In this paper, a comprehensive review of essential components of the PV (Photovoltaic) system is elaborated, and their comparative unique features are discussed. The paper describes hardware design (power converters topologies specifically) employed in PV based energy generation systems to harvest maximum power from the available energy source. In this study, thirty different Maximum Power Point Tracking (MPPT) techniques have been critically analyzed and their response with respect to partial shading condition has been discussed. It is very difficult to say which technique is best as one must consider various factors and parameters while selecting a technique such as application, convergence speed, accuracy, efficiency, system reliability, and cost and performance of available hardware. Aiming at the complexity, hardware implementation, tracking speed, steady-state accuracy, or global maximum detection of the algorithm, an MPPT algorithm based on a rule table is proposed. In addition, the MPPT of a PV system based on bio inspired techniques is considered. The bio inspired algorithms and its application in PV system are compared for the authenticity of the review, and six different MPPT techniques are implemented on PV systems. A comparative analysis is made based on the results of four different cases of irradiance.

Load forecasting is useful for various applications, including maintenance planning. The study of load forecasting using recent state-of-the-art hybrid artificial intelligence (AI) and deep learning (DL) techniques is limited in South Africa (SA) and South African power distribution networks. This paper proposes a novel hybrid AI and DL South African distribution network load forecasting system. The system comprises of modules that handle the collection of the loading data from the field, analysis of data integrity using fuzzy logic, data preprocessing, consolidation of the loading and the temperature data, and load forecasting. The load forecasting results are then used to inform maintenance planning. The load forecasting is conducted using a hybrid AI/DL load forecasting module. A novel comparative study of recent state-of-theart AI techniques is also presented to determine the best technique to deploy in this module when forecasting South African power redistributing customers' loads. The impact of the inclusion of weather parameters and loading data clean up on the load forecasting performance of a hybrid AI technique, optimally pruned extreme learning machines (OP-ELM), and a deep learning technique, long short-term memory (LSTM), is also investigated. These techniques are compared with each other and also with a commonly used powerful hybrid AI technique, adaptive neuro-fuzzy inference system (ANFIS). LSTM was found to achieve higher load forecasting accuracies than ANFIS and OP-ELM in forecasting the two distribution customers' loads in this paper. Only the LSTM models' performance improved with the inclusion of temperature in their development.INDEX TERMS Adaptive neuro-fuzzy inference systems, artificial intelligence, deep learning, distribution networks, extreme learning machines, load forecasting, recurrent neural networks, long short-term memory.

No abstract

No abstract

No abstract