The design, operational planning, and integration of wind power plants with other renewables and the grid face challenges attributed to the intermittent nature of wind power generation. Addressing this issue necessitates the development of a smart wind power (and in particular wind speed) forecasting approach. This is a complex task due to substantial fluctuations in wind speed. To overcome the inherent stochastic nature of wind speed and mitigate related challenges, traditionally, numerical weather prediction (NWP) models are employed for wind speed forecasting. However, the applicability of NWP models is limited to short-term forecasting due to their computational constraints. In this study, a hybrid AI-based approach is proposed to improve forecast accuracy over a 48 h horizon for the city of Montreal. The results demonstrate that by integrating the probability distribution of wind speed with a deep learning model, the forecasted values align closely with the observed values in terms of seasonality and trend, exhibiting enhanced accuracy. Evaluation metrics reveal a substantial reduction in the root mean squared error (13–31%) across three prediction horizons (summer, fall, and winter) compared to a single long, short-term memory model. Furthermore, integrating the improved model with the numerical weather prediction model yields increased accuracy and decreased error compared to the LSTM–Weibull model.

Building decarbonization is a major challenge for cities. Deciding which buildings to retrofit buildings, and when and how, is difficult, given the complex interaction between energy costs and investment requirements. Several tools have been developed in recent years to help public and private stakeholders with these decisions, but none cover aspects the authors think are fundamental. For this reason, an urban buildings retrofit tool was developed and is presented in this article. This new tool is based on a bottom-up approach, with all buildings simulated individually, considering aspects such as shading and adjacencies. As a second step, three scenarios with different levels of ambition were implemented in the tool, and the energy demand and emissions resulting from these scenarios were calculated. As a third step, the retrofitting scenarios’ initial investment and operational costs were implemented using a detailed Life Cycle Costing (LCC) approach. A robust and scalable structure was developed and applied to calculate the LCC of various retrofitting scenarios in Montréal, which will be described in detail.

Biogas technology is an important alternative energy source worldwide. Blackwater and kitchen refuse represent ideal waste streams for bioenergy recovery through anaerobic co-digestion. Modeling of the biokinetics of anaerobic digestion on several aspects, such as microbial activity, substrate degradation, and methane production, from co-digestion of black water (BW) and kitchen refuse (KR) was the objective of this research. A mathematical model was developed towards a simulation based on mass balances on biomass, the organic substrate, and biogas. The model was implemented in INSEL and experimental data from the literature were used for model validation. The study shows that the simulation results fit well with the experimental data. The energy consumption and generation potential of anaerobic co-digestion of BW and KR were calculated to investigate if the produced biogas could supply the digester’s energy demand. This study can be used to pre-design anaerobic digestion systems in eco-districts.

Many key studies in recent times have proposed integration of renewable energy and transition to 100% renewable energy as a solution to tackling climate change. However, there is little consensus and a wide range of assumptions made across the various studies. This study attempts to draw the most reliable set of parameters identified and numbers available from reputed sources and use them to provide incisive insights on the impact of Renewable Energy (RE) integration towards climate change mitigation with special attention paid to the speed of implementation, EROI of the sources utilized, associated carbon emissions and the resulting temperature increase. These are studied across pathways suggested within literature and contrast them for pessimistic, neutral and optimistic transformation scenarios. The temporal impacts of the transition over time, from today to 2100 have been elaborated upon. Results across the board show the difficulty in achieving 100% renewable energy integration and their consequent impact on the temperature increases, a large majority of them failing to stop at the oft-quoted 1.5 °C mark. These results underline the difficulty of the task at-hand, especially if decarbonisation and temperature increase goals are to be successfully met.