Abstract:Background: With the development of smart grids, accurate electric load forecasting has become increasingly important as it can help power companies in better load scheduling and reduce excessive electricity production. However, developing and selecting accurate time series models is a challenging task as this requires training several different models for selecting the best amongst them along with substantial feature engineering to derive informative features and finding optimal time lags, a commonly used input features for time series models. Methods: Our approach uses machine learning and a long short-term memory (LSTM)-based neural network with various configurations to construct forecasting models for short to medium term aggregate load forecasting. The research solves above mentioned problems by training several linear and non-linear machine learning algorithms and picking the best as baseline, choosing best features using wrapper and embedded feature selection methods and finally using genetic algorithm (GA) to find optimal time lags and number of layers for LSTM model predictive performance optimization. Results: Using France metropolitan's electricity consumption data as a case study, obtained results show that LSTM based model has shown high accuracy then machine learning model that is optimized with hyperparameter tuning. Using the best features, optimal lags, layers and training various LSTM configurations further improved forecasting accuracy. Conclusions: A LSTM model using only optimally selected time lagged features captured all the characteristics of complex time series and showed decreased Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) for medium to long range forecasting for a wider metropolitan area.

Short term electric load forecasting plays a crucial role for utility companies, as it allows for the efficient operation and management of power grid networks, optimal balancing between production and demand, as well as reduced production costs. As the volume and variety of energy data provided by building automation systems, smart meters, and other sources are continuously increasing, long short-term memory (LSTM) deep learning models have become an attractive approach for energy load forecasting. These models are characterized by their capabilities of learning long-term dependencies in collected electric data, which lead to accurate prediction results that outperform several alternative statistical and machine learning approaches. Unfortunately, applying LSTM models may not produce acceptable forecasting results, not only because of the noisy electric data but also due to the naive selection of its hyperparameter values. Therefore, an optimal configuration of an LSTM model is necessary to describe the electric consumption patterns and discover the time-series dynamics in the energy domain. Finding such an optimal configuration is, on the one hand, a combinatorial problem where selection is done from a very large space of choices; on the other hand, it is a learning problem where the hyperparameters should reflect the energy consumption domain knowledge, such as the influential time lags, seasonality, periodicity, and other temporal attributes. To handle this problem, we use in this paper metaheuristic-search-based algorithms, known by their ability to alleviate search complexity as well as their capacity to learn from the domain where they are applied, to find optimal or near-optimal values for the set of tunable LSTM hyperparameters in the electrical energy consumption domain. We tailor both a genetic algorithm (GA) and particle swarm optimization (PSO) to learn hyperparameters for load forecasting in the context of energy consumption of big data. The statistical analysis of the obtained result shows that the multi-sequence deep learning model tuned by the metaheuristic search algorithms provides more accurate results than the benchmark machine learning models and the LSTM model whose inputs and hyperparameters were established through limited experience and a discounted number of experimentations.

Time series analysis using long short term memory (LSTM) deep learning is a very attractive strategy to achieve accurate electric load forecasting. Although it outperforms most machine learning approaches, the LSTM forecasting model still reveals a lack of validity because it neglects several characteristics of the electric load exhibited by time series. In this work, we propose a load-forecasting model based on enhanced-LSTM that explicitly considers the periodicity characteristic of the electric load by using multiple sequences of inputs time lags. An autoregressive model is developed together with an autocorrelation function (ACF) to regress consumption and identify the most relevant time lags to feed the multi-sequence LSTM. Two variations of deep neural networks, LSTM and gated recurrent unit (GRU) are developed for both single and multi-sequence time-lagged features. These models are compared to each other and to a spectrum of data mining benchmark techniques including artificial neural networks (ANN), boosting, and bagging ensemble trees. France Metropolitan’s electricity consumption data is used to train and validate our models. The obtained results show that GRU- and LSTM-based deep learning model with multi-sequence time lags achieve higher performance than other alternatives including the single-sequence LSTM. It is demonstrated that the new models can capture critical characteristics of complex time series (i.e., periodicity) by encompassing past information from multiple timescale sequences. These models subsequently achieve predictions that are more accurate.

Due to its dynamics, non-linearity and complexity nature, stock market is inherently difficult to predict. One of the attractive objectives is to predict stock market movement direction by using public sentiments analysis. However, there is an active debate about the usefulness of this approach and the strength of causality between stock market trends and sentiments. The opinions of researchers range from rejecting the relationship to confirming a clear causality between sentiments and trading in stock markets. Nevertheless, many advanced computational methods have adopted sentiment-based features, yet did not attain maturity and performance. In this paper, we are contributing constructively in this debate by empirically investigating the predictability of stock market movement direction using an enhanced method of sentiments analysis. Precisely, we experiment on stock prices history, sentiments polarity, subjectivity, N-grams, customized text-based features in addition to features lags that are used for a finer-grained analysis. Five research questions have been investigated towards answering issues associated with stock market movement prediction using sentiment analysis. We have collected and studied the stocks of ten influential companies belonging to different stock domains in NASDAQ. Our analysis approach is complemented by a sophisticated causality analysis, an algorithmic feature selection and a variety of machine learning techniques including regularized models stacking. A comparison of our approach with other sentiment-based stock market prediction approaches including Deep learning, establishes that our proposed model is performing adequately and predicting stock movements with a higher accuracy of 60%.

No abstract

No abstract

No abstract