Many a route is established and its nodes have

Many of the activities that are
taking place in today’s world are dependent on services offered by computer
networks, and MANET networks are of the networks that have many applications.
Load balancing and network congestion are major problems in MANET network
routing, and therefore the issue that becomes important is creating load
balancing in this kind of network so that all data is transmitted intact. For
this purpose, it is necessary to perform routing in the network so that the load
is balanced in all directions.

It is therefore necessary that all
the deficiencies that may unbalance the network be identified. Characteristics
such as high mobility of the nodes and thus dynamic topology of the network,
low bandwidth, and even limited power and energy lead to the complexity of
routing algorithms in ad hoc networks. All of these characteristics make most
of the ideas contained in routing algorithms on other networks not be applicable
for ad hoc networks. Algorithms that perform routing as a single route and are
of algorithms based on demands have not generally solved the problem of load.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now

Among ad hoc routing-networks
algorithms, some algorithms perform routing as a multi-route operation using
multi-route routing where fault tolerance effectively increases. Most multi-route
routing algorithms after route discovery process where they found multiple routes
from source to destination choose one of these routes as the main route and
begin sending data via the same route. They keep the other routes as
alternative routes and in case of failure of the main route, they use one of
the alternative routes for sending data, and until a route is established and its
nodes have energy, the same route is used eventually, leading to end nodes

Ending of the node energy on a route
and failure of nodes create gaps in the network and the network is fragmented
that has a direct impact on network performance and routing. This is seen both
in one-path and multi-route algorithms.

Given the need for load balancing
in MANETs and its importance, in this paper, the aim is to improve load
balancing in this type of networks by considering upgrading parameters that
directly affect the type of balance. To this end, here a framework based on
learning automata is proposed for load balancing by considering nodes energy,
signal strength, number of steps, and the amount of nodes for each route for


Many studies have been proposed in
the field of load balancing in MANET, the most important of which are as

In 1, a method has been proposed
to balance load that distributes traffic on three key metrics: 1) Route Energy,
2) queue traffic, and 3) the number of steps with the corresponding weight. In
2, priority-scheduling technique based on fuzzy is used to determine effects
of this method on reactive routing protocols AODV and DSR. In this method, a
priority index is added to each packet in the queue nodes, and this priority
index is based on queue length, data rate, and packet expiry time.

In 3, stable routing algorithms
based on fuzzy are provided for MANET whose aim is to strengthen QOS. One of
the major problems in QOS routing in MANET is ensuring that one route is
established in the network until the end of data transmission, to reduce the
number of broken routes, a reliable new routing algorithm that uses fuzzy logic
is presented. When routing, this algorithm chooses a sustainable route based on
the position of nodes and data rate. Moreover, a new protocol has been
presented for maintenance/repair routes so that when a route breaks, a new
route is established. In 4, Energy Efficiency in MANET routing protocols load
balancing is studied. The work presented in this paper is: 1) energy efficiency
in routing protocols of storage of node based on AODV with volume of work load
balancing (AODV-NC-WLB), 2) a new application of parameters of energy
efficiency in routing protocols MANET, 3) implementation and simulation of the
study in NS2 in energy efficiency AODV-NC-WLB, significant maintaining of
improvement in throughput, overflow, delivery rates, and delay more than AODV
standard for high-volume scenarios. In 5, multiple adaptive routing has been
offered for load balancing. In this method, an algorithm is used that detects
multiple routes to the destination called Fail-Safe routing. There is one main route,
in all of which there are intermediate nodes and multiple routes are composed of
nodes with minimal remaining load, time, power, and energy, and have the
highest bandwidth. In routing when the average load of a node has an increase
beyond the threshold, to reduce the traffic load on that congested route,
traffic is distributed over multiple other routes. In 6, a new method of
routing MANETs by considering energy by learning automata is suggested. In this
method, for MANETs based on best route selection using learning automata
technique is proposed. The proposed protocol is able to apply effectively on
track with regard to limited energy. This method is applied in a version of
AODV routing algorithm (i.e., routing AODV with learning automata) (AAODV).A
representative of learning automata runs on each node runs, and this representative
dynamically trains the best route. The protocol consists of three modes, and
each node trains the best route to the destination. In 7, the efficiency of
routing protocols of traffic-oriented load balancing in MANET has been compared.

In 8, Load Balancing Parallel
Routing Protocol (LBPRP) has been provided that solves the problems of previous
multiple routing protocols and distributes data in parallel in all directions
at the same time. In this paper, a simple test scenario has been presented to
ensure that the model is effective and credible. LBPRP creates load balancing,
reduces delay, increases packet delivery ratio, and throughput. In 9, the
analysis of the performance of load balancing in MANET using multiple routing
protocols on demand is offered. In 10, the protocols of load balancing in
MANET are tackled. In addition to the above-mentioned methods that are more important,
other methods are provided in the literature for load balancing in MANET.


The process
during which organisms learn various subjects has long been of interest to
experts. Studies done in this area are generally concentrated in two branches:1)
Understanding the process where living things learn.2) Obtaining methods by
using which this learning capability can be created in machines.

A research group called Tsetlin in
the Soviet Union introduced the concept of random automaton for the first time
in the early 1960s. After that in later research, several examples of the
application of learning methods in engineering systems were developed of which routing in phone, pattern
recognition, Object Partitioning, and Adaptive Control could be named.

Each Stochastic Learning Automata (SLA)
is made up of two main components: 1) a stochastic automata with a limited
number of operative and is in interaction with a stochastic environment. 2) A learning
algorithm by using which the automaton learns doing the optimal action.

Each automaton can be seen as a
Finite State Machine (FSM) that can be observed by the following pentamerous:

                                                                                                       Eq. (1.3)

The parameters in this pentamerous

• Set of automaton operations

• Set of the automaton input

• Function that maps input and the current
states to the next state

• Output function that maps the
current state to the next output    

• The set of the internal states of
the automaton at the n-th moment

Set ?
includes applying the automaton where the automaton in each iteration, chooses one
of them. Inputs ? define automaton input
the details of which will be discussed in the next section. F and G mappings convert
the current state and input to the next output (action) selected by the
automaton. If mappings F and G are decisive, the automaton is called
Deterministic Automata.

In such a case, by having primary and
input modes, output and the next state are uniquely obtained. If mappings F and
G are random, automata is called stochastic automata. In that case, only the
probabilities related to the next state and corresponding outputs could be
determined. Stochastic Automata is divided into two categories: 1) Automaton
with a fixed structure 2) Automaton with Variable Structure.

Learning automata with variable
structure a used here is LR-P where the probability selecting p for
each action of ? is updated according to the following equations. In case of
receiving a favorable response from the environment ?(k)=0, possibility of that
action is rewarded by the following equation:


In case of receiving an unfavorable
response from the environment ?(k)=1, possibility of that action is fined by
the following equation:


In both of the above equations: pj
(k + 1) is probability automaton at the time k + 1, pj (k) is
the probability automaton at time k, a is reward, b is fine and r is number of

After creating the existing nodes
in the network stochastically, two nodes are selected randomly, one of which is
a resource and the other plays the role of the destination. If two nodes are
directly connected to each other, routing does not make sense and packet
transmission is performed. Otherwise, the routes between two nodes are
determined. An example of this is shown in Figure 1.