In this paper, a hybrid electricity price forecasting method which is composed of two-stage feature selection method and optimized adaptive neuro-fuzzy inference system (ANFIS) technique as a forecasting engine is proposed to accurately forecast electricity price. A multi-objective feature selection approach comprises of multi-objective binary-valued backtracking search algorithm (MOBBSA) as an efficient evolutionary search algorithm and ANFIS method is developed in this paper to extract the most influential subsets of input variables with maximum relevancy and minimum redundancy. Through the combination of backtracking search algorithm (BSA) in learning process of ANFIS approach, a hybrid machine learning algorithm has been developed to forecast the electricity price more accurately. Real-world electricity demand and price dataset from Ontario power market; which is reported as among the most volatile market worldwide, has been used as case study to validate the performance of the proposed approach. From the simulation results, it has been seen that the proposed hybrid forecasting method was effective in accurately forecast the Ontario electricity price. In addition, to prove the superiority of the proposed hybrid forecasting method the simulation results obtained using ANN and ANFIS models optimized by other well-known optimization methods have been compared with that of proposed method.INDEX TERMS Adaptive neuro-fuzzy inference system, backtracking search algorithm, electricity price forecasting, feature selection.

Technology advancement for renewable energy resources and its integration to the distribution network (DN) has garnered substantial interest in the last few decades. Integrating such resources has proven to reduce power losses and improve the reliability of DN. However, the growing number of these resources in DN has imposed additional operational and control issues in voltage regulation, system stability, and protection coordination. Incorporation of various types of distributed generators (DG) into DN causes significant changes in the system. These including new fault current sources, new fault levels, a blinding effect in the protection scheme, reduction in the reach of relays, and decrement in the detection of lowlevel fault currents for existing relays. Such changes will jeopardize the effectiveness of the entire protection scheme in the DN. This research aims to propose a robust protection scheme in which the relay coordination settings are optimized based on the network layout. The potential impacts of DGs on the DN are mitigated by utilizing a user-defined overcurrent-based relay characteristic to obtain the minimum operating time while satisfying protection coordination constraints. A hybrid optimization algorithm based on Metaheuristic and Linear Programming that has the capability to attain the optimal solution and reduces computational time is proposed in this work. The performance of the proposed technique is tested on radial DN integrated with microgrid (MG). The results obtained show the proposed technique has successfully reduced the relay operating time while meeting the protection coordination requirements for dynamic operating modes of a network.

Smart grid has evolved into a viable platform for participants of electricity market to effectively regulate their bidding strategies based on demand-side management (DSM) models ascribed to its immense technological advancements in recent years. Reliability of system operation as well as capital cost investments can improve greatly with responsiveness of market participants. In this regard, efficient design, implementation, evaluation of numerous demand response measures and development of robust short-term price forecasting in the day-ahead transactions are of the utmost importance. Accuracy and efficiency of the day-ahead price forecasting process are complex challenges in deregulated electricity market. The unstable nature of electricity price compared to load series causes lower accuracy. Therefore, this research proposes a hybrid method for electricity price forecasting via artificial neural network (ANN) and artificial cooperative search algorithm (ACS). In parallel, a feature selection technique based on the combination of mutual information (MI) and neural network (NN) is developed in this study to select the input variables subsets, which have substantial impact on forecasting of electricity price. Actual data sets are collected from Ontario electricity market of the year 2017 for the verification of simulation results. Finally, the simulation results validated the premise of the proposed hybrid method through enhanced accuracy compared to the results acquired by implementing hybrid support vector machine (SVM) and hybrid ANN optimization methods.

In recent years significant changes in climate have pivoted the distribution system towards renewable energy, particularly through distributed generators (DGs). Although DGs offer many benefits to the distribution system, their integration affects the stability of the system, which could lead to blackout when the grid is disconnected. The system frequency will drop drastically if DG generation capacity is less than the total load demand in the network. In order to sustain the system stability, under-frequency load shedding (UFLS) is inevitable. The common approach of load shedding sheds random loads until the system’s frequency is recovered. Random and sequential selection results in excessive load shedding, which in turn causes frequency overshoot. In this regard, this paper proposes an efficient load shedding technique for islanded distribution systems. This technique utilizes a voltage stability index to rank the unstable loads for load shedding. In the proposed method, the power imbalance is computed using the swing equation incorporating frequency value. Mixed integer linear programming (MILP) optimization produces optimal load shedding strategy based on the priority of the loads (i.e., non-critical, semi-critical, and critical) and the load ranking from the voltage stability index of loads. The effectiveness of the proposed scheme is tested on two test systems, i.e., a 28-bus system that is a part of the Malaysian distribution network and the IEEE 69-bus system, using PSCAD/EMTDC. Results obtained prove the effectiveness of the proposed technique in quickly stabilizing the system’s frequency without frequency overshoot by disconnecting unstable non-critical loads on priority. Furthermore, results show that the proposed technique is superior to other adaptive techniques because it increases the sustainability by reducing the load shed amount and avoiding overshoot in system frequency.