Electric Vehicles (EVs) are gaining more and more popularity in today’s world due to their exceptional advantages. Effective planning is required to carry out EV charging smoothly, as the random charging process could lead to problems like transformer overloading and increased feeder energy losses. The proposed work includes the implementation of a G2V scheme for smart charging of vehicles with charging cost minimization and V2G technology into the distribution network to support grid voltage. An IEEE 33 bus distribution network is used as the test system for evaluating the proposed smart charging strategy. The main objective is to minimize the overall charging costs for EVs. It is done by developing an objective function that considers various cost factors associated with EV charging. Vehicle-to-grid (V2G) technology is incorporated into the system to allow EVs to discharge energy back to the grid when needed. This bi-directional energy flow supports grid voltage regulation and enhances the overall stability of the distribution network. Linear programming is employed to solve the objective function. This mathematical approach is chosen for its effectiveness in handling linear constraints and objective functions, ensuring an optimal solution for cost minimization.

Forecasting is a process in which future demand is predicted with the help of past and current data. Uncertainty in real-world data makes this forecasting process challenging. Short-term load forecasting for individual electric customers is necessary to forecast future demand at the residential level. It has been observed that many loads forecasting approaches that are good for grid or substation load forecasting don’t fit the residential load forecasting problems. So, it will be implicated on the residential level. Recurrent Neural Network (RNN), Artificial Neural Network (ANN), Adaptive Network-based Fuzzy Interference System (ANFIS), Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) Neural Network are some of the forecasting methods. In this paper, the ANFIS method will forecast the residential level. Weather factor (temperature, pressure, humidity, wind speed, etc.) is considered for better prediction. Forecasting is done for 24 h, and demand at a different time is observed. It is compared with the ANN method.

The electricity prices find wide applications in the present electricity markets. Generation companies use the forecasted electricity prices to plan their expenses, which helps the aggregator provide better consumer services. The market players also use it to strategize selling electricity to the distribution companies in the energy exchange market. The forecasted electricity prices are also used to implement Demand Response (DR) programs. DR programs reduce peak demand, which can be achieved by scheduling the loads. All these applications require accurate forecasting of electricity prices, but its volatile nature makes it challenging to make accurate predictions. Electricity price forecasting on hourly basis is presented using the Long Short Term Memory (LSTM) Neural Network model. LSTM model can extract highly complex relationships between parameters. It uses feedback property to predict electricity prices accurately. The proposed model predicts the prices based on the historical hourly prices, historical load demand data, and other quantities on which the prices depend. The accuracy of the model is compared with other baseline models. The model comes out to be the most accurate of all and has the lowest Mean Absolute Percentage Error (MAPE) and the highest R2 value.

To meet the targets of the Paris agreement and to offset the depleting reserves of conventional sources of energy, there has been a significant push for renewables, particularly Solar and Wind. Since the energy output from a solar unit is highly unpredictable and depends on the weather parameters such as temperature, cloud cover, humidity, angle of incidence, etc. the power output varies with changing conditions. Therefore, forecasting the available energy in advance is important to maintain a balance between the power supply and demand. This paper uses the artificial neural network (ANN) model for forecasting the solar energy availability, and it is more accurate as compared to existing models of linear regression (LR) and support vector machine (SVM) used for forecasting.