• High peak load demand

• High distribution cost at peak load

• Load scheduling with consumers’ consent

Solving these problems can be beneficial for both Distribution Companies(DISCOMs) and customers

Utilizing electricity tariffs, monetary incentives, and government regulations to :-

• Mitigate the peak load demand
• Reduce overall distribution cost
• Maximize the use of renewable energy and battery storage

• It is a population based stochastic optimization technique
• Each particle contains records of their best fitness value, P_best, and the best fitness value of the entire swarm, G_best
• At each iteration we calculate fitness value of a bird and then compare it with Global P_best and G_best to update them if required.
• The swarm will move towards best solutions by minimizing objective function

• Day ahead load price

• Forecasted Load data

• Optimisation Function : We take it to be inverse of Day a head load price

• PSO Parameters : velocity_clamping_factor, individual learning rate, social parameter, etc.

• User load preference data:

• For Residential load data

• For Commercial load data

• For Industrial load data

• Above results clearly show the reduction in peak load demand, total cost incurred
• The profit obtained in industrial load DSM was more than that of commercial and residential load. This is due to large ratings devices used in industries. So, shift of even a single controllable device from peak, can result in high load getting shifted and more effective and percent cost reduction is maximum in Industrial Loads
• When the data of end time was included along with start time. Hence, increasing the constraints on scheduling time. Due to these restrictions and enforcement’s on device to be scheduled, some sharp peaks were observed in the load profile after DSM. Less cost reduction was observed in this case