International Journal of Engineering Trends and Technology (IJETT) – Volume 34 Number 3- April 2016 Data Mining Approach to Energy Efficiency in Wireless Sensor Networks Anisha kamboj#1 , Tanu Sharma*2 1 M.Tech., CSE Department, JMIT, Radaur, Kurukshetra University, India 2 Assistant Professor, CSE Department, JMIT, Radaur, Kurukshetra University, India Abstract —Collection of sensor nodes systematized into a network is known as WSNs. A sensor is a small device which observes the environment of physical parameters like pressure, temperature, sound, pollutants or vibration. In sensor networks data mining is the method of selecting applicationoriented standards and patterns with acceptable accuracy from fast and continuous flow of data streams from sensor networks (SN). In this case, data must be processed quickly and cannot be stored. Data mining methods has to be fast to process highspeed arriving data. Main objective of this review paper is comparative analysis of various data aggregation; mining techniques are discuses with associates’ advantage of accuracy, complexity, reduce energy consumption. Other factors such data mining techniques that affect the prediction are also discussed. Keywords — Wireless Sensor Network; data aggregation; Clustering; Data Mining Introduction Collection of sensor nodes which is organized into a network is known as wireless sensor network. A small device i.e sensor which observes the environment of physical parameters like relative humidity, pressure, temperature, motion, sound pollutants or vibration, at different locations. WSN is highly distributed networks of wireless sensor nodes, used in large numbers to monitor the system or environment. Sensor nodes organize themselves in an ad hoc manner and the transmission range of sensor nodes is limited, which means that two sensor nodes cannot reach each other directly, transmits on other sensor nodes to carry data between them. In general, data packets from the source node have to traverse multiple hops before they reach the destination. A wireless sensor network is an Adhoc network which consist sensor nodes, cluster heads and sink nodes. Sensor networks are self organized networks. Large numbers of tiny devices in the wireless sensor network are known as sensor nodes which are distributed to check physical and environmental conditions. Sensor nodes have to coordinate with each other, to get information about the environment [10]. ISSN: 2231-5381 Fig 1 Wireless Sensor Network A. Routing mechanism and Data Collection for WSNs The conventional routing mechanisms and data collection for WSNs can be largely divided into two categories: 1) Periodic data collection: All sensor nodes are periodically change their awareness to the sink based on the current information of the interested data. In multi hop-relay data delivery, typical traditional wireless sensor network relay sensor observations to a sink through a tree-based structure. However, multi hop-relay approaches inevitably involve large amount of data exchange between nodes, in addition many overheads to maintain the network architecture. 2) Event-based data collection: Sensors are responsible for reporting and detecting a specific event to one or more sinks in event-based data collection [10]. B. Applications of WSN Different types of sensors which are consist by the sensor network such as thermal, magnetic, visual, radar and infrared, which are able to monitor a wide variety of conditions. These sensor nodes (SN) can be put for location sensing, continuous sensing, motion sensing event detection and continuous sensing. There are the following applications are as follows:a. Environmental applications -few Environmental applications of sensor networks include forest fire detection, flood detection and air pollution detection, landslide detection. They can also be used for tracking the movement of insects, planetary exploration, small animals and birds, monitoring http://www.ijettjournal.org Page 121 International Journal of Engineering Trends and Technology (IJETT) – Volume 34 Number 3- April 2016 conditions that affect facilitating irrigation and livestock and crops. b. Area monitoring applications-It is a very common application of WSNs. The WSN is deployed over a region in this application where some phenomenon or physical activity is to be monitored. When the sensors detect the event being monitored (vibration, sound), the event is reported to the BS (base station), which then takes some action (e.g., send a message on the internet or to a satellite). Equivalently, WSN can be deployed in security systems to detect motion of the unwanted, highspeed vehicles is to be catches by the traffic control system. Also wireless sensor network finds application in military area for battled surveillance, ammunition and equipment, monitoring friendly forces, terrain reconnaissance of opposing forces, battle damage assessment targeting. c. Industrial applications-wireless sensor network are widely used in industries, like in machinery condition-based maintenance. Previously impassable locations, rotating machinery, mobile assets and restricted areas or hazardous can now are reached with wireless sensors. They can also be used to monitor and measure the water levels within all ground wells; control leach ate accumulation and removal. d. Health applications - For sensor networks the health applications are providing interfaces for the disabled, diagnostics, integrated patient monitoring, patients inside a hospital, monitoring the movements and internal processes of small animals or insects. C. Data Mining in WSN In sensor network Data mining is the method of selecting patterns with acceptable accuracy from continuous and application-oriented standard, probably non ended flow of data streams from sensor networks. In this case, all data processed quickly and can’t be stored. Data mining is a sufficient method to process high-speed arriving data. Data mining methods are meant to handle the multi scan mining algorithms for reviewing constant datasets and stationary data. Therefore, new