecasting in Microgrid
Authors: Şakir Bingöl, Abdullah Emre Aydemir, Abdullah Saado, Ahmet Akıl, Elif Canbaz, Feyza Nur Bulgurcu, Gizem Uzun, Günsu Bilge Dal, Muhammedcan Pirinççi
Abstract:
Smart contracts, which can be applied in many different areas, from financial applications to the internet of things, come to the fore with their security, low cost, and self-executing features. In this paper, it is focused on peer-to-peer (P2P) energy trading and the implementation of the smart contract on the Ethereum blockchain. It is assumed a microgrid consists of consumers and prosumers that can produce solar and wind energy. The proposed architecture is a system where the prosumer makes the purchase or sale request in the smart contract and the maximum price obtained through the distribution system operator (DSO) by forecasting. It is aimed to forecast the hourly maximum unit price of energy by using deep learning instead of a fixed pricing. In this way, it will make the system more reliable as there will be more dynamic and accurate pricing. For this purpose, Istanbul's energy generation, energy consumption and market clearing price data were used. The consistency of the available data and forecasting results is observed and discussed with graphs.Keywords: energy trading smart contract, deep learning, microgrid, forecasting, Ethereum, peer to peer
Procedia PDF Downloads 1286545 A Comparative Analysis of ARIMA and Threshold Autoregressive Models on Exchange Rate
Authors: Diteboho Xaba, Kolentino Mpeta, Tlotliso Qejoe
Abstract:
This paper assesses the in-sample forecasting of the South African exchange rates comparing a linear ARIMA model and a SETAR model. The study uses a monthly adjusted data of South African exchange rates with 420 observations. Akaike information criterion (AIC) and the Schwarz information criteria (SIC) are used for model selection. Mean absolute error (MAE), root mean squared error (RMSE) and mean absolute percentage error (MAPE) are error metrics used to evaluate forecast capability of the models. The Diebold –Mariano (DM) test is employed in the study to check forecast accuracy in order to distinguish the forecasting performance between the two models (ARIMA and SETAR). The results indicate that both models perform well when modelling and forecasting the exchange rates, but SETAR seemed to outperform ARIMA.Keywords: ARIMA, error metrices, model selection, SETAR
Procedia PDF Downloads 2396544 On the Added Value of Probabilistic Forecasts Applied to the Optimal Scheduling of a PV Power Plant with Batteries in French Guiana
Authors: Rafael Alvarenga, Hubert Herbaux, Laurent Linguet
Abstract:
The uncertainty concerning the power production of intermittent renewable energy is one of the main barriers to the integration of such assets into the power grid. Efforts have thus been made to develop methods to quantify this uncertainty, allowing producers to ensure more reliable and profitable engagements related to their future power delivery. Even though a diversity of probabilistic approaches was proposed in the literature giving promising results, the added value of adopting such methods for scheduling intermittent power plants is still unclear. In this study, the profits obtained by a decision-making model used to optimally schedule an existing PV power plant connected to batteries are compared when the model is fed with deterministic and probabilistic forecasts generated with two of the most recent methods proposed in the literature. Moreover, deterministic forecasts with different accuracy levels were used in the experiments, testing the utility and the capability of probabilistic methods of modeling the progressively increasing uncertainty. Even though probabilistic approaches are unquestionably developed in the recent literature, the results obtained through a study case show that deterministic forecasts still provide the best performance if accurate, ensuring a gain of 14% on final profits compared to the average performance of probabilistic models conditioned to the same forecasts. When the accuracy of deterministic forecasts progressively decreases, probabilistic approaches start to become competitive options until they completely outperform deterministic forecasts when these are very inaccurate, generating 73% more profits in the case considered compared to the deterministic approach.Keywords: PV power forecasting, uncertainty quantification, optimal scheduling, power systems
Procedia PDF Downloads 766543 Solar Power Forecasting for the Bidding Zones of the Italian Electricity Market with an Analog Ensemble Approach
Authors: Elena Collino, Dario A. Ronzio, Goffredo Decimi, Maurizio Riva
Abstract:
The rapid increase of renewable energy in Italy is led by wind and solar installations. The 2017 Italian energy strategy foresees a further development of these sustainable technologies, especially solar. This fact has resulted in new opportunities, challenges, and different problems to deal with. The growth of renewables allows to meet the European requirements regarding energy and environmental policy, but these types of sources are difficult to manage because they are intermittent and non-programmable. Operationally, these characteristics can lead to instability on the voltage profile and increasing uncertainty on energy reserve scheduling. The increasing renewable production must be considered with more and more attention especially by the Transmission System Operator (TSO). The TSO, in fact, every day provides orders on energy dispatch, once the market outcome has been determined, on extended areas, defined mainly on the basis of power transmission limitations. In Italy, six market zone are defined: Northern-Italy, Central-Northern Italy, Central-Southern Italy, Southern Italy, Sardinia, and Sicily. An accurate hourly renewable power forecasting for the day-ahead on these extended areas brings an improvement both in terms of dispatching and reserve management. In this study, an operational forecasting tool of the hourly solar output for the six Italian market zones is presented, and the performance is analysed. The implementation is carried out by means of a numerical weather prediction model, coupled with a statistical post-processing in order to derive the power forecast on the basis of the meteorological projection. The weather forecast is obtained from the limited area model RAMS on the Italian territory, initialized with IFS-ECMWF boundary conditions. The post-processing calculates the solar power production with the Analog Ensemble technique (AN). This statistical approach forecasts the production using a probability distribution of the measured production registered in the past when the weather scenario looked very similar to the forecasted one. The similarity is evaluated for the components of the solar radiation: global (GHI), diffuse (DIF) and direct normal (DNI) irradiation, together with the corresponding azimuth and zenith solar angles. These are, in fact, the main factors that affect the solar production. Considering that the AN performance is strictly related to the length and quality of the historical data a training period of more than one year has been used. The training set is made by historical Numerical Weather Prediction (NWP) forecasts at 12 UTC for the GHI, DIF and DNI variables over the Italian territory together with corresponding hourly measured production for each of the six zones. The AN technique makes it possible to estimate the aggregate solar production in the area, without information about the technologic characteristics of the all solar parks present in each area. Besides, this information is often only partially available. Every day, the hourly solar power forecast for the six Italian market zones is made publicly available through a website.Keywords: analog ensemble, electricity market, PV forecast, solar energy
Procedia PDF Downloads 1456542 Forecasting Models for Steel Demand Uncertainty Using Bayesian Methods
Authors: Watcharin Sangma, Onsiri Chanmuang, Pitsanu Tongkhow
Abstract:
A forecasting model for steel demand uncertainty in Thailand is proposed. It consists of trend, autocorrelation, and outliers in a hierarchical Bayesian frame work. The proposed model uses a cumulative Weibull distribution function, latent first-order autocorrelation, and binary selection, to account for trend, time-varying autocorrelation, and outliers, respectively. The Gibbs sampling Markov Chain Monte Carlo (MCMC) is used for parameter estimation. The proposed model is applied to steel demand index data in Thailand. The root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) criteria are used for model comparison. The study reveals that the proposed model is more appropriate than the exponential smoothing method.Keywords: forecasting model, steel demand uncertainty, hierarchical Bayesian framework, exponential smoothing method
Procedia PDF Downloads 346