鄭卓然 鄭向偉 田杰



摘 要:針對傳統無線體域網(WBAN)預測模型對感知數據預測精度低、計算量大、能耗高的問題,提出一種基于懲罰誤差矩陣的自適應三次指數平滑算法。首先在感知節點與路由節點之間建立輕量級預測模型,其次采用地毯式搜索方式對預測模型進行參數優化處理,最后采用懲罰誤差矩陣對預測模型參數作進一步的細粒化處理。實驗結果表明,與ZigBee協議相比,在1000時隙范圍內,所提方法可節省12%左右的能量;而采用懲罰誤差矩陣與地毯式搜索方式相比,預測精度提高了3.306%。所提方法在有效降低計算復雜度的同時能進一步降低WBAN的能耗。
關鍵詞:無線體域網;懲罰誤差矩陣;輕量級預測模型;地毯式搜索;體域網
中圖分類號: TP393
文獻標志碼:A
Abstract: To solve the problem that traditional Wireless Body Area Network (WBAN) prediction model has low prediction accuracy, large computational complexity and high energy consumption, an adaptive cubic exponential smoothing algorithm based on penalty error matrix was proposed. Firstly, a lightweight prediction model was established between the sensing node and the routing node. Secondly, blanket search was used to optimize the parameters of the prediction model. Finally, penalty error matrix was used to further refine the parameters of the prediction model. The experimental results showed that compared with the ZigBee protocol, the proposed method saved about 12% energy in 1000 time slot range; compared with blanket search method, the prediction accuracy was improved by 3.306% by using penalty error matrix. The proposed algorithm can effectively reduce the computational complexity and further reduce the energy consumption of WBAN.
Key words: Wireless Body Area Network (WBAN); penalty error matrix; lightweight prediction model; blanket search; body area network
0 引言本文的文字比較差
作為信息通信技術和醫學的交叉領域,無線體域網(Wireless Body Area Network, WBAN)[1-2]旨在為公眾提供實時的健康服務[3-4],如臨床決策支持[5]、家庭健康監測[6]等。
為了給予WBAN用戶更寬廣的活動空間與優質的用戶體驗,節點必須在多跳網絡環境中進行通信[7]。路由節點負責接收和轉發監測數據,接收器負責分析來自路由節點的感知數據,通過Serial Interface通信或TCP(Transmission Control Protocol)通信將監測數據發送至數據處理中心[8-9]。在多跳環境下的WBAN中,將接收器作為協調器簡化了復雜的同步過程的需要,能夠提高數據傳輸過程中的能量效率,但感知節點與路由節點將承受較大的計算消耗和報文轉發負擔,因此降低感知節點與路由節點的能耗,延長WBAN生命周期成為本文研究的關鍵問題。
但遺憾的是,目前尚未見到在多跳WBAN環境中節點低功耗的解決方案,為此,降低感知節點能耗成為解決電池續航能力的一大出路。文獻[10]中提出了基于小波變換量最小二乘支持向量機(Wavelet Transform-Least Squares Support Vector Machine, WT-LSSVM)的輕量級預測模型,通過在感知節點與路由節點之間建立同步預測模型減少冗余數據的傳輸,但該算法不適合于在硬件資源嚴重受限的無線傳感網絡中應用。目前無線體域網領域的專家提出了關于IEEE802.15.6[11]的改進版以及在媒體訪問控制(Media Access Control, MAC)層中基于時分多址(Time Division Multiple Access, TDMA)的一種改進方案,但并沒有針對無線體域網應用層進行有效的設計和改進。
通過對數據的同步分析預測可大大減少接收節點和發送節點打開收發機的次數以降低無線體域網能耗
本文在應用層部分通過對數據的同步分析預測減少接收節點和發送節點打開收發機的次數以降低無線體域網能耗。因此在本文研究中,選擇以ZigBee多跳樹形網絡架構[12]為基礎,在感知節點和路由節點之間建立以基于懲罰誤差矩陣的自適應三次指數平滑算法[13]為骨架的輕量級預測模型,并針對預測模型權重參數進行細粒化調節。該算法能自適應調節權重參數,提高預測準確率,同時降低感知節點與路由節點能耗,可以為長期健康監測應用提供更加長久的網絡服務。
本文首先采用自適應三次指數平滑算法在感知節點與路由節點之間建立輕量級預測模型以減少冗余數據的轉發,實現了有限的節能效果;然后通過引入懲罰誤差矩陣細粒化預測模型參數自適應調節權重參數,實現了預測模型參數精度和預測效果的顯著提升;最后通過實驗驗證了引入懲罰誤差矩陣提升了自適應三次指數平滑算法構建的預測模型的預測精度,對整個WBAN網絡節能效果的提升有很大的幫助。
1 輕量級預測模型融合
1.1 自適應三次指數平滑算法
4 結語
本文提出了一種基于懲罰誤差矩陣的同步預測體域網節能方法,實現了數據有效傳輸與低功耗。通過在感知節點和路由節點之間建立基于懲罰誤差矩陣的自適應三次指數平滑輕量級預測模型對周期非線性生理信息進行更加有效的細粒化預測,節省了大量的能耗,避免了頻繁地更換電池,能實現對感知節點的低功耗管理和控制。
參考文獻:
[1] BAE J, SONG K, LEE H, et al. A 0.24-nJ/b wireless body-area-network transceiver with scalable double-FSK modulation [J]. IEEE Journal of Solid-State Circuits, 2011, 47(1): 310-322.
