HYBRID-CNN: An Efficient Scheme for Abnormal Flow Detection in the SDN-Based Smart Grid

<div>Parameter study of <span class="nowrap"><svg height="6.1673pt" id="M105" style="vertical-align:-0.2063904pt" version="1.1" viewbox="-0.0498162 -5.96091 5.63229 6.1673" width="5.63229pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M401 397C401 420 368 448 302 448C245 448 169 416 122 377C62 327 23 254 23 169C23 45 83 -12 181 -12C252 -12 323 29 374 85L358 107C305 62 257 43 210 43C147 43 110 98 110 189V214L313 208L321 256L115 250C132 342 190 405 253 405C291 405 323 389 346 360C356 348 364 348 377 357C392 367 401 384 401 397Z"></path></g></svg>.</span> (a) Training loss. (b) Validation loss. (c) Training accuracy. (d) Validation accuracy.</div>

Security and Communication Networks

fig14

Figure 14

Figure 14: HYBRID-CNN: An Efficient Scheme for Abnormal Flow Detection in the SDN-Based Smart Grid 