在無線感測網路中，多收集點 (Multi-Sink) 的建置是一種延長網路存活時間的方法，大量的感測資料將可分散給各收集點，避免收集點周遭的熱點做過多次資料代傳，提早將電量耗盡。而過去針對多收集點負載平衡 (Load balancing) 的研究裡，感測器多半選擇最近的收集點做為資料傳送目的地，此策略可減少網路的整體電量消耗，然而在無線感測網路裡，事件的發生經常會集中在特定的區域，若該地區的感測器均傳送資料到最近的收集點，將會使該收集點鄰近的熱點負擔過重，提早將電量耗盡，導致收集點被孤立在網路外，並造成大量的路由路徑斷裂。因此本文提出了一個適用於多收集點無線感測網路的負載平衡機制。透過我們所提出的移動式錨點 (Mobile Anchor)，將感測網路動態的劃分成數個地區，以分配適當的資料量給各收集點。而為了適應各種型態的資料流量，我們將機器學習 (Machine Learning) 的強化學習法導入移動式錨點，並實現一個Q-Learning學習代理人。代理人經過一段時間的學習後，將可取得一個最佳的錨點移動策略，遵循此策略將可達到熱點的負載平衡，避免特定收集點提早被孤立，同時延長整個網路的存活時間。
除此之外，本文亦提出一種以太陽能為基礎的動態節點演算法可以在便於佈建的條件下還能提升無線感測器的監控效能。無線感測網路是藉由佈建許多的感測器，並將感測到的資料傳回Sink，然而感測器電量不足以長期供應始終是無線感測網路的缺點，許多選擇節點或路徑問題方面的論文僅考量到感測器本身電力的因素，因此只能在有限的電力環境下盡可能延長使用壽命。為了解決無線感測器的電力問題，本文額外加入太陽能作為我們供電的基礎以解決電力問題，因此本文針對太陽能感測器進行深入的探討。而在挑選感測器上的問題，本文提出一動態演算法，透過適性化的節點挑選能使用最少的節點以來提高每個無線感測器的覆蓋率以及高持續力。此篇論文也考慮到在不同環境下太陽能裝置的效率以及是否受到降雨的影響做為挑選節點的依據。而實驗結果顯示此篇論文所提出的以太陽能充電式無線感測環境下的動態節點演算法，可以因應在不同環境變化下，還一邊監控住我們的目標區域。
目前為止已經有一些研究針對太陽能能量的分析與研究，但大多數的論文都假設佈建於一般環境中。當考量監測河流岸邊的環境時，因為特殊的地理環境限制，感測器的分佈情形使得在建立連線時可選擇的節點受到限制，若能源的使用沒有有效率的使用，則感測器死亡後易造成整體網路的瓶頸，許多的感測資料將無法傳回同時也無法有效的監控目標區域。因此本文針對河流特性進行分析，將河流分成不同河岸區段(stream)，河流環境可以區分出兩種可能的案例，分別是單一區段案例(single-stream case)與交叉區段案例(cross-stream case)，位於河流環境中的感測器分別三種連線，包括了河流間的連線(inter-stream connection)、河岸區段間的連線 (inter-segment connection)和河岸區段的連線(intra-segment connection) ，以此為基礎來挑選在該時段需啟用的感測器來降低封包在傳送過程中的使用能量。實驗結果顯示本文所提出的基於太陽能模組之動態排程機制可以有效地增加能源使用率，並且能持續監控該環境。該機制可擴展至許多類似河流的環境，例如鐵路、高速公路，甚至是城市中人來人往的街道。

In many researches on load balancing in multi-sink WSN, sensors usually choose the nearest sink as destination for sending data. However, in WSN, events often occur in specific area. If all sensors in this area all follow the nearest-sink strategy, sensors around nearest sink called hotspot will exhaust energy early. We propose an adaptive learning scheme for load balancing scheme in multi-sink WSN. The agent in a centralized mobile anchor with directional antenna is introduced to adaptively partition the network into several zones according to the residual energy of hotspots around sink nodes. In addition, machine learning is applied to the mobile anchor to make it adaptable to any traffic pattern. Through interactions with the environment, the agent can discovery a near-optimal control policy for movement of mobile anchor. The policy can achieve minimization of residual energy’s variance among sinks, which prevent the early isolation of sink and prolong the network lifetime.
