Application of a modified perceptron learning algorithm to monitoring and control

Zambia has faced economic challenges since the beginning of 2015. The economy has come under strain in 2015 due to climate change. As a result, the water levels in the main source of electricity, the Kariba Dam, have dropped. This has caused a critical power deficit. This problem has negatively affected the economy and has further resulted in reduced GDP for the country. Solar energy is a possible alternative to mitigate this crisis. Despite government efforts in embracing renewable solar energy, the current photovoltaic (PV) systems require additional mechanisms to monitor and control individual appliances. In this paper, we propose a system that uses a modified perceptron-learning algorithm to control and monitor individual appliances. The proposed system is capable of finding the best combination of household appliances that optimizes user priorities and limits the power consumed from the grid. The algorithm has also been shown to be computationally efficient.