data mining methods are not suitable for handling the high dimensionality, large quantity, and the wireless sensor network is used to generate distributed data. The aim of the data mining process is to extract information from huge volume of a data and convert it into an understandable structure for further use [10]. The fast development of information technology and computer in the last few years has fundamentally changed almost every field in science and engineering, calling for the development of new data methods to conduct research in science and engineering and converting many disciplines from data-poor to increasingly data-rich. Make ensure that the advancements of data mining research and technology will effectively asset the progress of science and engineering, the challenges on data ISSN: 2231-5381 mining in engineering is important to examine and explore how to develop the technology to advances in science and engineering and facilitate new discoveries [5]. D. Data aggregation in WSNs WSN typically consists of a sink node referred to as a number of small wireless sensor network and a base station. Assumed the sensors nodes are to be unsecured with limited available energy while assumed to the base station are being secure with unlimited available energy. The sensor nodes control a geographical area and collect sensory information. Through wireless hop by hop transmissions the Sensory information is communicated to the base station. To conserve energy, by applying aggregation function on the received data this information is accumulated at intermediate sensor nodes. Aggregation reduces energy consumption on sensor nodes by reduce the amount of network traffic, It however complicates already existing security challenges for WSN and requires new security techniques. Providing security to aggregate data in WSN is known as secure data aggregation in WSN. II. Related Study Onur tekdas & volkan isler et.al [1], Explore synergies among wireless sensor networks and mobile robots in the environmental monitoring through a system in which measurement gathered by sensing nodes which is collect by data mules. Daniele Apiletti & Elena Baralis et.al [2], Represents the complete design, validation, and implementation of the SeReNe framework. Given historical sensor readings, SeReNe acquire efficient sensor network data by discovering energy-saving models SeReNe exploits different clustering algorithms to discover temporal correlations and spatial which allow the identification of sets of sensor data streams and correlated sensors. Select the representative sensors from the given clusters of correlated sensors, to reduce the communication computation and power Costs, only the representative sensors are queried rather than directly querying all network nodes S.Anandamurugan & C.Venkatesh et.al [3], Presents several advantages of heterogeneous architecture for WSNs. It consists of some resource rich simple undynamic nodes and mobile relay nodes. The mobile relays have high energy as compare to undynamic nodes. The mobile relays help relieve sensors that are highly burdened by heavy network traffic and can dynamically move around the entire network, thus improving the lifetime. Tzung-Cheng Chen & Tzung-Shi Chen et.al [4], Suggested from a wireless sensor network (WSN) a novel data-collecting algorithm using a mobile robot http://www.ijettjournal.org Page 122 International Journal of Engineering Trends and Technology (IJETT) – Volume 34 Number 3- April 2016 to get sensed data that possesses islanded/ partitioned WSNs is proposed in this paper. This algorithm allows the improvement of data collecting performance by the base station by identifying the locations of navigating a mobile robot and partitioned/islanded WSNs to the desired location. Two control approaches, a global- and local-based approach are proposed to identify the locations of the partitioned/islanded WSNs. Laxmi Choudhary et.al [5], Define about large amount of data in science and engineering has been and continuously generated with the fast development of computer and information technology in the last few years. Moreover, such data has been widely made available via the Internet. Such tremendous amount of data has fundamentally changed science and engineering, converting many disciplines from data-poor to data-rich, dataintensive methods to conduct research in science and engineering. Miao Zhao & Yuanyuan Yang et.al [6], represents a great benefit can be achieved for data gathering in WSNs by employing mobile collectors that gather data by short-range communications. A mobile collector should traverse the transmission range of each sensor in the field to pursue maximum energy saving at sensor nodes. Emad M. Abdelmoghith & Hussein T. Mouftah et.al [7], presents a amount of research work to minimize the volume of transmitted traffic by using data compression techniques and reducing power consumption levels in WSNs. In this paper, the present a data oriented approach called Model-based Clustering (MBC) which reduces the flows of communication between sink node and sensor nodes. S.Nithyakalyani & Dr.S.Suresh Kumar et.al [8], given a brief comparative study is made from different research proposals; it suggests some of the cluster head selection approach for the data aggregation. The algorithms under study are Voronoi based Genetic clustering algorithm, Fuzzy C- means clustering algorithms and Data relay Kmeans clustering algorithm. Phiros Mansur & Sasikumaran Sreedharan et.al [9], represents some techniques which associates advantages of energy conservation and reduction of missing rate, accuracy of tracking. Moreover other factors like data mining techniques and clustering that affect the prediction. Vickey Sharma et.al [10], define the goal of the data mining process is to get information from a data set and converts it into an understandable form for further use. The main objective of this review paper to analyse and study of various data mining algorithms and data collection. ISSN: 2231-5381 http://www.ijettjournal.org Page 123 International Journal of Engineering Trends and Technology (IJETT) – Volume 34 Number 3- April 2016 TABLE I COMPARISON OF VARIOUS KEY MANAGEMENT TECHNIQUES S.No Key management Technique Proposed by Findings Advantage Disadvantage 1 Sensing device motes ONUR TEKDAS AND VOLKAN ISLER Robots as data mules. This approach is feasible and yields important savings in energy costs, thus prolonging the lifetime of the network The motes can spend the majority of their energy stores broadcasting collected data, especially because they might be required to forward the data for other motes in the Network. 