This study also proposes a solar power-based adaptive node-selection protocol mechanism for a wireless sensor network to increase the monitor performance of wireless sensors. Using renewable energy, such as solar power, to improve the efficiency of sensors in wireless sensor networks has become a popular topic. Equipping the sensors with solar-powered equipment signifies that the sensors no longer have the limited battery life problem. This design can collect solar power to charge the sensor’s battery. To solve node-selection problem, an adaptive node-selection mechanism (ANSM) scheme is proposed. The algorithm builds the energy-aware Steiner tree between sensors and sink. This scheme selects the least active node to reduce the overlapping of the sensor coverage but ensure constant coverage of the target area in solar-powered wireless sensor networks. This approach also considers the solar power consuming rate and humidity to solve the solar power problem in various environments.
While monitoring the stream environment, sensors are attached to the stream side to collect the sensed data and transmit the data back to the sink. The stream environment can be scaled in several similar environments. This type of geographic limitation not only exists in a stream environment, but also on streets, roads, and trails. This study presents an effective node-selection scheme to enhance the efficiency of saving power and coverage in stream environment of solar-powered WSNs. Analysis of the sensor deployment in the stream environment permits sensors to be classified into different segments, and then allows the selection of active nodes for building inter-stream connections, inter-segment connections, and intra-segment connections. Based on these connections, the number of active nodes and transmitted packets is minimized. Simulation results show that this scheme can significantly increase the energy efficient and maintain monitoring area in solar-powered WSNs.

[1] A. Abu-Baker, H. Huang, E. Johnson, S. Misra, R. Asorey-Cacheda, B. Bensaou,and M. Balakrishnan, “Maximizing α-Lifetime of Wireless Sensor Networks with Solar Energy Sources,” The Military Communications Conference - Unclassified Program - Networking Protocols and Performance Track, 2010.
[2] P. Balister, B. Bollobas, and A. Sarkar, and S. Kumar, “Reliable Density Estimates for Coverage and Connectivity in Thin Strips of Finite Length,” The ACM/IEEE Conference on Mobile Computing and Networking, 2007.
[3] I. Banerjee, A. Datta, and H. Rahaman, “Efficient Job Allocation and Scheduling Scheme for Wireless Sensor Network,” The IEEE International Symposium on Biomedical Imaging, 2010.
[4] A. G. Barto, S. J. Bradtke, and S. P. Singh, “Learning to act using real-time dynamic programming,” Artificial Intelligence, vol. 72, pp. 81–138, 1995.
[5] R. E. Bellman, “Dynamic Programming,” Princeton, NJ: Princeton Univ. Press, 1957.
[6] Q. Cao, T. Abdelzaher, T. He, and J. Stankovic, “Towards Optimal Sleep Scheduling in Sensor Networks for Rare-Event Detection,” The International Symposium on Information Processing in Sensor Networks, pp. 20-27, 2005.
[7] B. Chen, K. Jamieson, H. Balakrishnan, and R. Morris. “Span: An energy efficient coordination algorithm for topology maintenance in ad-hoc wireless networks,” The ACM/IEEE Conference on Mobile Computing and Networking, 2001.
[8] A. Forster, “Machine Learning Techniques Applied for Wireless Ad-Hoc Networks: Guide and Survey,” The International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Melbourne, pp. 367–370, 2007.
[9] S. Fortune, “Voronoi diagrams and Delaunay triangulations,” In Computing in Euclidean Geometry, D.-Z. Du and F. Hwang, Eds., vol. 1 of Lecture Notes Series on Computing. World Scientific, Singapore, pp. 193–233, 1992.
[10] W. R. Heinzelman, A. Chandrakasan, and H. Balakrishnan, “Energy efficient communication protocol for wireless microsensor networks,” The Hawaii International Conference on System Sciences, pp. 3005–3014, 2000.
[11] N. Jaggi, “Robust threshold based sensor activation policies under spatial correlation,” The International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, 2006.
[12] L. P. Kaelbling, M. L. Littman, and A. P. Moore, “Reinforcement learning: A survey,” Journal of Artificial Intelligence Research, vol. 4, pp. 237–285, 1996.
