This document describes a fuzzy adaptive gravitational search algorithm for strategic bidding in electricity markets. It involves agents submitting bids to an independent system operator who determines a market clearing price. The algorithm uses a gravitational search algorithm and fuzzy logic to determine optimal bidding coefficients for suppliers to maximize their profits. The gravitational search algorithm models agents as masses that are attracted to other masses representing better solutions. Fuzzy logic is used to adjust the gravitational constant over iterations for the search to gradually explore smaller areas of the solution space and find an optimal bidding strategy.

1. Fuzzy adaptive gravitational
search algorithm
PREPARED BY
K.GAUTHAM REDDY 2011A8PS364G

2. Bidding
 Agents submit bids (Quantity and cost) to either buy
or sell energy.
 Independent System Operator (ISO)
 Market clearing price
 Uniform pricing or pay as bid

3. Strategic bidding
 Knowing their own costs, technical constraints and




their expectation of rival and market
behavior, suppliers face the problem of constructing
the best optimal bid.
Three basic approaches:
i) Based on the estimation of market clearing price
ii) Estimation of rival’s bidding behavior and
iii)On game theory

4. Fuzzy adaptive GSA
Mathematical formulation
 Consider total of ‘m’ suppliers
 Uniform pricing method is followed
 The jth supplier bid with linear supply curve denoted
by Gj (Pj ) = aj + bj Pj
Pj is the active power output, ajand bj are nonnegative bidding coefficients of the jth supplier.

5. 

6.  When we solve the above equation we get the
solutions as
 Cost function :Cj (Pj ) = ej Pj + fj Pj2 , where
ej and fj are the cost coefficients of the jth supplier.

7. Profit maximization
 Hence our main objective is to maximize profits
which is the difference between the selling price and
the production price which is as follows
 The objective is to determine bidding coefficients aj
and bj so as to maximize F(aj,bj) subject to
equations 5 and 6.
 Keep one constant and vary other as they are
interdependent

8. Gravitational search algorithm:
 Follows two basic laws
i) Law of gravity
ii) Law of motion.
 Agents are considered as objects and their
performance is measured by their masses.
 Lighter masses gravitate towards the heavier masses
(which signify good solutions)
 The position of the masses correlates to the solution
space in the search domain while the masses
characterize the fitness space.

9.  As the iterations increase, and gravitational
interactions occur, it is expected that the masses
would conglomerate at its fittest position and
provide an optimal solution to the problem.
 Now, consider a system with N agents (masses), the
position of the ith agent is defined by:
Xi = (x1 , . . . , xd , . . . , xn ) for i = 1, 2, . . . , N
where xd presents the position with N agents
(masses), the position of the ith agent in the dth
dimension and n is the space dimension

10.  At a specific time ‘t’ we define the force acting on
mass ‘i’ from mass ‘j’ as following:
where Maj is the active gravitational mass related to
agent j, Mpi is the passive gravitational mass related
to agent i, G(t) is gravitational constant at time t, ε is a
small constant and Rij(t) is the Euclidian distance
between two agents i and j.

11.  The total force acting on each mass i is given in a
stochastic form as the following
 where rand(wj) ∈ [0, 1] is a randomly assigned weight.
Consequently, the acceleration of each of the masses, is
then as follows.
where Mii is the inertial mass of ith agent.

12.  The next velocity of an agent is considered as a
fraction of its current velocity added to its
acceleration. Therefore, its position and its velocity
could be calculated as follows:
vi (t + 1) = randi × vi (t) + ai (t)
xd (t + 1) = xd(t) + vd(t + 1)
where randi is a uniform random variable in the
interval [0,1].

13.  The gravitational constant, G, is initialized at the
beginning and will be reduced with time to control
the search accuracy. Hence, G is a function of the
initial value (G0) and time (t):
Here G0 is set to 100.

14.  Fuzzification:
 Inputs :
(i) normalized fitness value (NFV)
(ii) current gravitational constant (G)
Outputs:
The correction of the gravitational constant (dG).

15.  Input variables represented by three linguistic
values, S (small), M (medium) and L (large) where as
output variable (G) is presented in three fuzzy sets of
linguistic values; NE (negative), ZE (zero) and PE
(positive) with associated triangular membership
functions.

16.  The value of the parameter ‘G’ is large at the
beginning of the search process and gradually it
becomes small as the iterations are increasing.
The change in gravitational constant (dG) is small
and requires both positive and negative corrections.
 After we get a new value of G, GSA until iteration
reaches their maximum limit. Return the best fitness
(optimal bid value bj) computed at final iteration as a
global fitness. Using bj values, calculate MCP