[2] CHEN S-L, LEE H-Y, CHEN C-A, et al. Wireless body sensor network with adaptive low-power design for biometrics and healthcare applications[J]. IEEE Systems Journal, 2010, 3(4): 398-409.
[3] PENG Y, WANG X, GUO L, et al. An efficient network coding-based fault-tolerant mechanism in WBAN for smart healthcare monitoring systems [J]. Applied Sciences, 2017, 7(8): 817.
[4] KHATUN F, HEYWOOD A E, HANIFI S M A, et al. Gender differentials in readiness and use of mHealth services in a rural area of Bangladesh [J]. BMC Health Services Research, 2017, 17(1): 573.
[5] CHUNG K, PARK R C. PHR open platform based smart health service using distributed object group framework[J]. Cluster Computing, 2016, 19(1): 505-517.
[6] GREEN M L, RUFF T R. Why do residents fail to answer their clinical questions? A qualitative study of barriers to practicing evidence-based medicine[J]. Academic Medicine Journal of the Association of American Medical Colleges, 2005, 80(2): 176-182.
[7] FRANTZIDIS C A, GILOU S, BILLIS A, et al. Future perspectives toward the early definition of a multivariate decision-support scheme employed in clinical decision making for senior citizens [J]. Healthcare Technology Letters, 2017, 3(1): 41-45.
[8] RANI S, MALHOTRA S, SANGWAN V. Detailed study of RS-232 serial interface [J]. Elena F Pérez Carrillo, 2014: 417-426.
[9] KIM Y, LEE S, LEE S. Coexistence of ZigBee-based WBAN and WiFi for health telemonitoring systems [J]. IEEE Journal of Biomedical & Health Informatics, 2015, 20(1): 222-230.
[10] 王汝言, 翟美玲, 吳大鵬. 就帶有同步預測的WBAN時序數據融合算法[J]. 通信學報, 2015, 36(6):13-21.(WANG R Y,ZHAI M L, WU D P, Time series data aggregation algorithm with synchronous prediction for WBAN [J].Journal on Communications, 2015, 36(6): 13-21.)
[11] 梁正友,姚玉梅.IEEE 802.15.6中能量有效的無線體域網拓撲結構優化研究[J].通信學報,2016,37(6):1-10.(LIANG Z Y,YAO Y M. Study of energy efficient WBAN topology optimization in IEEE 802.15.6 [J].Journal on Communications,2016, 37(6): 13-21.)
[12] 張皛,鄔春學,陳凱明.基于負載均衡的ZigBee動態路由優化算法[J].計算機工程,2016,42(3):138-142. (ZHANG X, WU C X, CHEN K M. ZigBee dynamic routing optimization algorithm based on load balance [J]. Computer Engineering, 2016, 42(3): 138-142.)
[13] 王國權,王森,劉華勇,等.基于自適應的動態三次指數平滑法的風電場風速預測[J].電力系統保護與控制,2014(15):117-122. (WANG G Q, WANG S, LIU H Y, et al. Self-adaptive and dynamic cubic ES method for wind speed forecasting[J]. Power System Protection and Control, 2014(15): 117-122.)