[13] A. Kansal, D. Potter, and M. Srivastava, “Performance aware tasking for environmentally powered sensor networks,” The International Conference on Mathematical Methods for Curves and Surfaces, 2004.
[14] K. Kar, A. Krishnamurthy, and N. Jaggi, “Dynamic node activation in networks of rechargeable sensors,” The International Conference on Computer Communications, 2005.
[15] A. Keshavarzian, H. Lee, and L. Venkatraman, “Wakeup Scheduling in Wireless Sensor Networks,” The ACM International Symposium on Mobile Ad Hoc Networking and Computing, pp. 322-333, 2006.
[16] Y. Kiri, M. Sugano, and M. Murata, "Self-Organized Data-Gathering Scheme for Multi-Sink Sensor Networks Inspired by Swarm Intelligence," The International Conference on Self-Adaptive and Self-Organizing Systems, pp.161-172, 2007.
[17] S. Kumar, T. H. Lai, and A. Arora, “Barrier Coverage With Wireless Sensors,” The ACM/IEEE Conference on Mobile Computing and Networking, 2005.
[18] S. Kumar, T. H. Lai, M. E. Posner, and P. Sinha, “Maximizing the Lifetime of a Barrier of Wireless Sensors”, IEEE Transactions on Mobile Computing, vol. 9, no. 8, 2010.
[19] H. Lee, K. Lee, and L. Lin ”Energy Efficient Data Management for Wireless Sensor Networks with Data Sink Failure,” The IEEE International Conference on Mobile Ad Hoc and Sensor Systems Conference, 2005.
[20] Y. Lin and Q. Wu, ”Energy-Conserving Dynamic Routing in Multi-Sink Heterogeneous Sensor Networks,” The International Conference on Communications and Mobile Computing, pp. 269-273, 2010.
[21] B. Liu, O. Dousse, J. Wang, and A. Saipulla, “Strong Barrier Coverage of Wireless Sensor Networks,” The ACM International Symposium on Mobile Ad Hoc Networking and Computing, 2008.
[22] M. Meng, X. Wu, H. Xu, B. Jeong, S. Lee, and Y. Lee, “Energy efficient routing in multiple Sink sensor networks,” The International Conference on Computational Science and its Applications, pp. 561-566, 2007.
[23] B. O. Priscilla Chen and E. Callaway, “Energy efficient system design with optimum transmission range for wireless ad-hoc networks,” The IEEE International Conference on Communications, pp. 945–952, 2002.
[24] M.L. Puterman, “Markov Decision Processes,” Wiley Interscience,1994. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction. The MIT Press, March 1998.
[25] Z. Shelby, C. Pomalaza-Raez, and H. Karvonen, “Energy optimization in multihop wireless embedded and sensor networks,” International Journal of Wireless Information Networks, vol. 12, no. 1, pp. 11-20, 2005.
[26] M. Soyturk and T. Altilar, ”A Novel Stateless Energy-Efficient Routing Algorithm for Large-Scale Wireless Sensor Networks with Multiple Sinks,” The IEEE Annual Wireless and Microwave Technology Conference, 2006.
[27] T. Suzuki, M. Bandai and T. Watanabe, “DispersiveCast: Dispersive Packets Transmission to Multiple sinks for Energy Saving in Sensor Networks,” The Personal, Indoor and Mobile Radio Communications, 2006.
[28] M. Toussaint, “Lecture Notes: Markov Decision Processes” April 13, 2009.
[29] C. J. C. H. Watkins and P. Dayan, “Technical note: Q learning,” Machine Learning, vol. 8, no. 3, pp. 279-292, 1992.
[30] C. Wang and W. Wu, "A Load-balance Routing Algorithm for Multi-sink Wireless Sensor Networks," The International Conference on Communication Software and Networks, 2009.
[31] Y. Yu and V. K. Prasanna, “Energy-balanced task allocation for collaborative processing in wireless sensor networks,” Mobile Networks and Applications, vol. 10, no. 1-2, pp. 115–131, Feb. 2005.
[32] J. Zhao and R. Govindan, “Understanding packet delivery performance in dense wireless sensor networks,” The ACM Conference on Embedded Networked Sensor Systems, pages 1-13, 2003.