A major challenge of today’s society is to make large urban centres more sustainable. Improving the energy efficiency of the various infrastructures that make up cities is one aspect being considered when improving their sustainability, with Wastewater Treatment Plants (WWTPs) being one of them. Consequently, this study aims to conceive, tune, and evaluate a set of candidate deep learning models with the goal being to forecast the energy consumption of a WWTP, following a recursive multi-step approach. Three distinct types of models were experimented, in particular, Long Short-Term Memory networks (LSTMs), Gated Recurrent Units (GRUs), and uni-dimensional Convolutional Neural Networks (CNNs). Uni- and multi-variate settings were evaluated, as well as different methods for handling outliers. Promising forecasting results were obtained by CNN-based models, being this difference statistically significant when compared to LSTMs and GRUs, with the best model presenting an approximate overall error of 630 kWh when on a multi-variate setting. Finally, to overcome the problem of data scarcity in WWTPs, transfer learning processes were implemented, with promising results being achieved when using a pre-trained uni-variate CNN model, with the overall error reducing to 325 kWh.

The evolution of Mobile Networks and Internet of Things (IoT) architectures allows one to rethink the way smart cities infrastructures are designed and managed, and solve a number of problems in terms of human mobility. The territories that adopt the sensoring era can take advantage of this disruptive technology to improve the quality of mobility of their citizens and the rationalization of their resources. However, with this rapid development of smart terminals and infrastructures, as well as the proliferation of diversified applications, even current networks may not be able to completely meet quickly rising human mobility demands. Thus, they are facing many challenges and to cope with these challenges, different standards and projects have been proposed so far. Accordingly, Artificial Intelligence (AI) has been utilized as a new paradigm for the design and optimization of mobile networks with a high level of intelligence. The objective of this work is to identify and discuss the challenges of mobile networks, alongside IoT and AI, to characterize smart human mobility and to discuss some workable solutions to these challenges. Finally, based on this discussion, we propose paths for future smart human mobility researches.

Traffic flow forecasting is an acknowledged time series problem whose solutions have been essentially grounded on statistical-based models. Recent times came, however, with promising results regarding the use of Recurrent Neural Networks (RNNs), such as Long Short-Term Memory networks (LSTMs), to accurately address time series problems. Literature is, however, evasive in regard to several aspects of the conceived models and often exhibits misconceptions that may lead to important pitfalls. This study aims to conceive and find the best possible LSTM model for traffic flow forecasting while addressing several important aspects of such models such as the multitude of input features, the time frames used by the model and the employed approach for multi-step forecasting. To overcome the spatial problem of open source datasets, this study presents and describes a new dataset collected by the authors of this work. After several weeks of model fitting, Recursive Multi-Step Multi-Variate models were the ones showing better performance, strengthening the perception that LSTMs can be used to accurately forecast the traffic flow for several future timesteps.