Navid Shirzadi

Accurate energy demand prediction is essential for effective control of energy consumption and generation, enabling optimal energy management and reducing emissions. This study introduces a hybrid model integrating a physics-based EnergyPlus simulation with a long short-term memory (LSTM) neural network to enhance energy demand forecasting for buildings. While physics-based models offer computational efficiency, they often result in significant discrepancies between predicted and actual energy demand. Conversely, LSTM models improve prediction accuracy but struggle with peak forecasting. The proposed hybrid approach leverages the strengths of both methods, combining simulation outputs with LSTM predictions to reduce the normalized mean absolute error (NMAE) and improve peak predictions. A feature importance algorithm is incorporated to identify key variables, such as water heater cycle on count, that influence peak values during the LSTM training process. The hybrid model demonstrates a 5% and 20% reduction in normalized root mean square error (NRMSE) compared to the standalone LSTM and simulation models, respectively, during the warmest week of summer. Slight improvements are also observed during winter, with NRMSE reductions of 3% and 11% for the coldest week. Additionally, the hybrid model outperforms the single LSTM in predicting peak energy demand across various thresholds, as evidenced by superior F 1-scores, precision and recall. While the model is less effective during certain winter periods, its overall robustness in predicting peaks and valleys across seasonal variations underscores its utility for real-world applications.

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.

Microgrids (MGs) can be used as a solution to ensure resilience against power supply failures in electricity grids caused by extreme weather conditions, unavailability of generation capacities, and problems with transmission components. The literature is rich in research focusing on strengthening the planning of microgrids based on overall load demand. In this study, a critical load demand indicator will be calculated and used to identify optimum operation strategies of microgrids in a power failure mode. An urban microgrid with a large educational building is selected for the case study. Operation dispatch scenarios are developed to reinforce the system’s resiliency in severe conditions. A mixed-integer linear programming (MILP) approach is employed to identify global optimum dispatch solutions based on a next 48 h plan for different seasons to formulate a whole-year operational model. The results show that the loss of power supply probability (LPSP), as an indicator of resiliency, could be lowered to near zero while minimizing operational cost.

This paper proposes an original multi-criteria decision-making optimization algorithm to select the best solar panels in an existing market and optimally size the photovoltaic (PV) system for an electric vehicle parking lot (EVPL). Our proposed algorithm is called rank-weigh-rank (RWR), and it is compared to the well-known technique for order of preference by similarity to ideal solution (TOPSIS) optimization algorithm under the same conditions for validation purposes. Results show that the speed of our proposed algorithm (RWR) in finding the best solution increases exponentially compared to TOPSIS when the numbers of alternatives and criteria increase. Moreover, 77% is the probability of obtaining results with more than 80% accuracy compared to TOPSIS, which validates the efficiency of our algorithm. In addition, we were able to design an EVPL with a power self-sufficiency ratio of 60.8%, the energy self-sufficiency ratio of 74.7%, and a payback period of 10.58 years. Moreover, the renewable energy-based EVPL was able to reduce the power losses on the network by 95.7% compared to an EVPL without a renewable energy system and improve the voltage deviation.

Due to severe climate change impact on electricity consumption, as well as new trends in smart grids (such as the use of renewable resources and the advent of prosumers and energy commons), medium-term and long-term electricity load forecasting has become a crucial need. Such forecasts are necessary to support the plans and decisions related to the capacity evaluation of centralized and decentralized power generation systems, demand response strategies, and controlling the operation. To address this problem, the main objective of this study is to develop and compare precise district level models for predicting the electrical load demand based on machine learning techniques including support vector machine (SVM) and Random Forest (RF), and deep learning methods such as non-linear auto-regressive exogenous (NARX) neural network and recurrent neural networks (Long Short-Term Memory—LSTM). A dataset including nine years of historical load demand for Bruce County, Ontario, Canada, fused with the climatic information (temperature and wind speed) are used to train the models after completing the preprocessing and cleaning stages. The results show that by employing deep learning, the model could predict the load demand more accurately than SVM and RF, with an R-Squared of about 0.93–0.96 and Mean Absolute Percentage Error (MAPE) of about 4–10%. The model can be used not only by the municipalities as well as utility companies and power distributors in the management and expansion of electricity grids; but also by the households to make decisions on the adoption of home- and district-scale renewable energy technologies.

Although renewable technologies are progressing fast, there are still challenges such as the reliability and availability of renewable energy sources and their cost issues due to capital intensity that hinder their broad adoption. This research aims at developing a configuration-sizing approach to enhance the cost efficiency and sourcing reliability of renewable energies integrated in microgrids. To achieve this goal, various technologies were considered, such as solar PV, wind turbines, converters, and batteries for system configuration with minimization of net present cost (NPC) as the objective. Grid connection scenarios with up to 100% renewable contribution were analyzed. The results show that the integration of renewable technologies with some grid backup could reduce the levelized cost of energy (LCOE) to about half of the price of the electricity that the university purchases from the grid. Also, different kinds of solar tracker systems were studied. The outcome shows that by using a vertical axis solar tracker, the LCOE of the system could be reduced by more than 50 percent. This research can help the decision-maker to opt for the best scenarios for generating reliable and cost-efficient electricity.