This study investigates the techno-economic impacts of various pricing policies on a photovoltaic (PV) system combined with battery energy storage (BES) as a single integrated system within a Dutch residential building. With the increasing adoption of PV systems, managing reverse power flow and grid stability becomes crucial. The study evaluates different scenarios, including net metering, feed-in tariffs (FiT) with time-of-use (TOU), RTP pricing, and subsidised BES. Using a multi-objective genetic algorithm, the optimal size and charging/discharging patterns of the PV-BES system were determined. The optimisation simultaneously minimises the Net Present Cost (NPC) and maximises the Self-Consumption Rate (SCR), to determine the PV-BES size that achieves an optimal balance between economic and technical performance. Results indicate that RTP pricing significantly enhances SCR. While the levelised cost of electricity (LCOE) and payback periods (PBP) are initially higher in the RTP pricing scenario, subsidising BES can mitigate these disadvantages. Additionally, incorporating price limit control variables into the energy management system (EMS) optimises the charging/discharging cycles, extending BES lifetimes and potentially increasing future revenues. These findings provide insights for policymakers to balance economic benefits and grid technical requirements through effective PV-BES integration.

The widespread adoption of solar photovoltaic (PV) technology as a prominent renewable energy source has significant implications for the economy of households and distribution system operators (DSOs). It is crucial to analyse these impacts in light of recent pricing policy changes, including Real-Time Pricing (RTP), Time-of-Use (TOU), and Feed-in Tariffs (FiT). This study analyses the impact of pricing policies based on actual load consumption, pricing rate, and PV generation data. An economic comparison of various scenarios for a typical household in the Netherlands is conducted by determining the optimal values for PV size. The findings suggest that transitioning to RTP policies reduces households’ economic advantages. The introduction of FiT further diminishes the financial benefits for households and increases the Payback period (PP). Moreover, the study reveals that imposing an export power limit of less than 3 kW can increase households’ energy costs.

Forecasting energy consumption is vital for smart grid operations to manage demand, plan loads, and optimize grid operations. This work aims at reviewing and experimentally evaluating six univariate deep learning architectures to forecast load for a single household using a real-world dataset. Multi-layer perceptron (MLP), Convolutional neural network (CNN) and recurrent neural networks (Simple RNN, Long Short Term Memory (LSTM)) were the neural network methods that were analysed along with robust LSTM architectures like Bidirectional LSTM and CNN-LSTM Hybrid. All the models were tuned using Bayesian optimization and evaluated using root mean squared error (RMSE) as the metric. In addition to neural network models, Seasonal ARIMA (SARIMA) a statistical model is also presented to observe the performance. As a result, Bi-directional LSTM was observed to have achieved the best performance with the smallest value of RMSE; however, it was also observed that differences in performances between other neural network models were quite low, especially between the RNN architectures. Additionally, although machine learning methods performed better than SARIMA the former model was more complex and computationally intensive.

The parabolic growth rate constant (k_p) of high-temperature oxidation of steels is predicted via a data analytics approach. Four machine learning models including Artificial Neural Networks, Random Forest, k-Nearest Neighbors, and Support Vector Regression are trained to establish the relations between the input features (composition and temperature) and the target value (k_p). The models are evaluated by the indices: Mean Absolute Error, Mean Squared Error, Root Mean Squared Error and Coefficient of Determination. The steel composition regarding Cr and Ni content and the temperature were the most significant input features controlling the oxidation kinetics.