DERN: Deep Ensemble Learning Model for Short- and Long-Term Prediction of Baltic Dry Index

A hybrid forecasting model using LSTM and Prophet for energy consumption with decomposition of time series data

For decades, time series forecasting had many applications in various industries such as weather, financial, healthcare, business, retail, and energy consumption forecasting. An accurate prediction in these applications is a very important and also difficult task because of high sampling rates leading to monthly, daily, or even hourly data. This high-frequency property of time series data results in complexity and seasonality. Moreover, the time series data can have irregular fluctuations caused by various factors. Thus, using a single model does not result in good accuracy results. In this study, we propose an efficient forecasting framework by hybridizing the recurrent neural network model with Facebook's Prophet to improve the forecasting performance. Seasonal-trend decomposition based on the Loess (STL) algorithm is applied to the original time series and these decomposed components are used to train our recurrent neural network for reducing the impact of these irregular patterns on final predictions. Moreover, to preserve seasonality, the original time series data is modeled with Prophet, and the output of both sub-models are merged as final prediction values. In experiments, we compared our model with state-of-art methods for real-world energy consumption data of seven countries and the proposed hybrid method demonstrates competitive results to these state-of-art methods.

A Meta-Modeling Power Consumption Forecasting Approach Combining Client Similarity and Causality

Power forecasting models offer valuable insights on the electricity consumption patterns of clients, enabling the development of advanced strategies and applications aimed at energy saving, increased energy efficiency, and smart energy pricing. The data collection process for client consumption models is not always ideal and the resulting datasets often lead to compromises in the implementation of forecasting models, as well as suboptimal performance, due to several challenges. Therefore, combinations of elements that highlight relationships between clients need to be investigated in order to achieve more accurate consumption predictions. In this study, we exploited the combined effects of client similarity and causality, and developed a power consumption forecasting model that utilizes ensembles of long short-term memory (LSTM) networks. Our novel approach enables the derivation of different representations of the predicted consumption based on feature sets influenced by similarity and causality metrics. The resulting representations were used to train a meta-model, based on a multi-layer perceptron (MLP), in order to combine the results of the LSTM ensembles optimally. This combinatorial approach achieved better overall performance and yielded lower mean absolute percentage error when compared to the standalone LSTM ensembles that do not include similarity and causality. Additional experiments indicated that the combination of similarity and causality resulted in more performant models when compared to implementations utilizing only one element on the same model structure.

IoT-Blockchain Enabled Optimized Provenance System for Food Industry 4.0 Using Advanced Deep Learning

Agriculture and livestock play a vital role in social and economic stability. Food safety and transparency in the food supply chain are a significant concern for many people. Internet of Things (IoT) and blockchain are gaining attention due to their success in versatile applications. They generate a large amount of data that can be optimized and used efficiently by advanced deep learning (ADL) techniques. The importance of such innovations from the viewpoint of supply chain management is significant in different processes such as for broadened visibility, provenance, digitalization, disintermediation, and smart contracts. This article takes the secure IoT-blockchain data of Industry 4.0 in the food sector as a research object. Using ADL techniques, we propose a hybrid model based on recurrent neural networks (RNN). Therefore, we used long short-term memory (LSTM) and gated recurrent units (GRU) as a prediction model and genetic algorithm (GA) optimization jointly to optimize the parameters of the hybrid model. We select the optimal training parameters by GA and finally cascade LSTM with GRU. We evaluated the performance of the proposed system for a different number of users. This paper aims to help supply chain practitioners to take advantage of the state-of-the-art technologies; it will also help the industry to make policies according to the predictions of ADL.