k lenin - Research Scholar, JNTU, Hyderabad ۵۰۰۰۸۵, India
b Ravindhranathreddy - Deputy Executive Engineer, JNTU, Hyderabad ۵۰۰۰۸۵, India
m Suryakalavathi - Professor, Department of Electrical and Electronics Engineering, JNTU, Hyderabad, ۵۰۰۰۸۵, India

This paper presents an optimization and search technique Poll Algorithm (PA), inspired by assembly and parliament polls in India. Commonly evolutionary algorithms are population based approach like that in poll algorithm population is common people and each person may be a candidate or a voter. Certain number of people will form different groups to establish political parties in the solution space. Promotion movement is the basic of this PA algorithm and it contains three core phases: optimistic campaign, opposing campaign and alliance campaign. During optimistic campaign, the contenders announce themselves through emphasizing their optimistic descriptions and potentials. In the opposing campaign, candidates contend with each other to upsurge their reputation and vilify their challengers. In special cases, the candidates that have analogous ideas can allied together in order to upsurge the chance of victory of the combined party. Campaigns optimistically cause the people to converge to a state of solution space that is the global optimum. All these determinations lead up to poll Day (ending condition). On poll day, the candidate who accomplished the maximum votes is proclaimed as the victor and matches to the greatest solution that is found for the problem. The proposed PA has been tested in standard IEEE 30 bus test system and simulation results show clearly about the improved performance of the proposed algorithm in reducing the real power loss with control variables within the limits.

campaign, opposing campaign, alliance campaign, optimal reactive power, transmission loss