2 SERENE Framework(Sele cting Representative in a Sensor Network) Daniele Apiletti · Tania Cerquitelli energy-saving models to efficiently access sensor network data SERENE prototype has designed to be stable, fast, able to manage a huge amount of sensor data stream and easy to access. The issue in this context is energy saving during data collection. 3 Mobile Relay Approach S.Anandamuru gan, C.Venkatesh AR (Aggregation Routing) Algorithm Efficient Improve lifetime of the network. It has high energy then undynamic nodes. The problem of maximizing lifetime as a linear programming problem and arrive the optimal schedule for the mobile node. 4 Mobile Robots Tzung-Cheng Chen, TzungShi Chen GBA(global-Based approach LBA(local Based approach) Improve sensed data collecting performance in apportion or islanded WSNs. When energy depletion of a sensor node results in a dead mode that is unable to Communicate with other nodes. 5 Data Mining Laxmi Choudhary Machine learning pattern recognition database Extract the knowledge from huge volume of data. One such issue is the development of invisible data mining (DM) functionality for science and engineering. 6 Mobile collector Miao Zhao and Yuanyuan Yang Polling – based mobile gathering approach Improve efficiency The number of transmission hops should not be arbitrarily large as it may increase the energy consumption on packet relay. 7 Data compression technique Emad M. Abdelmoghith, Hussein T. Mouftah Model Based Clustering(data oriented approach) Reducing energy power consumption level in WSN. Added complication Effect of errors in transmission Slower of sophisticated method. 8 Data aggregation technique S.Nithyakalyani Dr.S.Suresh Kumar Node clustering algorithm Aggregation reduces energy consumption on sensor nodes by reduce the amount of network traffic. If a cluster head is compromised, then the base station cannot be ensure about the correctness of the aggregate data that has been send to it. 9 Prediction algorithm for object tracking Phiros Mansur, Sasikumaran Sreedharan clustering and data mining Make the prediction process more accurate that will help to reduce the missing rate. The major drawback of this method is that they assume the target always follows the same movement pattern. 10 data collection and routing mechanisms Vickey Sharma Data Mining Data mining process is to extract information from a data set and alter t it into an understandable form for further use. These schedules are either inapplicable to or inefficient in sharing with dynamic traffic patterns. ISSN: 2231-5381 http://www.ijettjournal.org Page 124 International Journal of Engineering Trends and Technology (IJETT) – Volume 34 Number 3- April 2016 III. CONCLUSIONS This paper describes the various techniques which uses the concept of clustering and data mining. Sensing device motes using the approach is feasible and yields important savings in energy costs. SERENE Framework (Selecting Representative in a Sensor Network) discovers energy-saving models to efficiently acquire sensor network data while minimizing energy consumption for data collection. Data mining technique is used to extract the knowledge from huge volume of the data. Data compression technique introduced an unsupervised learning scheme called Model-based Clustering (MBC) to shrink the amount of transmitted packets between sensor nodes and the sink node. Data aggregation technique describes the comparison between different clustering algorithms for data aggregation using Voronoi diagram are classified and discussed. Algorithms used in this paper for comparative studies are Data relay K-means clustering algorithm, Fuzzy C-means clustering algorithms and Voronoi based Genetic clustering algorithm. Finally it is concluded from the study that, all the algorithms are good enough for energy efficiency and stable clustering method, for data aggregation in wireless sensor networks. REFERENCES [1] Onur tekdas and volkan isler, jong hyun lim and andreas terzis, “using mobile robots to harvest data from sensor fields”, IEEE Wireless Communications, January 2009. [2] Daniele Apiletti · Elena Baralis · Tania Cerquitelli, “Energysaving models for wireless sensor networks”, London Limited : Springer-Verlag, april 2010. [3] S.Anandamurugan, C.Venkatesh, “Increasing the Lifetime of Wireless Sensor Networks by using AR (Aggregation Routing) Algorithm”, IJCA, 2010. [4] Tzung-Cheng Chen, Tzung-Shi Chen, “On Data Collection Using Mobile Robot in Wireless Sensor Networks”, IEEE Transactions On Systems, November 2011. [5] Laxmi Choudhary, “Challenges for data mining”, IJREAS, February 2012. [6] Miao Zhao and Yuanyuan Yang, “Bounded Relay Hop Mobile Data Gathering in Wireless Sensor Networks”, IEEE Transactions on Computers, February 2012. [7] Emad M. Abdelmoghith, Hussein T. Mouftah, “A Data Mining Approach to Energy Efficiency in Wireless Sensor Networks”, IEEE 24th International Symposium on Personal, Indoor and Mobile Radio Communications, 2013. [8] S.Nithyakalyani, Dr.S.Suresh Kumar, “Data aggregation in WSNs using node clustering algorithms”,IEEE Conference on Information and Communication Technologies , 2013. [9] Phiros Mansur, Sasikumaran Sreedharan, “Survey of Prediction Algorithms for Object Tracking in Wireless Sensor Networks”, IEEE International Conference on Computational Intelligence and Computing Research, 2014. [10] Vickey Sharma,“Data Mining and Data Gathering Algorithm in WSN”, IJARCSSE , April 2015. ISSN: 2231-5381 http://www.ijettjournal.org Page 125