Reliability is an essential factor in distribution networkt expansion planning. However, standard distribution reliability assessment techniques rely on quantifying the impact of a pre-specified set of events on service continuity through the simulation of component outages, one at a time. Due to such a simulation-based nature, the incorporation of reliability into distribution network expansion planning has customarily required the application of heuristic and metaheuristic approaches. Recently, alternative mixed-integer linear programming (MILP) models have been proposed for distribution network expansion planning considering reliability. Nonetheless, such models suffer from either low computational efficiency or over-simplification. To overcome these shortcomings, this paper proposes an enhanced MILP model for multistage reliability-constrained distribution network expansion planning. Leveraging an efficient, yet accurate reliability evaluation model, proposing a customized technique for effectively imposing radial operation, as well as utilizing pragmatic measures to model reliability-related costs are the salient features of this work. In this respect, practical reliability-related costs are considered based on reliability incentive schemes and the revenue lost due to undelivered energy during customer outages. The proposed planning approach is tested on four networks with 24, 54, 86, and 138 nodes to illustrate its efficiency and applicability.

Machine learning is a subcategory of artificial intelligence, which aims to make computers capable of solving complex problems without being explicitly programmed. Availability of large datasets, development of effective algorithms, and access to the powerful computers have resulted in the unprecedented success of machine learning in recent years. This powerful tool has been employed in a plethora of science and engineering domains including mining and minerals industry. Considering the ever-increasing global demand for raw materials, complexities of the geological structure of ore deposits, and decreasing ore grade, high-quality and extensive mineralogical information is required. Comprehensive analyses of such invaluable information call for advanced and powerful techniques including machine learning. This paper presents a systematic review of the efforts that have been dedicated to the development of machine learning-based solutions for better utilizing mineralogical data in mining and mineral studies. To that end, we investigate the main reasons behind the superiority of machine learning in the relevant literature, machine learning algorithms that have been deployed, input data, concerned outputs, as well as the general trends in the subject area.

This paper aims at proposing a mixed-integer linear formulation to incorporate reliability oriented costs into the expansion planning model of electricity distribution networks. In this respect, revenue lost associated with the undelivered energy caused by network interruptions, as well as costs incurred by the widely-used reward-penalty regulations are considered as the major reliability related costs from distribution companies point of view. A set of mixed-integer linear equations is proposed to calculate the most common distribution system reliability indices, i.e. EENS, SAIFI, and SAIDI. It is found that these equations can also facilitate the formulation of radiality constraint in the presence of DG units. Moreover, application of the proposed method is investigated through various case studies performed on two test distribution networks with 24 and 54 nodes.

This paper presents a mixed-integer linear stochastic model for optimal expansion planning of electricity distribution networks and distributed generation (DG) units. In the proposed framework, autonomous DG units are aggregated and modeled using the well-known energy hub concept. In this model, uncertainties of heat and electricity demand as well as renewable generation are represented using various scenarios. Although this is a standard technique to capture the uncertainties, it drastically increases the dimensions of this optimization problem and makes it practically intractable. In order to address this issue, a novel iterative method is developed in this paper to enhance the efficiency of the optimization model. The proposed framework is further utilized to assess the benefits of the collaborative distribution network and autonomous DG planning through various case studies performed on the 24-node distribution test grid. With 5.93% cost reduction, the obtained results indicate the importance of such collaborations in reaching an efficient network expansion solution. Moreover, total planning cost for the stochastic model is 1.23% lower than the deterministic case. Various sensitivity analyses are also carried out to investigate the impacts of parameters of the proposed model on the optimal planning solution. Scalability of the model is also assessed by its implementation on the 54-node distribution test network.

Home energy management (HEM) systems optimize electricity demand of appliances according to the price-based demand response (DR) programs. Undoubtedly, customer satisfaction is of such importance that if not taken into consideration, it prevents customers from participating in the DR. HEM systems suffer from high nonlinearity due to the variety of smart appliances and different criteria for customer satisfaction. In this paper, an advanced satisfaction-based HEM system using deep reinforcement learning is proposed to hourly schedule the controllable and time-shiftable appliances, including electric vehicle, air conditioner, and lighting system as controllable loads and washing machine, and dishwasher as time-shiftable loads. The proposed framework deploys a Deep Q-Network (DQN) method. Regarding customer dissatisfaction, this paper takes into consideration nonlinear precise functions. The Kano model for EV departure SoC, charging duration and lighting system satisfaction, desired temperature span for air conditioner, and the desirable operation period, waiting time, and consecutive mode of dishwasher and washing machine are taken into account. The proposed HEM system is applied to a smart home, and the results are compared with those of the Q-Learning algorithm. Numerical results prove the effectiveness of the proposed HEM system in reducing electricity cost and customer dissatisfaction, and the superiority of DQN over Q-Learning as well.