Within smart grids, end-users often seek to reduce electricity costs using a home energy management system, while the power utility aims to optimize the grid operation. This article proposes a novel three-level framework to tackle the contradictory nature of the objectives of end-user and distribution system operators (DSOs) by upward and downward flexibility provision. In addition, the proposed method designs a novel incentive program based on the flexibility provided by the end-users. Then, the aggregated flexibility is offered to the DSO. The model takes advantage of the local flexibility of home appliances to re-schedule their use based on the flexibility request from the DSO. The aggregator provides incentive programs based on the flexibility provided by the prosumers to reduce/shift energy consumption. The proposed methodology considers the alignment of the conflicting techno-economic objectives of the prosumers and system operators. The results show that our proposed strategy has increased the monetary benefits for prosumers for their flexibility services provided to the DSO compared to other scenarios. Moreover, the proposed method improves the voltage profiles and reduces the peak load and power losses by 20.8% and 24.6%, respectively, of the overall system.
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.
Decarbonizing buildings is crucial in addressing pressing climate change issues. Buildings significantly contribute to global greenhouse gas emissions, and reducing their carbon footprint is essential to achieving sustainable and low-carbon cities. Retrofitting buildings to become more energy efficient constitutes a solution. However, building energy retrofits are complex processes that require a significant number of simulations to investigate the possible options, which limits comprehensive investigations that become infeasible to carry out. Surrogate models can be vital in addressing computational inefficiencies by emulating physics-based models and predicting building performance. However, there is a limited focus on investigating feature engineering and selection methods and their effect on the model’s performance and optimization. Feature selection methods are considered effective with interpretable models such as multi-variate linear regression (MVLR) and multiple adaptive regression splines (MARS) for achieving stable prediction stability. This study proposes a modelling framework to create, optimize, and improve the performance of surrogate predictive models for energy consumption, carbon emissions, and the associated cost of building energy retrofit processes. The investigated feature selection methods are wrapper and embedded methods such as backward-stepwise feature selection (BSFS), recursive feature elimination (RFE), and Elastic Net embedded regularization in order to provide insights into the model’s behavior and optimize the model’s performance. The most accurate surrogate models developed achieved a mean absolute percentage error (MAPE) of 0.2–1.8% compared to the used test data. In addition, when calculated for a million samples, all developed surrogate models reduced the computational time by one-thousand-fold compared to physics-based models. The study’s findings pave the way towards low-computational accurate models that can comprehensively predict building performance in near real-time, ultimately leading to identifying decarbonization measures at scale.
Buildings consist of systems that have to interact and coordinate with various systems to function smoothly. It is essential to have models and representations of buildings in forms that are easy to read for effective simulation, control, and optimization of building systems. It is also necessary for integrating and creating novel applications and functions. A Building Energy Management System (BEMS) is a common feature of most commercial buildings. It contains models of some aspects of the building and its systems. However, these models in the BEMSs do not entirely model all systems and subsystems and their relationships because their primary function is to control heating, ventilation, air-conditioning (HVAC), and lighting. Project Haystack and Brick have made significant progress in modelling buildings for operational purposes by adopting a metadata approach. They offer machine and human-readable representations of buildings, systems, and their relationships. However, tags and tagsets in the metadata approach have some limitations that stem from a weak structure in defining entities, their properties, and relationships. In this study, we identify seven problems with the metadata approach to modelling buildings and address these problems with an object-oriented metamodel: Metamodel for Energy Things (MetamEnTh). Using an object-oriented modelling technique to establish structure and constraints, MetamEnTh produces a model that portrays a building and its systems. MetamEnTh adheres to the same naming convention of entities as other projects like Project Haystack and Brick. We accomplish a UML representation of the core structure of MetamEnTh and validate the representation through three different case studies.
The concept of Positive Energy Districts (PEDs) has emerged as a promising approach to achieving sustainable urban development. PEDs aim to balance the energy demand and supply within a district while reducing the carbon footprint and promoting renewable energy sources. Urban–Industrial Symbiosis (UIS) is another approach that involves the exchange of energy and resources between industrial processes and nearby urban areas to increase efficiency and reduce waste. Combining the concepts of PED and UIS can create self-sufficient, sustainable, and resilient districts. As the analysis and implementation of such systems are barely studied in North America, this research study was structured to fill the gap by evaluating the financial and environmental advantages of this combination. This study proposes a methodology to design a heat transmission system; then, it is applied to the case of a paper-making factory and a multifunctional heritage building in Montreal, Canada. The results show that the building’s new heating system can generate sufficient heat while emitting near-zero direct emissions. Overall, this paper argues that combining the concepts of PED and UIS can lead to a more sustainable and resilient urban area, and provides a roadmap for achieving this goal.