As advances in networking technology help to connect industrial control networks with the Internet, the threat from spammers, attackers and criminal enterprises has also grown accordingly. However, traditional Network Intrusion Detection System makes significant use of pattern matching to identify malicious behaviors and have bad performance on detecting zero-day exploits in which a new attack is employed. In this paper, a novel method of anomaly detection in industrial control network is proposed based on RNN-GBRBM feature decoder. The method employ network packets and extract high-quality features from raw features which is selected manually. A modified RNN-RBM is trained using the normal traffic in order to learn feature patterns of the normal network behaviors. Then the test traffic is analyzed against the learned normal feature pattern by using osPCA to measure the extent to which the test traffic resembles the learned feature pattern. Moreover, we design a semi-supervised incremental updating algorithm in order to improve the performance of the model continuously. Experiments show that our method is more efficient in anomaly detection than other traditional approaches for industrial control network.

In this paper, a new method of model predictive control (MPC) for a multi-hop control network (MHCN) is proposed. An MHCN is a control system in which plants and controllers are connected through a multi-hop wireless network. In the proposed method, (i) control inputs and (ii) paths used in transmission of control inputs are computed with constant period by solving the finite-time optimal control problem. First, a mathematical model for expressing an MHCN is proposed. This model is given by a switched linear system, and is compatible with MPC. Next, the finite-time optimal control problem using this model is formulated, and is reduced to a mixed integer quadratic programming problem. Finally, a numerical example is presented to show the effectiveness of the proposed method.

It is known that demand and supply power balancing is an essential method to operate power delivery system and prevent blackouts caused by power shortage. In this paper, we focus on the implementation of demand response strategy to save power during peak hours by using Smart Grid. It is obviously impractical with centralized power control network to realize the real-time control performance, where a single central controller measures the huge metering data and sends control command back to all customers. For that purpose, we propose a new architecture of hierarchical distributed power control network which is scalable regardless of the network size. The sub-controllers are introduced to partition the large system into smaller distributed clusters where low-latency local feedback power control loops are conducted to guarantee control stability. Furthermore, sub-controllers are stacked up in an hierarchical manner such that data are fed back layer-by-layer in the inbound while in the outbound control responses are decentralized in each local sub-controller for realizing the global objectives. Numerical simulations in a realistic scenario of up to 5000 consumers show the effectiveness of the proposed scheme to achieve a desired 10% peak power saving by using off-the-shelf wireless devices with IEEE802.15.4g standard. In addition, a small-scale power control system for green building test-bed is implemented to demonstrate the potential use of the proposed scheme for power saving in real life.

We consider a multi-hop control network where a wireless network is used for transmissions of input and output data between a plant and a computing system. We formulate a co-scheduling problem of sampling of the plant's outputs, execution of control tasks, and the routing of data transmissions in the network. Several constraints on control tasks and data transmission are described by logical formulae. By using a SAT solver, we obtain a scheduling satisfying the constraints. Through simulation, we investigate the relationship between the computation time in the SAT solver and the number of nodes in the network.

The control and diagnosis networks in Maglev Train are the most important parts. In the paper, the control and diagnosis network structures are discussed, and the disadvantages of them are described and analyzed. In virtue of role automation decentralized system (RoADS), some basic ideas of RoADS are applied in new network. The structure, component parts and application of new network are proposed, designed and discussed in detail. The comparison results show that new network not only embodies some RoADS' ideas but also better meets the demands of control and diagnosis networks in Maglev Train.

There are many kinds of control networks, which have been used in various non-IP network areas, such as BA (Building Automation), FA (Factory Automation) and PA (Process Automation). They are now introducing IP and face the issues of security and configuration complexity. The authors have proposed a model which intends to solve these issues while satisfying restrictions, i.e. small embedded devices, isolated networks and private naming system/name space, which are required when introducing new functionality into existing control networks. Secure bootstrap sequence and device-to-device communication using the chain of trust are the points of the model. This paper shows the practicability of the model through implementing the model experimentally.

Frequency channel allocation according to the interference among links is important in autonomous distributed control wireless base station networks from the viewpoint of efficient frequency utilization. It is generally difficult to estimate the interference imposed on other links in a distributed control scheme. This paper proposes a novel frequency channel allocation scheme employing distributed control utilizing broadcast signals to estimate the intensities and frequencies of the interference to other links. The frequency channel, which can be allocated to a link from the viewpoint of the degree of the interference imposed on other links, can be found by receiving broadcast signals. Simulation results show that the proposed scheme efficiently allocates frequency channels to each link to avoid the interference.