No abstract

Photovoltaic energy production is an important factor for increasing the electricity supply. The ability to predict the electric power production (EPP) of a photovoltaic (PV) farm supports from the management process of the power grid to the trade in the energy market and much more. Also, by predicting the production of PV power (PVP), it is possible to monitor the lifetime of the solar cells that form the backbone of any solar PV system. As a critical result, sudden failures of the PV plant can be avoided. Using a long short-term memory recurrent neural network (LSTM-RNN) model, this work evaluates the prediction accuracy of two forecasting strategies: the recursive strategy and the non-recursive Multiple-Input and Multiple-Output, respectively. The dataset consists of 5-years in-filed production data measurements collected from the CETATEA photovoltaic power plant, a research site facility for renewable energies located in Cluj-Napoca, Romania. The high granularity of the electric power production dataset values recorded each 1 hour guarantees the overall prediction accuracy of the system. The impact of the dataset size, the number of previous observations, and the forecast horizon on the neural network prediction accuracy is evaluated for each strategy. The performance metrics used to evaluate the prediction accuracy are the root mean square error, the mean bias error, and the mean average error. The results analysis demonstrates the ability of the implemented machine learning models to predict electric power production, as well as their importance in the energy loss management process.

No abstract

In industrial wireless sensors networks (IWSNs), the sensor lifetime predictability is critical for ensuring continuous system availability, cost efficiency and suitability for safety applications. When deployed in a real-world dynamic and centralised network, the sensor lifetime is highly dependent on the network topology, deployment configuration and application requirements. (In the absence of an energy-aware mechanism, there is no guarantee for the sensor lifetime). This research defines a conceptual model for enhancing the energy predictability and efficiency of IWSNs. A particularization of this model is the predictive energy-aware routing (PEAR) solution that assures network lifetime predictability through energy-aware routing, energy balancing and profiling. The PEAR solution considers the requirements and constraints of the industrial ISA100.11a communication standard and the VR950 IIoT Gateway hardware platform. The results demonstrate the PEAR ability to ensure predictable energy consumption for one or multiple network clusters. The PEAR solution is capable of intracluster energy balancing, reducing the overconsumption 10.4 times after 210 routing changes as well as intercluster energy balancing, increasing the cluster lifetime 2.3 times on average and up to 3.2 times, while reducing the average consumption by 23.6%. The PEAR solution validates the feasibility and effectiveness of the energy-aware conceptual indicating its suitability within IWSNs having real world applications and requirements.

No abstract